Road traffic system, vehicle sharing system and robotic car training system

Abstract

To provide a road traffic system capable of improving an automatic driving performance of a robotic car by utilizing experiences of the other vehicle.SOLUTION: A computing system 200 comprises: a driving behavior information reception function 210a which receives driving behavior information from a non-robotic car 100B; an optimization information generation function 210c which generates driving behavior information; an optimization information update function 210d by which the driving behavior information is updated to latest information and managed; and a driving behavior information transmission function 210b which transmits optimized driving behavior information to a robotic car 100A. The robotic car 100A includes: a travel situation identification section 100Aa; a driving behavior information reception section 100Ab which receives optimized driving behavior information from the computing system 200; and an automatic driving control section 100Ac which performs automatic driving control corresponding to the travel situation identified by the travel situation identification section 100Aa of the own vehicle while referring to the driving behavior information received by the driving behavior information reception section 100Ab.SELECTED DRAWING: Figure 18

Description

[Technical field]

[0001] The present invention relates to a non-robot car having a driving assistance control function that assists driving by a human driver, a robot car that is driven by automatic driving control instead of by a human driver, and a road traffic system in which non-robot cars and robot cars run on roads. The present invention relates to a vehicle sharing system in which a vehicle is shared by a plurality of users. The present invention relates to a robot car training system and a robot car training method for improving the automatic driving performance of a robot car. [Background technology]

[0002] Many autonomous driving control technologies for automobiles have been proposed (Patent Documents 1-13, Non-Patent Documents 1-4). Many technologies related to vehicle sharing systems have been proposed (Patent Documents 14-26, Non-Patent Documents 1-4). These technologies include technologies related to rental car services, car sharing services, taxi services, etc. Vehicles used in vehicle sharing systems include vehicles equipped with driving assistance systems and vehicles with autonomous driving functions (Patent Documents 1-13). Among these technologies are those related to machine learning of driving operations (Patent Documents 27-44). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2015-087928 [Patent Document 2] Patent Publication 2014-153317 [Patent Document 3] Patent Publication No. 2014-123232 [Patent Document 4] Patent Publication 2014-102802 [Patent Document 5] Patent Publication No. 2014-066521 [Patent Document 6] Patent Publication No. 2012-146251 [Patent Document 7] Patent Publication No. 2012-118951 [Patent Document 8] Patent Publication No. 2012-076627 [Patent Document 9] Patent Publication No. 2011-195026 [Patent Document 10] Patent Publication No. 2011-073565 [Patent Document 11] Patent Publication No. 2007-323598 [Patent Document 12] Patent Publication No. 2007-30568 [Patent Document 13] Patent Publication No. 11-282530 [Patent Document 14] Patent Publication 2015-18464 [Patent Document 15] Patent Publication 2015-101306 [Patent Document 16] Patent Publication No. 2015-69584 [Patent Document 17] Patent Publication 2014-211778 [Patent Document 18] Patent Publication No. 2014-41475 [Patent Document 19] Patent Publication No. 2013-242818 [Patent Document 20] Patent Publication 2012-128019 [Patent Document 21] Patent Publication No. 2012-48308 [Patent Document 22] Patent Publication No. 2012-43167 [Patent Document 23] Patent Publication No. 2012-076627 [Patent Document 24] Patent Publication 2011-180827 [Patent Document 25] Patent Publication No. 2008-293253 [Patent Document 26] Patent Publication No. 11-313410 [Patent Document 27] Patent Publication 2015-157569 [Patent Document 28] Patent Publication 2015-110403 [Patent Document 29] Patent Publication 2015-89801 [Patent Document 30] Patent Publication No. 2015-67154 [Patent Document 31] Patent Publication No. 2015-54580 [Patent Document 32] Patent Publication No. 2014-65392 [Patent Document 33] Patent Publication 2013-249002 [Patent Document 34] Patent Publication No. 2012-108653 [Patent Document 35] Patent Publication No. 2011-073565 [Patent Document 36] Patent Publication No. 2010-134865 [Patent Document 37] Patent Publication No. 2008-298475 [Patent Document 38] Patent Publication No. 2008-018872 [Patent Document 39] Patent Publication No. 2006-113836 [Patent Document 40] Patent Publication No. 2001-005979 [Patent Document 41] Patent Publication No. 10-338057 [Patent Document 42] Re-table 2012 / 077204 [Patent Document 43] WO2013 / 034338 [Patent Document 44] WO2012 / 073359 [Non-patent literature]

[0004] [Non-Patent Document 1] Robot Taxi Inc. website: http: / / robottaxi.com / [Non-Patent Document 2] Google Self-Driving Car Project http: / / www.google.com / selfdrivingcar / [Non-Patent Document 3] Google vs. Toyota: "Self-Driving Cars" is Just the Beginning (Kadokawa EPUB Selection) KADOKAWA / Chukei Publishing (2014 / 12 / 10) [Non-Patent Document 4] Uber homepage: http: / / uber.com / Summary of the Invention [Problem to be solved by the invention]

[0005] Conventional machine learning in automobiles involves learning the driving behavior of the vehicle's human driver and reflecting the results of that learning in the vehicle's autonomous driving control, thereby improving autonomous driving performance. For this reason, conventional machine learning in automobiles cannot be applied to robot cars, i.e., vehicles that run autonomously without the driving operation of a human driver. Also, when the vehicle is in an inexperienced (i.e. unlearned) situation, the vehicle can only demonstrate the driving performance of the initial value.

[0006] The problems to be solved by the present invention are as follows. (1) To provide a non-robotic car that can improve its driving assistance performance by utilizing not only its own vehicle's experience but also the experience of other vehicles. (2) To provide a robot car that can improve its autonomous driving performance by utilizing not only its own vehicle's experience but also the experience of other vehicles. (3) Provide a road traffic system that can improve the driving assistance performance of non-robotic cars and the autonomous driving performance of robotic cars. (4) To provide a vehicle sharing system that enables each vehicle to improve its driving performance by utilizing not only its own experience but also the experience of other vehicles. (5) To provide a robot car training system and a robot car training method that can improve the automatic driving performance of a robot car by having the robot car learn the driving behavior of a human driver. [Means for solving the problem]

[0007] [1. Structure and function of the road transport system] The road traffic system of the present invention includes a system having the following configuration. [Configuration 1.1] A road traffic system in which a plurality of vehicles travel on a road, the vehicles including a non-robot car having a driving assistance control function for assisting a human driver in driving, the non-robot car having a driving situation recognition unit that recognizes the driving situation of the vehicle itself, a driving behavior information acquisition unit that acquires driving behavior information of other vehicles, and a driving assistance control unit that performs driving assistance control based on the driving situation recognized by the driving situation recognition unit while referring to the driving behavior information acquired by the driving behavior information acquisition unit. In this road traffic system, non-robot cars perform driving assistance control based on the driving conditions of their own vehicles while referring to driving behavior information (empirical information) of other vehicles. Therefore, according to this road traffic system, even in a situation that the non-robot car has never experienced, it can handle the situation with the same level of driving performance as other vehicles by performing driving assistance control based on the driving behavior information of other vehicles that have experienced the situation. [Configuration 1.2] A road traffic system in which a plurality of vehicles travel on a road, the vehicles including a non-robot car having a driving assistance control function to assist driving by a human driver, the non-robot car having a driving situation recognition unit that recognizes the driving situation of the vehicle itself, a driving behavior information acquisition unit that acquires driving behavior information of other vehicles, and a driving assistance control unit that determines a driving operation to be performed based on the driving situation recognized by the driving situation recognition unit and performs driving assistance control so that the driving operation is performed, the driving assistance control unit having a driving knowledge unit that stores knowledge information to be referenced when determining the driving operation to be performed, and a learning processing unit (knowledge update processing unit) that updates the knowledge information stored in the driving knowledge unit based on the driving behavior information acquired by the driving behavior information acquisition unit. In this road traffic system, non-robot cars perform a learning process to update knowledge information (such as the criteria for determining the driving operation to be performed) based on driving behavior information of other vehicles, while referring to the knowledge information to determine driving operations according to the driving conditions and providing driving assistance control to ensure that the driving operations are carried out. Therefore, according to this road traffic system, even in a situation that the non-robot car has never experienced, it can learn the driving behavior of other vehicles that have experienced that situation and perform driving assistance control, so that it can handle the situation with the same level of driving performance as the other vehicles. [Configuration 1.3] A road traffic system in which a plurality of vehicles travel on a road, the vehicles including a non-robot car having a driving assistance control function for assisting a human driver in driving the vehicle; The non-robot car has a driving situation recognition unit that recognizes the driving situation of its own vehicle, a driving behavior information acquisition unit that acquires driving behavior information of other vehicles, and a driving assistance control unit that determines a driving operation to be performed based on the driving situation recognized by the driving situation recognition unit and performs driving assistance control so that the driving operation is executed, and the driving assistance control unit has a driving operation determination unit that determines by calculation a driving operation according to the driving situation recognized by the driving situation recognition unit, and a learning processing unit (parameter adjustment unit) that adjusts parameters of a driving operation decision function used in the driving operation determination unit based on the driving behavior information acquired by the driving behavior information acquisition unit. In this road traffic system, the non-robot car performs a learning process to adjust the parameters of a driving operation decision function based on driving behavior information of other vehicles, determines a driving operation according to the driving conditions using the driving operation decision function, and performs driving assistance control to execute the driving operation. Therefore, according to this road traffic system, even in a situation that the non-robot car has never experienced, it can learn the driving behavior of other vehicles that have experienced that situation and perform driving assistance control, so that it can handle the situation with the same level of driving performance as the other vehicles. [Configuration 1.4] A road traffic system in which a plurality of vehicles travel on a road, the vehicles including a robot car that is driven by automatic driving control instead of by a human driver, the robot car having a driving situation recognition unit that recognizes the driving situation of the robot car, a driving behavior information acquisition unit that acquires driving behavior information of other vehicles, and an automatic driving control unit that performs automatic driving control based on the driving situation recognized by the driving situation recognition unit while referring to the driving behavior information acquired by the driving behavior information acquisition unit. In this road traffic system, the robot car performs automatic driving control based on the driving conditions of its own vehicle while referring to driving behavior information (empirical information) of other vehicles. Therefore, according to this road traffic system, even in situations that the robot car has never experienced, it can handle the situation with the same level of driving performance as other vehicles by performing autonomous driving control based on driving behavior information of other vehicles that have experienced the same situation. [Configuration 1.5] A road traffic system in which a plurality of vehicles travel on a road, the vehicles including a robot car that is driven by an automatic driving control instead of a human driver, the robot car having a driving situation recognition unit that recognizes the driving situation of the vehicle itself, a driving behavior information acquisition unit that acquires driving behavior information of other vehicles, and an automatic driving control unit that determines a driving operation to be executed based on the driving situation recognized by the driving situation recognition unit and performs automatic driving control so that the driving operation is executed, the automatic driving control unit having a driving knowledge unit that stores knowledge information to be referred to when determining the driving operation to be executed, and a learning processing unit (knowledge update processing unit) that appropriately updates the knowledge information stored in the driving knowledge unit based on the driving behavior information acquired by the driving behavior information acquisition unit. Hmm. In this road traffic system, the robot car will navigate based on the driving behavior information of other vehicles. A learning process is performed to update knowledge information (such as the criteria for determining which driving operations should be performed) While referring to the knowledge information, the driving operation according to the driving situation is determined, and the driving operation is executed. The system will automatically control the operation so that the Therefore, according to this road traffic system, the robot car can navigate in situations that it has never experienced before. Even in such a situation, the system learns the driving behavior of other vehicles that have experienced the situation and performs autonomous driving control. By doing so, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.6] A road traffic system in which a plurality of vehicles travel on a road, the vehicles include a human driver. A robot car that is driven by an autonomous driving control system instead of a human driver will be developed. The robot car includes a driving situation recognition unit that recognizes the driving situation of the own vehicle and a driving situation recognition unit that recognizes the driving situation of other vehicles. A driving behavior information acquisition unit that acquires driving behavior information, and a driving situation recognition unit that recognizes the driving situation. Based on the driving situation, the system determines the driving operation to be performed and automatically executes the driving operation. and an automatic driving control unit that performs a driving control, and the automatic driving control unit is A driving operation determination unit that determines a driving behavior according to a more recognized driving situation by calculation; Based on the driving behavior information acquired by the driving behavior information acquisition unit, the driving operation determination unit a learning processing unit (parameter adjustment unit) that adjusts parameters of a driving operation decision function used in the vehicle; A road traffic system comprising: In this road traffic system, the robot car will navigate based on the driving behavior information of other vehicles. While performing a learning process to adjust the parameters of the driving operation decision function, the driving operation is adjusted according to the driving situation. is determined by the driving operation decision function, and automatic driving control is performed so that the driving operation is executed. . Therefore, according to this road traffic system, the robot car can navigate in situations that it has never experienced before. Even in such a situation, the system learns the driving behavior of other vehicles that have experienced the situation and performs autonomous driving control. By doing so, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.7] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from one or more vehicles; a driving behavior information receiving function for receiving the driving behavior information from a source different from a source of the driving behavior information; A driving behavior information transmission function for transmitting information to one or more vehicles, the vehicle being provided with a human driver. This includes non-robot cars with driving assistance control functions that assist the driver in driving the car. The non-robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself, and a driving behavior information receiving unit for receiving driving behavior information of another vehicle from the driving system; The driving situation recognition unit recognizes the driving situation while referring to the driving behavior information received by the dynamic information receiving unit. and a driving assistance control unit that performs driving assistance control based on the determined driving situation. A road transport system that In this road traffic system, the computing system is and receiving driving behavior information (experience information) from the The driving behavior information is transmitted from the computing system to one or more different vehicles. The non-robot car that receives the driving behavior information will refer to the driving behavior information and take appropriate action based on the driving situation of its own vehicle. This provides driving assistance control. Therefore, according to the road traffic system, non-robot cars are not able to navigate situations that they have not experienced before. In this case, the driving assistance system will be implemented while referring to the driving behavior information of other vehicles that have experienced the situation. By controlling the vehicle, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.8] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from one or more vehicles; a driving behavior information receiving function for receiving the driving behavior information from a source different from a source of the driving behavior information; A driving behavior information transmission function for transmitting information to one or more vehicles, the vehicle being provided with a human driver. This includes non-robot cars with driving assistance control functions that assist the driver in driving the car. The non-robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself, and a driving behavior information receiving unit for receiving driving behavior information of other vehicles from the driving system; A driving operation to be performed is determined based on the driving situation recognized by the situation recognition unit, and the driving operation is A driving assistance control unit that performs driving assistance control so that an operation is executed, The driving knowledge unit stores knowledge information to be referred to when determining the driving behavior, and the driving knowledge unit stores knowledge information to be referred to when determining the driving behavior. Based on the driving behavior information received by the behavior information receiving unit, A learning processing unit (knowledge update processing unit) that updates knowledge information stored in the road Transportation system. In this road traffic system, the computing system is and receiving driving behavior information (experience information) from the The driving behavior information is transmitted from the computing system to one or more different vehicles. The non-robot car receives the driving behavior information of other vehicles and then calculates knowledge information (driving instructions to be executed). While performing a learning process to update the knowledge information (e.g., criteria for deciding on an operation), and determines a driving operation according to the driving situation, and performs driving assistance control so that the driving operation is executed. Do the following. Therefore, according to this road traffic system, non-robot cars can navigate in a situation where they have no experience of it. Even in such a situation, the system learns the driving behavior of other vehicles that have experienced the same situation and provides driving assistance control. By doing so, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.9] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from one or more vehicles; a driving behavior information receiving function for receiving the driving behavior information from a source different from a source of the driving behavior information; A driving behavior information transmission function for transmitting information to one or more vehicles, the vehicle being provided with a human driver. This includes non-robot cars with driving assistance control functions that assist the driver in driving the car. The non-robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle, and a driving behavior information a driving behavior information receiving unit that receives the driving behavior information from the computing system; A driving operation to be performed is determined based on the driving situation recognized by the driving control unit, and the driving operation is and a driving assistance control unit that performs driving assistance control so that the driving assistance control unit is executed. A driving behavior is determined by calculation according to the driving situation recognized by the driving situation recognition unit. A driving operation determination unit and a driving behavior information acquisition unit acquire a driving behavior information based on the driving behavior information acquired by the driving behavior information acquisition unit. a learning processing unit that adjusts parameters of a driving operation decision function used in the driving operation decision unit; (parameter adjustment unit). In this road traffic system, non-robot cars will be able to navigate based on the driving behavior information of other vehicles. The learning process adjusts the parameters of the driving operation decision function based on the driving situation. The driving operation decision function is used to determine the driving operation, and driving assistance control is performed so that the driving operation is executed. cormorant. Therefore, according to this road traffic system, non-robot cars can navigate in a situation where they have no experience of it. Even in such a situation, the system learns the driving behavior of other vehicles that have experienced the same situation and provides driving assistance control. By doing so, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.10] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from one or more vehicles; a driving behavior information receiving function for receiving the driving behavior information from a source different from a source of the driving behavior information; A driving behavior information transmission function for transmitting information to one or more vehicles, the vehicle being provided with a human driver. A robot that is driven by an autonomous driving control system instead of a driver. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself, and a front a driving behavior information receiving unit for receiving the driving behavior information from the computing system; The driving situation recognition is performed while referring to the driving behavior information received by the driving behavior information receiving unit. and an automatic driving control unit that performs automatic driving control based on the driving situation recognized by the driving control unit. A road traffic system comprising: In this road traffic system, the computing system is and receiving driving behavior information (experience information) from the The driving behavior information is transmitted from the computing system to one or more different vehicles. The robot car then refers to the driving behavior information and takes appropriate action based on the driving situation of its own vehicle. Performs automatic driving control. Therefore, according to the road traffic system, the robot car will be able to navigate in situations that it has never experienced before. Even if the vehicle is in a similar situation, the system will control the vehicle automatically while referring to the driving behavior information of other vehicles that have experienced the situation. By doing so, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.11] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from one or more vehicles; a driving behavior information receiving function for receiving the driving behavior information from a source different from a source of the driving behavior information; A driving behavior information transmission function for transmitting information to one or more vehicles, the vehicle being provided with a human driver. A robot that is driven by an autonomous driving control system instead of a driver. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself, and a front A driving behavior information receiving unit that receives the driving behavior information from the computing system; determining a driving operation to be performed based on the driving situation recognized by the driving situation recognition unit; and an automatic driving control unit that performs automatic driving control so that the driving operation is executed, The driving control unit includes a driving knowledge unit that stores knowledge information to be referred to when determining the driving behavior. Based on the driving behavior information received by the driving behavior information receiving unit, A learning processing unit (knowledge update processing unit) that updates the stored knowledge information. A road transport system. In this road traffic system, the computing system is and receiving driving behavior information (experience information) from the The driving behavior information is transmitted from the computing system to one or more different vehicles. The robot car receives the driving behavior information of other vehicles and then calculates knowledge information (driving operations to be performed). While performing a learning process to update the knowledge information (e.g., criteria for deciding on an action), The system determines driving operations according to the driving conditions and performs automatic driving control so that the driving operations are executed. conduct. Therefore, according to this road traffic system, the robot car can navigate in situations that it has never experienced before. Even in such a situation, the system learns the driving behavior of other vehicles that have experienced the situation and performs autonomous driving control. By doing so, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.12] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from one or more vehicles; a driving behavior information receiving function for receiving the driving behavior information from a source different from a source of the driving behavior information; A driving behavior information transmission function for transmitting information to one or more vehicles, the vehicle being provided with a human driver. A robot that is driven by an autonomous driving control system instead of a driver. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself, and a front a driving behavior information receiving unit for receiving driving behavior information of other vehicles from the computing system; and determining a driving operation to be performed based on the driving situation recognized by the driving situation recognition unit. and an automatic driving control unit that performs automatic driving control so that the driving operation is executed. The autonomous driving control unit determines a driving behavior according to the driving situation recognized by the driving situation recognition unit. A driving operation determination unit that determines the driving operation by calculation, and a driving action acquired by the driving action information acquisition unit. Based on the information, the parameters of the driving operation decision function used in the driving operation decision unit are a learning processing unit (parameter adjustment unit) for adjusting the road traffic system . In this road traffic system, the robot car will navigate based on the driving behavior information of other vehicles. While performing a learning process to adjust the parameters of the driving operation decision function, the driving operation is adjusted according to the driving situation. is determined by the driving operation decision function, and automatic driving control is performed so that the driving operation is executed. . Therefore, according to this road traffic system, the robot car can navigate in situations that it has never experienced before. Even in such a situation, the system learns the driving behavior of other vehicles that have experienced the situation and performs autonomous driving control. By doing so, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.13] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system and wherein the computing system receives driving behavior information from the robot car. A driving behavior information receiving function and a driving behavior information transmitting function for transmitting the driving behavior information to a non-robot car. and a communication function, and the robot car operates in place of a human driver. A vehicle that is driven by automatic driving control, and the driving behavior information of the vehicle is input to the computer. a driving behavior information transmission unit that transmits the driving behavior information to a computing system, A vehicle having a driving assistance control function that assists a human driver in driving, A driving situation recognition unit that recognizes the driving situation of the vehicle and a driving behavior information processing unit that outputs the driving behavior information to the computing device. a driving behavior information receiving unit for receiving the driving behavior information from a driving system; While referring to the driving behavior information, the driving situation is recognized by the driving situation recognition unit. A road traffic system comprising: a driving assistance control unit that performs driving assistance control. In this road traffic system, the computing system is Receive driving behavior information (experience information) and transmit the driving behavior information to non-robot cars. The non-robot car receives driving behavior information from the computing system and While referring to the information, driving assistance control is performed based on the vehicle's driving conditions. Therefore, according to the road traffic system, non-robot cars are not able to navigate situations that they have not experienced before. In this case, the driver will refer to the driving behavior information of a robot car that has experienced the situation. By providing assistance control, the vehicle can handle the situation with driving performance equivalent to that of the robot car. can. This road traffic system allows robot cars and non-robotic cars to coexist. In this situation, a non-robot car is made to learn the driving techniques of a robot car. The driving assistance performance of non-robot cars can be improved highly efficiently. As the number of road users increases, the operational efficiency of the entire road transport system will improve, as will safety. do. [Configuration 1.14] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system and wherein the computing system receives driving behavior information from the robot car. A driving behavior information receiving function and a driving behavior information transmitting function for transmitting the driving behavior information to a non-robot car. and a communication function, and the robot car operates in place of a human driver. A vehicle that is driven by automatic driving control, and the driving behavior information of the vehicle is input to the computer. a driving behavior information transmission unit that transmits the driving behavior information to a computing system, A vehicle having a driving assistance control function that assists a human driver in driving, A driving situation recognition unit that recognizes the driving situation of the vehicle and a driving behavior information processing unit that outputs the driving behavior information to the computing device. A driving behavior information receiving unit receives information from a driving system, and a driving situation recognition unit recognizes the driving behavior information. Based on the driving situation, the driving operation to be performed is determined, and the driving support is provided so that the driving operation is performed. and a driving assistance control unit that performs a driving assistance control, the driving assistance control unit being configured to determine the driving behavior. a driving knowledge unit that stores knowledge information (criteria for judgment, etc.) to be referred to when determining whether or not the driving behavior is correct; Based on the driving behavior information received by the driving knowledge unit, A road traffic system comprising: . In this road traffic system, the computing system is Receive driving behavior information (experience information) and transmit the driving behavior information to non-robot cars. The non-robot car receives driving behavior information from the computing system and Knowledge information based on driving behavior information (e.g., criteria for deciding which driving operations to perform) While performing a learning process to update the knowledge information, the vehicle determines driving operations according to the driving situation by referring to the knowledge information. The driving assistance control unit 100 determines the driving operation to be performed and performs driving assistance control so that the driving operation is performed. Therefore, according to this road traffic system, non-robot cars can navigate in a situation where they have no experience of it. Even in such a situation, the robot car will learn the driving behavior of a robot car that has experienced the situation and provide driving support. By providing assisted control, the vehicle can handle the situation with driving performance equivalent to that of the robot car. Cut. This road traffic system allows robot cars and non-robotic cars to coexist. In this situation, a non-robot car is made to learn the driving techniques of a robot car. The driving assistance performance of non-robot cars can be improved highly efficiently. As the number of road users increases, the operational efficiency of the entire road transport system will improve, as will safety. do. [Configuration 1.15] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system and wherein the computing system receives driving behavior information from the robot car. A driving behavior information receiving function and a driving behavior information transmitting function for transmitting the driving behavior information to a non-robot car. and a communication function, and the robot car operates in place of a human driver. A vehicle that is driven by automatic driving control, and the driving behavior information of the vehicle is input to the computer. a driving behavior information transmission unit that transmits the driving behavior information to a computing system, A vehicle having a driving assistance control function that assists a human driver in driving, A driving situation recognition unit that recognizes the driving situation of the vehicle and a driving behavior information processing unit that outputs the driving behavior information to the computing device. A driving behavior information receiving unit receives information from a driving system, and a driving situation recognition unit recognizes the driving behavior information. Based on the driving situation, the driving operation to be performed is determined, and the driving support is provided so that the driving operation is performed. and a driving assistance control unit that performs a driving assistance control, the driving assistance control unit being configured to A driving operation determination unit that determines a driving behavior according to a more recognized driving situation by calculation; Based on the driving behavior information acquired by the driving behavior information acquisition unit, the driving operation determination unit a learning processing unit (parameter adjustment unit) that adjusts parameters of a driving operation decision function used in the vehicle; A road traffic system comprising: In this road traffic system, non-robot cars will be able to use the driving behavior information of the robot car. The driving operation decision function parameters are adjusted based on the driving situation of the vehicle. A driving operation corresponding to the driving condition is determined by a driving operation decision function, and the driving operation is executed. Performs rolling assistance control. Therefore, according to this road traffic system, non-robot cars can navigate in a situation where they have no experience of it. Even in such a situation, the robot car will learn the driving behavior of a robot car that has experienced the situation and provide driving support. By providing assisted control, the vehicle can handle the situation with driving performance equivalent to that of the robot car. Cut. This road traffic system allows robot cars and non-robotic cars to coexist. In this situation, a non-robot car is made to learn the driving techniques of a robot car. The driving assistance performance of non-robot cars can be improved highly efficiently. As the number of road users increases, the operational efficiency of the entire road transport system will improve, as will safety. do. [Configuration 1.16] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from a non-robotic car; a driving behavior information receiving function for receiving the driving behavior information from the driving behavior information receiving device and a driving behavior information sending function for sending the driving behavior information to the robot car; and a communication function, and the non-robot car is driven by a human driver. a vehicle that transmits driving behavior information of the vehicle to the computing system; and a driving behavior information transmission unit, and the robot car is driven by a human driver. A vehicle in which driving operation is performed by automatic driving control instead of A driving situation recognition unit that recognizes the driving situation of the vehicle and a driving behavior information processing unit that outputs the driving behavior information to the computer. a driving behavior information receiving unit that receives the driving behavior information from a driving system; Based on the driving situation recognized by the driving situation recognition unit, and an automatic driving control unit that performs automatic driving control by using the vehicle speed information. In this road traffic system, the computing system is different from the non-robot cars. The controller receives driving behavior information (experience information) from the driver and transmits the driving behavior information to the robot car. The robot car receives the driving behavior information from the computing system and The system performs automatic driving control based on the vehicle's driving conditions while referring to the information from the surrounding area. Therefore, according to this road traffic system, the robot car can navigate in situations that it has never experienced before. In this case, the robot will refer to the driving behavior information of non-robot cars that have experienced the situation. By implementing autonomous driving control, the robot car can operate in the same level of driving performance as a non-robotic car in the given situation. can be dealt with. This road traffic system allows robot cars and non-robotic cars to coexist. In this situation, the driving technique of a human driver who drives a non-robotic car is trained on a robotic car. By having the robot learn the autonomous driving performance of the robot car, the autonomous driving performance can be improved highly efficiently. As the autonomous driving capabilities of mobile cars improve, the operational efficiency of the entire road transport system will improve. Safety will be improved, etc. [Configuration 1.17] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from a non-robotic car; a driving behavior information receiving function for receiving the driving behavior information from the driving behavior information receiving device and a driving behavior information sending function for sending the driving behavior information to the robot car; and a communication function, and the non-robot car is driven by a human driver. a vehicle that transmits driving behavior information of the vehicle to the computing system; and a driving behavior information transmission unit, and the robot car recognizes the driving status of the vehicle. A situation recognition unit and a driving behavior unit that receives the driving behavior information from the computing system. An information receiving unit and a driving operation to be performed based on the driving situation recognized by the driving situation recognition unit. An automatic driving control unit that determines an operation and performs automatic driving control so that the driving operation is executed; The autonomous driving control unit stores knowledge information to be referred to when determining the driving behavior. and based on the driving behavior information received by the driving knowledge unit, A learning processing unit that updates the knowledge information stored in the driving knowledge unit. A road transport system. In this road traffic system, the computing system is different from the non-robot cars. The controller receives driving behavior information (experience information) from the driver and transmits the driving behavior information to the robot car. The robot car receives driving behavior information from the computing system and operates in a similar manner to the non-robot car. Knowledge information based on driving behavior information (e.g., criteria for deciding which driving operations to perform) While performing a learning process to update the knowledge information, the vehicle determines driving operations according to the driving situation by referring to the knowledge information. The system then performs automatic driving control so that the driving operation is carried out. Therefore, according to this road traffic system, the robot car can navigate in situations that it has never experienced before. Even in such a situation, the robot can learn the driving behavior of a non-robot car that has experienced the situation. By providing assisted control, the robot can handle the situation with driving performance equivalent to that of a non-robotic car. can. This road traffic system allows robot cars and non-robotic cars to coexist. In this situation, the driving technique of a human driver who drives a non-robotic car is trained on a robotic car. By having the robot learn the autonomous driving performance of the robot car, the autonomous driving performance can be improved highly efficiently. As the autonomous driving capabilities of mobile cars improve, the operational efficiency of the entire road transport system will improve. Improved safety, etc. will be achieved. [Configuration 1.18] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from a non-robotic car; a driving behavior information receiving function for receiving the driving behavior information from the driving behavior information receiving device and a driving behavior information sending function for sending the driving behavior information to the robot car; and a communication function, and the non-robot car is driven by a human driver. a vehicle that transmits driving behavior information of the vehicle to the computing system; and a driving behavior information transmission unit, and the robot car recognizes the driving status of the vehicle. A situation recognition unit and a driving behavior unit that receives the driving behavior information from the computing system. An information receiving unit and a driving operation to be performed based on the driving situation recognized by the driving situation recognition unit. An automatic driving control unit that determines an operation and performs automatic driving control so that the driving operation is executed; The autonomous driving control unit is configured to control a driving situation according to the driving situation recognized by the driving situation recognition unit. A driving operation determination unit that determines a driving behavior by calculation, and Based on the driving behavior information, a driving operation decision function used in the driving operation decision unit is A road traffic system comprising: a learning processing unit that adjusts parameters. In this road traffic system, the robot car will be able to use the driving behavior information of non-robot cars. The driving operation decision function parameters are adjusted based on the driving situation of the vehicle. A driving operation corresponding to the driving condition is determined by a driving operation decision function, and the driving operation is automatically executed. Dynamic operation control. Therefore, according to this road traffic system, the robot car can navigate in situations that it has never experienced before. Even in such a situation, the robot can learn the driving behavior of a non-robot car that has experienced the situation. By providing assisted control, the robot can handle the situation with driving performance equivalent to that of a non-robotic car. can. This road traffic system allows robot cars and non-robotic cars to coexist. In this situation, the driving technique of a human driver who drives a non-robotic car is trained on a robotic car. By having the robot learn the autonomous driving performance of the robot car, the autonomous driving performance can be improved highly efficiently. As the autonomous driving capabilities of mobile cars improve, the operational efficiency of the entire road transport system will improve. Improved safety, etc. will be achieved. [Configuration 1.19] The driving behavior information of the other vehicle includes a driving situation of the other vehicle and a driving operation performed in the other vehicle. A road traffic system according to any one of configurations 1.1 to 1.6, which is driving behavior information associated with a driving operation. Stem. [Configuration 1.20] The non-robot car has a driving behavior information output unit that outputs driving behavior information of the vehicle to the outside. The driving behavior information of the vehicle includes a driving situation of the vehicle and a driving behavior of the vehicle. The road traffic control method according to any one of the configurations 1.1 to 1.3, wherein the road traffic control method is a driving behavior information associated with a driving operation. Pass system. [Configuration 1.21] The robot car has a driving behavior information output unit that outputs driving behavior information of the vehicle to the outside. The driving behavior information of the vehicle includes a driving situation of the vehicle and a driving behavior of the vehicle. The road traffic control method according to any one of the configurations 1.4 to 1.6, wherein the driving behavior information is associated with an operation. system. [Configuration 1.22] The non-robot car detects driving operations by a human driver of the vehicle. A work detection unit, The driving situation recognized by the driving situation recognition unit and the driving operation detected by the driving operation detection unit and transmitting driving behavior information associated with the driving operation to the computing system. A road traffic system according to any one of configurations 1.16 to 1.18, comprising: a dynamic information transmission unit. [Configuration 1.23] The computing system may include a driving system that receives driving behavior information of one or more vehicles. A behavior information receiving function and generating optimized driving behavior information based on the driving behavior information. An optimization information generating function and updating and managing the optimized driving behavior information to the latest information. An optimization information update function and a driving control function for transmitting the optimized driving behavior information to one or more vehicles. A road traffic system according to any one of configurations 1.7 to 1.12 having a turnaround information transmission function. Hmm. [Configuration 1.24] The computing system is a driving system that receives driving behavior information from a robot car. a dynamic information receiving function and a function for generating optimized driving behavior information based on the driving behavior information. A function for generating optimized driving behavior information and a function for updating and managing the optimized driving behavior information to the latest information. An optimization information update function and a driving behavior update function for transmitting the optimized driving behavior information to a non-robot car. A road traffic system according to any one of configurations 1.13 to 1.15, having a dynamic information transmission function. Hmm. [Configuration 1.25] The computing system is a driving system that receives driving behavior information from a non-robotic car. A behavior information receiving function and generating optimized driving behavior information based on the driving behavior information. An optimization information generating function and updating and managing the optimized driving behavior information to the latest information. An optimization information update function and a driving behavior control function for transmitting the optimized driving behavior information to the robot car. A road traffic system according to any one of configurations 1.16 to 1.18, having a dynamic information transmission function. Hmm. [Configuration 1.26] Instead of a human driver operating the vehicle, the vehicle is operated by an automated driving control system. A road traffic system in which a robot car that is equipped with a computing system runs on a road. The computing system is configured to control driving behavior information of one or more robot cars. a driving behavior information receiving function for receiving information from a transmission source of the driving behavior information; a driving behavior information transmission function for transmitting the driving behavior information to one or more different robot cars; The robot car includes a driving situation recognition unit that recognizes a driving situation of the vehicle itself, and a driving behavior information recognition unit that recognizes the driving situation of the vehicle itself. a driving behavior information receiving unit for receiving driving behavior information; The driving situation recognition unit of the vehicle automatically recognizes the driving situation based on the driving situation recognized by the driving situation recognition unit of the vehicle while referring to the information. An automatic driving control unit that performs driving control, and a driving situation recognized by the driving situation recognition unit and an automatic driving control unit that performs driving control. Driving behavior information associated with driving operations by driving control is input to the computing system. a driving behavior information transmission unit for transmitting the driving behavior information to the ... A road traffic system characterized in that the information is information that associates driving conditions with driving operations. In this road traffic system, the computing system is Driving behavior information (experience information) is received, and the sending source of the driving behavior information is The driving behavior information is then sent to different robot cars. The robot car that receives the signal will refer to the driving behavior information of the other robot cars and adjust the driving situation of its own vehicle. Therefore, the robot car can control autonomous driving based on the situation that the vehicle has never experienced before. In this case, the robot car will refer to the driving behavior information of other robot cars that have experienced the situation. By controlling autonomous driving according to the driving conditions of the vehicle, it will be able to achieve the same level of performance as other robot cars. Bell's driving performance can handle the situation. According to this road traffic system, the robot cars will share driving behavior information with each other. This will increase the learning efficiency of robot cars in road traffic systems and rapidly improve autonomous driving performance. It is possible to rapidly improve the autonomous driving performance of all robot cars in the road traffic system. This will rapidly improve the operational efficiency, safety, etc. of the entire road transport system. Improve. [Configuration 1.27] Instead of a human driver operating the vehicle, the vehicle is operated by an automated driving control system. A road traffic system in which a robot car that is equipped with a computing system runs on a road. the computing system controls the driving behavior of one or more robotic cars; A driving behavior information receiving function for receiving information, and a driving behavior information receiving function for receiving information, An optimization information generation function for generating behavior information, and updating the optimized driving behavior information to the latest information and an optimization information update function for updating and managing the optimized driving behavior information to one or more and a driving behavior information transmission function for transmitting driving behavior information to the robot car. A driving situation recognition unit that recognizes the driving situation of the vehicle and a driving behavior information receiving unit that receives the driving behavior information. a driving behavior information receiving unit for receiving the driving behavior information from the driving behavior information receiving unit; An automatic driving control that performs automatic driving control based on the driving situation recognized by the driving situation recognition unit. a driving situation recognition unit that recognizes the driving situation and a driving operation by an automatic driving control unit; Transmitting the associated driving behavior information to the computing system. and a driving operation control unit, the driving behavior information being associated with a driving situation of the robot car. A road traffic system characterized in that the information is In this road traffic system, the computing system is Receive driving behavior information (experience information) and optimize driving behavior based on the driving behavior information The optimized driving behavior information is updated to the latest information and managed, and the driving behavior information is The behavioral information is sent to the robot car. Driving behavior information is sent from this computing system to the robot car. The robot car that receives the information refers to the driving behavior information of the other robot cars and adjusts its own driving status. Therefore, the robot car will perform autonomous driving control based on the situation. Even in such a situation, the robot car can predict the driving behavior based on the driving behavior information of other robot cars that have experienced the situation. By referring to the optimized driving behavior information, the autonomous driving control is performed. It can handle the situation with driving performance equal to or better than that of a car. According to this road traffic system, the robot cars will share driving behavior information with each other. This will increase the learning efficiency of robot cars in road traffic systems and rapidly improve autonomous driving performance. It is possible to rapidly improve the autonomous driving performance of all robot cars in the road traffic system. This will rapidly improve the operational efficiency, safety, etc. of the entire road transport system. Improve. [Configuration 1.28] The optimized driving behavior information is based on the vehicle attributes of the vehicle to which the driving behavior information is provided. and optimizing the driving behavior information according to the driving behavior information. Driving behavior information optimized to minimize the possibility of causing a malfunction; Driving behavior information optimized to minimize the energy consumption of the vehicle in the driving behavior information; Driving behavior information optimized to maximize the regenerative energy of the vehicle receiving the information, The number of accelerations or the acceleration time for a given travel distance or a given travel time is minimized. Optimized driving behavior information, the number of braking events or braking time for a specified driving distance or a specified driving time Driving behavior information optimized to minimize or maximize time from departure point to destination point Driving behavior information optimized to minimize the distance traveled, or from the starting point to the destination Configuration 1.23, which is driving behavior information optimized to minimize the driving time to 1 .24, 1.25 or 1.27 road traffic systems. [Configuration 1.29] The optimization information generation function is a function for optimizing the driving status of a vehicle that receives the driving behavior information and the driving status of the vehicle. Based on the attributes of both vehicles, the vehicle is determined to be in a position that minimizes the possibility of the vehicle coming into contact with an obstacle. , and a function for correcting the driving behavior information, 7 road transport systems. In this road traffic system, a vehicle that provides driving behavior information (provider vehicle) When the attributes of the vehicle receiving the driving behavior information (recipient vehicle) differ from the attributes of the vehicle receiving the driving behavior information, Driving behavior information that has been modified to minimize the possibility of the destination vehicle coming into contact with an obstacle The information is provided to the recipient vehicle. According to this road traffic system, the vehicle attributes of the vehicle providing the driving behavior information and the vehicle receiving the information are Even if there are differences, vehicles can refer to each other's driving behavior information and perform driving assistance control or autonomous driving control. It can be done. [Configuration 1.30] A road traffic system in which a plurality of vehicles travel on a road, A function of providing driving behavior information to other vehicles, a function of receiving driving behavior information of other vehicles, and a function of receiving driving behavior information of other vehicles. and a function of controlling the driving of the vehicle based on the driving behavior information of the vehicle. The dynamic information is a driving information that corresponds the driving situation of the vehicle with the driving operation performed on the vehicle. The driving behavior information of the other vehicle is information on the driving situation of the other vehicle and The information is associated with a driving operation performed. Vehicles in this road traffic system exchange driving behavior information (experience information) with each other. The driving behavior information of other vehicles can then be used to control the driving of the vehicle itself. Therefore, the vehicle of this road traffic system can recognize the situation even if it is in a situation that it has not experienced before. By referring to the driving behavior information of other vehicles that have experienced the situation, The vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.31] A road traffic system in which a plurality of vehicles travel on a road, the vehicles being a self vehicle and other vehicles a function of receiving driving behavior information of the other vehicle through communication between the other vehicle and the and a function of controlling driving of the vehicle by referring to the driving behavior information of the other vehicle. The information corresponds to the driving conditions of both vehicles and the driving operations performed by the other vehicle. A road transport system. Vehicles in this road traffic system receive driving behavior information (experience information) of other vehicles through vehicle-to-vehicle communication. The driving behavior information of other vehicles can be used for driving control of the vehicle itself. Therefore, the vehicles in this road traffic system can navigate in the appropriate situation even in situations that they have never experienced before. By referring to the driving behavior information of other vehicles that have experienced the situation, driving control is performed. , and can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.32] A road traffic system in which a plurality of vehicles travel on a road, the vehicles are connected to a ground station A function to receive driving behavior information of other vehicles through communication with other vehicles and a function to receive driving behavior information of other vehicles and a function of controlling driving of the vehicle by referring to the driving behavior information of the other vehicle. The information corresponds to the driving conditions of both vehicles and the driving operations performed by the other vehicle. A road transport system. Vehicles in this road traffic system communicate with stationary objects on the ground to obtain driving behavior information (e.g., The driving behavior information of other vehicles can be used to control the driving of the vehicle. Therefore, the vehicles in this road traffic system can use the Even if the vehicle is in a similar situation, driving control can be performed by referring to the driving behavior information of other vehicles that have experienced the situation. This allows the vehicle to handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.33] A road traffic system in which a plurality of vehicles travel on a road, the vehicles each having a vehicle-specific road and a road-specific road-specific road information. The function of receiving driving behavior information of other vehicles through communication between the vehicles and the and a function of controlling the driving of the vehicle by using the driving behavior information of the other vehicle. The information is characterized in that the driving situation of the other vehicle is associated with the driving operation performed in the other vehicle. A road transport system that Vehicles in this road traffic system receive driving behavior information (experience information) of other vehicles through road-to-vehicle communication. The driving behavior information of other vehicles can be used for driving control of the vehicle itself. Therefore, the vehicles in this road traffic system can navigate in the appropriate situation even in situations that they have never experienced before. By referring to the driving behavior information of other vehicles that have experienced the situation, driving control is performed. , and can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.34] A road traffic system in which a plurality of vehicles travel on a road, the vehicles each having a mobile terminal The function of receiving driving behavior information of other vehicles through communication between the terminal and the vehicle and the function of transmitting driving behavior information of other vehicles and a function of controlling driving of the vehicle by referring to the driving behavior information of the other vehicle. The information is particularly intended to associate the driving conditions of the other vehicle with the driving operations performed by the other vehicle. A road transport system characterized by Vehicles in this road traffic system communicate with mobile devices to obtain driving behavior information (experience) of other vehicles. The driving behavior information of other vehicles can be used to control the driving of the vehicle. Therefore, the vehicle in this road traffic system can In addition, driving control is performed by referring to the driving behavior information of other vehicles that have experienced the situation. This allows the vehicle to handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.35] A road traffic system in which a plurality of vehicles travel on a road, The function of uploading dynamic information to a computing system on the network and Downloading vehicle driving behavior information from a computing system on the network functions and driving behavior information downloaded from a computing system on the network and a function of controlling the driving of the vehicle based on the driving behavior information of the vehicle. The information is information that associates a driving situation of a vehicle with a driving operation performed on the vehicle, The driving behavior information of the other vehicle includes the driving situation of the other vehicle and the driving operation performed by the other vehicle. A road traffic system characterized in that the information is associated with each other. The vehicles in this road traffic system communicate with a large number of other vehicles via a network. The driving behavior information of other vehicles can be shared with the vehicle. Therefore, the vehicle in this road traffic system can control the vehicle's driving. Even in such a situation, the driving control is performed by referring to the driving behavior information of other vehicles that have experienced the situation. By controlling the vehicle, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 1.36] A road traffic system in which a plurality of vehicles travel on a road includes a network that stores driving behavior information of the vehicles. The function of uploading the driving behavior of the vehicle to a computing system on the network The driving behavior information generated based on the driving behavior information of other vehicles is transmitted to the computer on the network. The ability to download from a computing system and to The function of controlling the driving of the vehicle by referring to the driving behavior information downloaded from the driving system The driving behavior information of the vehicle is based on the driving status of the vehicle and the driving behavior of the vehicle. The driving behavior information of the other vehicle corresponds to the driving operation of the other vehicle. The information is characterized in that it is information that associates the situation with the driving operation performed in the other vehicle. A road transport system. Vehicles in this road traffic system transmit their own driving behavior information (experience information) to the network. The driving behavior information of the vehicle and the driving behavior information of other vehicles are uploaded to the computing system of the The driving behavior information generated based on the behavior information (experience information) is sent to the computer on the network. The vehicle's driving behavior information can be downloaded from the vehicle management system. The driving behavior information generated based on the driving behavior information of the other vehicle is used for driving control of the own vehicle. Therefore, the vehicles in this road traffic system can navigate in situations they have never experienced before. Based on the driving behavior information of the vehicle and the driving behavior information of other vehicles that have experienced the situation, By referring to the driving behavior information generated by the vehicle, the vehicle can be controlled at the same level as the other vehicle. A driver with driving ability of at least 1500m can handle the situation. [Configuration 1.37] A road traffic system in which a plurality of vehicles travel on a road, the plurality of vehicles are provided with a hi-fi. A vehicle in which driving operations are performed by automatic driving control instead of by a human driver. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle. A learning processing unit that learns about surrounding objects and driving operations of the vehicle, and a driving behavior information processing unit that learns about surrounding objects and driving operations of the vehicle a driving behavior information acquisition unit for acquiring driving behavior information; The driving situation recognized by the driving situation recognition unit of the vehicle while referring to the information and the learning process and an automatic driving control unit that performs automatic driving control based on a learning result by the automatic driving control unit. The driving behavior information is a data set that associates the driving status of the other vehicle with the driving operations performed by the other vehicle. A road traffic system comprising operation history information. The robot car in this road traffic system refers to the driving behavior information (experience information) of other vehicles. At the same time, the system performs automatic driving control based on the driving conditions of the vehicle and the learning results of the vehicle. In this road traffic system, the vehicle is able to experience a situation even when the vehicle has not experienced the situation before. By referring to the driving behavior information of other vehicles that have been in the same vehicle, the system performs automatic driving control. It can handle the situation with the same level of driving performance as both vehicles. [Configuration 1.38] A road traffic system in which a plurality of vehicles travel on a road, the plurality of vehicles are provided with a hi-fi. A vehicle in which driving operations are performed by automatic driving control instead of by a human driver. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle. A learning processing unit that learns about surrounding objects and driving operations of the vehicle, and a driving behavior information processing unit that learns about surrounding objects and driving operations of the vehicle a driving behavior information acquisition unit for acquiring driving behavior information; The driving situation recognized by the driving situation recognition unit of the vehicle while referring to the information and the learning process The autonomous driving control unit controls autonomous driving based on the learning results of the autonomous driving control unit, and the autonomous driving control unit controls the driving behavior of the vehicle. a driving behavior information output unit that outputs information on the driving behavior of the other vehicle to an outside, The information is information that associates the driving conditions of the two vehicles with the driving operations performed by the other vehicle. The vehicle driving behavior information includes the driving conditions of the vehicle and the driving operations performed by the automatic driving control of the vehicle. A road traffic system that is information that corresponds to the operation of the road. The robot car in this road traffic system refers to the driving behavior information (experience information) of other vehicles. At the same time, the system performs automatic driving control based on the driving conditions of the vehicle and the learning results of the vehicle. The robot car of this road traffic system is able to experience situations even when it is in an unfamiliar situation. By referring to the driving behavior information of other vehicles that have been in the same vehicle, the system performs automatic driving control. The robots in this road traffic system can handle the situation with the same level of driving performance as a car. The robot car outputs driving behavior information (experience information) of its own vehicle to the outside, so The driving behavior information output from the vehicle is referred to by other vehicles to perform driving assistance control or automatic driving control. The other vehicle can also use the robot that has experienced the situation, even if it is in an unfamiliar situation. By referring to the driving behavior information of the car, driving assistance control or automatic driving control is performed. The situation can be handled with the same level of driving performance as the robot car. [Configuration 1.39] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from a non-robotic car; a driving behavior information receiving function for receiving the driving behavior information from the driving behavior information receiving device and a driving behavior information sending function for sending the driving behavior information to the robot car; and a communication function, and the non-robot car is driven by a human driver. A vehicle having a driving situation recognition unit that recognizes a driving situation of the vehicle and a human driver of the vehicle. A driving operation detection unit detects a driving operation by a driver, and a driving situation recognition unit recognizes the driving situation. operation history information that associates the driving situation with the driving operation detected by the driving operation detection unit. a driving behavior information transmitting unit that transmits driving behavior information including the driving behavior information to the computing system; The robot car is autonomously driven instead of being driven by a human driver. A vehicle that is driven by a driving control system and recognizes the driving conditions of the vehicle. a machine learning unit that learns about surrounding objects and driving operations of the vehicle; a driving behavior information receiving unit for receiving driving behavior information from the computing system; The driving situation recognition unit of the vehicle refers to the driving behavior information received by the information receiving unit. The automated driving control is performed based on the recognized driving situation and the learning result by the machine learning unit. A road traffic system comprising: The computing system of this road traffic system can then determine the driving behavior of non-robotic cars. The computer receives information (experience information) and transmits the driving behavior information to the robot car. The robot car receives driving behavior information from the driving system and drives the non-robot car. Autonomous driving control is performed based on the vehicle's driving conditions and learning results while referring to behavioral information. Therefore, the robot car in this road traffic system will be able to navigate in situations that it has never experienced before. Even if the robot is in a situation where it is not in a robotic state, it will still be able to drive autonomously by referring to the driving behavior information of non-robot cars that have experienced the situation. By controlling the vehicle's rotation, the robot can handle the situation with the same driving performance as a non-robotic car. can. According to this road traffic system, robot cars and non-robotic cars coexist. In this study, we aim to have a robot car learn the driving techniques of a driver who drives a non-robotic car. This can improve the autonomous driving performance of robot cars highly efficiently. As performance improves, the operational efficiency of the entire road transport system will improve, safety will increase, etc. It can be planned. [Configuration 1.40] A road traffic system in which a plurality of vehicles travel on a road, comprising a computing system the computing system receiving driving behavior information from a non-robotic car; and a driving behavior information receiving function for generating optimized driving behavior information based on the driving behavior information. An optimization information generation function that creates the optimized driving behavior information and updates it to the latest information to manage it. An optimization information update function that manages the driving behavior of the robot car and transmits the optimized driving behavior information to the robot car. A driving behavior information transmission function is provided, and the non-robot car is driven by a human driver. A vehicle in which a steering operation is performed, comprising: a driving situation recognition unit that recognizes a driving situation of the vehicle; a driving operation detection unit that detects a driving operation by a human driver, and the driving situation recognition unit and a driving operation detected by the driving operation detection unit. and transmitting driving behavior information including the operation history information to the computing system. and a dynamic information transmission unit, and the robot car is operated in place of a human driver. Instead, it is a vehicle that is driven by automatic driving control and recognizes the driving situation of the vehicle. a machine learning unit that learns about surrounding objects and driving operations of the vehicle; a driving behavior information receiving unit that receives the driving behavior information from the computing system; The driving behavior information receiving unit receives the driving behavior information, and the driving status of the vehicle is updated. The automatic driving is performed based on the driving situation recognized by the situation recognition unit and the learning result by the machine learning unit. and an automatic driving control unit that performs driving control. The computing system of this road traffic system can then determine the driving behavior of non-robotic cars. It receives information (experience information) and generates optimized driving behavior information based on the driving behavior information. The optimized driving behavior information is updated to the latest information and managed, and the driving behavior information is The robot car receives driving behavior information from this computing system. The robot car refers to the driving behavior information of the non-robot car and estimates the driving situation and The autonomous driving control is based on the learning results of the vehicle. The bot car is a vehicle that can control the vehicle in a situation that it has never experienced before, even if it is in a situation that it has never experienced before. Based on the driving behavior information of the car, the system performs autonomous driving control by referring to optimized driving behavior information. By doing so, the robot will be able to handle the situation with driving performance equal to or better than that of a non-robotic car. It can be dealt with.

[0008] [2. Vehicle configuration and function in road transport systems] The vehicle of the present invention includes a vehicle having the following configuration. [Configuration 2.1] A non-robot car with driving assistance control functions to assist human drivers in driving. The driving situation recognition unit recognizes the driving situation of the vehicle and acquires driving behavior information of other vehicles. a driving behavior information acquisition unit that acquires driving behavior information by referring to the driving behavior information acquired by the driving behavior information acquisition unit; and performing driving assistance control based on the driving situation recognized by the driving situation recognition unit. and an assistance control unit. This non-robot car refers to the driving behavior information (experience information) of other vehicles while driving its own vehicle. Driving assistance control is performed based on the situation. Therefore, this non-robot car can pass through a situation that it has never experienced before. By performing driving assistance control based on driving behavior information of other vehicles that have been experienced, The vehicle can handle the situation with the same level of driving performance as other vehicles. [Configuration 2.2] A non-robot car with driving assistance control functions to assist human drivers in driving. The driving situation recognition unit recognizes the driving situation of the vehicle and acquires driving behavior information of other vehicles. a driving behavior information acquisition unit that performs a driving operation based on the driving situation recognized by the driving situation recognition unit; Driving assistance that determines the driving operation to be performed and performs driving assistance control so that the driving operation is performed and a control unit, the driving assistance control unit being configured to determine the driving behavior based on knowledge information. A driving knowledge unit that stores driving behavior information (judgment criteria) acquired by the driving behavior information acquisition unit. A learning processing unit (knowledge processing unit) that updates the knowledge information stored in the driving knowledge unit based on the dynamic information. A non-robot car having a vehicle identification update processing unit. This non-robotic car generates knowledge information (the driving operation to be performed) based on the driving behavior information of other vehicles. While performing a learning process to update the knowledge information (e.g., criteria for deciding on an action), The driving operation according to the driving situation is determined based on the driving assistance control, and the driving assistance control is performed so that the driving operation is performed. conduct. Therefore, this non-robot car can pass through a situation that it has never experienced before. By learning the driving behavior of other vehicles that have been experienced, the system performs driving assistance control to It can handle the situation with the same level of driving performance as both vehicles. [Configuration 2.3] A non-robot car with driving assistance control functions to assist human drivers in driving. The driving situation recognition unit recognizes the driving situation of the vehicle and acquires driving behavior information of other vehicles. a driving behavior information acquisition unit that performs a driving operation based on the driving situation recognized by the driving situation recognition unit; Driving assistance that determines the driving operation to be performed and performs driving assistance control so that the driving operation is performed and a control unit, wherein the driving assistance control unit is configured to recognize the driving condition recognized by the driving condition recognition unit. A driving operation determination unit that determines a driving behavior according to a situation by calculation, and the driving behavior information acquisition unit The driving operation determination unit determines a driving operation to be used based on the driving behavior information obtained from the driving operation determination unit. A learning processing unit (parameter adjustment unit) that adjusts the parameters of the decision function. A non-robot car. This non-robot car adjusts the parameters of the driving operation decision function based on the driving behavior information of other vehicles. While performing a learning process to adjust the driving conditions, the driving operation decision function determines the driving operation according to the driving situation. The driving assistance control unit 100 determines the driving operation to be performed and performs driving assistance control so that the driving operation is performed. Therefore, this non-robot car can pass through a situation that it has never experienced before. By learning the driving behavior of other vehicles that have been experienced, the system performs driving assistance control to It can handle the situation with the same level of driving performance as both vehicles. [Configuration 2.4] The driving behavior information acquisition unit acquires driving behavior information of the other vehicle through communication between the host vehicle and the other vehicle. A non-robotic device according to any one of configurations 2.1 to 2.3, which is a driving behavior information receiving unit that receives information. Hot car. [Configuration 2.5] The driving behavior information acquisition unit acquires driving behavior information of other vehicles through communication between the vehicle and a ground stationary object. A non-robotic device according to any one of configurations 2.1 to 2.3, which is a driving behavior information receiving unit that receives information. Hot car. [Configuration 2.6] The driving behavior information acquisition unit acquires driving behavior information of other vehicles through communication between the vehicle and a road. A non-robot car according to any one of configurations 2.1 to 2.3, which is a driving behavior information receiving unit that receives - [Configuration 2.7] The driving behavior information acquisition unit acquires driving behavior information of other vehicles through communication between the vehicle and a mobile terminal. The non-robotic device according to any one of configurations 2.1 to 2.3, which is a driving behavior information receiving unit that receives driving behavior information. Tokar. [Configuration 2.8] The driving behavior information acquisition unit acquires driving behavior information of other vehicles from a computer on a network. Any one of configurations 2.1 to 2.3, which is a driving behavior information receiving unit that receives information from a driving system. 1 non-robot car. [Configuration 2.9] A driving behavior information output unit outputs driving behavior information of the vehicle to an outside, The behavior information is a driving information that corresponds the driving situation of the vehicle with the driving operation performed on the vehicle. A non-robot car according to any one of configurations 2.1 to 2.3, the non-robot car being a moving object. [Configuration 2.10] A driving operation detection unit that detects a driving operation by a human driver of the vehicle; The driving situation recognized by the situation recognition unit and the driving operation detected by the driving operation detection unit are Transmitting the associated driving behavior information to the computing system. A non-robot car according to any one of configurations 2.1 to 2.3 having a unit. [Configuration 2.11] Instead of a human driver operating the vehicle, the vehicle is operated by an automated driving control system. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself and a driving situation recognition unit that recognizes the driving situation of other vehicles. A driving behavior information acquisition unit that acquires behavior information; While referring to the behavior information, the automatic driving is performed based on the driving situation recognized by the driving situation recognition unit. and an automatic driving control unit that performs driving control. This robot car refers to the driving behavior information (experience information) of other vehicles and predicts the driving status of its own vehicle. Automatic driving control is performed based on the situation. Therefore, this robot car can experience a situation even if the vehicle itself has not experienced that situation. By performing automated driving control based on the driving behavior information of other vehicles that have The situation can be handled with the same level of driving performance as the vehicle. [Configuration 2.12] Instead of a human driver operating the vehicle, the vehicle is operated by an automated driving control system. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself and a driving situation recognition unit that recognizes the driving situation of other vehicles. A driving behavior information acquisition unit that acquires behavior information, and a driving situation recognized by the driving situation recognition unit. Based on the situation, the system determines the driving operation to be performed and controls the automatic driving so that the driving operation is performed. and an automatic driving control unit that controls the driving behavior determination unit to drive the vehicle. A driving knowledge unit that stores knowledge information to be referred to when deciding an action, and the driving action information acquisition unit Based on the driving behavior information acquired by the above, the knowledge information stored in the driving knowledge unit is adapted. and a learning processing unit (knowledge updating processing unit) that appropriately updates the knowledge. This robot car generates knowledge information (driving operations to be performed) based on the driving behavior information of other vehicles. While performing a learning process to update the criteria for determining the Determines driving operations according to driving conditions and performs automatic driving control to execute the driving operations. cormorant. Therefore, this robot car can experience a situation even if the vehicle itself has not experienced that situation. By learning the driving behavior of other vehicles that have driven in the past, the system performs automatic driving control. The situation can be handled with the same level of driving performance. [Configuration 2.13] Instead of a human driver operating the vehicle, the vehicle is operated by an automated driving control system. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself and a driving situation recognition unit that recognizes the driving situation of other vehicles. A driving behavior information acquisition unit that acquires behavior information, and a driving situation recognized by the driving situation recognition unit. Based on the situation, the system determines the driving operation to be performed and controls the automatic driving so that the driving operation is performed. and an automatic driving control unit that controls the driving situation recognition unit. A driving operation determination unit that determines a driving behavior according to the recognized driving situation by calculation; Based on the driving behavior information acquired by the behavior information acquisition unit, the driving operation determination unit A learning processing unit (parameter adjustment unit) that adjusts the parameters of the driving operation decision function used in the vehicle. A robot car characterized by: This robot car calculates the parameters of the driving operation decision function based on the driving behavior information of other vehicles. While performing the learning process to adjust the vehicle, the driving operation decision function determines the driving operation according to the driving situation. Then, automatic driving control is performed so that the driving operation is executed. Therefore, this robot car can experience a situation even if the vehicle itself has not experienced that situation. By learning the driving behavior of other vehicles that have driven in the past, the system performs automatic driving control. The situation can be handled with the same level of driving performance. [Configuration 2.14] The driving behavior information acquisition unit acquires driving behavior information of the other vehicle through communication between the host vehicle and the other vehicle. A driving behavior information receiving unit according to any one of configurations 2.11 to 2.13, which receives information. Bot car. [Configuration 2.15] The driving behavior information acquisition unit acquires driving behavior information of other vehicles through communication between the vehicle and a ground stationary object. A driving behavior information receiving unit according to any one of configurations 2.11 to 2.13, which receives information. Bot car. [Configuration 2.16] The driving behavior information acquisition unit acquires driving behavior information of other vehicles through communication between the vehicle and a road. The robot according to any one of configurations 2.11 to 2.13, which is a driving behavior information receiving unit for receiving car. [Configuration 2.17] The driving behavior information acquisition unit acquires driving behavior information of other vehicles through communication between the vehicle and a mobile terminal. A non-role vehicle according to any one of configurations 2.11 to 2.13, which is a driving behavior information receiving unit that receives driving behavior information. Bot car. [Configuration 2.18] The driving behavior information acquisition unit acquires driving behavior information of other vehicles from a computer on a network. Any one of configurations 2.11 to 2.13, which is a driving behavior information receiving unit that receives information from a driving system. This is the No.1 robot car. [Configuration 2.19] The driving behavior information of the other vehicle includes a driving situation of the other vehicle and a driving operation performed in the other vehicle. The robot car of any one of configurations 2.11 to 2.13, which is information that corresponds to the work. [Configuration 2.20] The driving behavior information of the other vehicle includes a driving situation of the other vehicle and a driving operation performed in the other vehicle. The robot car of any one of configurations 2.11 to 2.13, which is information that corresponds to the work. [Configuration 2.21] A driving behavior information output unit outputs driving behavior information of the vehicle to an outside, The behavior information is information that associates the driving situation of the vehicle with the driving operation performed on the vehicle. The robot car of any one of configurations 2.11 to 2.13, which is information. [Configuration 2.22] A vehicle in a road traffic system in which a plurality of vehicles travel on a road, the vehicle being The vehicle driving control system has a function of controlling the driving of the vehicle by referring to the driving behavior information of the other vehicle. is information that associates the driving situation of the other vehicle with the driving operation performed in the other vehicle. A vehicle characterized by: This vehicle controls its own driving by referring to the driving behavior information of other vehicles. This vehicle can recognize the situation of other vehicles that have experienced the situation even if the vehicle itself has not experienced it. By controlling driving based on driving behavior information, driving performance is at the same level as other vehicles. This can be used to deal with the situation. [Configuration 2.23] A vehicle in a road traffic system in which a plurality of vehicles travel on a road, a function of providing information on the driving behavior of other vehicles to other vehicles, a function of receiving information on the driving behavior of other vehicles, and A function of controlling the driving of the vehicle based on the driving behavior information of the vehicle. is information that associates the driving situation of the vehicle with the driving operation performed on the vehicle. The driving behavior information of the other vehicle includes the driving situation of the other vehicle and the driving operation performed in the other vehicle. The vehicle is characterized in that the information corresponds to the operation. This vehicle provides driving behavior information (experience information) to other vehicles. In addition, the driving behavior information of other vehicles can be used for driving control of the vehicle itself. Therefore, even if the vehicle is in a situation that it has not experienced, the vehicle can recognize the situation from other vehicles that have experienced the situation. By referring to the driving behavior information of both vehicles and controlling driving, the system achieves driving at the same level as the other vehicle. The performance can handle the situation. [Configuration 2.24] A vehicle in a road traffic system in which multiple vehicles travel on a road, A function to receive driving behavior information of other vehicles through communication with the vehicle and a function to refer to the driving behavior information of other vehicles. and a function of controlling the driving of the vehicle by using the driving behavior information of the other vehicle. The information is characterized in that the driving situation of the other vehicle is associated with the driving operation performed in the other vehicle. A vehicle that does this. This vehicle can receive driving behavior information (experience information) of other vehicles through vehicle-to-vehicle communication. In addition, the driving behavior information of other vehicles can be used for driving control of the own vehicle. Even in a situation that the vehicle itself has not experienced, the vehicle will be able to follow the driving of other vehicles that have experienced that situation. By referring to the driving behavior information and controlling the driving, the driving performance is at the same level as the other vehicles. The situation can be dealt with. [Configuration 2.25] A vehicle in a road traffic system in which multiple vehicles travel on a road, the vehicle and a stationary object on the ground The function of receiving driving behavior information of other vehicles through communication between the vehicles and the and a function of controlling the driving of the vehicle by using the driving behavior information of the other vehicle. The information is characterized in that the driving situation of the other vehicle is associated with the driving operation performed in the other vehicle. A vehicle that does this. This vehicle receives driving behavior information (experience information) of other vehicles through communication with stationary objects on the ground. This allows the driving behavior information of other vehicles to be used for driving control of the vehicle itself. Therefore, even if the vehicle is in a situation that it has not experienced, the vehicle can detect the situation from other vehicles that have experienced the situation. By referring to the driving behavior information of the vehicle and controlling the driving, the driving level is the same as that of the other vehicle. The rotation capability can handle the situation. [Configuration 2.26] A vehicle in a road traffic system in which multiple vehicles travel on a road, The function of receiving driving behavior information of other vehicles through communication and the function of referencing the driving behavior information of other vehicles to automatically and a function of controlling driving of the vehicle, the driving behavior information of the other vehicle being a driving situation of the other vehicle. and the driving operation performed in the other vehicle are associated with each other. Both. This vehicle can receive driving behavior information (experience information) of other vehicles through road-to-vehicle communication. In addition, the driving behavior information of other vehicles can be used for driving control of the own vehicle. Even in a situation that the vehicle itself has not experienced, the vehicle will be able to follow the driving of other vehicles that have experienced that situation. By referring to the driving behavior information and controlling the driving, the driving performance is at the same level as the other vehicles. The situation can be dealt with. [Configuration 2.27] A vehicle in a road traffic system in which a plurality of vehicles travel on a road, the vehicle and a mobile terminal The function of receiving driving behavior information of other vehicles through communication between the vehicles and the driving behavior information of other vehicles is also included. and a function of controlling driving of the vehicle by using the driving behavior information of the other vehicle. The information is characterized in that it is information that associates the situation with the driving operation performed in the other vehicle. A vehicle. This vehicle can receive driving behavior information (experience information) of other vehicles by communicating with a mobile terminal. In addition, the driving behavior information of other vehicles can be used for driving control of the vehicle itself. Therefore, even if the vehicle is in a situation that it has not experienced, the vehicle can recognize the situation from other vehicles that have experienced the situation. By referring to the driving behavior information of both vehicles and controlling driving, the system achieves driving at the same level as the other vehicle. The performance can handle the situation. [Configuration 2.28] A vehicle in a road traffic system in which a plurality of vehicles travel on a road, The function of uploading the data to a computing system on the network and the operation of other vehicles The ability to download movement information from a computing system on the network; Based on the driving behavior information downloaded from the computing system on the network, and a function of controlling the driving of the vehicle based on the driving behavior information of the vehicle. A driving operation history information including a driving situation and a driving operation performed on the vehicle. The driving behavior information of the other vehicle is information on the driving situation of the other vehicle and The vehicle is characterized in that the information is associated with a driving operation performed. This vehicle exchanges driving behavior information (experience information) with multiple other vehicles via a network. Moreover, the driving behavior information of other vehicles can be used for driving control of the own vehicle. Therefore, even if the vehicle is in a situation that it has not experienced, the vehicle will not be able to detect the situation. By referring to the driving behavior information of other vehicles, the system can control driving in a manner equivalent to that of the other vehicles. This level of driving performance allows the vehicle to handle the situation. [Configuration 2.29] A vehicle in a road traffic system in which a plurality of vehicles travel on a road, The function of uploading the data to a computing system on the network and controlling the operation of the vehicle The driving behavior information generated based on the turning behavior information and the driving behavior information of other vehicles is transmitted to the network. The ability to download from a computing system on the network and The system controls the driving of the vehicle by referring to driving behavior information downloaded from the driving control system. and a function of detecting a driving status of the vehicle and a driving action of the vehicle. The driving behavior information of the other vehicle is information that corresponds to the driving operation performed by the other vehicle. The information is particularly intended to associate the driving conditions of the other vehicle with the driving operations performed by the other vehicle. The vehicle in question. This vehicle uses its own driving behavior information (experience information) to compute on the network. The driving behavior information of the vehicle itself and that of other vehicles are uploaded to the driving system. The driving behavior information generated by the system is downloaded from a computing system on the network. Based on the driving behavior information of the vehicle and the driving behavior information of the other vehicle, The driving behavior information generated by the vehicle can be used for driving control of the vehicle. Even in a situation where the vehicle has not experienced the situation, the vehicle's driving behavior information and the vehicle's experience of the situation can be used to The driving control is performed by referring to the driving behavior information generated based on the driving behavior information of the other vehicle. This allows the vehicle to handle the situation with driving performance equal to or better than that of the other vehicle. [Configuration 2.30] Instead of a human driver operating the vehicle, the vehicle is operated by an automated driving control system. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself and a surrounding area recognition unit that recognizes the driving situation of the vehicle itself. A learning processing unit that learns about objects and driving operations, and a driving operation unit that acquires driving behavior information of other vehicles. A behavior information acquisition unit and a driving behavior information acquisition unit. A driving situation recognized by the driving situation recognition unit of the vehicle and a learning result by the learning processing unit and an automatic driving control unit that performs automatic driving control based on the driving behavior information of the other vehicle. , which is information associating the driving situation of the other vehicle with the driving operation performed in the other vehicle; A robot car characterized by the above. This robot car refers to the driving behavior information (experience information) of other vehicles and predicts the driving status of its own vehicle. The robot car performs autonomous driving control based on the situation and the learning results of the vehicle itself. Even in a situation that the vehicle has not experienced, the driving behavior of other vehicles that have experienced the situation can be By referring to the information and performing automatic driving control, the vehicle will be able to operate with the same level of driving performance as other vehicles. The situation can be dealt with. [Configuration 2.31] Instead of a human driver operating the vehicle, the vehicle is operated by an automated driving control system. The robot car includes a driving situation recognition unit that recognizes the driving situation of the vehicle itself and a surrounding area recognition unit that recognizes the driving situation of the vehicle itself. A learning processing unit that learns about objects and driving operations, and a driving operation unit that acquires driving behavior information of other vehicles. A behavior information acquisition unit and a driving behavior information acquisition unit. A driving situation recognized by the driving situation recognition unit of the vehicle and a learning result by the learning processing unit The autonomous driving control unit controls autonomous driving based on the driving behavior of the vehicle and outputs the driving behavior information of the vehicle to the outside. and a driving behavior information output unit for outputting driving behavior information of the other vehicle, the driving behavior information of the other vehicle corresponding to a driving situation of the other vehicle. The information is associated with a driving operation performed in the other vehicle, The driving behavior information of the vehicle is based on the driving situation of the vehicle and the automatic driving control of the vehicle. A robot car, in which information is associated with the driving operations performed. This robot car refers to the driving behavior information (experience information) of other vehicles and predicts the driving status of its own vehicle. The robot car performs autonomous driving control based on the situation and the learning results of the vehicle itself. Even in a situation that the driver has never experienced before, the driver can refer to the driving behavior information of other vehicles that have experienced the situation. By controlling autonomous driving based on the situation, the vehicle can handle the situation with the same level of driving performance as other vehicles. This robot car can also send out driving behavior information (experience information) of its own vehicle to the outside. Therefore, other vehicles can refer to the driving behavior information output from the robot car and perform driving assistance control. The other vehicle can also perform automatic driving control. The driving assistance control or the automatic driving control are performed by referring to the driving behavior information of the robot car that has experienced the situation. By controlling the vehicle's running, the vehicle can handle the situation with the same level of driving performance as the robot car. Cut.

[0009] [3. The structure and function of computing systems] The computing system of the present invention has the following configuration: Includes: [Configuration 3.1] A computing system for a road traffic system in which a plurality of vehicles travel on a road. A driving behavior information receiving function for receiving driving behavior information of one or more vehicles; A driving behavior information transmission method for transmitting driving behavior information to one or more vehicles different from a transmission source of the driving behavior information. A computing system having a function. The computing system calculates driving behavior information (experience information) of one or more vehicles. and transmits the driving behavior information to one or more vehicles different from the transmission source of the driving behavior information. The vehicle that receives the driving behavior information from this computing system The behavioral information can be used for driving control of the vehicle. Even in such a situation, driving control is performed based on the driving behavior information of other vehicles that have experienced the situation. By doing so, the vehicle can handle the situation with the same level of driving performance as the other vehicle. [Configuration 3.2] A computing system for a road traffic system in which a plurality of vehicles travel on a road. A driving behavior information receiving function for receiving driving behavior information of one or more vehicles; an optimization information generating function for generating optimized driving behavior information based on the information; An optimization information update function for updating the optimized driving behavior information to the latest information and managing the information; A driving behavior information transmission function for transmitting the driving behavior information to one or more vehicles. Computing system. The computing system calculates driving behavior information (experience information) of one or more vehicles. and generating optimized driving behavior information based on the driving behavior information. The controller updates the driving behavior information collected and transmits it to one or more vehicles. The vehicle that receives the driving behavior information from the computing system In other words, the vehicle can control the driving of both vehicles even in situations that the vehicle has never experienced before. Driving behavior optimized based on driving behavior information of other vehicles that have experienced the situation By referring to the information and controlling the driving, the driving performance is equal to or higher than that of the other vehicle. This can be used to deal with the situation. [Configuration 3.3] A computing system for a road traffic system in which a plurality of vehicles travel on a road. A driving behavior information receiving function for receiving driving behavior information from the robot car; and a driving behavior information transmission function for transmitting the driving behavior information to a non-robot car. A car that is driven by an automated driving control system instead of a human driver. A driving situation recognition unit that recognizes a driving situation of the vehicle, and The driving behavior information that corresponds the recognized driving situation and the driving operation by the automatic driving control is and a driving behavior information transmission unit for transmitting the driving behavior information to the non-robot computing system. The vehicle is equipped with a driving assistance function that assists the human driver in driving. A driving situation recognition unit that recognizes a driving situation of a vehicle and a driving behavior information receiving unit that receives the driving behavior information. A receiving unit and a driving behavior information receiving unit are provided to receive driving behavior information from the driving behavior information receiving unit. A driving assistance system that performs driving assistance control based on the driving situation recognized by the driving situation recognition unit. and a control unit. This computing system receives driving behavior information (experience information) from the robot car. The computing system receives the driving behavior information from the robot car and transmits the driving behavior information to the non-robotic car. The robot car that receives the driving behavior information refers to the driving behavior information and adjusts the driving of the vehicle. Therefore, non-robot cars will perform driving assistance control based on the situation. In such a situation, the robot car can refer to the driving behavior information of other robot cars that have experienced the situation. By using this technology, the robot can achieve driving performance equivalent to that of a non-robotic car in the given situation. Can deal with the situation. According to this computing system, robot cars and non-robotic cars In a situation where humans and robots coexist, a non-robotic car will learn the driving techniques of a robotic car, and This can improve the driving assistance performance of robot cars highly efficiently. As support performance improves, the operational efficiency of the entire road transport system will improve, safety will increase, and etc. will be achieved. [Configuration 3.4] A computing system for a road traffic system in which a plurality of vehicles travel on a road. A driving behavior information receiving function for receiving driving behavior information from a non-robot car; and a driving behavior information transmission function for transmitting driving behavior information to the robot car, and the non-robot car is A vehicle that is driven by a human driver and that recognizes the driving conditions of the vehicle. The driving situation recognition unit detects the driving operation of the human driver of the vehicle. a driving situation recognized by the driving situation recognition unit and a driving operation detection unit; and transmitting driving behavior information associated with the driving operation thus determined to the computing system. and a driving behavior information transmission unit for transmitting driving behavior information to the robot car, the robot car being driven by a human driver. A vehicle in which driving operations are performed by automatic driving control instead of the driver's own operation, a driving situation recognition unit that recognizes the driving situation, a driving behavior information receiving unit that receives the driving behavior information, The driving situation of the vehicle is determined while referring to the driving behavior information received by the driving behavior information receiving unit. An automatic driving control unit that performs automatic driving control based on the driving situation recognized by the recognition unit. 16. A computing system comprising: This computing system receives driving behavior information (experience information) from non-robotic cars. The computing system receives the driving behavior information and transmits it to the robot car. The robot car that receives the driving behavior information refers to the driving behavior information and adjusts the driving of the vehicle. Therefore, the robot car will be able to control the autonomous driving based on the situation. Even in such a situation, the robot can refer to the driving behavior information of non-robot cars that have experienced the situation. By controlling autonomous driving, the robot car can operate in the same driving conditions as a non-robotic car. Can deal with the situation. According to this computing system, robot cars and non-robotic cars In this study, we aim to improve the driving technique of a human driver who drives a non-robotic car in a situation where a robot coexists with a human driver. By having the robot car learn, it is possible to efficiently improve the autonomous driving performance of the robot car. As the autonomous driving capabilities of robot cars improve, the operational efficiency of the entire road transport system will also improve. The aim is to improve efficiency, safety, etc. [Configuration 3.5] A computing system for a road traffic system in which a plurality of vehicles travel on a road. a driving behavior information receiving function for receiving driving behavior information of one or more robot cars; Transmit driving behavior information to one or more robot cars different from the transmission source of the driving behavior information. A driving behavior information transmission function is provided, and the robot car is driven by a human driver. A vehicle in which driving operations are performed by automatic driving control instead of the driver's own operation, a driving situation recognition unit that recognizes the driving situation, a driving behavior information receiving unit that receives the driving behavior information, The driving situation of the vehicle is determined while referring to the driving behavior information received by the driving behavior information receiving unit. An automatic driving control unit that performs automatic driving control based on the driving situation recognized by the recognition unit; The driving situation recognized by the driving situation recognition unit is associated with the driving operation by the autonomous driving control. A driving behavior information transmission unit that transmits driving behavior information to the computing system. The driving behavior information is information that associates the driving situation of the robot car with the driving operation. A computing system. This computing system receives driving behavior information (experience information) from the robot car. and transmits the driving behavior information to a robot car different from the sending source of the driving behavior information. The robot car receives driving behavior information from this computing system and can then control other robots. The system performs automatic driving control based on the vehicle's driving conditions while referring to the driving behavior information of the other vehicle. Therefore, the robot car can experience a situation that the vehicle itself has never experienced. The robot car can automatically adjust its own driving conditions based on the driving behavior of other robot cars that have driven it before. By controlling the driving, the robot car can deal with the situation with the same level of driving performance as other robot cars. It can be dealt with. This computing system allows robot cars in the road traffic system to communicate with each other. By sharing driving behavior information, the learning efficiency of robot cars in road traffic systems can be improved. By improving the system, autonomous driving performance can be improved rapidly. This will enable rapid improvement in the autonomous driving performance of bot cars, which will contribute to the entire road transport system. The operational efficiency, safety, etc. will be rapidly improved. [Configuration 3.6] A computing system for a road traffic system in which a plurality of vehicles travel on a road. a driving behavior information receiving function for receiving driving behavior information of one or more robot cars; An optimization information generating function for generating optimized driving behavior information based on the driving behavior information; An optimization information update function for updating and managing the optimized driving behavior information to the latest information; A driving behavior information transmission function that transmits optimized driving behavior information to one or more robot cars. and the robot car is operated autonomously instead of by a human driver. A vehicle in which driving operation is performed by a driving control, the driving situation of the vehicle being recognized a recognition unit, a driving behavior information receiving unit that receives the driving behavior information, and the driving behavior information receiving unit The driving situation recognition unit of the vehicle recognizes the driving situation while referring to the driving behavior information received by the driving behavior recognition unit. An automatic driving control unit that performs automatic driving control based on the driving situation, and The driving behavior information that corresponds the recognized driving situation and the driving operation by the automatic driving control is a driving behavior information transmission unit for transmitting the driving behavior information to a computing system; is information that associates the driving situation and driving operation of the robot car, Operating system. This computing system receives driving behavior information (experience information) from the robot car. and generating optimized driving behavior information based on the driving behavior information. The driving behavior information is updated and managed, and the driving behavior information is sent to the robot car. The robot car receives driving behavior information from this computing system and then drives it in a controlled manner. The system performs autonomous driving control based on the driving conditions of the vehicle while referring to the driving behavior information of the robot car. Therefore, the robot car can navigate through situations that it has never experienced before. The system provides optimized driving behavior information based on the driving behavior information of other robot cars it has experienced. By referencing the driver's own vehicle and controlling autonomous driving, the car will achieve a level equal to or higher than that of other robot cars. Driving performance can handle the situation. This computing system allows robot cars in the road traffic system to communicate with each other. By sharing driving behavior information, the learning efficiency of robot cars in road traffic systems can be improved. By improving the system, autonomous driving performance can be improved rapidly. This will enable rapid improvement in the autonomous driving performance of bot cars, which will contribute to the entire road transport system. The operational efficiency, safety, etc. will be rapidly improved. [Configuration 3.7] The optimized driving behavior information is based on the vehicle attributes of the vehicle to which the driving behavior information is provided. and optimizing the driving behavior information according to the driving behavior information. Driving behavior information optimized to minimize the possibility of causing a malfunction; Driving behavior information optimized to minimize the energy consumption of the vehicle in the driving behavior information; Driving behavior information optimized to maximize the regenerative energy of the vehicle receiving the information, The number of accelerations or the acceleration time for a given travel distance or a given travel time is minimized. Optimized driving behavior information, the number of braking events or braking time for a specified driving distance or a specified driving time Driving behavior information optimized to minimize or maximize time from departure point to destination point Driving behavior information optimized to minimize the distance traveled, or from the starting point to the destination Configuration 3.2 or 3, which is driving behavior information optimized to minimize the driving time to .6 computing system. [Configuration 3.8] The optimization information generation function is based on vehicle attributes of a vehicle that receives the driving behavior information. The driving behavior information is modified so as to minimize the possibility of the vehicle coming into contact with an obstacle. A computing system according to any one of configurations 3.2 and 3.6, including the ability to correct This computing system is a vehicle that provides driving behavior information (provider vehicle). When the attributes of both vehicles differ from the vehicle attributes of the vehicle receiving the driving behavior information (recipient vehicle) , a driving behavior corrected so as to minimize the possibility of the provided vehicle coming into contact with an obstacle. The information is provided to the recipient vehicle. According to this computing system, the driving behavior information is provided by a source vehicle and a destination vehicle. Even if the vehicle attributes are different, the vehicles can refer to each other's driving behavior information and perform driving assistance control or automatic Operation control can be performed.

[0010] [4. Computer Programs] The computer program of the present invention includes a program having the following configuration. [Configuration 4.1] The road traffic system according to any one of the configurations 1.1 to 1.39 is configured to be implemented by one or more computers. A computer program to realize this using data. This computer program is executed on one or more computers constituting a road traffic system. The road traffic system according to any one of the configurations 1.1 to 1.39 is It will be realized. [Configuration 4.2] The non-robot car according to any one of configurations 2.1 to 2.10 is connected to one or more computers. A computer program to realize this using the data. This computer program is then transmitted to one or more computers constituting a non-robot car. By executing the above, the non-robot car according to any one of configurations 2.1 to 2.10 It will be realized. [Configuration 4.3] The robot according to any one of configurations 2.11 to 2.22, 2.30, and 2.31. A computer program for implementing the car using one or more computers. This computer program is executed by one or more computers that constitute the robot car. By executing the above, any of the configurations 2.11 to 2.22, 2.30, and 2.31 can be realized. The non-robot car described in any one of the above is realized. [Configuration 4.1] A computing system according to any one of configurations 3.1 to 3.8 is configured to include one or more A computer program for implementing the functions of a computer. By executing this computer program on one or more computers, A computing system according to any one of configurations 3.1 to 3.8 is implemented.

[0011] [5. Configuration and Function of Shared Vehicle System] In the road traffic system according to any one of the configurations 1.1 to 1.40, a vehicle is used in a plurality of ways. A vehicle sharing system characterized in that the vehicle is shared by multiple users. According to the present invention, a vehicle sharing system can be constructed by utilizing the road traffic system of the present invention. do. According to the vehicle sharing system of the present invention, a situation in which robot cars and non-robot cars coexist can be realized. Below, we show how to train a non-robotic car to learn the driving techniques of a robotic car. Driving assistance performance can be improved highly efficiently. Driving assistance performance of non-robot cars is improved. As a result, the overall operational efficiency of the shared vehicle system will improve, safety will increase, and customer satisfaction will increase. The above, etc. are aimed at. According to the vehicle sharing system of the present invention, a situation in which robot cars and non-robot cars coexist can be realized. Below, we show how to train a non-robotic car to learn the driving techniques of a robotic car. Driving assistance performance can be improved highly efficiently. Driving assistance performance of non-robot cars is improved. As a result, the overall operational efficiency of the shared vehicle system will improve, safety will increase, and customer satisfaction will increase. The above, etc. are aimed at. According to the vehicle sharing system of the present invention, the robot cars in the vehicle sharing system can drive with each other. By sharing dynamic information, the learning efficiency of the robot cars in the shared vehicle system can be improved. All robots in the shared vehicle system can be rapidly improved in autonomous driving performance. This will allow the autonomous driving performance of cars to be rapidly improved, making it possible to operate the entire shared vehicle system. Efficiency, safety, customer satisfaction, etc. will improve rapidly.

[0012] [6. Computer Programs] A computer for implementing the vehicle sharing system of the present invention using one or more computers. Computer program. By executing this computer program on one or more computers, A vehicle sharing system can be constructed by utilizing the road traffic system of the present invention. [7. Configuration and Function of Robot Car Training System] The robot car training system of the present invention includes a system having the following configuration. [Configuration 7.1] A robot car and a non-robot car that runs along the same route as the robot car are included. The non-robot car is a vehicle that is driven by a human driver. A driving situation recognition unit that recognizes the driving situation of both vehicles and a driving operation unit operated by a human driver of the vehicle a driving operation detection unit that detects the driving situation recognized by the driving situation recognition unit and the driving operation A driving behavior information output unit that outputs driving behavior information associated with the driving operation detected by the operation detection unit. and an information output unit, and the robot car operates in place of a human driver. A vehicle that is driven by automatic driving control and recognizes the driving situation of the vehicle. a driving situation recognition unit; and a driving behavior information acquisition unit for acquiring driving behavior information of the non-robot car; and performing automatic driving control based on the driving situation recognized by the driving situation recognition unit of the vehicle. At the same time, the non-robotic and an automatic driving control unit that performs a learning process to learn the driving behavior of the autonomous vehicle. A robot car training system. In this robot car training system, the non-robot car is Outputting driving behavior information associated with driving operations performed by a human driver of a vehicle The robot car receives the driving behavior information output from the non-robot car. Then, The robot car performs autonomous driving control based on the driving conditions of the vehicle and also uses the acquired driving Learn the driving behavior of a non-robot car based on driving behavior information. This robot car training system allows human drivers to learn how to drive a non-robotic car. By having the robot car learn the driving behavior of the driver, the autonomous driving performance of the robot car can be improved. As the autonomous driving performance of robot cars improves, the safety and Road traffic systems that are more reliable and, ultimately, allow robotic and non-robotic cars to coexist Overall safety and reliability are improved. [Configuration 7.2] The autonomous driving control unit processes the driving behavior information acquired by the driving behavior information acquisition unit into a learning data. The driving behavior is recorded as a data set (a pair of a driving situation and a driving operation performed in that situation). The robot car performs the same driving operation (correct operation) as the non-robot car in each driving situation included in the dynamic information. A learning process (a learning process using supervised learning) is performed so that the above-mentioned operation is performed in the vehicle. Robot car training system configuration 7.1. According to this robot car training system, the driving behavior information of a non-robot car is used as learning data. Using supervised learning with a set of human drivers to drive non-robotic cars It is possible to teach robot cars to learn behaviors. [Configuration 7.3] The autonomous driving control unit is configured to control the autonomous driving of the non-robot car based on the driving behavior information of the non-robot car. The more the non-robot behaves in a manner similar to the driving behavior of the car, the more positive the reward will be. The more the driving behavior is different from the driving behavior of the target car, the more negative the reward (punishment) is given. The vehicle learns to take driving actions that are likely to yield the most rewards (learning process using reinforcement learning). A robot car training system with configuration 7.1 that performs autonomous driving (control). This robot car training system uses training based on the driving behavior information of non-robotic cars. Through learning, the driving behavior of a human driver who drives a non-robot car is imitated by the robot car. It can be made to learn. [Configuration 7.4] A robot car and a non-robot car that runs along the same route as the robot car are included. The non-robot car is a vehicle that is driven by a human driver. A driving situation recognition unit that recognizes the driving situation of both vehicles and a driving operation unit operated by a human driver of the vehicle a driving operation detection unit that detects the driving situation recognized by the driving situation recognition unit and the driving operation A driving behavior information output unit that outputs driving behavior information associated with the driving operation detected by the operation detection unit. and an information output unit, and the robot car operates in place of a human driver. A vehicle that is driven by automatic driving control and recognizes the driving situation of the vehicle. A driving situation recognition unit and a driving control unit to be executed based on the driving situation recognized by the driving situation recognition unit. An automatic driving control unit that determines a driving operation and performs automatic driving control so that the driving operation is executed and a driving behavior information acquisition unit for acquiring the driving behavior information output from the non-robot car. and the automatic driving control unit is configured to determine the driving operation by using knowledge information (judgment A driving knowledge unit storing the driving behavior information acquired by the driving behavior information acquisition unit. A learning process is performed to update the knowledge information stored in the driving knowledge unit based on the information. A robot car training system comprising: a processing unit (knowledge update processing unit). In this robot car training system, the non-robot car is Outputting driving behavior information associated with driving operations performed by a human driver of a vehicle The robot car receives the driving behavior information output from the non-robot car. Then, The robot car refers to the knowledge information to determine a driving operation according to the driving situation, and The system controls the autonomous driving so that the above-mentioned tasks are executed, and also performs knowledge sharing based on the acquired driving behavior information. A learning process is performed to update information (such as the criteria for determining which driving maneuvers should be performed). This robot car training system allows human drivers to learn how to drive a non-robotic car. By having the robot car learn the driving behavior of the driver, the autonomous driving performance of the robot car can be improved. As the autonomous driving performance of robot cars improves, the safety and Road traffic systems that are more reliable and, ultimately, allow robotic and non-robotic cars to coexist Overall safety and reliability are improved. [Configuration 7.5] The learning processing unit converts the driving behavior information acquired by the driving behavior information acquisition unit into learning data. The driving behavior information is then calculated as a set (a set of a driving situation and a driving operation performed in that situation). The driving operation (correct operation) is the same as that of the non-robot car in each driving situation included in the information. A learning process for updating the knowledge information stored in the driving knowledge unit so that the above is performed in the vehicle. A robot car training system with configuration 7.4 that performs processing (learning processing using supervised learning). According to this robot car training system, the driving behavior information of a non-robot car is used as learning data. Using supervised learning with a set of human drivers to drive non-robotic cars It is possible to teach robot cars to learn behaviors. [Configuration 7.6] The learning processing unit is configured to detect a driving behavior of the non-robot car based on the driving behavior information of the non-robot car. The more the non-robot performs driving behavior that is closer to the driving behavior of the The more the driving behavior is different from the car's driving behavior, the more negative the reward (punishment) is given. The knowledge information stored in the driving knowledge unit is used to select a driving action that is likely to obtain the greatest reward. The robot car training of configuration 1.4 performs a learning process (learning process by reinforcement learning) to update system. This robot car training system uses training based on the driving behavior information of non-robotic cars. Through learning, the driving behavior of a human driver who drives a non-robot car is imitated by the robot car. It can be made to learn. [Configuration 7.7] A robot car and a non-robot car that runs along the same route as the robot car are included. The non-robot car is a vehicle that is driven by a human driver. A driving situation recognition unit that recognizes the driving situation of both vehicles and a driving operation unit operated by a human driver of the vehicle a driving operation detection unit that detects the driving situation recognized by the driving situation recognition unit and the driving operation A driving behavior information output unit that outputs driving behavior information associated with the driving operation detected by the operation detection unit. and an information output unit, and the robot car operates in place of a human driver. A vehicle that is driven by automatic driving control and recognizes the driving situation of the vehicle. A driving situation recognition unit and a driving control unit to be executed based on the driving situation recognized by the driving situation recognition unit. An automatic driving control unit that determines a driving operation and performs automatic driving control so that the driving operation is executed and a driving behavior information acquisition unit for acquiring the driving behavior information output from the non-robot car. and the autonomous driving control unit is configured to: a driving operation determination unit that determines a driving behavior based on the driving behavior information acquired by the driving behavior information acquisition unit; Based on the driving behavior information obtained, a driving operation decision function used in the driving operation decision unit is A learning processing unit (parameter adjustment unit) that adjusts the parameters of the number of Botcar teaching system. In this robot car training system, the non-robot car is Outputting driving behavior information associated with driving operations performed by a human driver of a vehicle The robot car receives the driving behavior information output from the non-robot car. Then, The robot car determines the driving operation according to the driving situation of the vehicle using a driving operation decision function, The system performs automatic driving control so that the driving operation is executed, and also performs the driving behavior information acquired. Based on the result, a learning process is performed to adjust the parameters of the driving operation decision function. This robot car training system allows human drivers to learn how to drive a non-robotic car. By having the robot car learn the driving behavior of the driver, the autonomous driving performance of the robot car can be improved. As the autonomous driving performance of robot cars improves, the safety and Road traffic systems that are more reliable and, ultimately, allow robotic and non-robotic cars to coexist Overall safety and reliability are improved. [Configuration 7.8] The learning processing unit converts the driving behavior information acquired by the driving behavior information acquisition unit into learning data. The driving behavior information is then calculated as a set (a set of a driving situation and a driving operation performed in that situation). The driving operation (correct operation) is the same as that of the non-robot car in each driving situation included in the information. A learning process for adjusting the parameters of the driving operation decision function so that the following is performed in the vehicle: A robot car training system with configuration 9.7 that performs learning processing using supervised learning. According to this robot car training system, the driving behavior information of a non-robot car is used as learning data. Using supervised learning with a set of human drivers to drive non-robotic cars It is possible to teach robot cars to learn behaviors. [Configuration 7.9] The learning processing unit is configured to detect a driving behavior of the non-robot car based on the driving behavior information of the non-robot car. The more the non-robot performs driving behavior that is closer to the driving behavior of the The more the driving behavior is different from the car's driving behavior, the more negative the reward (punishment) is given. The parameters of the driving operation decision function are adjusted so that the driver takes the driving action that is likely to obtain the most reward. The robot car training system of configuration 9.7 performs learning processing (learning processing by reinforcement learning) to adjust the Tem. This robot car training system uses training based on the driving behavior information of non-robotic cars. Through learning, the driving behavior of a human driver who drives a non-robot car is imitated by the robot car. It can be made to learn. [Configuration 7.10] The non-robot car travels along the route ahead of the robot car. The robot car training system of any one of configurations 9.1 to 9.9. In this robot car training system, the driving behavior of a non-robot car that has previously traveled the same route is Based on the dynamic information, the driving behavior of the human driver who drives the non-robot car is simulated by the robot. The car is then trained. This robot car training system allows the robot car to experience new situations while The driving behavior of a human driver who has already experienced the situation is compared to that of a robot. It is possible to have the car learn (learn based on prior information). [Configuration 7.11] The non-robot car travels along the route after the robot car. The robot car training system of any one of configurations 7.1 to 7.9. In this robot car training system, the driving behavior of a non-robot car that traveled the same route later is Based on the dynamic information, the driving behavior of the human driver who drives the non-robot car is simulated by the robot. The car is then trained. According to this robot car training system, after exposing the robot car to new situations, The driving behavior of a human driver of a non-robot car who experienced the situation is then transferred to the robot car. It is possible to make it learn (learn based on ex-post information). [Configuration 7.12] a computing system, the computing system being configured to a driving behavior information receiving unit for receiving driving behavior information from a mobile car; a driving behavior information transmission unit that transmits the driving behavior information to a bot car, Transmitting driving behavior information of a non-robotic car to the computing system. The driving behavior information acquisition unit is a driving behavior information transmission unit, and the driving behavior information acquisition unit transmits the driving behavior information to the computing device. Any one of configurations 7.1 to 7.11, which is a driving behavior information receiving unit that receives driving behavior information from a driving system. No. 1 robot car training system. . In this robot car training system, the computing system is The system receives driving behavior information (experience information) from the driving car and transmits the driving behavior information to the robot car. do. According to this robot car training system, the robot car is The driving behavior information of the non-robot car is acquired through the It is possible for the system to learn the driving behavior of a human driver operating a supercar. [Configuration 7.13] The computing system includes a driving behavior information receiving unit. an optimization information generating unit that generates optimized driving behavior information based on the information; The latest driving behavior information generated by the optimization information generating unit is transmitted to the robot car. A robot car training system according to configuration 7.12, comprising: a driving behavior information transmission unit for transmitting driving behavior information to the driving behavior information transmission unit; In this robot car training system, the computing system is a non-robotic It receives driving behavior information (experience information) from the driver and optimizes the driving behavior based on the driving behavior information. The controller 100 generates optimized driving behavior information and transmits the optimized driving behavior information to the robot car. The robot car receives optimized driving behavior information from the computing system. A human driver drives the non-robot car based on the optimized driving behavior information. It can learn the driving behavior of a vehicle. [Configuration 7.14] The optimized driving behavior information is provided to the robot car. Driving behavior information optimized according to both attributes, and a robot car receiving the driving behavior information. Driving behavior information optimized to minimize the possibility of the vehicle coming into contact with an obstacle; The robot car is provided with dynamic information and its operation is optimized to minimize its energy consumption. The robot car that receives the driving behavior information and the driving behavior information is provided with a system that maximizes the regenerative energy of the robot car. The driving behavior information optimized for a given driving distance or a given driving time is or driving behavior information optimized to minimize acceleration time, a predetermined mileage or a predetermined Driving patterns optimized to minimize or maximize the number of braking operations or braking time during the trip Dynamic information, driving behavior optimized to minimize the distance traveled from the starting point to the destination Information or driving optimized to minimize travel time from start to finish Robot car teaching system with configuration 7.13, which is behavioral information. [Configuration 7.15] The autonomous driving control unit is equipped with a multi-layer neural network program. The learning process is performed by the multi-layer neural network program. .9 Robot car training system. According to this robot car teaching system, the multi-layer neural network program By equipping robot cars with the deep learning capabilities that are emerging, we will be able to create human-driven cars that can drive non-robotic cars. The robot car extracts and learns the characteristics of the driver's driving behavior (recognition, judgment, planning, operation) by itself. It is possible to have them practice the practice. [Configuration 7.16] The autonomous driving control unit includes a neuromorphic chip. A robot controller according to any one of the configurations 7.1 to 7.9, which performs the learning process by using a learning chip. -Teaching system. According to this robot car teaching system, the neuromorphic chip is By equipping robot cars with deep learning capabilities that can be used to drive non-robotic cars, The robot car learns by extracting the characteristics of the driver's driving behavior (recognition, judgment, planning, operation) by itself. It can be carried out. [Configuration 7.17] The neuromorphic chip is equipped with a spiking neural net. This is a robot car training system with configuration 7.16. This robot car training system uses spiking neural networks to By equipping a robot car with a learning function that mimics the real brain, a human driver can drive a non-robotic car. The robot car is designed to extract the characteristics of human driver's driving behavior (recognition, judgment, planning, operation) It is possible to have them go out and learn.

[0013] [9. Configuration and Function of Robot Car Training Method] The robot car training method of the present invention includes a robot car training method having the following configuration. [Configuration 8.1] Enabling a robot car to learn the driving behavior of a human driver who drives a non-robotic car A robot car driving training method for teaching the driving of the robot car by a non-robot car running step in which the non-robot car runs along the same route as the robot car; A non-robot car driving situation recognition system that recognizes the driving situation of the non-robot car while driving. The robot car is then driven by a human driver while traveling along the route. a driving operation detection step for detecting a driving operation; and a driving operation detection step for correlating the driving situation with the driving operation. A driving behavior information output step in which the non-robot car outputs behavior information; A robot car traveling step of traveling along a route, and the robot car traveling along the route A step of recognizing the driving situation of the robot car and a step of recognizing the driving situation of the robot car. A driving behavior information acquisition step of acquiring driving behavior information of the robot car; An automatic driving control step of performing automatic driving control based on the driving situation; A robot car learns the driving behavior of a human driver who drives a non-robotic car. A robot car training method comprising: In this robot car training method, the non-robot car is The driving behavior information is output in association with the driving operations performed by the human driver. The robot car acquires the driving behavior information output from the non-robot car. The car performs autonomous driving control based on the driving conditions of the vehicle and also uses the acquired driving behavior. The driving behavior of a human driver driving a non-robot car is learned based on dynamic information. According to this robot car training method, the human driver who drives a non-robot car By having the robot car learn driving behavior, it is possible to improve the autonomous driving performance of the robot car. As the autonomous driving performance of robot cars improves, the safety and reliability of robot cars will also increase. This will lead to an entire road traffic system in which robotic and non-robotic cars coexist. The safety and reliability of the system will be improved. [Configuration 8.2] The learning step includes learning the driving behavior information acquired by the driving behavior information acquisition step. The driving conditions and the driving operations performed in the conditions are used as a training data set. In each driving situation included in the driving behavior information, the robot car performs the same driving operation as the non-robot car (correct answer The vehicle performs learning (supervised learning) so that the above-mentioned operation can be performed on the vehicle. The robot car training method of configuration 8.1 is the next step. According to this robot car training method, the driving behavior information of a non-robot car is added to a learning data set. By using supervised learning to simulate the driving behavior of a human driver driving a non-robotic car, The robot car can learn this. [Configuration 8.3] The learning step includes learning a driving behavior of the non-robot car based on driving behavior information of the non-robot car. The more the non-robotic driver behaves in a manner similar to the non-robotic driver's behavior, the more positive the reward will be given. When the driving behavior was farther from the car's driving behavior, a more negative reward (punishment) was given. The system learns to take driving actions that are likely to yield the most rewards (learning process using reinforcement learning) The robot car training method of configuration 8.1, which is a step of performing According to this robot car training method, reinforcement learning based on driving behavior information of a non-robot car is performed. This allows the robot car to learn the driving behavior of a human driver who drives a non-robotic car. It can be done. [Configuration 8.4] Enabling a robot car to learn the driving behavior of a human driver who drives a non-robotic car A robot car driving training method for teaching the driving of the robot car by a non-robot car running step in which the non-robot car runs along the same route as the robot car; A non-robot car driving situation recognition system that recognizes the driving situation of the non-robot car while driving. The robot car is then driven by a human driver while traveling along the route. a driving operation detection step for detecting a driving operation; and a driving operation detection step for correlating the driving situation with the driving operation. A driving behavior information output step in which the non-robot car outputs behavior information; A robot car traveling step of traveling along a route, and the robot car traveling along the route A robot car driving situation recognition step for recognizing a driving situation of a non-robot car. a driving behavior information acquisition step of acquiring driving behavior information of the robot car; A driving operation determination step of determining a driving operation to be executed based on the driving situation of the vehicle; An automatic driving control step of performing automatic driving control so that an operation is executed; An operation knowledge storage step for storing knowledge information (criteria, etc.) to be referred to when determining whether or not the operation is performed; The knowledge information is updated based on the driving behavior information acquired by the driving behavior information acquisition step. and a learning step of performing a learning process to learn the robot car. In this robot car training method, the non-robot car is The driving behavior information is output in association with the driving operations performed by the human driver. The robot car acquires the driving behavior information output from the non-robot car. The car refers to the knowledge information to determine the driving operation according to the driving situation, and the driving operation is executed. It also performs automatic driving control so that the driver can drive smoothly and accurately, and provides knowledge and information based on the acquired driving behavior information. The system performs a learning process that updates the driving maneuvers to be performed (such as the criteria for determining which driving maneuvers to perform). This robot car training system allows human drivers to learn how to drive a non-robotic car. By having the robot car learn the driving behavior of the driver, the autonomous driving performance of the robot car can be improved. As the autonomous driving performance of robot cars improves, the safety and Road traffic systems that are more reliable and, ultimately, allow robotic and non-robotic cars to coexist Overall safety and reliability are improved. [Configuration 8.5] The learning step includes learning the driving behavior information acquired by the driving behavior information acquisition step. The driving conditions and the driving operations performed in the conditions are used as a training data set. In each driving situation included in the driving behavior information, the robot car performs the same driving operation as the non-robot car (correct answer The driving knowledge storing step stores the driving knowledge stored in the driving knowledge storing step so that the driving knowledge storing step is performed in the vehicle. This is the step of performing learning processing (learning processing by supervised learning) to update knowledge information. How to teach robot cars for students 8.4. According to this robot car training method, the driving behavior information of a non-robot car is added to a learning data set. By using supervised learning to simulate the driving behavior of a human driver driving a non-robotic car, The robot car can learn this. [Configuration 8.6] The learning step includes learning a driving behavior of the non-robot car based on driving behavior information of the non-robot car. The more the non-robotic driver behaves in a manner similar to the non-robotic driver's behavior, the more positive the reward will be given. When the driving behavior was farther from the car's driving behavior, a more negative reward (punishment) was given. The driving knowledge storage step stores the driving behavior that is likely to obtain the most reward. This is a step of performing a learning process (learning process by reinforcement learning) to update the stored knowledge information. ,Robot car teaching method of configuration 8.4. According to this robot car training method, reinforcement learning based on driving behavior information of a non-robot car is performed. This allows the robot car to learn the driving behavior of a human driver who drives a non-robotic car. It can be done. [Configuration 8.7] Enabling a robot car to learn the driving behavior of a human driver who drives a non-robotic car A robot car driving training method for teaching the driving of the robot car by a non-robot car running step in which the non-robot car runs along the same route as the robot car; A non-robot car driving situation recognition system that recognizes the driving situation of the non-robot car while driving. The robot car is then driven by a human driver while traveling along the route. a driving operation detection step for detecting a driving operation; and a driving operation detection step for correlating the driving situation with the driving operation. A driving behavior information output step in which the non-robot car outputs behavior information; A robot car traveling step of traveling along a route, and the robot car traveling along the route A robot car driving situation recognition step for recognizing a driving situation of a non-robot car. a driving behavior information acquisition step of acquiring driving behavior information of the robot car; A driving operation determination step of determining a driving behavior according to the driving situation by calculation; An automatic driving control step of performing automatic driving control so that the driving action information is executed; In the driving operation determination step, based on the driving behavior information acquired in the acquisition step, A learning step for performing a learning process to adjust the parameters of the driving operation decision function to be used; A robot car training method comprising: In this robot car training method, the non-robot car is The driving behavior information is output in association with the driving operations performed by the human driver. The robot car acquires the driving behavior information output from the non-robot car. The driver determines the driving operation according to the driving situation of the vehicle using a driving operation decision function. The system controls the automatic driving so that the driver can perform driving operations and automatically adjusts the driving behavior based on the acquired driving behavior information. A learning process is then performed to adjust the parameters of the driving operation decision function. According to this robot car training method, the human driver who drives a non-robot car By having the robot car learn driving behavior, it is possible to improve the autonomous driving performance of the robot car. As the autonomous driving performance of robot cars improves, the safety and reliability of robot cars will also increase. This will lead to an entire road traffic system in which robotic and non-robotic cars coexist. The safety and reliability of the system will be improved. [Configuration 8.8] The learning step includes learning the driving behavior information acquired by the driving behavior information acquisition step. The driving conditions and the driving operations performed in the conditions are used as a training data set. In each driving situation included in the driving behavior information, the robot car performs the same driving operation as the non-robot car (correct answer The parameters of the driving operation decision function are adjusted so that the driving operation (operation) is performed in the vehicle. The robot of configuration 8.7, which is the step of performing the learning process (learning process by supervised learning). Car training methods. According to this robot car training method, the driving behavior information of a non-robot car is added to a learning data set. By using supervised learning to simulate the driving behavior of a human driver driving a non-robotic car, The robot car can learn this. [Configuration 8.9] The learning step includes learning a driving behavior of the non-robot car based on driving behavior information of the non-robot car. The more the non-robotic driver behaves in a manner similar to the non-robotic driver's behavior, the more positive the reward will be given. When the driving behavior was farther from the car's driving behavior, a more negative reward (punishment) was given. The parameters of the driving operation decision function are adjusted so that the driver takes the driving action that is likely to obtain the most reward. The robot in configuration 8.7 performs the learning process (learning process by reinforcement learning) to adjust the How to teach car driving. According to this robot car training method, reinforcement learning based on driving behavior information of a non-robot car is performed. This allows the robot car to learn the driving behavior of a human driver who drives a non-robotic car. It can be done. [Configuration 8.10] The non-robot car travels along the route ahead of the robot car. A robot car training method according to any one of configurations 8.1 to 8.9. In this robot car training method, the driving behavior information of a non-robot car that previously traveled the same route is used. Based on the information, the driving behavior of the human driver who drives the non-robot car is changed to that of the robot. Let the car learn. According to this robot car training method, the robot car is made to experience new situations while The robot car learns the driving behavior of a human driver of a non-robotic car who has already experienced the situation. It is possible to make the system learn based on prior information. [Configuration 8.11] The non-robot car travels along the route after the robot car. A robot car training method according to any one of configurations 8.1 to 8.9. In this robot car training method, the driving behavior of a non-robot car that traveled the same route later is used. Based on the information, the driving behavior of the human driver who drives the non-robot car is changed to that of the robot. Let the car learn. According to this robot car teaching method, after the robot car experiences a new situation, The robot car learns the driving behavior of a non-robot car's human driver who has experienced the situation. (Learning based on ex-post information) [Configuration 8.12] A computing system is used, and the computing system performs the non-robotic A driving behavior information receiving step of receiving driving behavior information from a computer; a driving behavior information transmitting step in which the driving system transmits the driving behavior information to the robot car; and a driving behavior information output step for outputting driving behavior information of the non-robot car. transmitting driving behavior information to the computing system; The information acquisition step is a step in which the robot car transmits the driving behavior information to the computing system. A robot car according to any one of configurations 8.1 to 8.9, which is a step of receiving from the system Teaching methods. In this robot car training method, a computing system - Receive driving behavior information (experience information) from the robot car and transmit the driving behavior information to the robot car. . According to this robot car training method, the robot car has a computing system The driving behavior information of the non-robotic car is acquired through the vehicle, and the non-robotic car is controlled based on the driving behavior information. It is possible for the system to learn the driving behavior of human drivers operating autonomous vehicles. [Configuration 8.13] The driving behavior information received by the computing system through the driving behavior information receiving step An optimization information generating step of generating optimized driving behavior information based on the behavior information; The computing system generates the latest operation information by the optimization information generating step. A driving behavior information transmission step of transmitting driving behavior information to the robot car. .12 Robot car training methods. In this robot car training method, a computing system Generates optimized driving behavior information based on driving behavior information (experience information) received from The optimized driving behavior information is then transmitted to the robot car. The robot car receives the optimized driving behavior information from the system and executes the optimized driving behavior. Based on this information, the robot can learn the driving behavior of a human driver who drives a non-robotic car. This can be done. [Configuration 8.14] The optimized driving behavior information is provided to the robot car. Driving behavior information optimized according to both attributes, and a robot car receiving the driving behavior information. Driving behavior information optimized to minimize the possibility of the vehicle coming into contact with an obstacle; The robot car is provided with dynamic information and its operation is optimized to minimize its energy consumption. The robot car that receives the driving behavior information and the driving behavior information is provided with a system that maximizes the regenerative energy of the robot car. The driving behavior information optimized for a given driving distance or a given driving time is or driving behavior information optimized to minimize acceleration time, a predetermined mileage or a predetermined Driving patterns optimized to minimize or maximize the number of braking operations or braking time during the trip Dynamic information, driving behavior optimized to minimize the distance traveled from the starting point to the destination Information or driving optimized to minimize travel time from start to finish Robot car training method in configuration 8.13, which is behavioral information.

[0014] [9. Computer Programs] The computer program of the present invention includes a program having the following configuration. [Structure 9.1] The robot car training system according to any one of configurations 7.1 to 7.17 may be configured to include one or more A computer program for implementation using a computer. By executing this computer program on one or more computers, A robot car training system according to any one of configurations 7.1 to 7.17 is realized. [Configuration 9.2] The robot car training method according to any one of the configurations 8.1 to 8.15 is performed by using one or more computers. A computer program for implementation using a computer. By executing this computer program on one or more computers, The robot car training method according to any one of the configurations 8.1 to 8.15 is realized. Effect of the Invention

[0015] According to the present invention, in a road traffic system in which a plurality of vehicles travel on a road, each vehicle Even if the vehicle is in a situation that it has not experienced, information on the driving behavior of other vehicles that have experienced that situation By controlling driving based on the above, the vehicle can deal with the situation with the same level of driving performance as the other vehicle. We can deal with it. According to the present invention, in a vehicle sharing system in which a vehicle is shared by a plurality of users, Even in a situation that the vehicle has not experienced, the vehicle may be aware of the driving of other vehicles that have experienced the situation. By controlling driving based on behavioral information, the vehicle can operate with the same level of driving performance as other vehicles. The situation can be dealt with. According to the present invention, the driving behavior of a human driver who drives a non-robot car is simulated by a robot car. By having the car learn, the autonomous driving performance of the robot car can be improved. As autonomous driving performance improves, the safety and reliability of robot cars will improve, and The safety and reliability of the entire road traffic system in which robotic cars and non-robotic cars coexist is being considered. Improve. [Brief description of the drawings]

[0016] [Figure 1] FIG. 1 is a conceptual diagram showing an example of the configuration of a road traffic system according to the present invention; [Diagram 2] A functional block diagram showing an example of a system configuration of a vehicle (automobile) in the road traffic system of the present invention. [Diagram 3] FIG. 1 is an explanatory diagram of an embodiment of a road traffic system according to the present invention; [Figure 4] FIG. 1 is a conceptual diagram illustrating a data structure of driving behavior information; [Diagram 5] (A): Data ID explanation diagram (B): Route ID explanation diagram [Figure 6] An explanation of the route [Figure 7] FIG. 2 is an explanatory diagram showing an example of a method for transferring driving operation information from another vehicle to the vehicle; [Figure 8] FIG. 2 is an explanatory diagram showing an example of a method for transferring driving operation information from another vehicle to the vehicle; [Figure 9] FIG. 2 is an explanatory diagram showing an example of a method for transferring driving operation information from another vehicle to the vehicle; [Figure 10] FIG. 2 is an explanatory diagram showing an example of a method for transferring driving operation information from another vehicle to the vehicle; [Figure 11] FIG. 2 is an explanatory diagram showing an example of a method for transferring driving operation information from another vehicle to the vehicle; [Figure 12]FIG. 1 is an explanatory diagram of another embodiment of a vehicle (automobile) in the road traffic system of the present invention. [Figure 13] Continuation of Fig. 12 [Figure 14] FIG. 14 is an explanatory diagram of an embodiment based on FIGS. 12 and 13. [Figure 15] A conceptual diagram showing an example of an embodiment of a computing system in a road traffic system of the present invention. [Figure 16] A conceptual diagram showing an example of another embodiment of a computing system in a road traffic system of the present invention. [Figure 17] FIG. 1 is a conceptual diagram showing another example of the configuration of a road traffic system according to the present invention; [Figure 18] FIG. 13 is a conceptual diagram showing yet another example of the configuration of the road traffic system of the present invention. [Figure 19] FIG. 13 is a conceptual diagram showing yet another example of the configuration of the road traffic system of the present invention. [Figure 20] FIG. 13 is a conceptual diagram showing yet another example of the configuration of the road traffic system of the present invention. [Figure 21] FIG. 13 is a conceptual diagram showing yet another example of the configuration of the road traffic system of the present invention. [Figure 22] (A): A functional block diagram showing a configuration example of the autonomous driving control unit of the robot car in FIG. 17 to FIG. 21. (B): A functional block diagram showing a configuration example of the driving assistance control unit of the non-robot car in FIG. 19. [Diagram 23] (A): A functional block diagram showing another example of the configuration of the automatic driving control unit of the robot car in FIG. 17 to FIG. 21. (B): A functional block diagram showing another example of the configuration of the driving assistance control unit of the non-robot car in FIG. 19. [Figure 24] FIG. 1 is a conceptual diagram showing an example of the configuration of a robot car training system according to the present invention. [Diagram 25] A functional block diagram showing an example of the system configuration of the robot car in the robot car training system of the present invention. [Figure 26] A functional block diagram showing an example of the system configuration of a non-robot car in the robot car training system of the present invention. [Figure 27] FIG. 25 is a flow chart illustrating the operation of the robot car training system of FIG. 24; [Figure 28] A flow chart illustrating the contents of the learning steps in FIG. [Figure 29] (A): An explanatory diagram of a manner in which a non-robot car runs ahead of a robot car. (B): An explanatory diagram of a manner in which a robot car runs ahead of a non-robot car. [Diagram 30] FIG. 22(B) is a flow diagram illustrating the contents of the learning steps executed in the configuration example of FIG. 22(A). [Diagram 31] FIG. 23(B) is a flow diagram illustrating the contents of the learning steps executed in the configuration example of FIG. 23(A). [Diagram 32] FIG. 1 is a conceptual diagram showing another example of the configuration of a robot car training system according to the present invention; [Diagram 33] FIG. 33 is a flow chart illustrating the operation of the robot car training system of FIG. 32; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] [Terminology explanations, etc.] A robot car is a car that can run autonomously without a human driver. It is also called an "autonomous vehicle." In English, it is written as "autonomous car." "self-driving car" "manned ground vehicle" "driverless car" It is also called "ar". (Quoted from Wikipedia) A non-robot car is a car other than a robot car. The vehicle is operated by a driver. Automobiles that do not have the ability to drive autonomously without human drivers (autonomous driving function) are considered non- The non-robot car has both manual and driving assistance functions, and is an autonomous car. This includes vehicles that do not have a driving function. Vehicles equipped with the system will be treated as non-robotic cars when driving in manual or assisted driving modes. When driving in autonomous mode, it functions as a robot car. The driving situation (driving situation) includes a self situation and a non-self situation (external environment). The vehicle's own status includes the vehicle's position on the earth (latitude, longitude), the vehicle's motion status ( These include the subject's internal environment, its relative situation to surrounding objects, etc. The vehicle's motion status is the center of gravity position (x, y, z), yaw (ψ), roll (φ), and pitch (θ), velocity (first-order time derivative of the center of gravity position), acceleration (second-order time derivative of the center of gravity position), angle It is expressed in terms of speed (yaw rate), etc. The surrounding objects are objects that exist around the vehicle. The surrounding objects include vehicles, pedestrians, stationary objects on the ground, and the like. The relative situation with respect to surrounding objects includes the positional relationship between the vehicle and surrounding objects, Distance from the body, etc. Stationary objects on the ground include traffic signals, road signs, crosswalks, road shoulders, guardrails, utility poles, fences, and cars. This includes warehouses, houses, etc. Examples of non-self situations (external environment) include the driving route, driving lane, driving lane width, number of lanes, road Road shape, road gradient, road surface type, road surface condition, surrounding brightness, weather, traffic light display, surroundings Number of vehicles in the vicinity, vehicle speed ahead, vehicle acceleration ahead, surrounding obstacles, type of lane, etc. This can be done. The driving operation is a concept that includes the content of the operation and the amount of the operation. Examples of the operations include operations to adjust the propulsive force of the vehicle (accelerator operation), Operation for adjusting the braking force of the vehicle (brake operation), steering angle or steering angle of the vehicle Operation to adjust speed (steering operation), gears of the transmission of the vehicle Examples of such operations include operations that change the combination of (shift operations). The driving behavior information is a data set that associates the driving conditions of the vehicle with the driving operations performed in the vehicle. Information on the route position-driving operation response information, entry / exit route position-driving operation response information, etc. Included. As an example of route location-driving operation response information, Information on braking operations recorded (route position-brake operation correspondence table), Information on braking and steering operations performed in the operation correspondence table), information on braking and accelerating operations performed at each point on the route Information (route position - brake operation / accelerator operation correspondence table), at each point on the route Information on accelerator and steering operations (route position - accelerator operation - steering Braking operation correspondence table), braking and shifting operations performed at each point on the route Operation information (route position - brake operation / shift operation correspondence table), Information on steering and shift operations performed along the route (route position - steering operation Shift operation correspondence table), accelerator operation and shift operation performed at each point on the route Operation information (route position - accelerator operation / shift operation correspondence table), Information on braking, accelerating, steering and shifting operations performed by the vehicle (including Road position - Brake operation, accelerator operation, steering operation, shift operation corresponding table) ,Information that associates routes with driving operations and energy consumption (route-driving operations-energy consumption) correspondence table), information relating routes to driving operations and regenerative energy absorption rates (route-driving operations Examples include a table of rotation operation and regenerative energy absorption rate. Entry / exit route position - An example of driving operation information is entering (parking) a parking space. Information on parking operations (driving operations) performed at each point on the movement route (entrance route position - Driving operation table), at each point on the route to exit the parking space Information on departure operations (driving operations) performed (location on departure route - driving operation correspondence table), etc. Some examples include: The learning process involves learning based on various data obtained during manual driving and learning based on data obtained during driving assistance. Learning based on various data collected during autonomous driving and learning based on various data collected during autonomous driving Includes: Learning includes learning action plans, learning about operation tendencies, learning about surrounding objects, etc. Included. Learning the action plan involves learning the knowledge (data) to determine the driving maneuvers to be performed, This includes learning the formulas (programs) to determine the driving operations to be performed. As an example of knowledge learning, the driving behavior information of other vehicles is used as a learning dataset. This is called supervised learning, which learns the criteria (driving knowledge) for determining driving operations. In this case, the vehicle can take the same action as other vehicles in a given driving situation. The knowledge is updated so that the turning operation (the correct operation) can be performed on the own vehicle. Another example of knowledge learning is the learning of driving behavior of other vehicles based on the driving behavior information of other vehicles. A positive reward is given when the vehicle performs driving behavior that is closer to the other vehicle's behavior, and a positive reward is given when the vehicle performs driving behavior that is closer to the other vehicle's behavior. By giving a negative reward (punishment) when a driver takes a bad driving action, the driver is given a negative reward (punishment) when a driver takes a bad driving action. The robot learns which actions are most likely to yield rewards, and the robot takes the action that is most likely to yield rewards. In this case, the most reward is obtained by updating knowledge so that the By updating the knowledge so that the driver takes the action that is most likely to obtain the best driving behavior, This will be possible. As an example of formula (program) learning, we will consider what should be executed based on the driving behavior information of other vehicles. The so-called parameter learning is to learn the driving operation decision function (calculation formula) that determines (estimates) the driving operation. In this case, for example, given the driving behavior information of other vehicles and the driving operation decision function, The parameters of the driving operation decision function are adjusted so that the error between the actual driving operation and the actual driving operation is minimized. In this case, the parameter learning involves using driving behavior information from other vehicles as a learning data set. The driving behavior information includes driving operations that are the same as the other vehicle (correct driving operations) in each driving situation. A learning process that adjusts the parameters of the driving operation decision function so that the driving operation (operation) is performed in the vehicle. (Learning process using supervised learning). Another example of formula (program) learning is the learning of other vehicles based on driving behavior information. A positive reward is given when the vehicle performs driving behavior that is close to that of the other vehicle, and the vehicle's driving behavior is improved. How to determine how to behave by giving negative rewards (punishment) when driving behavior is farther from turning behavior The robot learns how much reward it is likely to get for each movement, and then selects the movement that will give it the most reward. The so-called reinforcement learning method adjusts the parameters of the driving operation decision function to take such actions. In this case, the driving operation decision function is set to take the action that is likely to obtain the most reward. By adjusting the parameters, optimal driving behavior is achieved. As an example of learning about operation trends, the number of passes at each point and the operations performed at each point Learning based on the number of operations and the amount of operations can be used. For example, The ratio of the number of times a specific driving operation was performed at the point is calculated, and if the ratio is equal to or greater than a predetermined value, If so, the point is set as an operation-required point, and if the ratio is less than a predetermined value, the point is set as an operation-required point. As a result of learning, at points that are set as operation-required points, the driving assistance control or automatic operation is performed. Dynamic operation control is executed. Examples of specific driving operations include braking operations in which the amount of operation is greater than or equal to a predetermined value, Accelerator operation of 100% or more, steering operation with a specified amount of operation or more (change in gear ratio) Shifting the input signal by a predetermined value or more. As an example of learning about surrounding objects, the number of passes at each point and the surrounding objects at each point are For example, learning based on the number of times each point is passed and the number of times the point is detected can be used. The ratio of the number of times a specific surrounding object is detected in the If the ratio is less than a predetermined value, the location is set as a standard caution location. As a result of learning, at points that are set as caution points, The detection process for surrounding objects is performed with a higher accuracy than the detection accuracy, and the Therefore, driving assistance control or automatic driving control that takes safety into consideration is executed. As an example of driving assistance control that takes safety into consideration, Driving assistance control (contact avoidance assistance control) to reduce the possibility of the vehicle coming into contact with a specific surrounding object. Examples of such control include driving assistance control (braking assistance control) that reduces the impact of contact. Cut. As an example of autonomous driving control that takes safety into consideration, Autonomous driving control (contact avoidance driving control) to reduce the possibility of the vehicle coming into contact with a specific surrounding object. Examples of such measures include automatic driving control (braking control) to reduce the impact of contact. Cut. Learning about surrounding objects includes learning about surrounding objects at different times. In the case of time-of-day learning of edge objects, the ratio is calculated for each time of day, Caution points are set for each time period. Learning about driving operations and surrounding objects takes into account vehicle attributes Includes: Examples of specific surrounding objects are pedestrians or cyclists on the crosswalk in front of the vehicle, road Examples of obstacles include pedestrians and bicycles crossing the road, oncoming vehicles, overtaking vehicles, and obstacles on the road. do. Examples of obstacles on the road include vehicles parked or stopped on the side of the road, utility poles on the side of the road or at corners, and vehicles parked on the road. Examples include trash cans and signs, signs and trees sticking out over the road, etc.

[0018] Vehicle attributes include vehicle type, vehicle dimensions, wheel difference between inside and outside, vehicle weight, vehicle usage, and vehicle type. These include the vehicle number, door opening width, engine type, etc. Examples of vehicle usage include private cars, commercial cars, freight vehicles, and passenger transport vehicles (taxi). , passenger transport vehicles (buses), etc. Vehicle types are classified into large vehicles, small vehicles, , motorcycles, etc. In the case of learning about driving operations that take into account vehicle attributes, for example, The ratio of the rotation operation is calculated, and the points where the ratio is equal to or greater than a predetermined value are set as caution points. will be done. In the case of learning about surrounding objects taking into account vehicle attributes, for example, The percentage of surrounding objects likely to approach within a certain time is calculated, and the percentage is set to a predetermined value. The above locations are designated as caution locations. Examples of driving maneuvers that should be avoided due to vehicle attributes include vehicles with a high center of gravity (vehicles with high vehicle height, High-speed driving and sudden steering operations on curved roads, etc., of vehicles with heavy loads, buses, etc. Examples of such accidents include sudden acceleration or braking in a taxi. Examples of objects that are likely to approach within a certain distance based on the vehicle attributes include buses and Examples of this include passengers getting on and off in taxis, utility poles and signs hanging out on the road in the case of large vehicles, etc. This can be done.

[0019] The driving behavior of the driver of the vehicle during manual driving ("recognition," "judgment / planning," and "operation") A driving control system that performs machine learning and performs driving assistance control of the vehicle by referring to the results of the learning. This method is well known. The robot car training system of the present invention also uses this method for non-robot cars. A variety of machine learning-based driving control methods are available. A general-purpose image recognition system capable of detecting any object such as a surrounding vehicle or pedestrian is known. The vehicle of the robot car training system of the present invention also uses a known general-purpose image recognition system. As a method for detecting pedestrians and other vehicles, HOG (Histogr ams of Orientied Gradients) feature extraction, machine learning techniques One of them is threshold learning using SVM (Support Vector Machine), etc. are known.

[0020] The present invention relates to a road traffic system, a vehicle sharing system, and a robot car training system. Computing systems include cloud computing systems. This includes the Intelligent Computing System. Cloud computing is distributed computing that uses the Internet. It is one of the. Cloud refers to the data centers and services within them that enable cloud computing. This refers to a group of server computers operated by a single company. Cloud technology allows large amounts of data to be accessed without users being aware of where the data is located on the Internet. It is capable of processing large amounts of data. By utilizing cloud technology, the road traffic system, vehicle sharing system, and and big data in the robot car training system, that is, data from a large number of vehicles running on the earth. A huge amount of data is transmitted from the vehicle (data on driving conditions, data on driving operations, etc.) ) can be processed.

[0021] The road traffic system, vehicle sharing system, and robot car training system of the present invention are patented. It can be applied to the types of systems described in documents 1-44, non-patent documents 1-4, etc.

[0022] [Road Traffic System] FIG. 1 is a conceptual diagram showing an example of the configuration of a road traffic system according to the present invention. The road traffic system 1 illustrated in FIG. 1 includes a vehicle 100 and a computing system 200. The computing system 200 includes a server computer 210 and a database 22. The server computer 210 is configured to record driving behaviors of multiple vehicles including the automobile 100. The server computer 210 receives the operation information via the Internet 300. The server computer 210 stores the travel behavior information in the database 220. The driving behavior information extracted from the sensor 220 is transmitted to a large number of vehicles including the automobile 100 via the Internet. The server computer 210 may be a single computer or multiple computers. Although the service 220 is located in one server computer, it may be located in multiple server computers. They may also be arranged in a distributed manner. The automobile 100 is equipped with an on-board gateway 110 . The vehicle gateway 110 includes a central processing unit (CPU) (not shown). g Unit ), ROM (Read Only Memory ), RAM (Random Information processing equipment with wireless communication capabilities, consisting mainly of The vehicle gateway 110 executes a control program stored in a ROM via a CPU. The vehicle gateway 110 executes various processes. Upload the data to the computing system 200 via the Internet 300 (server 210) and various data are transmitted to the computing system 20 0 via the Internet 300 (received from the server computer 210) The data transmitted between the automobile 100 and the computing system 200 is The driving behavior information data includes data on the driving behavior of the vehicle itself and data on the driving behavior of other vehicles.

[0023] FIG. 2 shows an example of a system configuration of a vehicle (automobile) in the road traffic system of the present invention. FIG. The automobile 100 includes an in-vehicle gateway 110 and a cruise control system 120 . The vehicle gateway 110 performs computing under the control of the driving control system 120. The vehicle gateway 110 communicates with the computing system 200. The data received from the vehicle control system 120 is input to the vehicle gateway 110. The computing system 200 receives data input from the driving control system 120. Send to. The driving control system 120 includes a detection unit 121, a vehicle information input unit 122, a positioning unit 123, A graphic information input unit 124, an operation unit 125, a communication unit 126, a display unit 127, a storage unit 129, and a control unit It is equipped with a unit 129, etc. The detection unit 121 detects the presence of surrounding objects (other vehicles, pedestrians, stationary objects on the ground, etc.) and It is composed of sensors to detect the body position, size, relative speed, etc. Detection unit 1 21 includes, for example, a sonar 121a, a radar 121b, a camera 121c, a three-dimensional range sensor, It is embodied in terms of Sa, etc. The sonar 121a transmits ultrasonic waves within a predetermined range from antennas facing forward, backward, left and right of the vehicle. Based on the received reflected waves, the system detects the front, rear, left and right sides of the vehicle. For objects present to the right, the radar 121 outputs the positional relationship between the vehicle and the object, the distance, etc. b) is a method of irradiating a laser beam or millimeter wave from an antenna directed in the front, rear, left and right directions of the vehicle. The vehicle is then detected based on the received reflected waves. Outputs the positional relationship, distance, relative speed, etc. of objects in the front, rear, left and right directions relative to the vehicle. The cameras 121c are provided at predetermined positions in the front, rear, left and right directions of the vehicle. It outputs image data showing surrounding vehicles in the front, rear, left and right directions. The sensors such as radar, camera 121c, and 3D range sensor are integrated together. It may be used in combination with other components or alone. The vehicle information input unit 122 receives information on the vehicle's motion status (center of gravity position, yaw, roll, pitch, speed, etc.) , acceleration, angular velocity, etc.) and driving operations (acceleration, braking, steering , shift operation) to the control unit 128. The positioning unit 123 measures the position (latitude, longitude) of the vehicle on the earth, and the control unit 128 The positioning unit 123 uses, for example, a high-precision GPS (Global Positioning System). This is realized by a corresponding high-precision positioning receiver, etc. The map information input unit 124 inputs road map information of the road on which the vehicle is currently traveling from a storage medium that stores road map information. The map information input unit 128 obtains information about the roads in the map and inputs it to the control unit 128. Examples of road information that can be input include the number of lanes, lane width, curves, gradients, merging, and regulations. Examples of such reports include: The operation unit 125 is used for turning on and off the driving control, switching the control mode, and displaying the information on the display unit 127. It is an input device for inputting operation instructions such as switching various displays. For example, This is realized by a switch or the like provided on the spokes of the steering wheel. The communication unit 126 communicates with communication devices installed on stationary objects on the ground and communication devices installed in surrounding vehicles. A ground stationary object is a communication device that communicates between vehicles. A ground stationary object includes a garage or a road. The display unit 127 includes a center display provided in the center of the instrument panel, The display unit 12 is a display device that is configured with an indicator provided in the meter panel. 7 displays information about the vehicle's status, as well as whether driving control is on or off and the control mode. The control modes include a manual driving mode, a driving assistance mode, and an automatic driving mode. . The memory unit 128 is a storage device that stores driving behavior information of the vehicle itself and driving behavior information of other vehicles. It is. The control unit 129 is an information processing device mainly composed of a CPU, a ROM, a RAM, etc. (not shown). The control unit 129 controls each part of the driving control system 120. The CPU executes the stored control programs to perform various processes. The control unit 129 receives the vehicle position (latitude, longitude) and map information from the positioning unit 123. Based on road map information input from the input unit 124, road structures such as utility poles and traffic lights are The detailed road data including the information on the road is calculated, and the three-dimensional range sensor of the detection unit 121 The 3D distance of the surrounding objects is detected by the vehicle. The 3D distance data is then compared with the road map. The system synthesizes the images in real time and determines whether the object detected by the 3D range sensor is a road structure or a road surface. Accurately identify objects on the road (vehicles, pedestrians, etc.). High-precision determination of the vehicle's position is achieved using known methods such as Monte Carlo localization. This is realized by GPS location information being used as secondary information. This situation can be realized by a known method such as a Kalman filter. The control unit 129 controls the detection unit 121, the vehicle information input unit 122, the positioning unit 123, and the map information The driving behavior information of the vehicle based on various information input from the information input unit 124 is stored in the memory unit 19. The driving behavior information of the vehicle is stored in the detection unit 121, the vehicle information input unit 122, the positioning unit 12 3, and the operation history information (position on the travel route-driving operation) obtained by the map information input unit 124 The table includes a table of correspondence between vehicle entry and exit route positions and driving operations, etc. The control unit 129 controls the computing system 200 via the in-vehicle gateway 110. and communicate. The control unit 129 transmits the driving behavior information of the vehicle stored in the storage unit 128 to the in-vehicle gateway. The received signal is transmitted to the computing system 200 via the I / F 110 . The control unit 129 receives the driving behavior information of the other vehicle via the in-vehicle gateway 110. The driving behavior information of the other vehicle is stored in the storage unit 128. Operation history information obtained by the input unit 122, the positioning unit 123, and the map information input unit 124 (Travel route position-driving operation correspondence table, entry / exit route position-driving operation correspondence table, etc. ) are included. The control unit 129 communicates with surrounding stationary ground objects and surrounding vehicles via the communication unit 126 . The control unit 129 transmits the driving behavior information of the vehicle stored in the memory unit 128 through the communication unit 126. The signal is then transmitted to stationary objects on the ground and to nearby vehicles via the satellite. The control unit 129 stores the driving behavior information of the other vehicle received via the communication unit 126 in the storage unit 12. Accumulate to 8. The control unit 129 is connected to a vehicle control unit 130 which is the subject of driving control. The vehicle control unit 130 includes an engine ECU (Electronic Control Unit) 130a, a brake Various electronic control ECUs such as steering ECU 130b, steering angle ECU 130c, and stability ECU 130d. The engine ECU 130a controls the amount of accelerator pedal operation and the state of the engine. The brake ECU 130b controls the engine output by issuing a control command according to the brake The braking force of the brake is controlled according to the amount of operation of the rake pedal. The Stability ECU 130d controls the steering angle. do. The control unit 129 is configured to detect driving operation amounts (accelerator operation amount, brake operation amount, steering operation amount, etc.) , etc.), a command is given to each ECU in the vehicle control unit 130 to control the running of the vehicle. To control. In the driving assistance mode, the control unit 129 detects the driving conditions of the vehicle, which change from moment to moment. While analyzing in real time, the analysis results and driving behavior information of the vehicle and / or the driving behavior of other vehicles are The driving support information is generated based on the turning behavior information, and the driving support information is displayed on the display unit 127, etc. is used to notify the driver. In the automatic driving mode, the control unit 129 detects the driving conditions of the vehicle, which change from moment to moment. While analyzing in real time, the analysis results and driving behavior information of the vehicle and / or the driving behavior of other vehicles are The vehicle control unit 130 determines the amount of driving operation based on the driving behavior information and issues a command to each ECU in the vehicle control unit 130. can. In the above example, the vehicle gateway 110 and the driving control system 120 exist separately. However, the vehicle gateway 110 can be integrated with the cruise control system 120.

[0024] The automobile 100 configured as described above is configured to detect the driving status of the vehicle and driving behavior information of the vehicle. The vehicle 100 performs driving assistance and automatic driving based on the driving behavior information of other vehicles. When driving in driving mode or driving assistance mode, it functions as a non-robot car, and when driving in autonomous driving mode, it functions as a non-robot car. When driving on the road, it functions as a robot car.

[0025] FIG. 3 is an explanatory diagram of an embodiment of a vehicle (automobile) of the present invention. The vehicle V1 (100) has never traveled along the route R before. The vehicle V2 (100) has traveled along a route R before. The vehicle V2 acquires various driving data while traveling along the route R, and The vehicle V2 stores the data in the storage unit 128 of the vehicle. The driving behavior information including the various data collected is provided to the vehicle V1. The information includes a route R and driving operations performed by the vehicle V1 at each point on the route R. The information includes information that associates the The vehicle (own vehicle) V1 transmits the driving behavior information of the vehicle (other vehicle) V2 to the driving support of the vehicle V1. This can be used for assisted control and automatic driving control. Vehicle V1 has never driven on route R. Based on the driving behavior information of a vehicle (other vehicle) V2 that has traveled along route R, By implementing driving assistance control and automatic driving control, the vehicle can achieve the same driving level as an automobile (other vehicle) V2. It can provide driving assistance and autonomous driving capabilities.

[0026] For example, if route R is a narrow, winding road with many obstacles such as utility poles, If the road is narrow, it may be difficult for inexperienced drivers or car sharing services to For drivers who drive different vehicles, it is necessary to drive route R smoothly. It is not easy to drive smoothly on this type of road. Driving cars is also difficult. However, if the car V2 is a vehicle that drives route R smoothly on a daily basis, By referring to the driving behavior information of V2, the vehicle V1 performs driving assistance control. When the driver of the vehicle is inexperienced or when the vehicle V1 is used for a car sharing service, Even if both are in a single vehicle, vehicle V1 can complete route R smoothly with the same driving performance as vehicle V2. Even if the car V1 is a robot car, the car V2 can run smoothly. By referring to the driving behavior information, the vehicle V1 performs automatic driving control. It becomes possible to travel smoothly along route R with driving performance at the same level as vehicle V2.

[0027] FIG. 4 shows a concept of an example of a route position-driving operation correspondence table included in driving behavior information. FIG. 1 is a diagram showing the driving behavior information managed by a data ID. is a unique value that can identify one piece of driving behavior data from a huge amount of driving behavior data. The data ID is a unique combination of the vehicle ID (Car ID) and the route ID (Root ID). The vehicle ID identifies one vehicle among many vehicles (see Figure 5(A)). The vehicle ID also identifies the vehicle attributes of the vehicle. The route ID is The route ID is a unique value that can identify a route from a huge number of routes. A set of Starting Point, Destination Point and Pass Point The alignment is identified (see FIG. 5(B)). The driving behavior information illustrated in FIG. 4 is generated when a vehicle V2 travels along a route R on a map illustrated in FIG. The starting point of route R is S1, the destination point is S2, and the destination point is S3. The route point is D1, and the pass points are PP1, PP2, and PP3. The turning information is made by vehicle V1 at each point (P1, P2, . . . , Pn) on route R. For example, at point P1, the acceleration operation (start operation) At point P2, the driver accelerates, at point P3, the driver decelerates (brakes), and at point P4, the driver turns left (hands off). At point P5, a right turn operation (turning the handle back) is performed, and at point P6, At point Pn-2, the driver is turning right (hand wheel) and at point Pn-3, the driver is decelerating (braking). At point Pn-1, a left turn (a steering wheel return operation) is performed, and at point Pn, a left turn (a steering wheel return operation) is performed. The "xxx" in the figure indicates each operation. It is the amount of operation in the operation.

[0028] The method of transferring driving behavior information from vehicle V2 to vehicle V1 is arbitrary. Examples of the method include As examples, the communication between the vehicle V1 and the other vehicle V2 (see FIG. 7), the communication between the vehicle V1 and the stationary object 4 on the ground, 10 (see FIG. 8), communication between the vehicle V1 and the road 420 (see FIG. 9), Communication between the vehicle V1 and the mobile terminal 500 (see FIG. 10 ), the computing system ( Examples of such methods include the transfer of information via the cloud system 200 (see FIG. 11 ). can. In FIG. 8, a traffic light on a road is illustrated as an example of a ground stationary object 410. Vehicles V1 and V2 uses a traffic light 410 as an access point (AP) to transmit and receive driving behavior information. In the example of FIG. 8, the driving behavior information of the vehicle V2 transmitted from the vehicle V2 is transmitted via the traffic light 410. The vehicle V1 receives the driving behavior information as a traffic light 410 and the The traffic lights 410 transmitting the driving behavior information may be the same traffic light or different traffic lights. may be also possible. In the example of Figure 9, access points (APs) are placed at regular intervals along the road. The access points (AP) may be buried in the road surface or installed on the side of the road. Good too. In the example of FIG. 10, the driving behavior information of the vehicle (other vehicle) V2 is The driving behavior information is stored in the mobile terminal 500 of the driver. The vehicle information is downloaded from the mobile terminal 430 to the system 200. By short-distance wireless communication within the vehicle, driving behavior information of the vehicle (other vehicle) V2 is transmitted to the mobile terminal 43. 0 to car V1. In the configuration of FIG. 11, vehicles V1 and V2 communicate with each other via the Internet 300. As an access point for communicating with the system 200, for example, a geostationary Using an access point (AP) provided on the object 410 or the road 420 shown in FIG. This can be achieved by:

[0029] FIG. 12 is an explanatory diagram of another embodiment of the automobile of the present invention. Garage G is the garage in which car V2 (100) is used on a daily basis. Garage G faces a narrow road, ST, so it is difficult for inexperienced drivers or car sharing users to use the parking lot. For drivers who drive different vehicles for driving services, parking operations are difficult. . Diagonally forward to the left of garage G is a recess D that branches off from road ST. In order to put the car V2 into the garage G, first, as shown in FIG. Car V2 must be moved forward diagonally to the right until the right tip of enters the recess D. Then, as shown in Figure 13(B), carefully adjust the steering angle so that the trajectory forms an arc. Then, vehicle V2 must proceed. When the vehicle V2 enters the garage G, various driving data are acquired. The vehicle V2 stores the data in the storage unit 128 of the vehicle. Driving behavior information including the various data is provided to the automobile V1 (100). The behavioral information includes the route to enter the garage G and the vehicle V at each point on the route. 2 and the driving operation performed by the vehicle entrance / exit route position-driving operation correspondence table ) The method by which vehicle V2 provides its driving behavior information to vehicle V1 is arbitrary. .

[0030] FIG. 14 shows the transfer of driving behavior information between cars V1 and V2 and garage G. In the example of FIG. 14, a parking space is provided near the entrance of the garage G. The garage parking experience information providing device 440 is provided with Receive the driving behavior information (experience information) (driving behavior information receiving function) and The driving behavior information is stored in the storage unit (driving behavior information storage function). When the vehicle V1 approaches the garage G, the driving behavior information stored in the memory unit is automatically Send to car V1. Vehicle V1 uses the driving behavior information of vehicle V2 for the driving assistance control and automatic driving control of its own vehicle. Car V1 has never been parked in garage G, but uses garage G on a daily basis. By performing driving assistance control and automatic driving control based on the driving behavior information of the vehicle V2, The vehicle can enter garage G with the same level of driving assistance and autonomous driving performance as vehicle V2. The same applies to shipments.

[0031] FIG. 15 shows an example of the configuration of a computing system in the road traffic system of the present invention. This is a conceptual diagram. A server computer 210 in the computing system 200 may include one or more The driving behavior information (experience information) of vehicles V1, V2, V3, etc. is received via the Internet. (Driving behavior information receiving function 210a) The data is transmitted to one or more different vehicles V1, V2, V3, etc. via the Internet 300. (driving behavior information transmission function 210b) receives driving behavior information from the server computer 210. Vehicles that receive this driving behavior information can use it for their own driving assistance control and autonomous driving control. Even in a situation that the vehicle has not experienced, the vehicle can learn from the driving behavior of other vehicles that have experienced the situation. Based on this information, driving assistance control and automated driving control are performed to achieve the same level as other vehicles. The driving assistance and autonomous driving capabilities of the vehicle can handle such situations. In this system, a number of vehicles V1, V2, V3, ..., Vn are By utilizing each other, the driving assistance performance and autonomous driving performance of each vehicle can be efficiently improved. This allows multiple vehicles V1, V2, V3, ..., Vn to Improve the driving assistance and autonomous driving performance of each vehicle by utilizing the experience of both parties as well as that of other vehicles. It is possible to realize a road traffic system that can improve

[0032] FIG. 16 shows another example of the configuration of a computing system in the road traffic system of the present invention. FIG. A server computer 210 in the computing system 200 may The driving behavior information (experience information) of both vehicles is received via the Internet 300 (driving behavior information reception function 210a), and generates optimized driving behavior information based on the driving behavior information (optimization and updating and managing the optimized driving behavior information to the latest information. (Optimization information update function 210d) and transmits the information to one or more vehicles via the Internet. (Driving behavior information transmission function 210b). The vehicle that receives the driving behavior information from the server computer 210 automatically This can be used for vehicle driving control. Even in situations that the vehicle has never experienced, Driving assistance based on driving behavior information optimized based on driving behavior information of other vehicles By controlling the vehicle and carrying out automatic driving control, the vehicle will be able to provide driving assistance at a level equal to or higher than that of the other vehicle. The situation can be handled with the vehicle's performance and autonomous driving capabilities. In this system, a number of vehicles V1, V2, V3, ..., Vn are By utilizing each other, the driving assistance performance and autonomous driving performance of each vehicle can be efficiently optimized. This allows multiple vehicles V1, V2, V3, ..., Vn to By utilizing the experience of both vehicles as well as that of other vehicles, the driving assistance and autonomous driving performance of each vehicle will be improved. It is possible to realize a road traffic system that can be optimized efficiently. includes consumed energy, regenerated energy, accident occurrence rate, etc. The server computer 210 stores the vehicle attributes (vehicle attributes) of the vehicle that provides the driving behavior information and the vehicle that provides the driving behavior information. If the vehicle type, vehicle dimensions, inner and outer wheel difference, etc. are different, the vehicle will be provided according to the vehicle attributes of the vehicle to be provided. The driving behavior information is corrected to the optimal value. Therefore, the vehicle attributes of the source vehicle and the destination vehicle are Even if the information is different, the vehicle is provided with driving behavior information optimized for that vehicle. An example of optimized driving behavior information is the provision of information to the destination vehicle according to the driving conditions at the time. The vehicle is then given modified driving behavior information that minimizes the possibility of the vehicle coming into contact with an obstacle. With this configuration, for example, when the source vehicle and the destination vehicle are traveling on the same route, Even if both vehicles are used at the same time, if the vehicle dimensions or wheel difference between the inside and outside of the two vehicles are different, the steering Driving behavior information in which the operation amount and timing of the brake operation have been corrected is provided to the destination vehicle. The relationship between the source vehicle and the destination vehicle may be a many-to-one relationship. In this case, the driving behavior information of the multiple source vehicles is corrected to provide the driving behavior information to the destination vehicle. It is desirable to provide

[0033] FIG. 17 is a conceptual diagram showing another example of the configuration of the road traffic system of the present invention. The vehicle 100 constituting this road traffic system 1 is a robot car (automatic driving vehicle) 100 They are broadly divided into 100A and 100B, which are non-robot cars (manually driven cars or cars with driving assistance functions). FIG. 17 shows only one robot car 100A and one non-robot car 100B. In the actual system, there are multiple robot cars 100A and non-robot cars. There may be one or more 100Bs. The server computer 210 in the computing system 200 is A driving behavior information receiving function 210a for receiving driving behavior information (experience information) from the driving behavior information receiving function 210B; A driving behavior information transmission function 210b for transmitting driving behavior information to the robot car 100A. do. The Robot Car 100A is an autonomous driving system that operates autonomously instead of being driven by a human driver. The robot car 100A is a vehicle that is driven by the driver. The driving situation recognition unit 100Aa recognizes the driving behavior information of the non-robot car 100B. A driving behavior information receiving unit 100Ab receives driving behavior information from a driving behavior information receiving system 200. The driving situation recognition unit 100Ab of the vehicle refers to the driving behavior information received by the driving behavior information receiving unit 100Ab. An automatic driving control unit 100A that performs automatic driving control according to the driving situation recognized by the automatic driving control unit 100Aa c. The robot car 100A performs driving operations based on various data obtained during autonomous driving. The robot car 100A learns and controls the driving automatically. This includes so-called driver-assisted autonomous vehicles in which the driver can take evasive action. The non-robot car 100B is a vehicle that is driven by a human driver. The non-robot car 100B has a driving situation recognition unit 100Ba that recognizes the driving situation of the vehicle. a driving operation detection unit 100Bb for detecting a driving operation by a human driver of the vehicle; The driving situation recognized by the driving situation recognition unit 100Ba and the driving operation detection unit 100Bb The driving behavior information associated with the detected driving operation is stored in the computing system 200. The non-robot car 100B has a driving behavior information transmission unit 100Bc that transmits the driving behavior information. Driving assistance control is executed while learning the driving operations of both drivers.

[0034] The driving condition recognition units 100Aa and 100Ba include a detection unit 121, a vehicle information input unit 122, a measurement A position unit 123, a map information input unit 124, an operation unit 125, a communication unit 126, etc., and a control unit 129. This is achieved by: The driving operation detection unit 100Bb is realized by the driving operation detection function of the vehicle information input unit 122. can be. The driving behavior information receiving unit 100Ab and the driving behavior information transmitting unit 100Bc are This is realized by I110. The automatic driving control unit 100Ac is realized by the control unit 129.

[0035] The non-robot car 100B transmits driving behavior information of the vehicle to the computing system 20. 0. The server computer 210 in the computing system 200 Driving behavior information of the robot car 100B is received via the Internet, and the driving behavior information The server computer 2 transmits the above to the robot car 100A via the Internet 300. The robot car 100A receives the driving behavior information of the non-robot car 100B from the The driving behavior information is used for automatic driving control of the vehicle. , referring to the driving behavior information of the non-robot car 100B received from the server computer 210 The robot car 100A will control the vehicle's driving situation according to the driving conditions. The driving behavior information received from the driving system 200 is used to The driving behavior information reflects the results of the driver's learning of driving operations. Therefore, according to this system, the robot car 100A is a vehicle that has no experience (no experience). Even in the situation of (practice), the non-robot car 100B is a vehicle that has experienced the situation. In some cases, the autonomous driving control is performed based on the driving behavior information of the non-robot car 100B. This allows the robot car 100B to handle the situation with driving performance at the same level as the non-robot car 100B.

[0036] FIG. 18 is a conceptual diagram showing yet another example of the configuration of the road traffic system of the present invention. The same components are denoted by the same reference numerals and their explanations are omitted as appropriate. The server computer 210 in the computing system 200 is A driving behavior information receiving function 210a for receiving driving behavior information (experience information) from the driving behavior information receiving function 210B; An optimization information generation function 210c that generates optimized driving behavior information based on the driving behavior information. and an optimization information update function that updates and manages optimized driving behavior information21. 0d, and transmitting optimized driving behavior information to the robot car 100A. Function 210b. The non-robot car 100B transmits driving behavior information of the vehicle to the computing system 20. 0. The server computer 210 in the computing system 200 Driving behavior information of the robot car 100B is received via the Internet, and the driving behavior information The system optimizes the driving behavior of the robot car 100A and constantly transmits the latest optimized driving behavior information to the internet. The server computer 210 transmits the operation command for the non-robot car 100B via the network 300. The robot car 100A that has received the driving behavior information uses the driving behavior information as an automatic driving control for the vehicle. It can be used for control. According to this system, the robot car 100A can navigate in situations that it has never experienced before. If the non-robot car 100B is a vehicle that has experienced the situation, -Autonomous driving based on the latest driving behavior information optimized based on 100B driving behavior information By performing driving control, the driving performance is equal to or higher than that of the non-robot car 100B. The situation can be dealt with by using the

[0037] According to the system of FIG. 17 and FIG. 18, the non-robot car 100B is driven by a driver. By learning every day and improving its driving assistance performance, the robot car 100A The autonomous driving performance can also be improved day by day. A driver who drives a non-robot car 100B in a situation where the non-robot car 100B coexists with the robot car 100B. The robot car 100A learns the driving techniques of the robot car and makes the robot car 100A autonomous. Driving performance can be improved highly efficiently. The autonomous driving performance of the robot car 100A has been improved. As the number of vehicles increases, the overall operational efficiency of the road transport system1 will improve, safety will increase, and customer satisfaction will also increase. Improvements, etc. will be made. According to the systems shown in Figs. 17 and 18, professionals such as taxi drivers and bus drivers Driving behavior information obtained when a practical driver drives the non-robot car 100B is It can be used to improve the operational efficiency of the entire road traffic system1, improve safety, etc. The project provided driving behavior information that will help improve the autonomous driving performance of the robot car 100A. By making it a system where professional drivers can earn compensation, The incentive for providing driving behavior information when driving the Toyota 100B is based on the profile. By providing this information to professional drivers, we can obtain driving behavior information based on their advanced driving techniques. This system can encourage the provision of robotic cars 100A and non-robotic cars 100B. In an environment where 00B and 00B coexist (a transitional environment until all vehicles become robot cars), We are working with companies that want to improve the autonomous driving performance of the robot car 100A, as well as taxi drivers and bus drivers. This is a system that is convenient for both the driver and the passenger.

[0038] By the way, there are robot cars that completely comply with traffic laws and robot cars that do not necessarily comply with traffic laws. In situations where a robot car and a non-robot car coexist, the driving behavior characteristics of both (especially "judgment and planning") ) may lead to accidents due to differences in the For example, if the traffic light in your direction changes from yellow (caution) to red (stop), If a vehicle approaches an intersection at this timing, if the vehicle is a robot car, Robot cars will always stop before an intersection, but non-robot cars may not necessarily stop before an intersection. As a result, if the vehicle following the robot car is a non-robot car, it will stop before the intersection. There are many accidents (hit-and-run accidents) in which a non-robot car crashes into a robot car from behind. There is a possibility that. In addition, if all vehicles on the road were robot cars, vehicle-to-vehicle and road-to-vehicle communications would become possible. By building a network of robot cars, we aim to create a safe and efficient driving environment. It will be possible to create a fleet of non-robotic cars driven by humans (manually operated vehicles). It is also anticipated that if even one bicycle were to enter the area, this cooperative system would collapse in an instant. It is possible. These problems are solved by the system shown in FIG. 17 and FIG. 18. The robot car 100A learns the driving behavior of a human driver, The driving behavior of the robot car 100A should be as close as possible to the driving behavior of the non-robot car 100B. For example, there is a risk of being hit by a non-robot car 100B. Under likely circumstances, the robot car 100A will behave in a similar manner to the non-robot car 100B. By deliberately making the driver choose a driving behavior that does not comply with traffic laws, This allows the driver to avoid danger. Also, the driver can maintain a precise distance (the distance or air distance that complies with traffic laws) Robot cars driving in a cooperative manner while maintaining a safe distance between vehicles (which reduces resistance as much as possible) In the group of 100A, there is a non-robot car 10 that travels at a distance different from the fixed distance. When 0B cuts in, several robot cars 10 in front of and behind the non-robot car 100B 0A has the same driving behavior as non-robot car 100B (a car with a different distance from the fixed distance mentioned above). By having the robot car 100A choose the driving behavior of driving at a distance from the target, It is possible to realize a safe and efficient driving environment while maintaining the group's cooperative system as much as possible.

[0039] In FIG. 17 and FIG. 18, the robot car 100A is configured to detect the driving behavior of the non-robot car 100A. The driving behavior information receiving unit (driving behavior information acquiring unit) Ab that receives information via the Internet However, the function of the robot car 100A to acquire driving behavior information is not based on this method. For example, vehicle-to-vehicle communication (see Fig. 7), communication between the vehicle and a stationary object on the ground, (see Fig. 8), road-to-vehicle communication (see Fig. 9), and communication between the vehicle and a mobile terminal (see Fig. 10). This can also be achieved by using the following methods:

[0040] FIG. 19 is a conceptual diagram showing still another example of the configuration of the road traffic system of the present invention. In the system configurations of FIGS. 17 and 18, the driving behavior information (experience) of the non-robot car 100B is The robot car 100A can only use the information (information) of the robot car 100A. It is also possible to configure a system in which the BotCar 100B and the BotCar 100B share driving behavior information with each other. In this case, the robot car 100A is, as shown in FIG. A driving behavior information output unit (driving behavior information transmission unit, etc.) for providing driving behavior information to other vehicles 100Ad. The non-robot car 100B is a car with a driving assistance function. As shown in FIG. 19B, a driving condition recognition unit 100B recognizes the driving condition of the vehicle. a, and a driving behavior information acquisition unit (driving behavior information The information receiving unit, etc.) 100Bd refers to the driving behavior information acquired from the robot car 100A. Driving assistance control according to the driving situation recognized by the driving situation recognition unit 100Ba of the vehicle The driving assistance control unit 100Be includes a control unit 1 This is realized by 29 (see FIG. 2). According to this system configuration, the non-robot car 100B is driven by a human driver. By learning every day and improving its driving assistance performance, the robot car 100A The autonomous driving performance can be improved day by day, and the robot car 100A can also be driven. By learning operations every day and improving its autonomous driving performance every day, it will be possible to develop a non-robotic car that is 10 times more powerful than the current model. The driving assistance capabilities of the 0B can also be improved day by day. In a situation where A and the non-robot car 100B coexist, drive the non-robot car 100B. The robot car 100A learns the driving techniques of a human driver. -100A can be efficiently improved in autonomous driving performance, while at the same time, the robot car 1 The non-robot car 100B learns the driving operation of the robot car 00A, and the driving operation of the non-robot car 100B is The driving support performance can be improved highly efficiently. - As the operational performance of the 100B improves, the operational efficiency of the entire road transport system1 will improve, Safety will be improved, etc.

[0041] A system in which driving behavior information of a robot car 100A can be used by a non-robot car 100B The configuration is that the autonomous driving performance of the robot car 100A imitates the driving techniques of a human driver. This is particularly suitable for the road traffic system 1 in the era after the time when the robot In an age where car 100A is better at driving than human drivers, We believe that it is pointless for the BotCar 100A to learn the driving operations of a human driver. Because it can be obtained.

[0042] 20 and 21 are conceptual diagrams showing still another example of the configuration of the road traffic system of the present invention. In the system configuration of FIG. 17 and FIG. 18, a robot car 100A and a non-robot car 100B The vehicles 100 that make up the road traffic system 1 are robot cars 100A and 100B. The system configuration is such that the robot cars 100A in the road traffic system 1 are driven by each other. It is also possible to make the behavioral information available to each other. As in the example of FIG. 19(A), the driving behavior information of the vehicle is provided to other vehicles. The vehicle driving apparatus has a driving behavior information output unit (driving behavior information transmission unit, etc.) 100Ad. According to this system configuration, the robot cars 100A in the road traffic system 1 can drive together. By utilizing behavioral information, the robot car 100A in the road traffic system 1 learns This will increase efficiency and rapidly improve autonomous driving performance. It can rapidly improve the autonomous driving performance of all 100A robot cars, so that the road The operational efficiency, safety, customer satisfaction, etc. of the entire transportation system1 will improve rapidly.

[0043] FIG. 22(A) shows the automatic driving control unit 100 of the robot car 100A shown in FIG. 17 to FIG. 21. FIG. 22(B) is a functional block diagram showing a configuration example of the non-robot car Ac in FIG. 10 is a functional block diagram showing a configuration example of a driving assistance control unit 100Be of the driving assistance control unit 100B. The automatic driving control unit 100Ac determines whether or not the driving situation is correct based on the driving situation recognized by the driving situation recognition unit 100Aa. Based on the result, the driving operation to be performed is determined, and the automatic driving control is performed so that the driving operation is performed. This is a functional block that performs the above. The driving assistance control unit 100Be determines the driving situation based on the driving situation recognized by the driving situation recognition unit 100Aa. Based on the result, a driving operation to be performed is determined, and driving assistance control is performed so that the driving operation is performed. This is a functional block that performs the above.

[0044] As shown in FIG. 22(A), the automatic driving control unit 100Ac determines a driving operation to be executed. A driving knowledge unit 101a stores knowledge information to be referred to when driving, and a driving behavior information acquisition unit (driving Based on the driving behavior information acquired by the behavior information receiving unit 100Ab, the driving knowledge unit 1 A learning processing unit (knowledge update processing unit) 102a that updates the knowledge information stored in the learning processing unit 101a. It has. According to this configuration, the robot car 100A can detect other vehicles (other robot cars 100A or non- Based on the driving behavior information of the robot car 100B, knowledge information (driving operations to be performed) is determined. While performing a learning process to update the knowledge information (e.g., the criteria for determining when to use the vehicle) The system determines the driving operation appropriate for the situation and performs automatic driving control so that the driving operation is executed. Therefore, the robot car 100A can experience a situation that the vehicle has not experienced before. It can learn the driving behavior of other vehicles it has driven and perform automatic driving control.

[0045] As shown in FIG. 22B, the driving assistance control unit 100Be A driving knowledge unit 101b that stores knowledge information to be referred to when determining the driving behavior information acquisition unit Based on the driving behavior information acquired by (driving behavior information receiving unit, etc.) 100Bd, A learning processing unit (knowledge update processing unit) 102 that updates the knowledge information stored in the learning unit 101b. b. According to this configuration, the non-robot car 100B can communicate with other vehicles (the robot car 100A or other Based on the driving behavior information of the non-robot car 100B, knowledge information (driving operations to be performed) is While performing a learning process to update the knowledge information (e.g., criteria for making decisions), the vehicle runs while referring to the knowledge information. The driving operation is determined according to the driving situation, and the driving assistance control is performed so that the driving operation is executed. Therefore, the non-robot car 100B can understand the situation even if the vehicle has not experienced the situation. The system can learn the driving behavior of other vehicles that have experienced this and perform driving assistance control.

[0046] FIG. 23(A) shows the automatic driving control unit 100 of the robot car 100A shown in FIG. 17 to FIG. 21. Fig. 23(B) is a functional block diagram showing another example of the configuration of the non-robot Ac in Fig. 19. FIG. 11 is a functional block diagram showing another example of the configuration of the driving assistance control unit 100Be of the car 100B. The automatic driving control unit 100Ac determines whether or not the driving situation is correct based on the driving situation recognized by the driving situation recognition unit 100Aa. Based on the result, the driving operation to be performed is determined, and the automatic driving control is performed so that the driving operation is performed. This is a functional block that performs the above. The driving assistance control unit 100Be determines the driving situation based on the driving situation recognized by the driving situation recognition unit 100Aa. Based on the result, a driving operation to be performed is determined, and driving assistance control is performed so that the driving operation is performed. This is a functional block that performs the above.

[0047] As shown in FIG. 23(A), the automatic driving control unit 100Ac includes a driving situation recognition unit 100Aa A driving operation determination unit 103 that determines, by calculation, a driving operation according to the driving situation recognized by the a and the driving behavior information acquired by the driving behavior information acquisition unit (driving behavior information receiving unit, etc.) 100Ab. Based on the dynamic information, the parameters of the driving operation decision function used in the driving operation decision unit 103a are and a learning processing unit 104a that adjusts the meta. According to this configuration, the robot car 100A can move in a direction parallel to the direction of the other vehicle (the other robot car 100A or Adjust the parameters of the driving operation decision function based on the driving behavior information of the non-robot car (B). While performing a learning process, a driving operation according to the driving situation is determined by a driving operation decision function; The robot car 100 performs automatic driving control so that the driving operation is performed. Even if A is in a situation that his vehicle has not experienced, he is aware of the driving behavior of other vehicles that have experienced the situation. It can learn vehicle behavior and perform automatic driving control. The learning processing unit 104a of the automatic driving control unit 100Ac is configured with a deep neural network. By doing so, in the future, we will be able to develop vehicles that have the same general driving knowledge and driving ability (strong AI) as humans. A robot car 100A having such a configuration can be realized.

[0048] As shown in FIG. 23B, the driving assistance control unit 100Be A driving operation decision unit that calculates and decides driving operations according to the driving conditions recognized by 0Ba 103b, and the driving behavior information acquisition unit (driving behavior information receiving unit, etc.) 100Bd A driving operation decision function used in the driving operation decision unit 103b based on the driving behavior information and a learning processing unit 104b that adjusts the parameters of the According to this configuration, the non-robot car 100B can communicate with other vehicles (the robot car 100A or other The parameters of the driving operation decision function are adjusted based on the driving behavior information of the non-robot car (B). While performing learning processing to adjust the driving behavior, the driving behavior decision function determines the driving behavior according to the driving situation. Therefore, the non-robot car 1 performs driving assistance control so that the driving operation is performed. 00B is a system that can detect the driving of other vehicles that have experienced the situation even if the vehicle has not experienced the situation before. It can learn turning behavior and provide driving assistance control. The learning processing unit 104b of the driving assistance control unit 100Be is configured with a deep neural network. By doing so, in the future, we will be able to develop vehicles that have the same general driving knowledge and driving ability (strong AI) as humans. A non-robot car 100B may be realized.

[0049] In the above embodiment, the automobile 100 is a vehicle that provides experience information and a vehicle that provides the experience information. If the vehicle attributes (such as the vehicle model and dimensions of each part of the vehicle) of a certain vehicle are different, The driving behavior information is adjusted to an optimal value according to the vehicle attributes of the vehicle, and the adjusted driving behavior information is used as a reference. It is desirable for the vehicle to have a function to perform driving assistance control or automatic driving control based on the vehicle's driving conditions.

[0050] [Vehicle sharing system] The embodiment of the road traffic system of the present invention shown in FIG. 1 to FIG. 23 is a vehicle shared system of the present invention. That is, the description of the embodiment of the road traffic system is also an embodiment of the road traffic system. By replacing the term "road traffic system" with "shared vehicle system," As an example of a vehicle sharing system, a rental car service services, car sharing services, robot taxi services, robot bus services Examples of the system include a system that can provide the above. In addition, in many cases, in a vehicle sharing system, the robot car 100A is used by multiple users. In many cases, the non-robot car 100B is a vehicle that is shared by multiple users. A vehicle other than a vehicle shared by multiple users.

[0051] [Robot car training system] FIG. 24 is a conceptual diagram showing an example of the configuration of a robot car training system according to the present invention. The robot car training system 1 illustrated in FIG. 24 is a robot car 100A and a non-robotic car 100B. The device includes a car 100B and a computing system 200. The computing system 200 includes a server computer 210 and a database 22. It has 0. The server computer 210 transmits driving behavior information of the non-robot car 100B to the Internet. A driving behavior information receiving unit 210a receives the driving behavior information via the network 300, and The driving behavior information received from the robot car 100 is transmitted to the robot car 100A via the Internet 300. and a driving behavior information transmitting unit 210b. The database 220 stores the driving behavior information received by the server computer 210. We are accumulating and managing them. The server computer 210 may be a single computer or multiple computers. Even if the files are located on a single server computer, they may be distributed across multiple server computers. It's fine.

[0052] The robot car 100A includes a driving situation recognition unit 100Aa that recognizes the driving situation of the vehicle itself, A driving behavior information receiving unit (driving behavior information receiver) for receiving driving behavior information of the non-robot car 100B Based on the driving situation recognized by the driving situation recognition unit 100A of the vehicle, The driving behavior information receiving unit 100Ab receives the driving behavior information and performs automatic driving control. Autonomous driving that performs learning processing to learn the driving behavior of the non-robot car 100B based on dynamic information The control unit 100Ac.

[0053] The non-robot car 100B has a driving situation recognition unit 100Ba that recognizes the driving situation of the vehicle. a driving operation detection unit 100Bb for detecting a driving operation by a human driver of the vehicle; The driving situation recognized by the driving situation recognition unit 100Ba and the driving operation detection unit 100Bb A driving behavior information transmission unit (driving behavior information transmission unit) that transmits driving behavior information associated with the detected driving operation Dynamic information output unit 100Bc.

[0054] FIG. 25 is a functional block diagram showing an example of the system configuration of the robot car 100A. 26 is a functional block diagram showing an example of the system configuration of the non-robot car 100A.

[0055] As shown in FIG. 25, the robot car 100A runs together with the in-vehicle gateway 110A. and a control system 120A. The vehicle gateway 110A is a computer under the control of the driving control system 120A. The vehicle gateway 110A communicates with the computing system 200. The data received from the vehicle control system 200 is input to the vehicle control system 120A. The computer 110A converts data input from the driving control system 120A into a computing system. Send the data to system 200. The driving control system 120A includes a detection unit 121A, a vehicle information input unit 122A, a positioning unit 12 3A, map information input unit 124A, operation unit 125A, communication unit 126A, display unit 127A, recording The driving condition recognition unit 100Aa in FIG. , a detection unit 121A, a vehicle information input unit 122A, a positioning unit 123A, and a map information input unit 124A. , the communication unit 126, etc., and the control unit 129. 0Ab is realized by the in-vehicle gateway 110A. Ac is realized by the control unit 129A. The detection unit 121A detects the presence of surrounding objects (other vehicles, pedestrians, stationary objects on the ground, etc.) and It is composed of sensors for detecting the position, size, relative speed, etc. of an object. 121A includes, for example, a sonar 121a, a radar 121b, a camera 121c, a three-dimensional range The present invention is embodied in a sensor, etc. The sonar 121a transmits ultrasonic waves within a predetermined range from antennas facing forward, backward, left and right of the vehicle. Based on the received reflected waves, the system detects the front, rear, left and right sides of the vehicle. For objects present to the right, the radar 121 outputs the positional relationship between the vehicle and the object, the distance, etc. b) is a method of irradiating a laser beam or millimeter wave from an antenna directed in the front, rear, left and right directions of the vehicle. The vehicle is then detected based on the received reflected waves. Outputs the positional relationship, distance, relative speed, etc. of objects in the front, rear, left and right directions relative to the vehicle. The cameras 121c are provided at predetermined positions in the front, rear, left and right directions of the vehicle. It outputs image data showing surrounding vehicles in the front, rear, left and right directions. The sensors such as radar, camera 121c, and 3D range sensor are integrated together. It may be used in combination with other components or alone. The vehicle information input unit 122A receives information on the motion status of the vehicle (center of gravity position, yaw, roll, pitch, speed, etc.) degree, acceleration, angular velocity, etc.) and driving operations (acceleration operation, braking operation, steering operation The information regarding the operation of the steering wheel (operation, shift operation) is input to the control unit 128. The positioning unit 123A measures the position (latitude, longitude) of the vehicle on the earth, and the control unit 12 The positioning unit 123A is, for example, a high-precision GPS (Global Positioning System). This is realized in a high-precision positioning receiver compatible with the GPS receiver. The map information input unit 124A receives road map information from a storage medium that stores road map information, and The map information input unit 128 obtains information about the roads in question and inputs it to the control unit 128A. Examples of road information entered by A include the number of lanes, lane width, curves, gradients, merging, and regulations. Examples of such information include: The operation unit 125A is used to input operation instructions such as switching various displays on the display unit 127A. It is an input device for The communication unit 126A communicates with a communication device provided on a stationary object on the ground or a communication device mounted on a nearby vehicle. The communication device is used to communicate between the following: Stationary objects on the ground include garages and roads. The display unit 127A is a center display provided in the center of the instrument panel. The display unit 1 is a display device that includes an indicator provided in the meter panel. Information indicating the state of the host vehicle is displayed in 27A. The memory unit 128A stores the recognition-related information of the vehicle itself, the driving behavior information of the vehicle itself, and the driving behavior information of other vehicles. It is a storage device that stores dynamic information. The control unit 129A is an information processing unit mainly composed of a CPU, a ROM, a RAM, etc. (not shown). The control unit 129A is a device that controls each part of the driving control system 120A. The CPU executes the control programs stored in the M to perform various processes. . The control unit 129A calculates the vehicle position (latitude, longitude) input from the positioning unit 123A and the map. Based on the road map information input from the information input unit 124A, roads such as utility poles and traffic lights are Detailed road data including information on structures is calculated, and the three-dimensional range of the detection unit 121A is The sensor detects the 3D distance of surrounding objects. The 3D distance data is then compared with the road map. The system synthesizes the 3D range sensor and the road structure in real time. It accurately identifies whether the object is a human or an object on the road (vehicle, pedestrian, etc.). High-precision determination of the vehicle's position is achieved using known methods such as Monte Carlo localization. GPS location information is used as secondary information. This situation can be realized by a known method such as a Kalman filter. The control unit 129A accumulates the recognition-related information of the vehicle in the storage unit 19A. includes the recognition results of surrounding objects and the like, and various data used in the recognition process. The control unit 129A includes a detection unit 121A, a vehicle information input unit 122A, a positioning unit 123A, and , and stores driving behavior information of the vehicle based on various information input from the map information input unit 124A. The driving behavior information of the vehicle is stored in the detection unit 121A, the vehicle information input unit 12 2A, the position on the route obtained by the positioning unit 123A and the map information input unit 124A - driving Operation response information (route position-driving operation response table, etc.), entry / exit route position-driving operation response It includes response information (such as an entry / exit route position-driving operation correspondence table). The control unit 129A controls the computing system 2 via the in-vehicle gateway 110A. Communicate with 00. The control unit 129A receives the non-robot car 100B via the vehicle-mounted gateway 110. The driving behavior information of the non-robot car 100B is stored in the storage unit 128A. The non-robot car 100B includes a detection unit 121B, a vehicle information input unit 122B, and a positioning unit 12 3B, and the route position-driving operation corresponding information (route Road position-driving operation correspondence table, etc.), entry / exit route position-driving operation correspondence information (entrance / exit route This includes road position-driving operation correspondence tables, etc. The control unit 129A communicates with surrounding ground stationary objects and surrounding vehicles via the communication unit 126A. . The control unit 129A receives the driving status of the non-robot car 100B via the communication unit 126A. The dynamic information is stored in storage unit 128A. A vehicle control unit 130A, which is a target for driving control, is connected to the control unit 129A. The vehicle control unit 130A includes an engine ECU (Electronic Control Unit) 130a, a brake Various electronics such as brake ECU 130b, steering angle ECU 130c, stability ECU 130d, etc. The engine ECU 130a controls the accelerator pedal operation amount and the engine status. The brake ECU 130b controls the engine output by issuing a control command according to the state of the engine. The steering angle ECU 130c controls the braking force of the brakes according to the amount of operation of the brake pedal. The Stability ECU 130d controls the vehicle's driving stability. To control. The control unit 129A is configured to detect driving operation amounts (accelerator operation amount, brake operation amount, steering operation amount, etc.) By giving commands to each ECU in the vehicle control unit 130A according to the vehicle speed, the vehicle running speed is controlled. Control. The control unit 129A detects the vehicle's status, which changes from moment to moment, detected by the detection unit 121A and the like. While analyzing the driving situation in real time, the analysis result and the driving behavior information of the vehicle and / or The vehicle control unit 1 determines the amount of driving operation based on the driving behavior information of the non-robot car 100B. It gives commands to each ECU in 30. The control unit 129A receives driving information from the in-vehicle gateway 110A and the communication unit 126A. A learning process is performed to learn the driving behavior of the non-robot car 100B based on the dynamic information. In the above example, the vehicle gateway 110A and the driving control system 120A are each separately Although present, the in-vehicle gateway 110A can be integrated with the cruise control system 120A.

[0056] The robot car 100A configured as described above is configured to detect the driving status and driving behavior of the vehicle. While performing automatic driving control based on the motion information of the robot car 100B or the driving behavior information of the non-robot car 100B. , and learns the driving behavior of a human driver driving the non-robot car 100B.

[0057] As shown in FIG. 26, a non-robot car 100B is running with an in-vehicle gateway 110B. and row control system 120B. The vehicle gateway 110B is a computer under the control of the driving control system 120B. The vehicle gateway 110B communicates with the computing system 200. The data received from the vehicle control system 200 is input to the vehicle control system 120B. The computing system 110B converts the data input from the driving control system 120B into Send the data to system 200. The driving control system 120B includes a detection unit 121B, a vehicle information input unit 122B, a positioning unit 12 3B, map information input section 124B, operation section 125B, communication section 126B, display section 127B, The driving condition recognition unit 100Ba in FIG. a detection unit 121B, a vehicle information input unit 122B, a positioning unit 123B, and a map information input unit 124 The driving operation is realized by the operation unit 125B, the communication unit 126B, etc., and the control unit 129B. The operation detection unit 100Bb is realized by the driving operation detection function of the vehicle information input unit 122B. The driving behavior information transmission unit 100Bc is realized by the vehicle gateway 110B. Detection unit 121B, vehicle information input unit 122B, positioning unit 123B, map information input unit 124B The configurations and functions of the communication unit 126B and the vehicle control unit 130B are the same as those of the robot car 100A. A notification unit 121A, a vehicle information input unit 122A, a positioning unit 123A, a map information input unit 124A, The configurations and functions of the signal receiving unit 126A and the vehicle control unit 130A are similar to those of the signal receiving unit 126A and the vehicle control unit 130A. The operation unit 125B is used to turn on / off the driving control, switch the control mode, and display the information on the display unit 127B. The operation unit 125 is an input device for inputting operation instructions such as switching various displays in the display. B is, for example, a switch or the like provided on the spoke of the steering wheel of the vehicle. This is embodied. The display unit 127B is a center display provided in the center of the instrument panel. The display unit 1 is a display device that includes an indicator provided in the meter panel. 27B displays information about the vehicle's status, as well as controls for turning on and off the driving control and The control mode is classified into a manual driving mode and a driving assistance mode. The memory unit 128B is a storage device that stores driving behavior information and recognition-related information of the vehicle. . The control unit 129B is an information processing unit mainly composed of a CPU, a ROM, a RAM, etc. (not shown). The control unit 129B is a device that controls each part of the driving control system 120B. The CPU executes the control programs stored in the M to perform various processes. . The control unit 129B calculates the vehicle position (latitude, longitude) input from the positioning unit 123B and the map. Based on the road map information input from the information input unit 124B, roads such as utility poles and traffic lights are Detailed road data including information on structures is calculated, and the three-dimensional range of the detection unit 121B is The sensor detects the 3D distance of surrounding objects. The 3D distance data is then compared with the road map. The system synthesizes the 3D range sensor and the road structure in real time. It accurately identifies whether the object is a human or an object on the road (vehicle, pedestrian, etc.). The control unit 129B controls the detection unit 121B, the vehicle information input unit 122B, the positioning unit 123B, and the The driving behavior information of the vehicle based on various information input from the image information input unit 124B is stored in the storage unit 1 The driving behavior information of the vehicle is stored in the detection unit 121B and the vehicle information input unit 122B. , the route position-driving operation correspondence obtained by the positioning unit 123B and the map information input unit 124B Information (route position-driving operation correspondence table, etc.), entry / exit route position-driving operation correspondence information ( This includes tables for vehicle entry / exit route positions and driving operations. A vehicle control unit 130B, which is a target of driving control, is connected to the control unit 129B. The control unit 129B is configured to detect driving operation amounts (accelerator operation amount, brake operation amount, steering operation amount, etc.) By giving commands to each ECU in the vehicle control unit 130B according to the vehicle speed, the vehicle running speed is controlled. Control. In the manual driving mode, the control unit 129B is configured to detect the driving conditions of the vehicle, which change from moment to moment. In real time, the vehicle is analyzed based on the analysis results and the driving behavior information of the vehicle. A learning process is performed to learn the driving behavior of a human driver who drives the vehicle. In the driving assistance mode, the control unit 129B detects the driving conditions of the vehicle, which change from moment to moment. in real time and provides driving assistance based on the analysis results and the vehicle's driving behavior information. Generate information and notify the driver of the driving support information using a display unit 127A or the like. The control unit 129B controls the human driver who drives the vehicle even in the driving assistance mode. A learning process is performed to learn the driving behavior of the vehicle. The control unit 129B stores the driving behavior information of the vehicle in the memory unit 128B. 8B is a driving simulation that reflects the learning results of the driving behavior of the human driver who drives the vehicle. The behavioral information is stored. The control unit 129B controls the computing system 2 via the in-vehicle gateway 110B. Communicate with 00. The control unit 129B transmits the driving behavior information of the vehicle stored in the storage unit 128B to the vehicle gate 10B to the computing system 200 via the line 110B. The control unit 129B communicates with surrounding ground stationary objects and surrounding vehicles via the communication unit 126B. . The control unit 129B transmits the driving behavior information of the vehicle stored in the storage unit 128B to the communication unit 12 The signal is transmitted via 6B to stationary objects on the ground and nearby vehicles.

[0058] The non-robot car 100B configured as described above is controlled by a human driver of the vehicle. The system controls the vehicle in response to the driver's driving operations while simulating the driving behavior of the human driver who drives the vehicle. The system performs various processes such as dynamic learning process, transmission process of driving behavior information of the vehicle, etc.

[0059] FIG. 27 is a flow chart illustrating the operation of the robot car training system shown in FIG. The flow chart shows the robot car training method realized by the robot car training system shown in Fig. 24. It is also a flow chart illustrating the contents of the law. In the robot car training system 1 and method, a robot car 100A and a non-robot car Drive the non-robot car 100B along the same route R (see Figure 29). By having the robot car 100A learn the driving behavior of a human driver, Driving lessons for the robot car 100A are conducted. In a case where the non-robot car 100B and the robot car 100B travel the same route R, A robot car 100A runs ahead of a non-robot car A (Fig. 29(A)). In another embodiment, the vehicle 100B runs ahead of the vehicle 100B (FIG. 29(B)). The following actions occur:

[0060] The non-robot car 100B travels along the same route R as the robot car 100A (S1: Robot car running steps). The non-robot car 100B recognizes the traveling situation of its own vehicle while traveling along the route R (S2: (Non-robot car driving situation perception step). The non-robot car 100B is driven by a human driver while traveling along route R. A driving operation is detected (S3: driving operation detection step). The non-robot car 100B stores driving behavior information that associates the driving situation of the vehicle with the driving operation. The driving behavior information is transmitted to the server 210 (S4: driving behavior information transmission step, driving behavior information output step). P). The non-robot car 100B determines whether or not its own vehicle is moving (S5). If so (Yes in S5), steps S2, S3 and S4 are executed repeatedly.

[0061] The computing system 200 receives driving behavior information from the non-robotic car 100B. (S11: driving behavior information receiving step). The computing system 200 receives the driving behavior from the non-robotic car 100B. The information is transmitted to the robot car 100A (S12: driving behavior information transmission step).

[0062] The robot car 100A travels along the same route R as the non-robot car 100B (S21: Robot car running steps). While traveling along the route R, the robot car 100A recognizes the traveling conditions of the vehicle itself (S22: Robot car driving situation recognition step). The robot car 100A determines the driving operation to be performed based on the driving situation of the vehicle. (S23: Driving operation decision step). The robot car 100A performs automatic driving control so that the determined driving operation is executed ( S24: Automatic driving control step). The robot car 100A receives driving behavior information of the non-robot car 100B from the server 210. The driving behavior information is received (S25: driving behavior information receiving step, driving behavior information acquiring step). The robot car 100A controls the non-robotic car based on the driving behavior information received from the server 210. The system learns the driving behavior of a human driver who drives the car 100B (S26: learning step). top).

[0063] FIG. 28 is a flow chart illustrating the contents of the learning step S26 in FIG. In the learning step S26, the robot car 100A first performs the automatic driving control (S24 ) to generate driving behavior information of the vehicle (S26a1: driving behavior information generation step). top). Then, the driving behavior information of the non-robot car 100B received in the driving behavior information receiving step S25 is Based on the difference between the dynamic information (learning dataset) and the driving behavior information of the own vehicle, In each driving situation included in the 0B driving behavior information, the driving operation is the same as that of a non-robot car. A learning process is performed so that the correct operation is performed in the vehicle (S26a2: Supervised) learning step).

[0064] According to the robot car training system 1 and method, a person can drive a non-robot car 100B. The robot car 100A is made to learn the driving behavior of a human driver. It can improve the autonomous driving performance of the 00A. The autonomous driving performance of the robot car 100A As the quality improves, the safety and reliability of the robot car 100A will improve, and the robot Safety of the entire road traffic system in which robotic cars 100A and non-robotic cars 100B coexist Improved reliability.

[0065] This robot car training system 1 and method is a robot car training system in which a non-robot car 100B is a robot car. The robot car 100A runs ahead of the robot car 100A (FIG. 29(A)). The robot car 100A is traveling ahead of the robot car 100B (FIG. 29(B)). Driving lessons can be conducted. According to the driving training in the form of FIG. 29(A), a non-robot car that previously traveled the same route R A human driver who drives a non-robot car 100B based on the driving behavior information of 100B. The robot car 100A can learn the driving behavior of a driver. While making the robot car 100A experience a new situation, the robot car 10 The robot car 100A learns the driving behavior of a human driver who drives the robot car 0B. The driving behavior information of the non-robot car 100B received by the robot car 100A is A driving test that reflects the learning results of the driving behavior of a human driver using the non-robot car 100B Therefore, the robot car 100A is driving the non-robot car 100B. By learning based on behavioral information, the human driver of the non-robot car 100B This makes it possible to efficiently learn the driving behavior of autonomous vehicles. According to the driving training in the manner of FIG. 29(B), the non-robot car 1 that traveled the same route later A human driver who drives the non-robot car 100B based on the driving behavior information of 00B. The robot car 100A can learn the driving behavior of a robot. After making 100A experience a new situation, the non-robot car 100B experienced that situation. A robot car learns the driving behavior of a human driver (Reinforcement learning: learning based on posterior information) In this embodiment, the robot car 100A can also learn to move around with a non-robot car. This makes it possible to efficiently learn the driving behavior of human drivers operating the -100B.

[0066] According to the embodiment of FIG. 29(A), the robot car 100A travels the same route R first. By performing automatic driving control based on the driving behavior information of the non-robot car 100B, It can travel along route R with the same high level of driving performance as the non-robot car 100B. For example, if route R is a narrow, winding road with many obstacles such as utility poles, If the road is narrow, drivers who are not familiar with driving or those using car sharing services may be For drivers who drive different vehicles each time, it is important to drive route R smoothly. It is not easy. Even the robot car 100A has difficulty driving smoothly on this type of road. It is. However, if the non-robot car 100B is a vehicle that runs smoothly on route R on a daily basis, The robot car 100A controls the autonomous driving by referring to the driving behavior information of the non-robot car 100B. By controlling the robot car 100A, the robot car 100A can operate at the same level as the non-robot car 100B. The turning performance makes it possible to travel smoothly along route R.

[0067] Description will be given again with reference to FIGS. The training of the robot car 100A is most preferably performed by a robot car 100A and a non-robot car. The car 100B travels along the same route R under the same driving conditions. To achieve the exact same driving conditions, a fake city was used for robot car training. This fake city has narrow, winding roads, utility poles, and many other obstacles. Narrow roads, bumpy roads, poorly visible intersections, urban highways, etc. The garage, which is difficult to exit, is reproduced just like the real thing. In this fake town, there are other vehicles, You can freely place pedestrians, livestock, etc. In this fake city, you can suddenly place pedestrians (dolls) on the road. You can also pop them out, throw baseballs or balloons, or scatter leaves. It can be done freely.

[0068] The robot car 100A detects the non-conformity at each point (P1, P2, . . . , Pn) on the route R. The driving operation of the robot car 100B is compared with the driving operation of the own vehicle, and the driving operation of the robot car 100B is compared with the driving operation of the own vehicle at each point (P1, P2,... , Pn), the same driving operation (correct operation) was performed as in the non-robot car 100B. For example, the learning process is performed at the point P3. The operation amount yyy of the deceleration operation (braking operation) of the own vehicle is the deceleration operation (braking operation) of the non-robot car 100B. If the operation amount of the vehicle (operation amount) is larger (or smaller) than xxx, Learn to make the deceleration (braking) operation amount yyy match (be as close as possible to) xxx The learning process is then carried out. This learning process focuses on the elements of driving behavior, particularly on "recognition" of the driving situation and the recognized The robot car 100A is designed to make decisions and plans for the driving situation. A process is performed to detect errors in the "perception" of the situation. If an error in the "perception" is detected, If a recognition error is not found, the recognition process is stopped. This process detects errors in "judgment and planning" for the driving situation. If an error is found, a learning process is carried out to correct the error. If not, the process returns to the process of finding the "recognition" error for another recognition object, or The learning process ends. For example, at point PP3, the non-robot car 100B does not perform a deceleration operation (braking operation). On the other hand, when the robot car 100A was decelerated (braked), -100A reaffirms the object recognized at point PP3 and the process that led to recognition. This reconfirmation is carried out by reading the driving behavior information and recognition information of the vehicle stored in the memory unit 128A. As a result, for example, a stone falling in front of the vehicle ( If the stone is “recognized”, the robot car 100A recognizes the driving situation by the driving situation recognition unit 10. The object recognized (detected) by the object recognition unit 0Aa (detection unit 121A) is recognized as a stone. A learning process is performed to modify the processing contents (program parameters and / or data) of the " At point PP3, non-robot car 100B did not perform deceleration (braking operation). This means that there may not have been any dangerous objects, such as falling stones, in front of the vehicle. In this example, the robot car 100A is designed to detect a tree that has fallen in front of the vehicle. There is a possibility that the robot may have mistaken a leaf (an object with a low degree of danger) for a stone (an object with a high degree of danger). There is great potential. Also, for example, at point Pn-2, the non-robot car 100B is turning right while traveling. The robot car 100A only slowed down (brakes) and did not perform any deceleration operation (braking operation). When the robot car 100A performs a braking operation, the robot car 100A recognizes the object and As a result, for example, the display state that allows a right turn may be changed to the state that allows a right turn. Traffic lights at intersections that have switched to a no-turn indication, and vehicles approaching from behind in close proximity to your vehicle If the robot car 100A recognizes the approaching vehicle, the robot car 100A performs the “recognition” of the driving situation of the own vehicle. The "judgment and planning" that led to the deceleration operation (braking operation) was judged to have been correctly performed. A learning process is performed to correct the processing contents (program parameters and / or data). In -2, even though the traffic light had switched to a state in which right turns were not permitted, The fact that Tocar 100B did not perform any deceleration (braking) operation means that the vehicle was approaching from behind. This is because it is highly likely that this was done to avoid a rear-end collision with another vehicle.

[0069] In the example of FIG. 24, a non-robot car 100B transmits a computing The driving behavior information is transferred via the driving system 200, but the driving behavior information is transferred from the non-robot car 100B. The method of transferring the driving behavior information from the robot car 100A to the robot car 100A is arbitrary. As an example, direct communication between the robot car 100A and the non-robot car 100B (vehicle-to-vehicle communication, Fig. 7), delivery via a stationary object 410 (see FIG. 8), delivery via a road 420 Delivery via a mobile terminal 500 (see FIG. 10 ), etc. can be mentioned.

[0070] FIG. 22(A) shows the robot car 100A in the robot car training system 1 shown in FIG. 1 is also a block diagram showing an example configuration of an automatic driving control unit Ac. The autonomous driving control unit 100Ac in this configuration example refers to the following when determining the driving operation of the host vehicle: A driving knowledge unit 101a that stores knowledge information (criteria for judgment, etc.) and a driving behavior information receiving unit 100A b. A learning processing unit (knowledge update processing unit) 102a that performs a learning process to update knowledge information stored in the memory. do.

[0071] FIG. 30 is a flow diagram illustrating the contents of learning step S26 in this configuration example. In the learning step S26, the robot car 100A first performs the automatic driving control (S24 ) to generate driving behavior information of the vehicle (S26b1: driving behavior information generation step). top). The driving behavior information of the non-robot car 100B received in the driving behavior information receiving step S25 is As a learning dataset (a set of driving situations and driving operations performed in those situations), The same driving operation as the non-robot car 100B in each driving situation included in the driving behavior information The knowledge stored in the driving knowledge unit 101a is used so that the correct operation is performed in the vehicle. A learning process that updates information (learning process using supervised learning) is performed (S26b2: learning step). According to the robot car training system 1 and method of this embodiment, a non-robot car 100 Using supervised learning with the driving behavior information of B as the learning dataset, we developed a The robot car 100A can learn the driving behavior of the human driver who drives B. can.

[0072] FIG. 23(A) shows the robot car 100A in the robot car training system 1 shown in FIG. 1 is also a block diagram showing another configuration example of the automatic driving control unit Ac. The automatic driving control unit 100Ac of this other configuration example is: The driving behavior according to the driving situation recognized by the driving situation recognition unit 100Aa is determined by calculation. A driving operation determination unit 103a for determining Based on the driving behavior information received (acquired) by the driving behavior information receiving unit 100Ab, A learning process for adjusting the parameters of the driving operation decision function used in the operation decision unit 103a. and a parameter adjustment unit 104a.

[0073] FIG. 31 is a flow diagram illustrating the contents of learning step S26 in this other configuration example. . In the learning step S26, the robot car 100A first performs the automatic driving control (S24 ) to generate driving behavior information of the vehicle (S26c1: driving behavior information generation step). top). The driving behavior information of the non-robot car 100B received in the driving behavior information receiving step S25 is As a learning dataset (a set of driving situations and driving operations performed in those situations), The same driving operation as the non-robot car 100B in each driving situation included in the driving behavior information The driving operation determination unit 103a uses the correct operation to perform the driving operation of the vehicle. A learning process that adjusts the parameters of the driving operation decision function to be used (learning process using supervised learning) (S26c2: supervised learning step). According to the robot car training system 1 and method of this embodiment, the non-robot car 100B Using supervised learning with the driving behavior information of 100 non-robot cars as a learning dataset, The robot car 100A can learn the driving behavior of a human driver. Cut.

[0074] FIG. 32 is a conceptual diagram showing another example of the configuration of the robot car training system of the present invention. The configuration of the server 210 differs from that of the previous system. The server of the computing system 200 in this robot car training system 1 210 optimizes the driving behavior information based on the driving behavior information received by the driving behavior information receiving unit 210a. an optimization information generating unit 210c for generating optimized driving behavior information; The optimization information update unit 210d updates and manages the latest driving behavior information. and a driving behavior information transmission unit 210b that transmits the driving behavior information to the bot car 100A.

[0075] FIG. 33 is a flow chart illustrating the operation of the robot car training system of FIG. The flow chart shows the robot car training method realized by the robot car training system shown in Fig. 32. The flow diagram in Figure 27 is a flow diagram illustrating the content of the method. The operation of the system 200 is different. The computing system 200 receives driving behavior information from the non-robotic car 100B. (S11: driving behavior information receiving step). The computing system 200 receives the driving behavior from the non-robotic car 100B. Generate optimized driving behavior information based on the information (S13: Optimization information generation step ). The computing system 200 updates the optimized driving behavior information. and manages it (S14: optimization information update step). The computing system 200 outputs the optimized and latest driving behavior information to the robot car. (S12: driving behavior information transmitting step). According to the robot car training system 1 and method of this embodiment, a computing system The robot car 100A receives the optimized driving behavior information from the system 200. A human driver who drives a non-robot car 100B based on optimized driving behavior information It can learn the driving behavior of a driver.

[0076] In this embodiment, the optimized driving behavior information includes a driver who receives the driving behavior information. Providing driving behavior information optimized according to the vehicle attributes of BotCar 100A The robot car 100A is optimized to minimize the possibility of contact with an obstacle. The driving behavior information provided by the robot car 100A and the driving behavior information are provided in such a manner that the energy consumption of the robot car 100A is minimized. Driving behavior information optimized to reduce driving accidents, and a robot car that receives driving behavior information Driving behavior information optimized to maximize the regenerative energy of the 00A, a specified mileage or Or, driving optimized to minimize the number of accelerations or acceleration times in a given travel time. Behavioral information, the number of braking events or the braking time during a specified driving distance or a specified driving time are minimized or Driving behavior information optimized to maximize the distance traveled from the starting point to the destination Driving behavior information optimized to minimize driving time from departure point to destination point The driving behavior information is optimized to be

[0077] The configuration of the automatic driving control unit Ac illustrated in FIG. 22(A), FIG. 23(A), and FIG. 16 is the same as that of FIG. The present invention can also be applied to the automatic driving control unit Ac of the robot car 100A in the system. The contents of learning step S26 in this case are similar to those in FIGS. [Other embodiments, etc.]

[0078] The robot car training system of the present invention is included in the road traffic system of the present invention. The embodiment of the robot car training system of the present invention is shown in FIG. The description of the embodiment also describes an embodiment of the road traffic system of the present invention. 12 to 14 show an embodiment of the robot car training system of the present invention. The road traffic system of the present invention is also illustrated in FIG. The description of the embodiment of the robot car training system of the present invention is also a description of the embodiment of the robot car training system of the present invention.

[0079] According to the robot car training system and method of the above embodiment, the non-robot car 100 B learns the driving behavior of the human driver of its own vehicle on a daily basis and improves the driving assistance performance on a daily basis. By doing so, the autonomous driving performance of the Robot Car 100A will be ...

Claims

1. A road traffic system in which a plurality of vehicles travel on a road, A computing system is provided. The computing system includes: A driving behavior information receiving unit that receives driving behavior information of one or more vehicles; an optimization information generating unit that generates optimized driving behavior information based on the driving behavior information; a driving behavior information transmission unit that transmits the optimized driving behavior information to one or more vehicles; The vehicle includes a robot car that is driven by an automatic driving control instead of a human driver, The robot car includes: A driving condition recognition unit that recognizes a driving condition of the host vehicle; a driving behavior information receiving unit that receives the optimized driving behavior information from the computing system; and an automatic driving control unit that performs automatic driving control based on the optimized driving behavior information and the driving conditions of the vehicle.

2. The robot car includes: A machine learning unit that learns about surrounding objects and driving operations of the vehicle, The road traffic system according to claim 1 , wherein the autonomous driving control unit performs autonomous driving control based on the optimized driving behavior information, a driving situation of the host vehicle, and a learning result by the machine learning unit.

3. A road traffic system in which a plurality of vehicles travel on a road, A computing system is provided. The computing system includes: A driving behavior information receiving unit that receives driving behavior information from a non-robot car; an optimization information generating unit that generates optimized driving behavior information based on the driving behavior information; a driving behavior information transmission unit that transmits the optimized driving behavior information to the robot car; The non-robot car is a vehicle that is driven by a human driver, The non-robot car is A driving condition recognition unit that recognizes a driving condition of the host vehicle; A driving operation detection unit that detects a driving operation by a human driver of the vehicle; a driving behavior information transmission unit that transmits to the computing system driving behavior information that associates the driving situation at each time point recognized by the driving situation recognition unit with the driving operation detected by the driving operation detection unit in each driving situation, The robot car is a vehicle that is driven by an automatic driving control instead of a human driver, The robot car includes: A driving condition recognition unit that recognizes a driving condition of the host vehicle; a driving behavior information receiving unit that receives the optimized driving behavior information from the computing system; and an automatic driving control unit that performs automatic driving control based on the optimized driving behavior information and the driving conditions of the vehicle.

4. A road traffic system in which a robot car that is driven by an automatic driving control instead of a human driver runs on a road, A computing system is provided. The computing system includes: A driving behavior information receiving unit that receives driving behavior information of one or more robot cars; an optimization information generating unit that generates optimized driving behavior information based on the driving behavior information; a driving behavior information transmission unit that transmits the optimized driving behavior information to one or more robot cars; The robot car includes: A driving condition recognition unit that recognizes a driving condition of the host vehicle; a driving behavior information receiving unit that receives the optimized driving behavior information from the computing system; an automatic driving control unit that performs automatic driving control based on the optimized driving behavior information and a driving situation of the vehicle; A road traffic system having a driving behavior information transmission unit that transmits to the computing system driving behavior information that corresponds the driving conditions at each point in time recognized by the driving condition recognition unit with driving operations under automatic driving control in each driving condition.

5. 5. The road traffic system according to claim 1, wherein the optimized driving behavior information is driving behavior information optimized according to vehicle attributes of a vehicle receiving the driving behavior information, driving behavior information optimized to minimize a possibility of a vehicle receiving the driving behavior information coming into contact with an obstacle, driving behavior information optimized to minimize energy consumption of a vehicle receiving the driving behavior information, driving behavior information optimized to maximize regenerative energy of a vehicle receiving the driving behavior information, driving behavior information optimized to minimize the number of accelerations or acceleration time in a specified traveling distance or a specified traveling time, driving behavior information optimized to minimize or maximize the number of braking operations or braking time in a specified traveling distance or a specified traveling time, driving behavior information optimized to minimize a traveling distance from a departure point to a destination point, or driving behavior information optimized to minimize a traveling time from a departure point to a destination point.

6. A computer program for implementing the road traffic system according to any one of claims 1 to 5 using one or more computers.

7. 6. The road traffic system according to claim 1, A vehicle sharing system in which a vehicle is shared by multiple users.

8. A computer program for implementing the vehicle sharing system according to claim 7 using one or more computers.

9. A robot car training system having a robot car and a non-robot car that travels along the same route as the robot car, A computing system is provided. The computing system includes: a driving behavior information receiving unit for receiving driving behavior information from the non-robot car; an optimization information generating unit that generates optimized driving behavior information based on the driving behavior information received by the driving behavior information receiving unit; a driving behavior information transmission unit that transmits the driving behavior information generated by the optimization information generation unit to the robot car, The non-robot car is A vehicle operated by a human driver, A driving condition recognition unit that recognizes a driving condition of the host vehicle; A driving operation detection unit that detects a driving operation by a human driver of the vehicle; a driving behavior information transmission unit that transmits to the computing system driving behavior information that associates the driving situation at each time point recognized by the driving situation recognition unit with the driving operation detected by the driving operation detection unit in each driving situation, The robot car includes: A driving condition recognition unit that recognizes a driving condition of the host vehicle; a driving behavior information receiving unit that receives the optimized driving behavior information from the computing system; and an automatic driving control unit that performs automatic driving control based on the optimized driving behavior information and the driving conditions of the vehicle.

10. The optimization information generation unit 10. The robot car training system according to claim 9, further comprising a function of correcting the driving behavior information based on vehicle attributes of a vehicle receiving the driving behavior information so as to minimize a possibility of the vehicle contacting an obstacle.

11. A computer program for implementing the robot car training system of claim 10 using one or more computers.

Images