Electronic control device and vehicle control method

Abstract

This electronic control device comprises: a travel experience determination unit that determines the travel experience at a travel position of a host vehicle; a collective knowledge storage unit that stores collective knowledge information generated from data relating to the movement of a plurality of vehicles; an experience knowledge storage unit that stores experience knowledge information generated from data relating to the movement of the host vehicle; a combination ratio determination unit that determines the combination ratio pattern between the collective knowledge information and the experience knowledge information; and a data generation unit that composites the collective knowledge information and the experience knowledge information on the basis of the travel experience and the combination ratio pattern, and generates data for controlling the host vehicle.

Description

Incorporation by Reference

[0001] This application claims priority from Japanese Patent Application No. 2022-16886, filed on February 7, 2022, the contents of which are incorporated herein by reference. [Technical Field]

[0002] The present invention relates to an electronic control device, and more particularly to a vehicle control method that is effective for driving assistance such as erroneous operation detection. [Background technology]

[0003] For functions to prevent mis-operation, such as functions to prevent pedal misapplication and lane departure, thresholds and other judgment data are set as triggers for the function's implementation. One method for setting judgment data is to use collective intelligence. This method determines judgment data from a collection of the behavior of multiple vehicles. If the behavior of the vehicle traveling in that area differs significantly from the behavior of other vehicles, it is judged to be an erroneous operation, and the erroneous operation prevention function is activated.

[0004] The following patent documents are cited as background art in this technical field: Patent Document 1 (JP 2005-99930 A) describes a vehicle cruise control system that performs automatic steering control of a vehicle based on vehicle cruise information, comprising: an information center; and an onboard device that is mounted on a vehicle and capable of communicating with the information center, wherein the information center comprises a center-side receiving means that receives cruise information from a plurality of vehicles, a center-side recommended cruise information generating means that generates center-side recommended cruise information based on the plurality of cruise information received by the center-side receiving means, and a center-side transmitting means that transmits the center-side recommended cruise information generated by the center-side recommended cruise information generating means, and wherein the onboard device comprises an onboard device receiving means that receives the center-side recommended cruise information transmitted by the center-side transmitting means, and a control means that controls steering of the vehicle based on the center-side recommended cruise information received by the onboard device receiving means.

[0005] Furthermore, paragraphs 0063-0064 of Patent Document 1 state, "Specifically, statistical processing is performed by merging the center's recommended driving line information with the driving line information stored in the vehicle. In other words, the vehicle-mounted device's recommended driving line is not generated solely based on the driving information recorded in the vehicle-mounted device, but is generated from the driving information recorded in the vehicle-mounted device and the center's recommended driving line information. To explain in more detail, the statistical processing calculation unit combines the vehicle's driving line (for one driving session) with the center's recommended driving line in a 1:5 ratio to generate the vehicle-mounted device's recommended driving line information. In other words, the center's recommended driving line has a weight equivalent to five driving sessions of the vehicle's driving line (for one driving session)." Summary of the Invention [Problem to be solved by the invention]

[0006] In this way, the vehicle driving control system described in Patent Document 1 has an information center that receives driving information from multiple vehicles and generates recommended driving information on the center side based on the received driving information, while also generating recommended driving information on the in-vehicle side based on information about the vehicle's past driving, and merging this with the recommended driving information on the center side through statistical processing to set judgment data that can reflect the user's preferences in areas where the vehicle has traveled frequently.

[0007] However, since the recommendation information on the center side and the recommendation information on the in-vehicle device side are combined and merged at a unique ratio, there is a limit to how much user preference can be reflected. Also, because user preference is reflected, the judgment data may be set in a way that delays the activation timing of the erroneous operation prevention function. [Means for solving the problem]

[0008] A representative example of the invention disclosed in this application is as follows: a driving environment acquisition unit that acquires a degree of congestion around the vehicle as a driving environment; a driving experience determination unit that determines a driving experience at a driving position of the vehicle; a collective intelligence storage unit that stores collective intelligence information generated from data related to the operations of a plurality of vehicles; and an experiential knowledge storage unit that stores experiential knowledge information generated from data related to the operation of the vehicle; According to the driving environment acquired above, The collective knowledge information and the experiential knowledge information Show the mixing ratio The system includes a blending ratio determination unit that determines a blending ratio pattern, and a data generation unit that generates control data for the vehicle by combining the collective intelligence information and the experiential intelligence information based on the driving experience and the blending ratio pattern. [Effects of the Invention]

[0009] According to one aspect of the present invention, collective intelligence information and experiential intelligence information are combined according to the driving environment and driving experience, thereby achieving both safety and convenience. Problems, configurations, and effects other than those described above will become clear from the description of the following embodiments. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating an example of the overall configuration of a driving assistance device and a control center according to an embodiment of the present invention. [Figure 2] FIG. 10 is a diagram showing a modified example of the overall configuration of the driving assistance device and the control center according to the embodiment of the present invention. [Figure 3] FIG. 10 is a diagram showing a modified example of the overall configuration of the driving assistance device and the control center according to the embodiment of the present invention. [Figure 4] FIG. 2 is a diagram illustrating a configuration of a determination data generating unit. [Figure 5] FIG. 1 is a diagram showing a driving situation in a parking lot, which is a typical environment in which the present embodiment is effective. [Figure 6] FIG. 1 is a diagram showing a grid in a parking lot, which is a typical environment in which the present embodiment is effective. [Figure 7] FIG. 10 is a diagram illustrating a simple configuration example of a blending ratio of collective knowledge information and experiential knowledge information. [Figure 8] FIG. 10 is a diagram illustrating a typical configuration example of a blending ratio of collective knowledge information and experiential knowledge information. [Figure 9] FIG. 10 is a diagram illustrating an example in which emphasis is placed on the experiential knowledge information in the blending ratio of collective knowledge information and experiential knowledge information. [Figure 10] FIG. 10 is a diagram illustrating an example of a blending ratio of collective wisdom information and experiential knowledge information in which emphasis is placed on collective wisdom information. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an embodiment of a driving assistance device will be described as an example of an electronic control device of the present invention with reference to the drawings.

[0012] 1 to 3 are diagrams showing an example of the overall configuration of a driving assistance device 100 and a control center 110 according to an embodiment of the present invention.

[0013] The driving assistance device 100 shown in FIG. 1 generates control data required for the host vehicle 1 to execute an erroneous operation prevention function and determines whether an operation has occurred. The driving assistance device 100 includes an information acquisition device 10 and a computing device 20. The control data includes, for example, determination data, which is a threshold for determining an erroneous operation in the erroneous operation prevention function and activating the function, and a control target value for the autonomous driving function. The computing device 20 includes a microcomputer, a storage device, and a communication interface. The microcomputer is a processor (e.g., a CPU) that executes programs stored in the storage device. The microcomputer executes predetermined programs to function as a functional unit that provides various functions. The storage device includes a nonvolatile storage area and a volatile storage area. The nonvolatile storage area includes a program area that stores programs executed by the microcomputer and a data area that temporarily stores data used by the microcomputer when executing the programs. The volatile storage area stores data used by the microcomputer when executing the programs. The communication interface connects to other electronic control devices via a network such as a CAN or Ethernet.

[0014] The control center 110 is a device that generates collective intelligence and experiential knowledge required when the driving assistance device 100 generates control data, and includes a collective intelligence generation unit 111, an experiential knowledge generation unit 112, and a transmission / reception unit 113. Because the generation process of the collective intelligence generation unit 111 and the experiential knowledge generation unit 112 imposes a high processing load, the control center 110 executes the process. However, the processing may also be executed by the arithmetic device 20 of the driving assistance device 100. In the configuration example shown in FIG. 1 , the control center 110 generates collective intelligence information and experiential knowledge information and transmits the generated collective intelligence information and experiential knowledge information to the driving assistance device 100 via the transmission / reception unit 113. This allows the control center to accurately control the vehicle using the latest collective intelligence information. Furthermore, even when the arithmetic device 20 does not have sufficient processing capacity, the vehicle can be accurately controlled by combining the collective intelligence information and the experiential knowledge information.

[0015] 2 is a diagram showing a modified example of the overall configuration of the driving assistance device 100 and the control center 110 according to the embodiment of the present invention. In the modified example shown in FIG. 2, the experiential knowledge generation unit 112 is provided in the driving assistance device 100, i.e., the computing device 20, rather than in the control center 110. In this manner, the control center 110 generates collective intelligence information, transmits the generated collective intelligence information to the driving assistance device 100 via the transmission / reception unit 113, and the driving assistance device 100 generates experiential knowledge information. Therefore, the vehicle can be accurately controlled using the latest collective intelligence information generated by the control center 110. Furthermore, by generating experiential knowledge on the vehicle side, the amount of communication required to obtain the experiential knowledge from the control center 110 can be reduced.

[0016] Fig. 3 is a diagram showing a modified example of the overall configuration of the driving assistance device 100 and the control center 110 according to an embodiment of the present invention. In the modified example shown in Fig. 3, the collective intelligence storage unit 21 stores pre-generated collective intelligence information at the time of shipping from the factory, and the collective intelligence information is updated at the time of regular inspection and repair of the vehicle. By storing experiential knowledge in advance on the vehicle side, it is possible to combine the collective intelligence information and experiential knowledge information without providing a control center 110 that distributes the collective intelligence information.

[0017] Next, referring to FIG. 1 in which the collective intelligence generation unit 111 and the experiential knowledge generation unit 112 are calculated in the control center 110, an example will be described in which judgment data, which is a threshold for activating the erroneous operation suppression function as control data, is generated.

[0018] (Information acquisition device 10) The information acquisition device 10 is a device that acquires the driving environment around the vehicle 1, vehicle information of the vehicle 1, and position information of the vehicle 1, and has a driving environment acquisition unit 11, a vehicle information acquisition unit 12, and a position information acquisition unit 13.

[0019] The driving environment acquisition unit 11 extracts driving environment information such as the degree of congestion of vehicles traveling around the vehicle 1, the road surface conditions (paved road, dirt road, wet road, dry road, etc.) of the road on which the vehicle 1 is traveling, and the weather (sunny, rainy, snowy, fog, etc.) based on the observation results of the outside world by external sensors such as a radar sensor using millimeter waves or lasers, or a camera using an image sensor, which are mounted on the vehicle 1, and outputs the information to the calculation device 20. The driving environment acquisition unit 11 may also acquire driving environment information such as the degree of congestion of the road on which the vehicle 1 is traveling, the road surface conditions, and the weather using a car navigation system or the like.

[0020] The vehicle information acquisition unit 12 acquires vehicle information relating to the operation of the vehicle, such as the traveling speed and steering angle of the vehicle 1, based on the outputs of vehicle sensors such as a speed sensor and a steering angle sensor mounted on the vehicle 1, and outputs the information to the calculation device 20. Furthermore, since the vehicle information acquisition unit 12 requires different vehicle information depending on which erroneous operation is to be suppressed, it is preferable that the vehicle information acquisition unit 12 appropriately acquires the required type of vehicle information using the erroneous operation suppression function.

[0021] The position information acquisition unit 13 acquires the current position of the vehicle 1 based on information from a global positioning system (GPS), a global navigation satellite system (GNSS), a gyro sensor, etc., and outputs the acquired position to the calculation device 20.

[0022] (Arithmetic unit 20) The arithmetic device 20 is a device that generates judgment data based on the driving environment, vehicle information, and position information acquired from the information acquisition device 10, and judges an erroneous operation, and includes a transmission / reception unit 113, a collective intelligence storage unit 21, an experiential knowledge storage unit 22, a judgment data generation unit 23, a judgment processing unit 24, and a vehicle control unit 25. Specifically, the arithmetic device 20 is a microcomputer mounted in an ECU (Electronic Control Unit) that includes a CPU and memory (ROM, RAM), and is a device that realizes each function such as the judgment data generation unit 23 by the CPU executing various processing programs stored in the memory.

[0023] The collective intelligence storage unit 21 stores collective intelligence information generated from data related to the operations of multiple vehicles, including other vehicles, generated by the collective intelligence generation unit 111. The collective intelligence information is, for example, a judgment threshold of an erroneous operation suppression function generated from data collecting the operations of multiple vehicles. The experiential knowledge storage unit 22 stores experiential knowledge information generated from data related to the operation of the host vehicle generated by the experiential knowledge generation unit 112. The experiential knowledge information is, for example, a judgment threshold of an erroneous operation suppression function generated from data collecting the operation of the host vehicle. The judgment data generation unit 23 combines the collective intelligence information and the experiential knowledge information at a predetermined blending ratio to generate judgment data, which is data for control at the host vehicle position. The judgment processing unit 24 judges an erroneous operation that has occurred in the host vehicle 1 based on the judgment data and vehicle information of the host vehicle 1.

[0024] Fig. 5 is a diagram showing a typical environment in which this embodiment is effective. As shown in Fig. 5, when the vehicle 1 is parking in a parking space T in a parking lot P, if the brake pedal is mistaken for the accelerator pedal, the pedal misapplication prevention function is activated. On the other hand, even if the driver does not mistake the pedal, if the pedal misapplication prevention function is activated, convenience is reduced. For this reason, it is necessary to appropriately set determination data for activating the pedal misapplication prevention function.

[0025] In conventional vehicle cruise control systems, in order to appropriately set the judgment data, an information center receives driving information from multiple vehicles, generates recommended driving information on the center side based on the received driving information, and distributes the generated recommended driving information to the vehicles. In an embodiment of the present invention, the vehicle generates recommended driving information based on information about the vehicle's past driving history, merges it with the recommended driving information distributed from the center side, and performs statistical processing to generate judgment data that can reflect the user's preferences for areas where the vehicle has traveled frequently. However, while merging the recommended driving information generated by the center side and the recommended driving information generated by the vehicle side at a unique ratio can reflect the user's preferences to a certain extent, there is an upper limit to how much the user's preferences can be reflected, and there are problems such as the setting of judgment data that delays the activation timing of the erroneous operation prevention function due to the reflection of the user's preferences.

[0026] Therefore, the driving assistance device 100 and the control center 110 of this embodiment extract collective intelligence information from the collective intelligence storage unit 21 and experiential intelligence information from the experiential intelligence storage unit 22 based on the host vehicle position information acquired by the position information acquisition unit 13. The judgment data generation unit 23 then determines the blending ratio of the collective intelligence information and the experiential intelligence information based on the driving environment around the host vehicle 1 acquired by the driving environment acquisition unit 11 and the driving experience at that location, and generates judgment data. Therefore, it is possible to prioritize the collective intelligence information to improve safety and the experiential intelligence information to improve convenience, depending on the driving environment around the host vehicle 1 and the driving experience. This allows the judgment data to be appropriately set depending on the situation, unlike the conventional system described above. Details of each component of the driving assistance device 100 and the control center 110 outlined above are described below.

[0027] (Explanation of how to generate collective intelligence and experiential intelligence) <Collective intelligence generation unit 111> The collective intelligence generator 111 generates collective intelligence information by statistical processing such as averaging and variance based on collected data on the behavior of multiple vehicles, including other vehicles. The collective intelligence information is judgment data for activating the erroneous operation prevention function, generated based on the behavior of multiple vehicles, including other vehicles. The judgment data is stored, for example, in a table format, as information associated with location information. Specifically, assuming an erroneous operation prevention function to prevent pedal misapplication in a parking lot P shown in FIG. 5, the judgment data for activating the erroneous operation prevention function include vehicle speed and vehicle acceleration. Information on the vehicle speeds, vehicle accelerations, and driving positions of multiple vehicles is collected, and the judgment data is generated based on the collected data by statistical processing such as average values and variance values. The judgment data may be an average value, or an average value and standard deviation taking the variance into account. The judgment data generated in this manner determines that an erroneous operation has occurred if the vehicle 1 exceeds a threshold defined by the average value or average value and standard deviation of the vehicle speeds and vehicle accelerations of other vehicles at a given location. The judgment data is stored, for example, in a table format. Alternatively, as shown in FIG. 6, the parking lot P may be divided into a grid and judgment data based on the vehicle behavior in each cell associated with a coordinate position may be stored.

[0028] <Experiential Knowledge Generation Unit 112> The experiential knowledge generation unit 112 generates experiential knowledge information by statistical processing such as averaging and variance based on collected data on the behavior of the vehicle 1. The experiential knowledge information is judgment data generated based on the behavior of the vehicle 1 and used to activate the erroneous operation prevention function. The judgment data is stored, for example, in a table format, as information associated with location information. The judgment data may also be stored as information associated with external observation results obtained by an external sensor. Specifically, similar to the collective intelligence generation unit 111 described above, assuming an erroneous operation prevention function to prevent pedal misapplication in a parking lot P shown in FIG. 5, the judgment data for activating the erroneous operation prevention function include vehicle speed and vehicle acceleration. Information on the vehicle speed, vehicle acceleration, and travel location of the vehicle 1 is collected, and the judgment data is generated based on the collected data by statistical processing such as average value and variance. The judgment data may be an average value, or an average value and standard deviation taking the variance into consideration. The judgment data generated in this manner is used to determine an erroneous operation when the vehicle 1 exceeds a threshold defined by the average value or average value and standard deviation of the vehicle's past speed and acceleration at a particular location. The judgment data is stored as information in a table format, for example, but as shown in Figure 6, the parking lot P may be divided into a grid and judgment data based on vehicle operations in each cell associated with a coordinate position may be stored.

[0029] (Explanation of how to combine collective knowledge and experiential knowledge) <Determination data generation unit 23> 4 is a diagram showing the configuration of the judgment data generation unit 23. The judgment data generation unit 23 generates judgment data by blending the collective knowledge information and the experiential knowledge information based on the driving environment obtained by the driving environment acquisition unit 11, the location information obtained by the location information acquisition unit 13, the collective knowledge information stored in the collective knowledge storage unit 21, and the experiential knowledge information stored in the experiential knowledge storage unit 22. The judgment data generation unit 23 includes a collective knowledge information determination unit 51, an experiential knowledge information determination unit 52, a driving experience determination unit 53, and a blending ratio determination unit 54.

[0030] <Collective intelligence information determination unit 51> The collective intelligence information determination unit 51 determines collective intelligence information from the collective intelligence information table stored in the collective intelligence storage unit 21 based on the vehicle position information acquired by the position information acquisition unit 13 .

[0031] <Experiential knowledge information determination unit 52> The experiential knowledge information determining unit 52 determines experiential knowledge information from the experiential knowledge information table stored in the experiential knowledge storage unit 22 based on the vehicle position information acquired by the position information acquiring unit 13 .

[0032] <Driving experience determination unit 53> The driving experience determination unit 53 determines experiential knowledge of past travels of the vehicle position from the experiential knowledge information table stored in the experiential knowledge storage unit 22, based on the vehicle position information acquired by the position information acquisition unit 13. For example, there is a method in which the number of travels is used as driving experiential knowledge and the number of past travels of the vehicle position is acquired. Furthermore, the driving experience determination unit 53 may determine experiential knowledge of past travels of a position corresponding to the observation result of the external world by an external sensor, from the experiential knowledge information table stored in the experiential knowledge storage unit 22.

[0033] <Mixing ratio determination section 54> The blending ratio determination unit 54 determines a blending ratio pattern of the collective intelligence information and the experiential knowledge information based on the driving environment acquired by the driving environment acquisition unit 11 and the driving experience acquired by the driving experience determination unit 53. For example, the determination value is determined by the sum of the judgment threshold of the erroneous operation suppression function generated from the collective intelligence information and the judgment threshold of the erroneous operation suppression function generated from the experiential knowledge information, each weighted by the blending ratio ratio. The blending ratio of the collective intelligence information and the experiential knowledge information can be determined by various methods, as illustrated in FIGS. 7 to 10. In the blending ratios shown in FIGS. 7 to 10, the horizontal axis represents the driving experience and the vertical axis represents the blending ratio of the judgment data. The blending ratios shown in FIGS. 7 to 10 may be stored in table format or may be given as a function representing the illustrated blending ratio curve. When the blending ratio is given as a function, the distribution ratio does not change stepwise and can be continuous. Furthermore, the resolution of the distribution ratio can be improved.

[0034] The blending ratio of the judgment data shown in Figure 7 is the simplest configuration, in which the collective knowledge information is 100% when there is no driving experience, and the blending of the experiential knowledge information is increased linearly as the driving experience increases, and the judgment data is determined so that the experiential knowledge information becomes 100% when the driving experience reaches a predetermined value. The blending ratio shown in Figure 7 increases the blending ratio of the collective knowledge information even if the driving experience is small. When the blending ratio is determined in this way, judgment data that emphasizes experiential knowledge information can be generated on roads that the driver is familiar with, reducing the opportunities for the driver to feel uncomfortable and improving convenience.

[0035] 8, the blending ratio of the judgment data increases linearly with the increase in driving experience, but judgment data is generated using only collective intelligence information without using experiential knowledge information until a predetermined number of driving experiences (for example, 10 driving times) have occurred. Since experiential knowledge is insufficient with a small number of driving times and there is a possibility of abnormal values, judgment data blended with experiential knowledge can be generated after the driver has become accustomed to the driving to a certain extent, and while abnormal values of experiential knowledge from a small number of driving times are eliminated, the chances of the driver feeling uncomfortable can be reduced and convenience can be improved.

[0036] The blending ratio of the judgment data shown in Fig. 9 generates judgment data only using collective intelligence information without using experiential knowledge information, similar to the blending ratio of the judgment data shown in Fig. 8, until a predetermined number of driving experiences (for example, 10 driving times) are generated. The blending ratio of the judgment data shown in Fig. 9 increases the blending of experiential knowledge information as the driving experience increases, but the blending ratio of experiential knowledge information is higher than when the blending ratio is determined linearly as shown in Fig. 8. When the blending ratio is determined in this way, judgment data can be generated based on the driver's preferred behavior, improving convenience.

[0037] The blending ratio of the judgment data shown in FIG. 10, like the blending ratio of the judgment data shown in FIG. 8, generates judgment data using only collective intelligence without using experiential knowledge until a predetermined number of driving experiences (e.g., 10 driving times) have occurred. The blending ratio of the judgment data shown in FIG. 10 increases the blending ratio of experiential knowledge as the driving experience increases, but the blending ratio of experiential knowledge is smaller than when the blending ratio is determined linearly as shown in FIG. 8. Determining the blending ratio in this way makes it possible to generate judgment data based on the behavior of other vehicles, reducing the possibility of contact with other vehicles and ensuring safety. This can alleviate traffic congestion and prevent traffic accidents with other vehicles.

[0038] In this way, by using a blending ratio of various judgment data, judgment data can be generated with emphasis on either collective intelligence or experiential intelligence. By using these blending ratio patterns according to the driving environment, driving assistance appropriate for the driving environment can be provided, thereby ensuring convenience and safety appropriately. For example, by using the linearly changing blending ratio shown in Figure 8 under normal conditions and using the blending ratio shown in Figure 9 when the road is empty, judgment data based on the driver's preferred behavior can be generated, improving convenience. On the other hand, by using the blending ratio shown in Figure 10 when the road is congested, judgment data based on the behavior of other vehicles can be generated, ensuring safety. The blending ratio patterns may be used depending on the driving environment, such as the degree of road congestion, road surface conditions, and weather.

[0039] <Determination processing unit 24> The determination processing unit 24 compares the vehicle information of the vehicle 1 acquired by the vehicle information acquisition unit 12 with the determination data acquired by the determination data generation unit 23 to determine whether an operation error has occurred. For example, if the determination data indicates a speed of 20 km / h while driving in a parking lot P shown in FIG. 4, it is determined that an operation error has occurred if the driver mistakenly presses the accelerator pedal instead of the brake pedal, causing the driving speed to exceed 20 km / h. The determination processing unit 24 outputs the determination result to the vehicle control unit 25.

[0040] <Vehicle control unit 25> Vehicle control unit 25 suppresses erroneous operation based on the result of erroneous operation determination by determination processing unit 24. For example, in the erroneous operation suppression function that prevents pedal misapplication, control is performed to decelerate the vehicle and suppress acceleration.

[0041] (Variation) In the above-described first embodiment, the function for preventing pedal misapplication in a parking lot P shown in FIG. 5 was described as a typical scenario in which the present invention is effective. However, the present invention can generate judgment data for various other erroneous operation prevention functions. For example, the lane departure prevention function uses the positional relationship between the white line and the vehicle as judgment data, and the wrong-way driving prevention function uses the direction of travel or movement as judgment data. On roads where wrong-way driving has not occurred before, there is no empirical knowledge, and control data (judgment data) is generated only from collective intelligence. Then, the judgment data can be compared with the vehicle's direction of travel to issue a warning against wrong-way driving.

[0042] So far, we have explained the activation threshold of the erroneous operation suppression function of the driving assistance device 100, but the same can also be applied to the control values output by the driving assistance function. That is, the control target value of the deceleration when the driving assistance function is activated, the control target value of the inter-vehicle distance, etc. may be determined by combining the collective intelligence information and the experiential intelligence information using the blending ratio of this embodiment.

[0043] In the above-described embodiment, one vehicle has one driver, but in reality, one vehicle has multiple drivers in a vehicle shared by a family or a rental car. Since the experiential knowledge information is information associated with the driver rather than the vehicle, it is preferable to provide a driver discrimination device in the information acquisition device 10 and collect and use the experiential knowledge information for each driver.

[0044] As described above, the electronic control device (driving assistance device 100) of the present invention includes a driving experience determination unit 53 that determines a driving experience at a driving position of the host vehicle, a collective intelligence storage unit 21 that stores collective intelligence information generated from data related to the operations of a plurality of vehicles, an experiential knowledge storage unit 22 that stores experiential knowledge information generated from data related to the operation of the host vehicle, a blending ratio determination unit 54 that determines a blending ratio pattern of the collective intelligence information and the experiential knowledge information, and a data generation unit (judgment data generation unit 23) that combines the collective intelligence information and the experiential knowledge information based on the driving experience and the blending ratio pattern to generate control data for the host vehicle, a position information acquisition unit 13 that acquires position information of the host vehicle, and a driving environment information acquisition unit 24 that acquires information on the driving environment around the host vehicle. The system includes a driving environment acquisition unit 11, a collective intelligence storage unit 21 that stores collective intelligence information generated from data collected from the behaviors of multiple vehicles including other vehicles, an experiential knowledge storage unit 22 that stores experiential knowledge information generated from data collected from the behavior of the vehicle itself, and a data generation unit (judgment data generation unit 23) that combines the collective intelligence information and the experiential knowledge information at a predetermined blending ratio to generate control data for the vehicle's position. The judgment data generation unit 23 has a driving experience determination unit 53 that determines the driving experience at the vehicle's position and a blending ratio determination unit 54 that determines the blending ratio based on the driving environment and the driving experience. This makes it possible to prioritize the collective intelligence information to improve safety or the experiential knowledge information to improve convenience, depending on the driving experience of the vehicle itself. This makes it possible to appropriately set the control data depending on the situation, unlike conventional systems.

[0045] The present invention is not limited to the above-described embodiments, but includes various modifications and equivalent configurations within the spirit and scope of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to configurations including all of the described configurations. Furthermore, part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Furthermore, the configuration of another embodiment may be added to the configuration of one embodiment. Furthermore, part of the configuration of each embodiment may be added, deleted, or replaced with other configurations.

[0046] Furthermore, the aforementioned configurations, functions, processing units, processing means, etc. may be realized in part or in whole in hardware, for example by designing them as integrated circuits, or may be realized in software by having a processor interpret and execute a program that realizes each function.

[0047] Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC card, an SD card, or a DVD.

[0048] In addition, the control lines and information lines shown are those that are considered necessary for explanation, and do not necessarily represent all the control lines and information lines that are necessary for implementation. In reality, it can be assumed that almost all components are interconnected.

Claims

1. A driving environment acquisition unit that acquires a degree of congestion around the vehicle as a driving environment; a driving experience determination unit that determines driving experience at a driving position of the vehicle; a collective intelligence storage unit that stores collective intelligence information generated from data related to the operations of a plurality of vehicles; an experiential knowledge storage unit that stores experiential knowledge information generated from data related to the operation of the host vehicle; a blending ratio determination unit that determines a blending ratio pattern indicating a blending ratio of the collective knowledge information and the experiential knowledge information based on the acquired running environment; and a data generating unit that generates control data for the host vehicle by combining the collective intelligence information and the experiential intelligence information based on the driving experience and the blending ratio pattern.

2. An electronic control device as described in claim 1, The electronic control device is characterized in that the blending ratio determination unit selects a function that represents the relationship between the driving experience and the blending ratio depending on the driving environment, and determines the blending ratio pattern according to the selected function.

3. An electronic control device as described in claim 1, The electronic control device is characterized in that, when the driving experience is smaller than a predetermined value, the mixing ratio determination unit determines the mixing ratio so as to generate control data using only the collective knowledge information without using the experiential knowledge information.

4. An electronic control device as claimed in claim 1, The blending ratio determination unit determines the blending ratio so that the experiential knowledge information is increased when the congestion level is high, and determines the blending ratio so that the collective knowledge information is increased when the congestion level is low.

5. An electronic control device as claimed in claim 1, An electronic control device comprising: a determination processing unit that determines whether an erroneous operation of the host vehicle has occurred based on the control data and operation information of the host vehicle.

6. A vehicle control method executed by an electronic control device, comprising: The electronic control device includes a processor that executes a program, a storage device accessible by the processor, and a driving experience acquisition unit that determines a driving experience at a driving position of the vehicle, the storage device stores collective intelligence information generated from data collected from operations of a plurality of vehicles including other vehicles, and experiential intelligence information generated from data collected from operations of the vehicle itself; The vehicle control method includes: The processor acquires a degree of congestion around the vehicle as a driving environment, the processor determines a blending ratio pattern of the collective intelligence information and the experiential intelligence information based on the acquired driving environment; a processor that synthesizes the collective intelligence information and the experiential intelligence information based on the driving experience and the blending ratio pattern, and generates control data for the host vehicle;

Images