Control device, program, signal control device, signal system, signal control program, information notification device, and information notification program for autonomous vehicle

Abstract

A control device for controlling a vehicle is provided with: an information acquisition unit for acquiring a plurality of pieces of information detected by a sensor provided in a traffic light; and a control unit that controls the vehicle using the plurality of pieces of information acquired by the information acquisition unit and the learned model.

Description

Technical Field

[0001] The present disclosure relates to a control device for an autonomous vehicle, a program, a signal control device, a signal device, a signal system, a signal control program, an information notification device, and an information notification program. Background Art

[0002] In Patent Document 1, a vehicle having an autonomous driving function is described.

[0003] Prior Art Documents

[0004] Patent Documents

[0005] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2022-035198 Summary of the Invention

[0006] Solutions to Problems

[0007] According to one embodiment of the present disclosure, there is provided a control device that controls a vehicle and includes: an information acquisition unit that acquires a plurality of information detected by sensors provided in a signal device; and a control unit that controls the vehicle using the plurality of information acquired by the information acquisition unit and a learned model. The control unit may control the vehicle in units of one billionth of a second using the plurality of information and the learned model.

[0008] When the vehicle enters an intersection where the signal device is provided, the control unit may control the vehicle using a plurality of information detected by sensors provided in the signal device and the learned model. When the vehicle travels on a driving path other than the intersection, the control unit may control the vehicle using a plurality of information detected by sensors mounted on the vehicle and the learned model.

[0009] When the vehicle enters the intersection and the output value of the learned model when a plurality of information detected by sensors provided in the signal device is input to the learned model is the same as the output value of the learned model when a plurality of information detected by sensors mounted on the vehicle is input to the learned model, the control unit may control the vehicle using the plurality of information detected by sensors provided in the signal device and the learned model.

[0010] According to one embodiment of the present disclosure, there is provided a program for causing a computer to function as the information acquisition unit and the control unit.

[0011] According to an embodiment of the present disclosure, a signal control device is provided. The signal control device includes: a first acquisition unit that acquires the traffic conditions around the intersection from sensors provided around the intersection; a second acquisition unit that acquires the driving plan of an autonomous vehicle scheduled to pass through the intersection; a determination unit that determines whether the driving plan of the autonomous vehicle will be delayed when the autonomous vehicle passes through the intersection based on the traffic conditions acquired by the first acquisition unit; and a control unit that controls the signal of the intersection to suppress the delay when it is determined by the determination unit that the delay will occur.

[0012] In this manner, based on the traffic conditions around the intersection acquired from sensors provided around the intersection, it is determined whether the driving plan of the autonomous vehicle will be delayed when the autonomous vehicle scheduled to pass through the intersection passes through the intersection. Moreover, in this manner, when it is determined that the driving plan of the autonomous vehicle will be delayed, the signal of the intersection is controlled to suppress the delay of the driving plan of the autonomous vehicle. Thereby, it is possible to suppress the occurrence of delay in the driving plan of the autonomous vehicle and to suppress the imposition of a large load such as re-making of the driving plan on the in-vehicle computer performing autonomous driving control during driving.

[0013] When it is determined by the determination unit that the delay will occur, the control unit may control the signal of the intersection so that the signal of the intersection is maintained at green during the period when the autonomous vehicle passes through the intersection.

[0014] In this manner, by maintaining the signal of the intersection at green during the period when the autonomous vehicle passes through the intersection, the control of the signal of the intersection is achieved to suppress the delay of the driving plan of the autonomous vehicle. Thereby, compared with the case of performing control such as extending the time for turning the signal of the intersection green by a certain time, it is possible to ensure the safety when the autonomous vehicle passes through the intersection and to suppress the time for turning the signal of the intersection green from becoming longer than necessary.

[0015] The autonomous vehicle for which the control unit controls the signal of the intersection to suppress the delay may be an autonomous vehicle whose preset emergency level is equal to or higher than a specified value.

[0016] According to this manner, for an autonomous vehicle whose emergency level is equal to or higher than a specified value, it is possible to suppress the occurrence of delay in the driving plan, and it is also possible to suppress the number of other vehicles other than the autonomous vehicle whose emergency level is equal to or higher than a specified value and whose driving may be affected by the control of the signal of the intersection by suppressing the number of times of controlling the signal of the intersection.

[0017] The foregoing signal control device may further include a coordination control unit. When the determination unit determines that the foregoing delay will occur, the coordination control unit controls the signal lights of a plurality of intersections that the foregoing autonomous vehicle is scheduled to pass through in sequence, so as to suppress the foregoing delay.

[0018] In this manner, since the signal lights of a plurality of intersections that the autonomous vehicle is scheduled to pass through in sequence are respectively controlled when it is determined that the driving plan of the autonomous vehicle will be delayed, it is possible to eliminate the delay of the driving plan of the autonomous vehicle during the period when the autonomous vehicle passes through the foregoing plurality of intersections in sequence.

[0019] According to an embodiment of the present disclosure, a signal light device is provided. The foregoing signal light device includes the foregoing signal control device and the foregoing signal light, and is provided for each intersection.

[0020] In this manner, since the foregoing signal control device is included, it is possible to suppress the delay of the driving plan of the autonomous vehicle.

[0021] According to an embodiment of the present disclosure, a signal light system is provided. The foregoing signal light system includes: the foregoing signal light device, which is respectively provided at a plurality of intersections; and a coordination control device, which controls the signal lights of a plurality of intersections that the foregoing autonomous vehicle is scheduled to pass through in sequence to suppress the foregoing delay when the determination unit of any one of the foregoing plurality of signal light devices determines that the foregoing delay will occur.

[0022] In this manner, since the foregoing coordination control device is included, it is possible to eliminate the delay of the driving plan of the autonomous vehicle during the period when the autonomous vehicle passes through the foregoing plurality of intersections in sequence.

[0023] According to an embodiment of the present disclosure, a signal control program is provided. The foregoing signal control program causes a computer to execute a process, and the foregoing process includes: obtaining the traffic conditions around the foregoing intersection from sensors provided around the intersection, and obtaining the driving plan of an autonomous vehicle scheduled to pass through the foregoing intersection; determining based on the obtained foregoing traffic conditions whether the driving plan of the foregoing autonomous vehicle will be delayed when the foregoing autonomous vehicle passes through the foregoing intersection; and controlling the signal light of the foregoing intersection to suppress the foregoing delay when it is determined that the foregoing delay will occur.

[0024] According to this manner, it is possible to suppress the occurrence of delay in the driving plan of the autonomous vehicle.

[0025] According to an embodiment of the present disclosure, an information notification device is provided. The information notification device includes: an acquisition unit that acquires the traffic conditions around the intersection from sensors provided around the intersection; a generation unit that generates notification information for an autonomous driving vehicle about to enter the intersection based on the traffic conditions acquired by the acquisition unit; and a display control unit that causes the notification information generated by the generation unit to be displayed as code information on a display unit provided around the intersection.

[0026] In this manner, the traffic conditions around the intersection are acquired from sensors provided around the intersection, and notification information for an autonomous driving vehicle about to enter the intersection is generated based on the acquired traffic conditions around the intersection. Then, the generated notification information is displayed as code information on a display unit provided around the intersection. Thus, the autonomous driving vehicle can photograph the display unit on which the code information is displayed and decode the code information included in the photographed image, thereby acquiring the notification information. In this way, in this manner, since the notification information can be notified to the autonomous driving vehicle without using a mobile communication network, the information can be notified to the autonomous driving vehicle without being affected by the communication state of the mobile communication network.

[0027] The generation unit may generate information including driving instruction information as the notification information, and the driving instruction information instructs each of a plurality of autonomous driving vehicles about to enter the intersection to drive.

[0028] In this manner, in the notification information, a plurality of driving instruction information is included, and the plurality of driving instruction information instructs each of a plurality of autonomous driving vehicles about to enter the intersection to drive, and the notification information is displayed as code information on the display unit. Thus, by causing a single notification information to be displayed as code information on the display unit, it is possible to issue a driving instruction to each of a plurality of autonomous driving vehicles about to enter the intersection.

[0029] The generation unit may consider the traffic conditions in a dead angle area around the intersection that is a dead angle in the view of the autonomous driving vehicle to generate the driving instruction information.

[0030] In this manner, when generating the driving instruction information, the traffic conditions in a dead angle area around the intersection that is a dead angle in the view of the autonomous driving vehicle are considered. Thus, it is possible to issue a driving instruction to the autonomous driving vehicle, and the driving instruction takes into account the traffic conditions in the dead angle area that is a dead angle in the view of the autonomous driving vehicle.

[0031] The display control unit may cause a two-dimensional barcode to be displayed as the code information on the display unit.

[0032] In this method, since the two-dimensional code is displayed as code information on the display unit, the amount of notification information that can be displayed as code information on the display unit can be increased compared to methods such as displaying a one-dimensional code as code information.

[0033] According to an embodiment of the present disclosure, a traffic signal device is provided. The aforementioned traffic signal device includes the aforementioned information notification device and a traffic signal, and is provided for each intersection.

[0034] In this method, since the aforementioned information notification device is included, information can be notified to the autonomous driving vehicle without being affected by the communication state of the mobile communication network.

[0035] According to an embodiment of the present disclosure, an information notification program is provided. The aforementioned information notification program causes a computer to execute processing, and the aforementioned processing includes: obtaining the traffic conditions around the intersection from sensors provided around the intersection; generating notification information for an autonomous driving vehicle about to enter the aforementioned intersection based on the obtained traffic conditions; and causing the generated notification information to be displayed as code information on a display unit provided around the aforementioned intersection.

[0036] According to this method, information can be notified to the autonomous driving vehicle without being affected by the communication state of the mobile communication network.

[0037] It should be noted that the above-mentioned summary of the disclosure does not list all the necessary features of the present disclosure. In addition, sub-combinations of these feature groups can also become the disclosed content. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Schematically shows the danger prediction ability of the AI for ultra-high-performance autonomous driving.

[0039] Figure 2 Schematically shows the Central Brain in ultra-high-performance autonomous driving.

[0040] Figure 3 It is a diagram for explaining the blind spot of a vehicle.

[0041] Figure 4 It is a diagram for explaining the sensors provided in the traffic signal.

[0042] Figure 5 Schematically shows Perfect Speed Control.

[0043] Figure 6 Schematically shows Perfect Bell Curves.

[0044] Figure 7 It is a schematic diagram of perfect cruising.

[0045] Figure 8 It is a schematic diagram of perfect cruising.

[0046] Figure 9 It is a schematic diagram of perfect cruising.

[0047] Figure 10 It is a schematic diagram of perfect cruising.

[0048] Figure 11 It is a schematic diagram of perfect cruising.

[0049] Figure 12 It is a schematic diagram of perfect cruising.

[0050] Figure 13 It is a schematic diagram of perfect cruising.

[0051] Figure 14 It is a block diagram showing an example of the functional configuration of the central brain.

[0052] Figure 15 It is a diagram for explaining the learned model.

[0053] Figure 16 It is a flowchart showing an example of the processing routine executed by the central brain.

[0054] Figure 17 It is a block diagram showing an example of the hardware configuration of a computer that functions as the central brain and the control device schematically.

[0055] Figure 18 It is a block diagram showing the schematic configuration of the signal control system according to the second embodiment.

[0056] Figure 19 It is a flowchart showing an example of the signal control process.

[0057] Figure 20 It is a timing diagram for explaining the operation of the signal control process.

[0058] Figure 21 It is a flowchart showing another example of the signal control process.

[0059] Figure 22 It is a block diagram showing the schematic configuration of the information notification system according to the third embodiment.

[0060] Figure 23 It is a front view showing the signal machine and the display unit according to the third embodiment.

[0061] Figure 24It is a top view showing the arrangement of the traffic signal and the display unit in the third embodiment.

[0062] Figure 25 It is a flowchart showing an example of information notification processing. Detailed implementation mode

[0063] Hereinafter, the present disclosure will be described through the disclosed embodiments, but the following embodiments do not limit the disclosure related to the claims. In addition, all combinations of the features described in the embodiments are not essential for the disclosed solution.

[0064] [First Embodiment]

[0065] Figure 1 It schematically shows the hazard prediction ability of artificial intelligence (AI) for ultra-high-performance autonomous driving related to this embodiment. In this embodiment, various sensor information is digitalized into AI data and stored in the cloud. The AI predicts and judges the optimal mix of situations every nanosecond to optimize the operation of the vehicle.

[0066] Figure 2 It schematically shows the Central Brain in ultra-high-performance autonomous driving related to this embodiment. The Central Brain is an example of a control device for a Level 6 autonomous driving vehicle.

[0067] It should be noted that Level 6 refers to the level indicating autonomous driving, which is equivalent to a level higher than Level 5 (Level 5 representing fully autonomous driving). Although Level 5 represents fully autonomous driving, it is at the same level as human driving and there is still a probability of accidents, etc. Level 6 refers to a level higher than Level 5, which is equivalent to a level with a lower probability of accidents than Level 5.

[0068] In this embodiment, as examples of sensors mounted on the vehicle, there can be mentioned radar, lidar (LiDAR), high-pixel / long-focus / ultra-wide-angle / 360-degree / high-performance cameras, visual recognition, faint sounds, ultrasonic waves, vibrations, infrared rays, ultraviolet rays, electromagnetic waves, temperature, humidity, spot AI weather forecast, high-precision multi-channel Global Positioning System (GPS), low-altitude satellite information, long-tail event AI data, etc. Long-tail event AI data refers to the trip data of a car equipped with Level 5.

[0069] As sensor information obtained from various types of sensors, examples include the movement of the center of gravity of the body weight, detection of road materials, detection of external air temperature, detection of external air humidity, detection of the uphill, downhill, lateral, and diagonal tilt angles of slopes, detection of the freezing mode of the road, detection of moisture content, the materials, wear conditions, and air pressure of each tire, road width, presence or absence of overtaking prohibition, oncoming vehicles, the vehicle types of the front and rear vehicles, the cruising states of these vehicles, surrounding conditions (birds, animals, footballs, accident vehicles, earthquakes, fires, winds, typhoons, heavy rains, light rains, snowstorms, fog, etc.). In this embodiment, these detections are performed every nanosecond.

[0070] In this embodiment, the central brain can, based on this information, perform a match with the most accurate weather forecast for each minimum fixed point of the entire road + using AI. In addition, the central brain can, based on this information, perform a match with the position information of other vehicles. In addition, the central brain can, based on this information, perform a match with the best estimated vehicle type (the remaining amount in this journey, the match per nanosecond of speed). In addition, the central brain can, based on this information, perform a match with the atmosphere such as the music the passengers are listening to. In addition, the central brain can, based on this information, perform conditional recombination at the moment of the desired mood change.

[0071] For example, the central brain can upload AI data to the cloud when the vehicle is charging. A data lake (DataLake) can be formed, analyzed by AI, and always uploaded to the latest state.

[0072] As Figure 3 shown, by using the sensors mounted on the vehicle on a straight line along the traveling direction, even for long distances, other vehicles and other objects can be detected. However, at intersections and other places, there are dead zones where objects cannot be detected by the sensors. In Figure 3 the example, the solid rectangle surrounded by the dashed rectangle represents the vehicle equipped with sensors, and the dashed arrow represents the traveling direction of the vehicle. In addition, the shaded area represents the dead zone where objects cannot be detected by the sensors mounted on this vehicle.

[0073] In this case, since there are dead zones for the vehicle, there is a risk of traffic accidents.

[0074] Therefore, as Figure 4 shown, in this embodiment, sensors 110 are provided for all traffic signal machines 100 on the street, and these sensors 110 can communicate with the central brain of a level 6 autonomous vehicle. Examples of the sensors 110 can include radars, lidars, and high-pixel / long-focus / ultra-wide-angle / 360-degree / high-performance digital cameras, etc. In Figure 4In the example, the sensor 110 is set on the upper part of the signal lamp 100, but the installation location of the sensor 110 is not limited to the upper part of the signal lamp 100. The sensor 110 can be set on the side of the signal lamp 100 or on the column part of the signal lamp 100.

[0075] In each signal lamp 100, the information detected by the sensor 110 in the area that is a blind spot for the autonomous vehicle is collected, and the information on the road conditions is sent to the level 6 autonomous vehicle using wireless communication.

[0076] The central brain acquires a plurality of information detected by the sensor 110 set in the signal lamp 100, and uses the acquired plurality of information and AI to control the vehicle.

[0077] As a method for optimizing the passage of the vehicle, the central brain can use both software and hardware. In terms of software, the central brain uses AI to optimally mix the plurality of information detected by the sensor 110 set in the signal lamp 100, the cloud storage information, and all the sensor information of the vehicle. The AI makes a judgment every nanosecond to achieve autonomous driving that meets the expectations of the passengers. In terms of hardware, the vehicle micro-controls the rotational output of the motor every 1 / 1 billion second (nanosecond). The vehicle is equipped with electrical equipment and motors that can communicate and control in nanoseconds. Since, according to the central brain, the AI anticipates a crisis, there is no need for braking, and the water in the cup will not spill, and it can park perfectly. In addition, the power consumption is also low, and there is no braking friction.

[0078] Figure 5 Schematically shows the perfect speed control (Perfect Speed Control) achieved by using the control of the central brain according to the present embodiment. Figure 5 The principle shown is an index for calculating the braking distance of the vehicle, but it is controlled by this basic equation. In the system according to the present embodiment, due to the existence of ultra-high performance input data, it can be calculated with a beautiful bell curve.

[0079] Figure 6 Schematically shows the perfect bell curves (Perfect Bell Curves) achieved by using the control of the central brain according to the present embodiment.

[0080] As the computing speed when achieving ultra-high performance autonomous driving, it can be achieved at 1 Million (million) TOPS (trillion operations per second).

[0081] As described above, in this embodiment, the central brain can achieve Perfect Cruise Control. The central brain can perform control corresponding to the expectations of the occupants sitting in the vehicle. Examples of the occupants' expectations include "shortest time", "longest battery life margin", "most want to avoid motion sickness", "most want to (safely) feel acceleration (G)", "most want to feel the scenery in a mixture of the above, etc.", "most want to feel a scenery different from the last time", "for example, want to recall the memory of the road visited with someone a few years ago", "most want to avoid the probability of an accident", etc. The central brain discusses various other conditions with the passengers. The central brain performs a perfect mixture with the vehicle by the number of passengers, weight, position, movement of the center of gravity of the weight (calculated per nanosecond), detection of the road material per nanosecond, detection of the temperature of the external air per nanosecond, detection of the humidity of the external air per nanosecond, and overall selection of the above conditions.

[0082] The central brain can consider and perform: "uphill, downhill, lateral, and diagonal tilt angles of the road slope", "matching with the entire journey + the most accurate weather forecast for each minimum fixed point using AI", "matching with the position information of other vehicles per nanosecond", "matching with their best estimated vehicle models (matching of the remaining amount and speed per nanosecond during their journey)", "matching with the atmosphere of the music etc. that the passengers are listening to", "condition reorganization at the moment of the desired mood change", "estimation of the optimal mixture of the freezing method, moisture content of the road per nanosecond, wear of the material of each tire such as 4, 2, 8, 16, etc., air pressure and the remaining road conditions", "lane width, angle on the road at that time, is it a no-passing lane?", "vehicle models in the oncoming lane, front and rear lanes and their cruise states (per nanosecond)", "the best mixture of all other conditions", and the like.

[0083] Among the widths of each lane, the position to be occupied is not the middle, but different. It is different according to the speed, angle, and road information at that time. For example, perform inference matching of the best probabilities of the impacts per nanosecond of flying birds, animals, oncoming vehicles, flying footballs, children, accident vehicles, earthquakes, fires, winds, typhoons, heavy rains, light rains, snowstorms, fog, and others.

[0084] Use the capabilities of the version of the central brain at that time point and the information of the latest update of the braincloud accumulated up to that time point to perform perfect matching.

[0085] This can be defined as the perfect cruise for ultra-high-performance autonomous driving. Therefore, in ultra-high-performance autonomous driving, 1 million TOPS requires the power management of the best battery and the AI-synchronized (synchronized) burst cooling function of the temperature at this time point.

[0086] Figures 7 to 13 It is a schematic diagram of the perfect cruise.

[0087] Next, a specific example of controlling a vehicle using a central brain will be described. Hereinafter, a vehicle that is both a vehicle controlled by the central brain and equipped with the central brain itself will be referred to as the "own vehicle".

[0088] Figure 14 It is a block diagram showing an example of the functional configuration of the central brain. As Figure 14 shown, the central brain includes an information acquisition unit 30, a determination unit 32, an inference unit 34, and a control unit 36. In addition, a learned model 40 is stored in the storage device included in the central brain. The functions of AI are realized by the learned model 40.

[0089] As an example, as Figure 15 shown, the learned model 40 takes the sensor information detected by various sensors as input and outputs an indexed value (hereinafter referred to as "index value") associated with the control of the vehicle as control information for controlling the driving of the vehicle. The learned model 40 is a model obtained through machine learning, and more specifically, through deep learning.

[0090] The information acquisition unit 30 acquires a plurality of information detected by sensors mounted on the own vehicle. In addition, the information acquisition unit 30 acquires a plurality of information detected by sensors 110 provided in the traffic signal 100.

[0091] The determination unit 32 determines whether the own vehicle has entered an intersection where the traffic signal 100 is provided, or whether the own vehicle is traveling on a driving path other than the intersection. In this determination, the determination unit 32 uses, for example, the position information of the own vehicle located by a GPS device mounted on the own vehicle and map information. It should be noted that in this determination, the determination unit 32 may also use an image of the periphery of the own vehicle captured by a digital camera included in the sensor group mounted on the own vehicle. In addition, when it is possible to communicate with the sensors 110 provided in the traffic signal 100, the determination unit 32 may determine that the own vehicle has entered the intersection.

[0092] When the determination unit 32 determines that the host vehicle has entered an intersection, the inference unit 34 inputs a plurality of pieces of information acquired by the information acquisition unit 30 and detected by the sensor 110 provided in the traffic signal 100 into the learned model 40. In addition, when the determination unit 32 determines that the host vehicle is traveling on a driving path other than an intersection, the inference unit 34 inputs a plurality of pieces of information acquired by the information acquisition unit 30 and detected by the sensors mounted on the host vehicle into the learned model 40. The learned model 40 outputs a plurality of index values based on the input plurality of pieces of information. The index value is an example of the output value of the learned model 40.

[0093] As described above, the inference unit 34 infers index values based on a plurality of sensor information. The inference unit 34 uses the computing power of level 6 and performs multivariate analysis on the data collected per nanosecond by a large number of sensor groups and the like using an integration method as shown in the following formula (1) (for example, refer to formula (2)), whereby accurate index values can be obtained. More specifically, while obtaining the integral values of various ultra-high resolution increment values using the computing power of level 6, the indexed values of each variable are obtained at the edge level and in real time, and the highest probability value of the result generated in the next nanosecond can be obtained.

[0094] [Calculation formula 1]

[0095]

[0096] [Calculation formula 2]

[0097] V n = DL(f(A, B, C, D,..., N)(dA n / dt)) (2)

[0098] Note that DL in the formula represents deep learning, and A, B, C, D,..., N represent air resistance, road resistance, road elements (such as garbage), and slip coefficient, etc.

[0099] The indexed values of each variable obtained by the inference unit 34 can be further refined by increasing the number of deep learning times. More accurate index values can be calculated by using a large amount of data such as, for example, the rotation of tires and motors, steering angles, road materials, weather, the influence of garbage or quadratic curve deceleration, slipping, loss of balance, or methods of steering and speed control for regaining balance.

[0100] The control unit 36 can perform the driving control of the present vehicle based on a plurality of index values determined by the inference unit 34. The control unit 36 can achieve the autonomous driving control of the present vehicle. Specifically, the highest probability value of the result generated in the next nanosecond can be obtained from the plurality of index values, and the driving control of the vehicle considering this probability value can be implemented. This control can be performed, for example, using a look-up table that corresponds combinations of a plurality of index values to control parameters for controlling the driving of the vehicle. Additionally, this control can be performed, for example, using a learned model that takes a plurality of index values as inputs and outputs control parameters for controlling the driving of the vehicle. Examples of control parameters include parameters for controlling the speed, acceleration, and traveling direction of the vehicle.

[0101] The central brain repeatedly executes Figure 16 the flowchart shown.

[0102] In step S10, the determination unit 32 determines whether the present vehicle has entered an intersection. If the determination in step S10 is an affirmative determination, the process proceeds to step S12. In step S12, the information acquisition unit 30 acquires a plurality of information detected by the sensor 110 provided in the traffic signal 100.

[0103] In step S14, as described above, the inference unit 34 infers a plurality of index values by inputting the plurality of information detected by the sensor 110 provided in the traffic signal 100 and acquired in step S12 into the learned model 40. In step S16, as described above, the control unit 36 performs the driving control of the present vehicle based on the plurality of index values determined in step S14. When the process of step S16 ends, the process of the flowchart ends.

[0104] On the other hand, when the determination unit 32 determines that the present vehicle is traveling on a driving path other than an intersection, the determination in step S10 is a negative determination, and the process proceeds to step S18. In step S18, the information acquisition unit 30 acquires a plurality of information detected by the sensors mounted on the present vehicle.

[0105] In step S20, as described above, the inference unit 34 infers a plurality of index values by inputting the plurality of information detected by the sensors mounted on the present vehicle and acquired in step S18 into the learned model 40. In step S22, as described above, the control unit 36 performs the driving control of the present vehicle based on the plurality of index values determined in step S20. When the process of step S22 ends, the process of the flowchart ends.

[0106] Note that when the determination unit 32 determines that the host vehicle has entered an intersection, and when the output value of the learned model 40 when a plurality of information detected by the sensor 110 provided in the traffic signal 100 is input to the learned model 40 is the same as the output value of the learned model 40 when a plurality of information detected by the sensors mounted on the host vehicle is input to the learned model 40, the control unit 36 can use the plurality of information detected by the sensor 110 provided in the traffic signal 100 and the learned model 40 to control the host vehicle. In this case, it is possible to suppress a sharp change in the behavior of the host vehicle when the host vehicle enters an intersection. When these output values are not the same, the control unit 36 continues to use the plurality of information detected by the sensors mounted on the host vehicle and the learned model 40 to control the host vehicle.

[0107] As described above, according to the present embodiment, sensors 110 capable of communicating with the central brain of a level 6 autonomous vehicle are provided for all traffic signals 100 on the street. The central brain of a level 6 autonomous vehicle can obtain information on blind spot areas from the sensors 110.

[0108] Therefore, since it is possible to obtain information on blind spot areas that cannot be detected from an autonomous vehicle, the risk of traffic accidents can be reduced. An autonomous vehicle can enter an intersection even when the traffic light is red and can run at high speed and accurately, so the traffic volume of the entire city can be increased by 10 times or more. As a result of these, the Gross Domestic Product (GDP) increases significantly.

[0109] Figure 17 A schematic example of the hardware configuration of a computer 1200 that functions as a central brain, which is an example of a control device, is shown. The program installed in the computer 1200 can cause the computer 1200 to function as one or more "units" of the device according to the present embodiment, or cause the computer 1200 to perform operations associated with the device according to the present embodiment or the one or more "units", and / or can cause the computer 1200 to execute the process according to the present embodiment or a stage of the process. Such a program can be executed by the CPU 1212 to cause the computer 1200 to perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described in this specification.

[0110] The computer 1200 according to the present embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216 that are interconnected via a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive can be a DVD-ROM drive, a DVD-RAM drive, etc. The storage device 1224 can be a hard disk drive, a solid state drive, etc. The computer 1200 also includes a ROM 1230 and conventional input / output units such as a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0111] The CPU 1212 operates according to programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 obtains image data generated by the CPU 1212 from a frame buffer provided in the RAM 1214 or within itself, and causes the image data to be displayed on the display device 1218.

[0112] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 within the computer 1200. The DVD drive reads programs or data from a DVD-ROM, etc., and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card, and / or writes programs and data to the IC card.

[0113] The ROM 1230 stores therein a boot program executed by the computer 1200 at startup, etc., and / or programs dependent on the hardware of the computer 1200. The input / output chip 1240 can also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0114] The program is provided by a computer-readable storage medium such as a DVD-ROM or an IC card. The program is read from the computer-readable storage medium, installed in the storage device 1224, the RAM 1214, or the ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. The information processing described in these programs is read by the computer 1200, and causes cooperation between the programs and the various types of hardware resources described above. The apparatus or method can be configured by implementing operations or processing of information according to the use of the computer 1200.

[0115] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into the RAM 1214 and command the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads the transmission data stored in the transmission buffer provided in a recording medium such as the RAM 1214, the storage device 1224, the DVD-ROM, or the IC card, and transmits the read transmission data to the network, or writes the received data received from the network into the reception buffer provided on the recording medium and the like.

[0116] In addition, the CPU 1212 may cause all or a necessary part of a file or database stored in an external recording medium such as the storage device 1224, the DVD drive (DVD-ROM), the IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. Next, the CPU 1212 may write the processed data back to the external recording medium.

[0117] Various types of information such as various types of programs, data, tables, and databases can be stored in the recording medium to undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214 and write the results back to the RAM 1214. The various types of processing include various types of operations, information processing, conditional judgment, conditional branch, unconditional branch, information retrieval / replacement, etc. described throughout this disclosure and specified by the instruction sequence of the program. In addition, the CPU 1212 may retrieve information in files, databases, etc. within the recording medium. For example, in a case where a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may retrieve an entry that matches the condition specifying the attribute value of the first attribute from the plurality of entries, and read the attribute value of the second attribute stored in the entry, thereby obtaining the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0118] The programs or software modules described above can be stored in a computer-readable storage medium on or near the computer 1200. In addition, a recording medium such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing a program to the computer 1200 via the network.

[0119] The blocks in the flowcharts and block diagrams in this embodiment may represent stages of a process of performing operations or "parts" of a device that functions to perform operations. Specific stages and "parts" may be implemented by dedicated circuits, programmable circuits supplied with computer-readable instructions stored on a computer-readable storage medium, and / or processors supplied with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuits may include digital and / or analog hardware circuits and may also include integrated circuits (ICs) and / or discrete circuits. The programmable circuits may include, for example, reconfigurable hardware circuits such as field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), which include logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, flip-flops, registers, and storage elements.

[0120] A computer-readable storage medium may include any tangible device capable of storing instructions executable by a suitable device. As a result, a computer-readable storage medium having instructions stored therein has a product including the instructions that can be executed to generate a unit for performing the operations specified in the flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy (registered trademark) disks, magnetic disks, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disc read-only memories (CD-ROMs), digital versatile discs (DVDs), Blu-ray (registered trademark) disks, memory sticks, integrated circuit cards, etc.

[0121] Computer-readable instructions can include any one of assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source code or object code described in any combination of one or more programming languages, where the one or more programming languages include object-oriented programming languages such as Smalltalk (registered trademark), JAVA (registered trademark), C++, etc. and traditional procedural programming languages such as the "C" programming language or similar programming languages.

[0122] The computer-readable instructions can be provided locally or via a local area network (LAN), a wide area network (WAN) such as the Internet, etc. to a processor or programmable circuit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, causing the processor or programmable circuit of the general-purpose computer, special-purpose computer, or other programmable data processing device to execute the computer-readable instructions to generate units for performing the operations specified in the flowchart or block diagram. As examples of the processor, include a computer processor, a processing unit, a microprocessor, a digital signal processor, a controller, a microcontroller, etc.

[0123] [Second Embodiment]

[0124] Next, a second embodiment of the present disclosure will be described. It should be noted that the same reference numerals are assigned to the same parts as those in the first embodiment, and the description thereof is omitted.

[0125] In Figure 18 is shown a traffic signal system 10 related to the second embodiment. The traffic signal system 10 includes a plurality of signal devices 12 provided for each intersection of a road, a plurality of autonomous vehicles 16, and a signal control device 22. The signal device 12 includes the traffic signal 100 and the sensor 110 described in the first embodiment, and a wireless communication unit 14 for wirelessly communicating with the signal control device 22. It should be noted that the sensor 110 in the second embodiment is configured to be able to detect traffic conditions such as an emergency vehicle (e.g., a police car, an ambulance, a fire truck, etc. sounding a siren) wanting to pass through the intersection where the signal device 12 is provided.

[0126] The autonomous vehicle 16 includes a travel plan creation unit 18 and a wireless communication unit 20 for wireless communication with the signal control device 22. The travel plan creation unit 18 is implemented by executing a prescribed program by the central brain described in the first embodiment. The travel plan creation unit 18 is triggered by the setting of the destination of the autonomous vehicle 16 and performs processing that subdivides the path to the set destination into travel reservations such as going straight or turning right / left at intersections, and creates a travel plan in which the execution reservation time for each travel reservation is determined. The central brain controls the autonomous vehicle 16 to travel autonomously in accordance with the travel plan created by the travel plan creation unit 18.

[0127] The signal control device 22 includes a CPU, a memory such as a ROM or a RAM, a non-volatile storage unit such as a hard disk drive (HDD) or a solid state disk (SSD), and a wireless communication unit 43. A signal control program is stored in the storage unit. The signal control device 22 functions as a first acquisition unit 24, a second acquisition unit 26, a determination unit 28, a control unit 41, and a coordination control unit 42 by the CPU executing the signal control program, and performs the signal control processing described later ( Figure 19 ). It should be noted that the signal control device 22 is an example of the signal control device in the present disclosure.

[0128] The first acquisition unit 24 acquires the traffic conditions around the intersection from sensors 110 provided around the intersection. The second acquisition unit 26 acquires the travel plan of the autonomous vehicle 16 scheduled to pass through the intersection. The determination unit 28 determines whether the travel plan of the autonomous vehicle 16 will be delayed when the autonomous vehicle 16 passes through the intersection based on the traffic conditions around the intersection acquired by the first acquisition unit 24.

[0129] When the determination unit 28 determines that the travel plan of the autonomous vehicle 16 will be delayed when the autonomous vehicle 16 passes through the intersection, the control unit 41 controls the traffic signal 100 at the intersection to suppress the delay of the travel plan of the autonomous vehicle 16 when the autonomous vehicle 16 passes through the intersection. When the determination unit 28 determines that the travel plan of the autonomous vehicle 16 will be delayed, the coordination control unit 42 controls the traffic signals 100 at a plurality of intersections that the autonomous vehicle 16 is scheduled to pass through in sequence to suppress the delay of the travel plan of the autonomous vehicle 16.

[0130] Next, the operation of the second embodiment will be described. In the second embodiment, the signal control device 22 regularly communicates with each autonomous driving vehicle 16 traveling on the road, and always grasps the position and vehicle speed of each autonomous driving vehicle 16. Then, when any autonomous driving vehicle 16 approaches within a specified distance of the intersection (hereinafter referred to as the control target intersection) where the signal device 12 is provided, the signal control device 22 triggers and performs Figure 19 the signal control process shown.

[0131] In step 50 of the signal control process, the first acquisition unit 24 of the signal control device 22 acquires the traffic conditions at the control target intersection from the sensor 110, such as whether an emergency vehicle is going to pass through the control target intersection.

[0132] In addition, in step 52, the second acquisition unit 26 acquires the driving plan from the autonomous driving vehicle 16 that is scheduled to pass through the control target intersection. Here, in the driving plan acquired by the second acquisition unit 26 from the autonomous driving vehicle 16, it includes information on the driving reservation (going straight / turning left / turning right) of the autonomous driving vehicle 16 at the control target intersection and the scheduled execution time of this driving reservation (the scheduled passing time of the control target intersection).

[0133] As an example, in Figure 20 , an example of the driving plan of the autonomous driving vehicle 16 acquired by the second acquisition unit 26 is marked as the "initial driving plan" and shown. In this "initial driving plan", it is the following driving plan: during the period when the traffic signal 100 at the control target intersection is green, it can pass through the control target intersection without waiting for the signal time.

[0134] In step 54, the determination unit 28 calculates the time when the autonomous driving vehicle 16 passes through the control target intersection based on the traffic conditions at the control target intersection acquired by the first acquisition unit 24 in step 50. In step 56, the determination unit 28 determines whether the intersection passing time calculated in step 54 is delayed by more than a specified time compared to the driving plan (the scheduled passing time of the control target intersection) of the autonomous driving vehicle 16.

[0135] For example, when there is no emergency vehicle or the like passing through the control target intersection, the time difference between the time calculated in step 54 and the driving plan (the scheduled passing time of the control target intersection) of the autonomous driving vehicle 16 is less than the specified time, so the determination in step 56 is negative. In this case, step 58 is skipped and the signal control process ends.

[0136] On the other hand, when there is an emergency vehicle or the like passing through the control target intersection, as an example, as shown in Figure 20As shown by “Actual driving schedule estimated according to surrounding traffic conditions”, the time required to pass through the control target intersection is added with the time for waiting for an emergency vehicle to pass or the time for waiting for a signal. Thus, as Figure 20 As shown by “Delay t1” in , the time calculated in step 54 is delayed by a specified time or more with respect to the driving plan of the autonomous vehicle 16 (the scheduled passing time of the control target intersection). Thus, the determination in step 56 is affirmative, and the process proceeds to step 58.

[0137] In step 58, the control unit 41 controls the traffic signal 100 of the control target intersection so that the traffic signal 100 of the control target intersection is maintained at green during the passage of the autonomous vehicle 16 through the control target intersection (also refer to Figure 20 “Color of the traffic signal after control” shown in ), and ends the signal control process. Thus, as an example, as Figure 20 As shown by “Driving schedule under the color of the traffic signal after control”, the time required to pass through the control target intersection is shortened by the time for waiting for a signal (also refer to “Delay suppression (t2)”), and the delay in the driving plan of the autonomous vehicle 16 is suppressed.

[0138] Next, with reference to Figure 21 , another example of the signal control process executed by the signal control device 22 will be described. Figure 21 The signal control process shown in transfers to step 60 after the process of step 60 is performed. In step 60, the coordination control unit 42 determines whether the delay in the driving plan of the autonomous vehicle 16 is eliminated due to the control of the traffic signal 100 of the control target intersection in step 58. If the determination in step 60 is affirmative, the signal control process ends.

[0139] On the other hand, if the determination in step 60 is negative, the process proceeds to step 62. In step 62, the coordination control unit 42 controls the traffic signal 100 of the next intersection so that the traffic signal 100 of the next intersection is maintained at green during the passage of the autonomous vehicle 16 through the next intersection. When the process of step 62 is performed, the process returns to step 60, and steps 60 and 62 are repeated until the determination in step 60 is affirmative. Thus, the traffic signals 100 of multiple intersections successively passed by the autonomous vehicle 16 are coordinatedly controlled to eliminate the delay in the driving plan of the autonomous vehicle 16.

[0140] As described above, in the second embodiment, the first acquisition unit 24 of the signal control device 22 acquires the traffic conditions around the control target intersection from the sensor 110 provided around the control target intersection, and the second acquisition unit 26 acquires the driving plan of the autonomous driving vehicle 16 that is scheduled to pass through the control target intersection. In addition, the determination unit 28 determines whether the driving plan of the autonomous driving vehicle 16 is delayed when the autonomous driving vehicle 16 passes through the control target intersection, based on the traffic conditions acquired by the first acquisition unit 24. Then, when the determination unit 28 determines that the above-mentioned delay will occur, the control unit 41 controls the traffic signal 100 of the control target intersection to suppress the above-mentioned delay. As a result, it is possible to suppress a delay in the driving plan of the autonomous driving vehicle 16 and to suppress a large load such as re-making of the driving plan being imposed on the in-vehicle computer (central brain) that performs autonomous driving control or the like during driving.

[0141] In addition, in the second embodiment, when the determination unit 28 determines that the above-mentioned delay will occur, the control unit 41 controls the traffic signal 100 of the control target intersection so that the traffic signal 100 of the control target intersection is maintained at green while the autonomous driving vehicle 16 passes through the control target intersection. As a result, compared with the case of performing control such as extending the time for turning the traffic signal 100 of the control target intersection green by a certain time, it is possible to ensure the safety when the autonomous driving vehicle 16 passes through the control target intersection and to suppress the time for the traffic signal of the control target intersection to turn green from becoming longer than necessary.

[0142] In addition, in the second embodiment, when the determination unit 28 determines that the above-mentioned delay will occur, the coordinated control unit 42 controls the traffic signals 100 of the multiple intersections that the autonomous driving vehicle 16 is scheduled to pass through in sequence to suppress the above-mentioned delay ( Figure 21 ). As a result, it is possible to eliminate the delay in the driving plan of the autonomous driving vehicle 16 while the autonomous driving vehicle 16 passes through multiple intersections in sequence.

[0143] It should be noted that in the second embodiment, the following aspects are described: when the driving plan of the autonomous vehicle 16 is likely to be delayed, all the autonomous vehicles 16 at the control target intersection are targeted, and the processing of the traffic signal 100 at the control target intersection is controlled. However, the present disclosure is not limited thereto. For example, the emergency level can be set in advance for each autonomous vehicle 16. When the driving plan of the autonomous vehicle 16 is likely to be delayed, the traffic signal 100 at the control target intersection is controlled for the autonomous vehicles 16 with an emergency level equal to or higher than a specified value. Thus, for example, by setting the emergency level of the autonomous vehicle 16 for transporting patients to be equal to or higher than the specified value, the driving plan of this autonomous vehicle 16 can be preferentially prevented from being delayed. In addition, by suppressing the number of times of controlling the traffic signal 100 at the control target intersection, the number of other vehicles other than the autonomous vehicles 16 with an emergency level equal to or higher than the specified value, whose driving may be affected by the control of the traffic signal 100 at the control target intersection, can be suppressed.

[0144] In addition, in the second embodiment, as an example of the traffic condition where the driving plan of the autonomous vehicle 16 is likely to be delayed, the case where the autonomous vehicle 16 encounters an emergency vehicle at an intersection is described. However, the present disclosure is not limited thereto. As other examples of the traffic condition where the driving plan of the autonomous vehicle 16 is likely to be delayed, the case where there are pedestrians interfering with the autonomous vehicle 16 when the autonomous vehicle 16 turns right / left at an intersection can be cited.

[0145] In addition, in the second embodiment, the method of providing one signal control device 22 for a plurality of signal devices 12 is described. However, the present disclosure is not limited thereto. For example, a signal control device 22 having each functional part (the first acquisition part 24, the second acquisition part 26, the determination part 28, and the control part 41) except the coordination control part 42 can be provided corresponding to each signal device 12 for each intersection. In this method, the devices (signal device 12 and signal control device 22) provided for each intersection are an example of the traffic signal device related to the present disclosure. In addition, in this method, when performing the coordination control of a plurality of traffic signals 100, a coordination control device that functions as the coordination control part 42 can be provided for a plurality of traffic signal devices (signal device 12 and signal control device 22). The traffic signal system 10 in the method provided with this coordination control device is an example of the traffic signal system related to the present disclosure.

[0146] [Third Embodiment]

[0147] Next, a third embodiment of the present disclosure will be described. It should be noted that the same reference numerals are assigned to the same parts as those in the first embodiment, and the description thereof will be omitted.

[0148] In Figure 22 , an information notification system 210 according to the third embodiment is shown. The information notification system 210 includes a plurality of signal devices 211 provided for each intersection of a road, and a plurality of autonomous driving vehicles 224 traveling on the road. The signal device 211 includes the signal 100 and the sensor 110 described in the first embodiment, a display unit 212, and an information notification device 214. It should be noted that in the first embodiment, the sensor 110 is configured to be able to wirelessly communicate with the central brain of the autonomous driving vehicle 224, but the function of the sensor 110 in the third embodiment to wirelessly communicate with the autonomous driving vehicle 224 or the like can be omitted.

[0149] As Figure 23 shown, the display unit 212 is provided near the signal 100 and has a resolution capable of displaying a prescribed two-dimensional code. It should be noted that although only one display unit 212 is shown in Figure 23 , the display unit 212 (and the signal 100) is provided for each road with a different direction of entering the intersection. For example, as Figure 24 shown, in the case of an intersection where a road extending in the east-west direction intersects with a road extending in the north-south direction, a separate display unit 212 is provided in each direction of "E (east)", "W (west)", "S (south)", and "N (north)" of the direction of entering the intersection.

[0150] The information notification device 214 includes a CPU, a memory such as a ROM or a RAM, and a non-volatile storage unit such as an HDD or an SSD. An information notification program is stored in the storage unit. The information notification device 214 functions as an acquisition unit 216, a generation unit 218, and a display control unit 220 by the CPU executing the information notification program, and performs the information notification process described later ( Figure 25 ). It should be noted that the information notification device 214 is an example of the information notification device according to the present disclosure.

[0151] The acquisition unit 216 acquires the traffic conditions around the intersection from the sensors 110 provided around the intersection. The generation unit 218 generates notification information for the autonomous driving vehicle 224 that is about to enter the intersection based on the traffic conditions around the intersection acquired by the acquisition unit 216. Then, the display control unit 220 causes the notification information generated by the generation unit 218 to be displayed as code information (a two-dimensional code in this third embodiment) on the display unit 212 provided around the intersection.

[0152] The autonomous vehicle 224 includes a camera 226 capable of photographing the display unit 212 and an autonomous driving control unit 228. The autonomous driving control unit 228 is implemented by executing a prescribed program by the central brain described in the first embodiment. The autonomous driving control unit 228 decodes the code information displayed in the area corresponding to the display unit 212 in the image photographed by the camera 226 to obtain notification information. Then, the autonomous driving control unit 228 (central brain) controls the autonomous vehicle 224 to travel by autonomous driving in accordance with the obtained notification information (more specifically, the driving instruction information for this vehicle included in the notification information).

[0153] Next, as the operation of the third embodiment, refer to Figure 25 , and the information notification process repeatedly executed periodically by the information notification device 214 at a prescribed time will be described. It should be noted that Figure 25 the information notification process shown is for the autonomous vehicle 224 entering the intersection from a specific entry direction (hereinafter referred to as the entry direction X), and the information notification device 214 also performs Figure 25 the information notification process for entry directions other than the entry direction X.

[0154] In step 250 of the information notification process, the acquisition unit 216 of the information notification device 214 acquires the traffic conditions of the intersection (hereinafter simply referred to as the "intersection") where the traffic signal device 211 is provided and its surroundings from the sensor 110.

[0155] In addition, in step 252, the generation unit 218 determines the autonomous vehicle 224 that will enter the intersection from the entry direction X based on the traffic conditions acquired in step 250, and determines the respective information (ID, position, vehicle speed, traveling direction (straight / right turn / left turn), etc.) of the determined autonomous vehicle 224. As the ID of the autonomous vehicle 224, for example, a character string recorded on a license plate can be applied. In addition, the traveling direction of the autonomous vehicle 224 can be determined, for example, from whether the turn signal is blinking or not.

[0156] It should be noted that in the third embodiment, the autonomous vehicle 224 is configured as follows: a lamp is provided at a position recognizable from the outside, such as on the vehicle roof, and when the autonomous driving control unit 228 performs autonomous driving, the aforementioned lamp is lit. In step 252, the generation unit 218 determines for each vehicle that will enter the intersection from the entry direction X whether a lamp is provided on the vehicle roof or the like and whether the lamp is lit, thereby determining the autonomous vehicle 224 that will enter the intersection from the entry direction X.

[0157] In step 254, based on the traffic conditions obtained in step 250, the generation unit 218 determines the traffic conditions in a blind spot area (for example, the area shown by diagonal lines in Figure 3 ) that is a blind spot for vehicles entering the intersection from the entry direction X. The traffic conditions in this blind spot area include information such as the presence or number, position, traveling direction, and moving speed of traffic participants such as vehicles and pedestrians in the blind spot area.

[0158] In step 256, based on the information of the autonomous driving vehicle 224 that is to enter the intersection from the entry direction X determined in step 252 and the traffic conditions in the blind spot area determined in step 254, the generation unit 218 generates driving instruction information for each autonomous driving vehicle 224.

[0159] As an example, for each autonomous driving vehicle 224 that is to enter the intersection from the entry direction X and has a traveling direction of "going straight", the generation unit 218 determines whether it can pass through the intersection during the period when the traffic light at the intersection is green when traveling at the current vehicle speed. Then, the generation unit 218 generates driving notification information instructing "maintain the current vehicle speed and travel" for the first autonomous driving vehicle 224 determined to be able to pass through the intersection during the period when the traffic light at the intersection is green, and generates driving notification information instructing "decelerate and stop in front of the intersection" for the second autonomous driving vehicle 224 determined to be unable to pass through the intersection during the period when the traffic light at the intersection is green. It should be noted that the ID of the corresponding autonomous driving vehicle 224 is included as information in the driving notification information for each autonomous driving vehicle 224.

[0160] As another example, for each autonomous driving vehicle 224 that is to enter the intersection from the entry direction X and has a traveling direction of "turning right" or "turning left", the generation unit 218 determines whether it interferes with pedestrians, etc. existing in the blind spot area when turning right / left. Then, the generation unit 218 generates driving notification information instructing "slowly pass through the crosswalk when turning right / left" for the third autonomous driving vehicle 224 determined not to interfere with pedestrians, etc. existing in the blind spot area when turning right / left, and generates driving notification information instructing "temporarily stop in front of the crosswalk when turning right / left" for the fourth autonomous driving vehicle 224 determined to interfere with pedestrians, etc. existing in the blind spot area when turning right / left.

[0161] In step 258, the display control unit 220 generates a QR code obtained by encoding the notification information, which includes the driving instruction information generated in step 256 for each autonomous driving vehicle 224 that will enter the intersection from the entry direction X. Then, in step 260, the display control unit 220 causes the QR code generated in step 258 to be displayed on the display unit 212 of the autonomous driving vehicle 224 that will enter the intersection from the entry direction X, and ends the information notification process.

[0162] It should be noted that in the foregoing information notification process, when the code information is displayed on the display unit 212 and notified to the autonomous driving vehicle 224, in the case where the color of the traffic signal 100 changes from green via yellow to red, the code information changes in accordance with the color of the traffic signal 100. In addition, the timing at which the code information displayed on the display unit 212 changes can be the timing simultaneous with the color change of the traffic signal 100, or the timing of a specified time before the color change of the traffic signal 100.

[0163] On the other hand, in the autonomous driving vehicle 224 that will enter the intersection, the autonomous driving control unit 228 obtains the notification information by decoding the code information displayed in the area corresponding to the display unit 212 in the image captured by the camera 226. Then, the autonomous driving control unit 228 extracts the driving instruction information for the own vehicle from the IDs included in the obtained notification information, and controls the autonomous driving vehicle 224 to travel by autonomous driving in accordance with the extracted driving instruction information.

[0164] Thus, for example, in the foregoing first autonomous driving vehicle 224, it is controlled to "maintain the current vehicle speed and travel" in accordance with the driving instruction information for the own vehicle, and in the foregoing second autonomous driving vehicle 224, it is controlled to "decelerate and stop before the intersection" in accordance with the driving instruction information for the own vehicle. In addition, for example, in the foregoing third autonomous driving vehicle 224, it is controlled to "slowly pass through the crosswalk when turning right / left" in accordance with the driving instruction information for the own vehicle, and in the foregoing fourth autonomous driving vehicle 224, it is controlled to "temporarily stop before the crosswalk when turning right / left" in accordance with the driving instruction information for the own vehicle.

[0165] As described above, in the third embodiment, the acquisition unit 216 of the information notification device 214 acquires the traffic conditions around the intersection from the sensor 110 provided around the intersection. Further, the generation unit 218 generates notification information for the autonomous driving vehicle about to enter the intersection based on the traffic conditions around the intersection acquired by the acquisition unit 216. The display control unit 220 causes the notification information generated by the generation unit 218 to be displayed as code information on the display unit 212 provided around the intersection. Thus, since the notification information can be notified to the autonomous driving vehicle 224 without using the mobile communication network, the information can be notified to the autonomous driving vehicle 224 without being affected by the communication state of the mobile communication network.

[0166] Further, in the third embodiment, the generation unit 218 generates information including driving instruction information as the notification information, and the driving instruction information instructs each of the multiple autonomous driving vehicles 224 about to enter the intersection to drive. Thus, by causing a single notification information to be displayed as code information on the display unit 212, driving instructions can be issued to the multiple autonomous driving vehicles 224 about to enter the intersection, respectively.

[0167] Further, in the third embodiment, the generation unit 218 generates the driving instruction information in consideration of the traffic conditions in the dead angle area, which is a blind spot in the view of the autonomous driving vehicle 224, around the intersection. Thus, a driving instruction considering the traffic conditions in the dead angle area, which is a blind spot in the view of the autonomous driving vehicle 224, can be issued to the autonomous driving vehicle 224.

[0168] Further, in the third embodiment, the display control unit 220 causes a two-dimensional barcode to be displayed as code information on the display unit 212. Thus, compared with a method of displaying a one-dimensional code as code information or the like, the amount of notification information that can be displayed as code information on the display unit 212 can be increased.

[0169] Note that, in the foregoing third embodiment, a method of generating the driving instruction information considering the traffic conditions in the dead angle area has been described, but the present disclosure is not limited thereto, and information indicating the conditions of the dead angle area may be included in the notification information as the dead angle area information. Further, the foregoing dead angle area information may be included in the notification information only for intersections with poor visibility where dead angle areas are generated by in-vehicle sensors.

[0170] Further, in the foregoing third embodiment, a method of causing the notification information to be displayed as a two-dimensional code, which is an example of the code information in the present disclosure, on the display unit 212 has been described, but the code information in the present disclosure may be other than a two-dimensional code, such as a one-dimensional barcode.

[0171] In addition, in the foregoing third embodiment, the manner in which the information notification device 214 related to the present disclosure is provided together with the traffic signal 100 and forms part of the traffic signal device 211 has been described. However, the present disclosure is not limited thereto. The information notification device 214 related to the present disclosure may also be provided together with the sensor 110 at an intersection where the traffic signal 100 is not provided, or at a convergence point where multiple roads converge but the traffic signal 100 is not provided, etc.

[0172] As described above, the technology of the present disclosure has been described using embodiments. However, the technical scope of the present disclosure is not limited to the scope described in the above embodiments. Those skilled in the art should understand that various changes or improvements can be made to the above embodiments. As can be seen from the claims, embodiments with such changes or improvements can also be included in the technical scope of the present disclosure.

[0173] It should be noted that the execution order of each process such as the actions, sequences, steps, and stages in the devices, systems, programs, and methods shown in the claims, the specification, and the drawings is not particularly specified as "before...", "earlier than...", etc., or as long as the output of the previous process is not used in the subsequent process, it can be implemented in any order. Regarding the action flow in the claims, the specification, and the drawings, even if it is described using "first", "next", etc. for convenience, it does not mean that it must be implemented in that order.

[0174] The entire disclosures of Japanese Patent Application No. 2022 - 165875 filed on October 14, 2022, Japanese Patent Application No. 2022 - 172347 filed on October 27, 2022, Japanese Patent Application No. 2023 - 036942 filed on March 9, 2023, and Japanese Patent Application No. 2023 - 041210 filed on March 15, 2023 are incorporated herein by reference in their entirety.

[0175] Reference Signs

[0176] 10 Signal control system, 12 Signal device, 16 Autonomous vehicle, 18 Travel plan creation unit, 22 Signal control device, 24 First acquisition unit, 26 Second acquisition unit, 28 Determination unit, 30 Information acquisition unit, 32 Determination unit, 34 Inference unit, 36 Control unit, 40 Learned model, 41 Control unit, 42 Coordination control unit, 100 Signal lamp, 110 Sensor, 210 Information notification system, 211 Signal lamp device, 212 Display unit, 216 Acquisition unit, 218 Generation unit, 220 Display control unit, 224 Autonomous vehicle, 1200 Computer, 1210 Host controller, 1212 CPU, 1214 RAM, 1216 Graphics controller, 1218 Display device, 1220 Input / output controller, 1222 Communication interface, 1224 Storage device, 1230 ROM, 1240 Input / output chip

Claims

1. A control device, wherein, The control device controls a vehicle and includes: an information acquisition unit that acquires a plurality of pieces of information detected by sensors provided in a traffic signal; and a control unit that controls the vehicle by using the plurality of pieces of information acquired by the information acquisition unit and a learned model.

2. The control device according to claim 1, wherein the control unit controls the vehicle in units of one billionth of a second by using the plurality of pieces of information and the learned model.

3. The control device according to claim 1 or 2, wherein when the vehicle enters an intersection where the traffic signal is provided, the control unit controls the vehicle by using a plurality of pieces of information detected by sensors provided in the traffic signal and the learned model, and when the vehicle travels on a driving path other than the intersection, the control unit controls the vehicle by using a plurality of pieces of information detected by sensors mounted on the vehicle and the learned model.

4. The control device according to claim 3, wherein when the vehicle enters the intersection and the output value of the learned model when a plurality of pieces of information detected by sensors provided in the traffic signal are input to the learned model is the same as the output value of the learned model when a plurality of pieces of information detected by sensors mounted on the vehicle are input to the learned model, the control unit controls the vehicle by using the plurality of pieces of information detected by sensors provided in the traffic signal and the learned model.

5. A program, wherein, The program causes a computer to function as the information acquisition unit and the control unit according to claim 1 or 2.

6. A signal control device, wherein, The signal control device includes: a first acquisition unit that acquires the traffic conditions around the intersection from sensors provided around the intersection; a second acquisition unit that acquires the driving plan of an autonomous driving vehicle that is scheduled to pass through the intersection; a determination unit that determines whether the driving plan of the autonomous driving vehicle will be delayed when the autonomous driving vehicle passes through the intersection based on the traffic conditions acquired by the first acquisition unit; and a control unit that, when the determination unit determines that the delay will occur, controls the traffic signal at the intersection to suppress the delay.

7. The signal control device according to claim 6, wherein when the determination unit determines that the delay will occur, the control unit controls the traffic signal at the intersection so that the traffic signal at the intersection is maintained green while the autonomous driving vehicle passes through the intersection.

8. The signal control device according to claim 6, wherein the autonomous driving vehicle whose control unit controls the traffic signal at the intersection to suppress the delay is an autonomous driving vehicle whose preset emergency level is equal to or higher than a specified value.

9. The signal control device according to claim 6, wherein The signal control device further includes a coordination control unit. When the determination unit determines that the delay will occur, the coordination control unit controls the signal lights of multiple intersections that the autonomous vehicle is scheduled to pass through in sequence, so as to suppress the delay.

10. A signal device, wherein, The signal light device is provided for each intersection and includes: The signal control device according to any one of claims 6 to 8; and The signal light.

11. A signal machine system, wherein, The signal light system includes: The signal light device according to claim 10, and the signal light devices are respectively provided at multiple intersections; and A coordination control device, which controls the signal lights of multiple intersections that the autonomous vehicle is scheduled to pass through in sequence when the determination unit of any one of the multiple signal light devices determines that the delay will occur, so as to suppress the delay.

12. A signal control program, wherein The signal control program is used to cause a computer to execute processing, and the processing includes: Obtain the traffic conditions around the intersection from sensors provided around the intersection, and obtain the driving plan of the autonomous vehicle scheduled to pass through the intersection; Based on the obtained traffic conditions, determine whether the driving plan of the autonomous vehicle will be delayed when the autonomous vehicle passes through the intersection; and When it is determined that the delay will occur, control the signal light of the intersection to suppress the delay.

13. An information notification device, wherein, The information notification device includes: An acquisition unit that acquires the traffic conditions around the intersection from sensors provided around the intersection; A generation unit that generates notification information for the autonomous vehicle about to enter the intersection based on the traffic conditions acquired by the acquisition unit; and A display control unit that causes the notification information generated by the generation unit to be displayed as code information on a display unit provided around the intersection.

14. The information notification device according to claim 13, wherein The generation unit generates information including multiple driving instruction messages as the notification information, and the multiple driving instruction messages instruct driving for each of multiple autonomous vehicles about to enter the intersection.

15. The information notification device according to claim 14, wherein The generation unit generates the driving instruction message in consideration of the traffic conditions in a blind spot area around the intersection that is a blind spot in the view of the autonomous vehicle.

16. The information notification device according to claim 13, wherein The display control unit causes a two-dimensional code to be displayed as the code information on the display unit.

17. A signal device, wherein, The signal light device is provided for each intersection and includes: The information notification device according to any one of claims 13 to 16; and The signal light.

18. An information notification program, wherein The information notification program is used to cause a computer to execute processing, and the processing includes: Obtain the traffic conditions around the intersection from sensors provided around the intersection; Generate notification information for an autonomous vehicle about to enter the intersection based on the obtained traffic conditions; and Cause the generated notification information to be displayed as code information on a display unit provided around the intersection.

Images