Vehicle control system, autonomous driving vehicle, and vehicle control method

Abstract

The present invention relates to a vehicle control system, an autonomous driving vehicle, and a vehicle control method. The vehicle control system predicts dangers that the vehicle should avoid based on information related to the surrounding environment of the vehicle. When a danger is predicted, the vehicle control system determines whether the autonomous driving system has rejected intervention in the autonomous driving, and further diagnoses whether the autonomous driving system is normal or abnormal. Then, when the autonomous driving system does not reject intervention in the autonomous driving, or when the autonomous driving system is abnormal even if intervention in the autonomous driving is rejected, the vehicle control system intervenes in the autonomous driving to avoid the predicted danger. However, when the autonomous driving system rejects intervention in the autonomous driving under normal conditions, the vehicle control system stops intervening in the autonomous driving.

Description

Technical Field

[0001] The present invention relates to a vehicle control system, an automatic driving vehicle, and a vehicle control method. Background Art

[0002] Japanese Patent Application Laid-Open No. 2016-203882 discloses a prior art in which a driving plan creation unit creates a driving plan for a vehicle based on a target route and surrounding information, and a driving control unit automatically causes the vehicle to drive according to the driving plan. The driving plan creation unit generates a target trajectory as the driving plan, which is the path the vehicle follows along the target route. The driving plan creation unit generates the target trajectory based on the status of obstacles around the vehicle, in a manner that avoids contact with the obstacles.

[0003] In the above-mentioned prior art, the target trajectory is generated by taking into account the presence of obstacles. However, it is difficult to deal with the dangers caused by unexpected sudden movements of obstacles, such as the sudden stop of the preceding vehicle, the sudden appearance of a person in front of the vehicle, and the sudden appearance of an obstacle, by the generation of a target trajectory. As a technology for avoiding collisions with obstacles, there is known a preventive safety function that evades danger by intervening in the driving control of the vehicle. PCS (Pre-Crash Safety) is an example of a preventive safety function. When PCS senses an obstacle with the possibility of collision, it slows down or stops the vehicle through automatic braking control, thereby avoiding a collision with the obstacle. When PCS is applied to the prior art, autonomous driving based on the target trajectory is usually performed, and when an obstacle with the possibility of collision is sensed, intervention in autonomous driving is performed by PCS.

[0004] However, if a preventive safety function like PCS intervenes in automated driving, the vehicle's behavior becomes different from that required to achieve the target trajectory. Therefore, while it is necessary to reliably avoid danger, it is desirable to prevent preventive safety functions from unnecessarily intervening in automated driving while the target trajectory is being achieved. Summary of the Invention

[0005] The present invention has been made in view of the above-mentioned problems, and an object of the present invention is to provide a vehicle control technology that can reliably avoid danger and suppress unnecessary intervention in autonomous driving in a situation where a target trajectory is to be achieved.

[0006] First, the vehicle control system of the present invention is described. The vehicle control system of the present invention is a system that is installed in a vehicle that performs automatic driving, predicts danger based on information related to the surrounding environment of the vehicle, and intervenes in the automatic driving to avoid the predicted danger. The vehicle control system of the present invention comprises: at least one memory containing at least one program; and at least one processor coupled to the at least one memory. The at least one processor performs the following actions by executing at least one program. The first action is to communicate with the automatic driving system. The automatic driving system is a system that generates a target trajectory for the vehicle and causes the vehicle to travel in a manner that follows the target trajectory through automatic driving. The second action is to receive an override signal from the automatic driving system to refuse intervention in the automatic driving. The third action is to diagnose whether the automatic driving system is normal or abnormal. Then, the fourth action is to stop intervening in the automatic driving only when the override signal is received and the automatic driving system is normal.

[0007] According to the vehicle control system having the above characteristics, when the automated driving system is functioning normally, the vehicle control system receives an override signal from the automated driving system and ceases intervention in automated driving. This prevents unnecessary intervention in automated driving to achieve the target trajectory. On the other hand, when the automated driving system is abnormal, the vehicle control system does not cease intervention in automated driving even if it receives an override signal from the automated driving system. This enables reliable avoidance of danger.

[0008] In the vehicle control system of the present invention, at least one processor may receive a self-diagnosis result from the autonomous driving system and, based on the self-diagnosis result, diagnose whether the autonomous driving system is normal or abnormal. Accordingly, if the self-diagnosis result reported by the autonomous driving system is normal, the autonomous driving system may be diagnosed as normal; if the self-diagnosis result reported by the autonomous driving system is abnormal, the autonomous driving system may be diagnosed as abnormal.

[0009] In the vehicle control system of the present invention, at least one processor may receive a survival confirmation signal periodically transmitted from the autonomous driving system and, based on the survival confirmation signal, diagnose whether the autonomous driving system is normal or abnormal. Accordingly, while the survival confirmation signal is periodically transmitted from the autonomous driving system, the autonomous driving system may be diagnosed as normal, and if the survival confirmation signal is interrupted, the autonomous driving system may be diagnosed as abnormal.

[0010] In the vehicle control system of the present invention, at least one processor may periodically or irregularly call the autonomous driving system and diagnose whether the autonomous driving system is normal or abnormal based on the autonomous driving system's response to the call. Accordingly, while the autonomous driving system is responding to the call from the vehicle control system, the autonomous driving system may be diagnosed as normal, and if it no longer responds to the call, the autonomous driving system may be diagnosed as abnormal.

[0011] In the vehicle control system of the present invention, at least one processor may evaluate the autonomous driving system and, based on the evaluation results, diagnose whether the autonomous driving system is normal or abnormal. Whether the autonomous driving system is normal or abnormal is reflected in the autonomous driving results. Therefore, by evaluating the autonomous driving, it is possible to diagnose whether the autonomous driving system is normal or abnormal.

[0012] Next, the autonomous driving vehicle of the present invention is described. The autonomous driving vehicle of the present invention comprises: an autonomous driving system that generates a target trajectory and performs autonomous driving in a manner that follows the target trajectory; and a vehicle control system that predicts danger based on information related to the surrounding environment and intervenes in the autonomous driving to avoid the predicted danger. When intervention in the autonomous driving by the vehicle control system is not required, the autonomous driving system sends an override signal to the vehicle control system to refuse intervention in the autonomous driving. The vehicle control system receives the override signal from the autonomous driving system and diagnoses whether the autonomous driving system is normal or abnormal. Then, the vehicle control system stops intervening in the autonomous driving only when the override signal from the autonomous driving system is received and the autonomous driving system is normal.

[0013] According to the autonomous vehicle having the above-mentioned features, when the autonomous driving system is functioning normally, the vehicle control system receives an override signal from the system and ceases intervention in autonomous driving. This prevents unnecessary intervention by the vehicle control system in pursuit of a target trajectory. On the other hand, when the autonomous driving system is abnormal, the vehicle control system does not cease intervention in autonomous driving even if it receives an override signal from the system. This enables reliable avoidance of danger by the vehicle control system.

[0014] In the autonomous driving vehicle of the present invention, the autonomous driving system may transmit an override signal to the vehicle control system when the vehicle control system is estimated to be intervening in autonomous driving and the estimated intervention in autonomous driving is unnecessary. Thus, when the autonomous driving system is operating normally, the override signal is transmitted to the vehicle control system before the estimated intervention in autonomous driving is performed, thereby stopping the intervention in autonomous driving.

[0015] In the autonomous driving vehicle of the present invention, the vehicle control system may, when intervening in autonomous driving, notify the autonomous driving system of the intervention, and the autonomous driving system may transmit an override signal to the vehicle control system when the intervention is not necessary. Thus, when the autonomous driving system is operating normally, the override signal may be transmitted to the vehicle control system before the intervention in autonomous driving, as notified by the vehicle control system, is performed, thereby stopping the intervention in autonomous driving.

[0016] In the autonomous driving vehicle of the present invention, the autonomous driving system may perform a self-diagnosis to determine whether it is normal or abnormal, and transmit the self-diagnosis results to the vehicle control system. The vehicle control system may then receive the self-diagnosis results from the autonomous driving system and, based on the self-diagnosis results, diagnose whether the autonomous driving system is normal or abnormal. Accordingly, if the self-diagnosis result reported by the autonomous driving system is normal, the autonomous driving system may be diagnosed as normal; if the self-diagnosis result reported is abnormal, the autonomous driving system may be diagnosed as abnormal.

[0017] In the autonomous driving vehicle of the present invention, the autonomous driving system may periodically transmit a survival confirmation signal to the vehicle control system. The vehicle control system may then receive the survival confirmation signal from the autonomous driving system and, based on the survival confirmation signal, diagnose whether the autonomous driving system is operating normally or abnormally. Accordingly, while the autonomous driving system is periodically transmitting the survival confirmation signal, the autonomous driving system can be diagnosed as normal, and if the survival confirmation signal is interrupted, the autonomous driving system can be diagnosed as abnormal.

[0018] In the autonomous driving vehicle of the present invention, the autonomous driving system may respond to irregular or regular calls from the vehicle control system. Furthermore, the vehicle control system may diagnose whether the autonomous driving system is normal or abnormal based on the response from the autonomous driving system. Accordingly, while the autonomous driving system is responding to calls from the vehicle control system, the autonomous driving system may be diagnosed as normal; if it no longer responds to calls, the autonomous driving system may be diagnosed as abnormal.

[0019] In the autonomous driving vehicle of the present invention, the vehicle control system may evaluate the autonomous driving system and, based on the evaluation results, diagnose whether the autonomous driving system is normal or abnormal. Whether the autonomous driving system is normal or abnormal is reflected in the autonomous driving results. Therefore, by evaluating the autonomous driving, it is possible to diagnose whether the autonomous driving system is normal or abnormal.

[0020] Next, the vehicle control method of the present invention is described. The vehicle control method of the present invention is a method for controlling a vehicle that is automatically driven by an automatic driving system in a manner that follows a target trajectory. According to the vehicle control method of the present invention, the danger that the vehicle should avoid is predicted based on information related to the surrounding environment of the vehicle. In the case of a danger that the vehicle should avoid is predicted, according to the vehicle control method of the present invention, it is determined whether the automatic driving system has rejected the intervention in the automatic driving, and a diagnosis is made as to whether the automatic driving system is normal or abnormal. In the case that the automatic driving system is abnormal or the automatic driving system has not rejected the intervention in the automatic driving, according to the vehicle control method of the present invention, intervention in the automatic driving is performed to avoid the predicted danger. However, in the case that the automatic driving system rejects the intervention in the automatic driving under normal conditions, according to the vehicle control method of the present invention, the intervention in the automatic driving is stopped.

[0021] According to the vehicle control method with the above characteristics, if the autonomous driving system refuses intervention when the system is operating normally, intervention in the autonomous driving is stopped. This prevents unnecessary intervention in the autonomous driving process when the target trajectory is being achieved. On the other hand, if the autonomous driving system is abnormal, intervention in the autonomous driving process is continued even if the system refuses intervention. This ensures reliable avoidance of danger.

[0022] In the vehicle control method of the present invention, the diagnosis of whether the automatic driving system is normal or abnormal can be performed based on at least one of the following.

[0023] a: Results of self-diagnosis performed by the autonomous driving system

[0024] b: Survival confirmation signal periodically sent from the autonomous driving system

[0025] c: Response from the autonomous driving system to the call when the autonomous driving system is called irregularly or regularly

[0026] d: Results of autonomous driving evaluation of the autonomous driving system

[0027] According to the present invention, if the autonomous driving system rejects intervention when the system is operating normally, intervention in the autonomous driving system is stopped. If the autonomous driving system is abnormal, intervention in the autonomous driving system is continued even if the system rejects intervention. This ensures that avoidable hazards can be avoided and prevents unnecessary intervention in the autonomous driving system when achieving the target trajectory. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Hereinafter, features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will be described with reference to the accompanying drawings, wherein like reference numerals denote like elements, and wherein:

[0029] Figure 1 This diagram explains the override of preventive safety functions achieved through the automated driving function.

[0030] Figure 2 This diagram explains the problem of overriding preventive safety functions achieved through automated driving functions.

[0031] Figure 3 This is a block diagram showing the configuration of a control system of an autonomous driving vehicle according to an embodiment of the present invention.

[0032] Figure 4 This is a block diagram showing the functions of the automatic driving system and the vehicle control system according to the embodiment of the present invention.

[0033] Figure 5 This is a flowchart showing the process of determining whether to execute / stop intervention in automatic driving, performed by the vehicle control system according to the embodiment of the present invention.

[0034] Figure 6 This is a timing chart explaining the first diagnostic method for the automatic driving system.

[0035] Figure 7 This is a timing chart explaining the second diagnostic method for the automatic driving system.

[0036] Figure 8 This is a timing chart explaining the third diagnostic method for the automatic driving system.

[0037] Figure 9 This is a timing chart explaining the fourth diagnostic method for the automatic driving system.

[0038] Figure 10A This is a diagram for explaining an evaluation method of autonomous driving related to a fourth diagnostic method of an autonomous driving system.

[0039] Figure 10B This is a diagram for explaining an evaluation method of autonomous driving related to a fourth diagnostic method of an autonomous driving system. DETAILED DESCRIPTION

[0040] The following describes embodiments of the present invention with reference to the accompanying drawings. However, when numerical values such as the number, quantity, amount, and range of various elements are mentioned in the embodiments shown below, the present invention is not limited to such numerical values unless otherwise specified or clearly determined in principle. Furthermore, with respect to the structures and steps described in the embodiments shown below, these are not necessarily required for the present invention unless otherwise specified or clearly determined in principle.

[0041] 1. Overview of the Autonomous Driving Vehicle of This Embodiment

[0042] 1-1. Autonomous Driving Functions and Preventive Safety Functions

[0043] The autonomous driving vehicle of this embodiment is a vehicle having an autonomous driving function for automatically driving the vehicle so as to follow a target trajectory and a preventive safety function for avoiding danger affecting the vehicle.

[0044] Autonomous driving is performed based on essential driving information, including map information and information about the vehicle's surroundings. Specifically, the optimal route to the destination is determined based on map information. A driving plan is then created to ensure the vehicle complies with traffic regulations and safely follows the optimal route. This driving plan includes actions such as maintaining the current lane and making lane changes.

[0045] In autonomous driving, a target trajectory is generated based on the driving plan. The target trajectory is the driving trajectory that the vehicle should ultimately take, and is determined after considering collisions with all obstacles in front of the vehicle based on information related to the vehicle's surrounding environment. The target trajectory includes a set of target positions of the vehicle within the road on which the vehicle is traveling and a target speed for each target position. In autonomous driving, in order to make the vehicle follow the target trajectory, the following steps are performed: calculating the deviation between the vehicle and the target trajectory (lateral deviation, yaw angle deviation, speed deviation, etc.), and controlling the steering, braking, or driving of the vehicle in a way that reduces this deviation.

[0046] The preventive safety function is to control the braking, driving, steering or a combination of these of the vehicle in order to avoid the danger approaching the vehicle. The danger approaching the vehicle in this specification refers to a type of danger that can be detected by sensors and can be avoided by controlling the vehicle. A representative example is a collision with an object including an obstacle. When a danger approaching the vehicle is predicted during the execution of autonomous driving, intervention in the autonomous driving is performed as a preventive safety function. As a specific example of a preventive safety function, PCS (Pre-Crash Safety) can be cited. In PCS, automatic braking by a brake actuator is used as a preventive safety method.

[0047] 1-2. Overriding Preventive Safety Functions through Automated Driving and the Issues

[0048] Preventive safety functions are the most important for ensuring vehicle safety. Therefore, in principle, preventive safety functions take precedence over other functions. However, to ensure vehicle safety, even during autonomous driving, a target trajectory is generated that takes collisions with surrounding objects into account. The safety benchmarks used for preventive safety and those used in autonomous driving are not necessarily consistent. Therefore, if autonomous driving and preventive safety functions operate completely independently, even if a target trajectory is generated to avoid collisions with surrounding objects, the preventive safety function may still be activated, making it impossible to follow the target trajectory.

[0049] For example, as a preventive safety function, PCS is used as an example. Figure 1 The upper layer of the figure shows an example in which an autonomous vehicle (hereinafter simply referred to as a vehicle) 2 is about to cross the center line CL and overtake a leading vehicle 3. In this case, the autonomous driving function recognizes the leading vehicle 3 as an object 4 using a camera, LiDAR (Light Detection and Ranging), etc., and generates a target trajectory TR so as not to collide with the object 4. Furthermore, in generating the target trajectory TR, the relative position and relative speed of the following vehicle 5 relative to the autonomous vehicle 2 are also taken into account to avoid interference with the following vehicle 5 traveling in the adjacent lane. Meanwhile, the PCS, a preventive safety function, recognizes the leading vehicle 3 using a camera, millimeter-wave radar, etc., and measures the lateral position of the leading vehicle 3 relative to the autonomous vehicle 2 and the TTC (Time To Collision) of the leading vehicle 3 relative to the autonomous vehicle 2. It then determines whether the leading vehicle 3 has entered a reaction area RA defined by the left and right limit positions of the lateral position and the limit time of the TTC.

[0050] When the autonomous driving vehicle 2 is about to overtake the preceding vehicle 3 by following the target trajectory TR, Figure 1 As shown in the lower layer of the diagram, due to the positional relationship between the target trajectory TR and the leading vehicle 3, the leading vehicle 3 could enter the reaction area RA. In this case, the preventive safety function intervenes in the automated driving, applying brakes BK to prevent a collision between the automated vehicle 2 and the leading vehicle 3. As a result, the trajectory of the automated vehicle 2 deviates from the target trajectory, preventing it from overtaking the leading vehicle 3. Furthermore, the vehicle decelerates rapidly while crossing the center line CL, potentially leading to a collision between the automated vehicle 2 and the following vehicle 5.

[0051] In order to prevent such a situation and to make the autonomous driving vehicle 2 travel in a manner that follows the target trajectory TR, the override of the preventive safety function implemented by the autonomous driving function is permitted. The override is a function that refuses the intervention of the autonomous driving implemented by the preventive safety function when it is predicted that the preventive safety function will be activated. Figure 2 In the example shown above, when a target trajectory TR for overtaking preceding vehicle 3 is generated, the autonomous driving function requests an override from the preventive safety function. If the preventive safety function accepts this request, the preventive safety function's intervention is temporarily suspended. This allows autonomous vehicle 2 to overtake preceding vehicle 3 while following the target trajectory TR without being hampered by the preventive safety function's intervention.

[0052] However, there is no guarantee that the automatic driving function will always function normally. If the automatic driving function does not function normally, the automatic driving vehicle 2 may not be able to follow the target trajectory TR, or the generated target trajectory TR may interfere with the preceding vehicle 3. In such a case, it is not preferable to allow the automatic driving function to override from the perspective of preventive safety. If the automatic driving function is allowed to override even if it is not functioning properly, for example, Figure 2 As shown in the lower layer of , when the target trajectory TR interferes with the preceding vehicle 3 , the preventive safety function does not operate, and therefore the risk of collision with the preceding vehicle 3 may increase.

[0053] As described above, if the preventive safety function implemented by the autonomous driving function is constantly allowed to override, depending on the state of the autonomous driving function, it may be impossible to avoid the danger that should be avoided. The autonomous driving vehicle 2 of this embodiment has a structure for reliably avoiding the danger that should be avoided and suppressing unnecessary intervention in the autonomous driving when the target trajectory is being achieved. The structure of the autonomous driving vehicle 2 of this embodiment is described below.

[0054] 2. Configuration of the Autonomous Driving Vehicle of This Embodiment

[0055] 2-1. Configuration of the Control System for Autonomous Vehicles

[0056] Figure 3 This is a block diagram showing the control system configuration of an autonomous vehicle 2 according to this embodiment. Autonomous vehicle 2 includes an autonomous driving system 10, a vehicle control system 20, onboard sensors 30 that input sensor information to the autonomous driving system 10 and vehicle control system 20, and vehicle actuators 40 that operate based on signals output from the vehicle control system 20. These actuators are connected via an in-vehicle network.

[0057] The onboard sensor 30 includes an external sensor 31, an internal sensor 32, and a GPS (Global Positioning System) receiver 33. The external sensor 31 is a sensor that obtains information related to the surrounding environment of the autonomous driving vehicle 2. The external sensor 31 includes a camera, a millimeter wave radar, and a LiDAR. Based on the information obtained by the external sensor 31, the following processing is performed: sensing of objects existing around the autonomous driving vehicle 2, measurement of the relative position and relative speed of the sensed object relative to the autonomous driving vehicle 2, and recognition of the shape of the sensed object. The internal sensor 32 is a sensor that obtains information related to the movement of the autonomous driving vehicle 2. The internal sensor 32 includes, for example, a wheel speed sensor, an acceleration sensor, a yaw angular velocity sensor, and a steering angle sensor. The GPS receiver 33 is used to obtain information related to the current position of the autonomous driving vehicle 2. In addition to these, the autonomous driving vehicle 2 is also equipped with a receiver for receiving information from the road traffic information communication system.

[0058] The vehicle actuator 40 includes a steering actuator 41 for steering the autonomous vehicle 2, a drive actuator 42 for driving the autonomous vehicle 2, and a brake actuator 43 for braking the autonomous vehicle 2. Examples of the steering actuator 41 include power steering systems, steer-by-wire systems, and rear-wheel steering systems. Examples of the drive actuator 42 include engines, EV (Electric Vehicle) systems, and hybrid systems. Examples of the brake actuator 43 include hydraulic brakes and regenerative brakes.

[0059] The autonomous driving system 10 and the vehicle control system 20 are independent ECUs (Electronic Control Units). Each includes a processor 10a, 20a and a memory 10b, 20b. Processors 10a, 20a are preferably multi-core processors. The memories 10b, 20b store various programs and data. The memories 10b, 20b referred to herein include a primary storage device and an auxiliary storage device. Necessary information is input and output between the autonomous driving system 10 and the vehicle control system 20, for example, via CAN (Controller Area Network) communication.

[0060] Although details will be described later, the autonomous driving system 10 is a system that manages the autonomous driving of the autonomous vehicle 2. The memory 10b included in the autonomous driving system 10 stores a program for autonomous driving, which can be executed by the processor 10a, and various information related to the program. This information includes map information. The autonomous driving program is executed by the processor 10a, thereby enabling the autonomous driving function in the autonomous driving system 10. The autonomous driving system 10 generates a target trajectory for autonomous driving and inputs the generated target trajectory to the vehicle control system 20. Furthermore, when the autonomous driving system 10 rejects intervention in autonomous driving as a preventive safety function, it inputs an override signal to the vehicle control system 20.

[0061] Although the details will be described later, the vehicle control system 20 is a system responsible for managing the movement of the autonomous driving vehicle 2. The vehicle control system 20 operates the vehicle actuator 40 so that the autonomous driving vehicle 2 follows the target trajectory input from the autonomous driving system 10. The memory 20b of the vehicle control system 20 stores programs that can be executed by the processor 20a and various information associated with the programs. The programs include preventive safety programs. The preventive safety programs are executed by the processor 20a, whereby the vehicle control system 20 functions as a preventive safety system. When the vehicle control system 20, which is a preventive safety system, predicts a danger approaching the autonomous driving vehicle 2, it intervenes in the autonomous driving so that the autonomous driving vehicle 2 moves in a manner that avoids the danger. However, when an override signal is input from the autonomous driving system 10, the vehicle control system 20 stops intervening in the preventive safety function only when the specified intervention stop conditions are met.

[0062] 2-2. Functions of the autonomous driving system and vehicle control system

[0063] Figure 4 This is a block diagram showing the functions of the automatic driving system 10 and the vehicle control system 20 of this embodiment. Figure 4 The details of each function of the automatic driving system 10 and the vehicle control system 20 will be described.

[0064] The autonomous driving system 10 includes a map database (map DB) 11, a driving plan generator 12, a target trajectory generator 13, and an override request determiner 14. These functions are implemented as the autonomous driving system 10 when the processor 10a executes programs stored in the memory 10b. The aforementioned map information is managed by the map DB 11. The map DB 11 is pre-stored on an auxiliary storage device such as an SSD (Solid State Disk) or HDD (Hard Disk Drive). However, map information can also be downloaded from an external server via the Internet, or referenced from an external server.

[0065] The driving plan generator 12 obtains the optimal route to the destination from the map database 11 and generates a driving plan so that the autonomous vehicle 2 complies with traffic regulations and safely travels along the optimal route. The driving plan includes the vehicle's route and the actions of the autonomous vehicle 2, such as maintaining the current lane and making lane changes.

[0066] The target trajectory generation unit 13 generates a target trajectory based on the driving plan. The target trajectory is the driving trajectory that the autonomous driving vehicle 2 should eventually take. The target trajectory generation unit 13 determines the target trajectory after considering the collision with all obstacles in front of the autonomous driving vehicle 2. The target trajectory generation unit 13 uses, for example, LiDAR, a camera, a fusion of LiDAR and a camera, or a fusion of them with a millimeter-wave radar to obtain information about the surroundings of the autonomous driving vehicle 2, and generates a target trajectory based on the information. The target trajectory generation unit 13 preferably generates the target trajectory in a manner having a plurality of groups consisting of two elements, namely, coordinate coordinates (p, v), which are a target position p fixed in the coordinate system of the autonomous driving vehicle 2 and a velocity v (or acceleration) at each target point. Here, each target position p has at least an x-coordinate and a y-coordinate position fixed in the coordinate system of the vehicle, or information equivalent to the position. The target trajectory generation unit 13 inputs the generated target trajectory into the vehicle control system 20.

[0067] The override request determination unit 14 determines whether to request an override of the preventive safety function from the vehicle control system 20. Conditions in which the actions of the autonomous driving vehicle 2, achieved through autonomous driving, would cause the preventive safety function to operate are pre-registered in the override request determination unit 14. For example, overtaking a preceding vehicle traveling as described above is one of the conditions in which the preventive safety function would operate. In addition, other conditions in which the preventive safety function would operate include passing by a parked vehicle or a fallen object, and changing lanes. The override request determination unit 14 determines whether the preventive safety function will operate based on the target trajectory generated by the target trajectory generation unit 13, and inputs an override signal to the vehicle control system 20 if the preventive safety function will operate.

[0068] The vehicle control system 20 includes a motion manager 21, a preventive safety system 22, and an automated driving system diagnostic unit 23. These functions are implemented as the vehicle control system 20 when the processor 20a executes programs stored in the memory 20b. However, if the vehicle control system 20 is composed of multiple ECUs, the functions of the motion manager 21 and the preventive safety system 22 (and the automated driving system diagnostic unit 23) may be allocated to each ECU.

[0069] The motion manager 21 performs following control to cause the autonomous vehicle 2 to follow the target trajectory. During following control, the braking and driving forces used to bring the actual acceleration calculated by the speed sensor into alignment with the target acceleration in the target trajectory are calculated. The calculated braking and driving forces are distributed as a requested braking force requested of the brake actuator 43 and a requested driving force requested of the drive actuator 42. Furthermore, during following control, the steering angle used to bring the vehicle's actual driving trajectory into alignment with the target trajectory is calculated as a requested steering angle requested of the steering actuator 41. The motion manager 21 converts the requested braking force, requested driving force, and requested steering angle used to cause the autonomous vehicle 2 to follow the target trajectory into operation signals and inputs them to the corresponding vehicle actuators 40. However, when receiving an instruction for avoidance action from the preventive safety system 22, as described below, the motion manager 21 prioritizes the instruction from the preventive safety system 22.

[0070] The preventive safety system 22 detects obstacles ahead of the autonomous vehicle 2 based on sensor information from external sensors 31. The sensor information used by the preventive safety system 22 may be the same as or different from the sensor information used by the target trajectory generator 13. For example, a camera or millimeter-wave radar may be used for obstacle detection. When an obstacle is detected ahead of the autonomous vehicle 2, the preventive safety system 22 determines the risk of collision between the autonomous vehicle 2 and the obstacle. Specifically, the preventive safety system 22 calculates the time-to-travel (TTC) based on the relative distance and relative speed from the autonomous vehicle 2 to the detected obstacle. If the TTC is below a threshold and the obstacle's lateral position relative to the autonomous vehicle 2 overlaps with the autonomous vehicle 2, the preventive safety system 22 determines that the risk of collision between the autonomous vehicle 2 and the detected obstacle is high. If the preventive safety system 22 determines that the risk of collision is high, it instructs the motion manager 21 to take evasive action to avoid the risk, unless a predetermined intervention stop condition is met. In other words, the preventive safety system 22 intervenes in the autonomous driving process. The content of the avoidance action instructed to the motion manager 21 is typically emergency braking by the brake actuator 43 , limitation of the driving force by the drive actuator 42 , avoidance steering by the steering actuator 41 , or a combination thereof.

[0071] The automatic driving system diagnostic unit 23 diagnoses whether the automatic driving system 10 is normal or abnormal. The aforementioned intervention stop condition refers to the input of an override signal from the automatic driving system 10 to the preventive safety system 22 and the normal operation of the automatic driving system 10. The automatic driving system diagnostic unit 23 inputs the diagnostic results of the automatic driving system 10 to the preventive safety system 22. The diagnostic method performed by the automatic driving system 10 will be described later.

[0072] 2-3. Flow of Judgment on Execution / Stop of Intervention in Autonomous Driving

[0073] As described above, in the present embodiment, when danger is predicted, the vehicle control system 20 intervenes in the automatic driving, but when a predetermined intervention stop condition is satisfied, the intervention in the automatic driving is stopped. Figure 5 The flow chart shows the process of determining whether to intervene in the automatic driving by the vehicle control system 20. Figure 5 The vehicle control method of this embodiment is also shown.

[0074] First, the vehicle control system 20 predicts danger based on sensor information about the surrounding environment of the autonomous vehicle 2 obtained by the external sensor 31 (step S1). Then, based on the prediction result of step S1, the vehicle control system 20 determines whether there is a danger that the autonomous vehicle 2 should avoid (step S2). If there is no danger to avoid, then intervention in the autonomous driving is not required, and the remaining processing is skipped.

[0075] If a danger that should be avoided exists, the vehicle control system 20 determines whether an override signal has been received from the automated driving system 10 (step S3). If no override signal has been received, the automated driving system 10 has not rejected the intervention of the preventive safety function. Therefore, in this case, the vehicle control system 20 executes the intervention of the automated driving system by the preventive safety function (step S6).

[0076] Upon receiving the override signal, the vehicle control system 20 determines whether the automated driving system 10 is operating normally using a diagnostic method described below (step S4). If the automated driving system 10 is not operating normally, for example, if the generated target trajectory interferes with an obstacle, even if the automated driving system 10 requests an override, the override cannot be granted. Therefore, if the automated driving system 10 is not operating normally, the vehicle control system 20 rejects the override request from the automated driving system 10 and intervenes in the automated driving process using the preventive safety function (step S6).

[0077] It should be noted that the automatic driving system 10 cannot continue driving as it is if an abnormality has occurred. Therefore, if the automatic driving system 10 is determined to be abnormal in step S4, the vehicle control system 20 intervenes in the automatic driving and then brings the automatic driving vehicle 2 to an emergency stop or moves the automatic driving vehicle 2 to a safe location and stops the vehicle there.

[0078] If the autonomous driving system 10 requests an override and is operating normally, the vehicle control system 20 stops intervening in the autonomous driving process through the preventive safety function (step S5). Thus, if the autonomous driving system 10 refuses to intervene while operating normally, the vehicle control system 20 stops intervening in the autonomous driving process. However, if the autonomous driving system 10 is abnormal, the autonomous driving process continues to intervene even if the system refuses to intervene. This ensures that avoidable hazards are reliably avoided and prevents unnecessary intervention in the autonomous driving process while achieving the target trajectory.

[0079] 2-4. Diagnostic Methods for Autonomous Driving Systems

[0080] 2-4-1. First diagnostic method

[0081] There are four diagnostic methods of the automatic driving system 10, namely the first diagnostic method to the fourth diagnostic method. First, use Figure 6 A first diagnostic method of the automatic driving system 10 will be described. Figure 6 This is a timing chart for explaining a first diagnostic method of the automatic driving system 10 .

[0082] like Figure 6 As shown, in the first diagnostic method, the automatic driving system 10 performs a self-diagnosis. During the self-diagnosis, specified items related to automatic driving are checked. When an override signal is sent to the vehicle control system 20, the automatic driving system 10 transmits the self-diagnosis results along with the override signal. The vehicle control system 20 receives the self-diagnosis results from the automatic driving system 10 and, based on the self-diagnosis results, diagnoses whether the automatic driving system 10 is normal or abnormal. Accordingly, if the self-diagnosis result reported by the automatic driving system 10 is normal, the automatic driving system 10 can be diagnosed as normal; if the self-diagnosis result reported is abnormal, the automatic driving system 10 can be diagnosed as abnormal.

[0083] It should be noted that in the timing diagram, the automated driving system 10 sends both the override signal and the self-diagnosis result simultaneously. However, the self-diagnosis result may be sent first. If the self-diagnosis result sent first is normal, the vehicle control system 20 reconfirms the self-diagnosis result after receiving the override signal. If the reconfirmed self-diagnosis result remains normal, the vehicle control system 20 ceases intervention in automated driving. However, if the self-diagnosis result becomes abnormal, intervention in automated driving is resumed.

[0084] 2-4-2. Second diagnostic method

[0085] Next, use Figure 7 The second diagnostic method of the automatic driving system 10 will be described. Figure 7 This is a timing chart for explaining the second diagnostic method of the automatic driving system 10 .

[0086] like Figure 7As shown, in the second diagnostic method, the automatic driving system 10 periodically sends a survival confirmation signal to the vehicle control system 20. A dedicated channel for sending and receiving the survival confirmation signal may also be set between the vehicle control system 20 and the automatic driving system 10. The vehicle control system 20 receives the survival confirmation signal periodically sent from the automatic driving system 10, and diagnoses whether the automatic driving system 10 is normal or abnormal based on the survival confirmation signal. Specifically, during the period when the survival confirmation signal is periodically sent from the automatic driving system 10, the automatic driving system 10 can be diagnosed as normal, and when the survival confirmation signal is interrupted, the automatic driving system 10 can be diagnosed as abnormal. Figure 7 In the example shown, the survival confirmation signal is interrupted before the override signal is received. Therefore, in this example, the vehicle control system 20 diagnoses that the automatic driving system 10 is abnormal and performs intervention in the automatic driving.

[0087] It should be noted that in Figure 7 In the illustrated example, the normality / abnormality of the automated driving system 10 is determined based on the interruption of the survival confirmation signal before receiving the override signal. However, the diagnosis can also be performed based on the survival confirmation signal after receiving the override signal. In this case, the vehicle control system 20 begins or prepares to intervene in automated driving upon receiving the override signal. If the survival confirmation signal cannot be confirmed after receiving the override signal, the vehicle control system 20 continues to intervene in automated driving. If the survival confirmation signal is confirmed, the vehicle control system 20 ceases to intervene in automated driving.

[0088] 2-4-3. Third diagnostic method

[0089] Next, use Figure 8 A third diagnostic method of the automatic driving system 10 will be described. Figure 8 This is a timing chart explaining the third diagnostic method of the automatic driving system 10 .

[0090] like Figure 8 As shown, in the third diagnostic method, calls are repeatedly made from the vehicle control system 20 to the automatic driving system 10, and the automatic driving system 10 responds to each call. Calls from the vehicle control system 20 can be either regular or irregular. In addition, a dedicated channel for exchanging call and response signals can also be set between the vehicle control system 20 and the automatic driving system 10. The vehicle control system 20 diagnoses whether the automatic driving system 10 is normal or abnormal based on the response to the call from the automatic driving system 10. Specifically, while the automatic driving system 10 responds to the call from the vehicle control system 20, it can be diagnosed that the automatic driving system 10 is normal, and when it no longer responds to the call, it can be diagnosed that the automatic driving system 10 is abnormal. Figure 8 In the example shown, before receiving the override signal, there is no response to the call from the vehicle control system 20. Therefore, in this example, the vehicle control system 20 diagnoses that the automatic driving system 10 is abnormal and performs intervention in the automatic driving.

[0091] It should be noted that Figure 8 Unlike the example shown, a call may be made to the automated driving system 10 after receiving an override signal, and the normality / abnormality of the automated driving system may be diagnosed based on whether the system responds to the call. In this case, the vehicle control system 20 begins or prepares to intervene in automated driving upon receipt of the override signal. If the automated driving system 10 does not respond to the call after receiving the override signal, the vehicle control system 20 continues to intervene in automated driving. If the automated driving system 10 responds to the call, the vehicle control system 20 ceases intervention in automated driving.

[0092] 2-4-4. Fourth diagnostic method

[0093] Next, use Figure 9 、 Figure 10A as well as Figure 10B A fourth diagnostic method of the automatic driving system 10 will be described. Figure 9 This is a timing chart explaining the fourth diagnostic method of the automatic driving system 10 . Figure 10A and Figure 10B This is a diagram for explaining an evaluation method of the automatic driving related to the fourth diagnostic method of the automatic driving system 10 .

[0094] like Figure 9 As shown, in the fourth diagnostic method, the vehicle control system 20 evaluates the autonomous driving system 10. Based on the results of this evaluation, the vehicle control system 20 diagnoses whether the autonomous driving system 10 is operating normally or abnormally. Whether the autonomous driving system 10 is operating normally or abnormally is reflected in the results of the autonomous driving. Therefore, by evaluating the autonomous driving system, it is possible to diagnose whether the autonomous driving system 10 is operating normally or abnormally.

[0095] For example, Figure 10A and Figure 10B As shown, the evaluation of the autonomous driving can be performed based on the longitudinal control amount and the lateral control amount of the autonomous driving vehicle 2 implemented by the autonomous driving system 10. The longitudinal control amount includes, for example, speed and acceleration, and the lateral control amount includes, for example, steering amount and lateral position. Figure 10A In FIG, the safe driving area and the high-risk area of the longitudinal control amount assumed by the vehicle control system 20 are shown. Figure 10B, the safe driving area and high-risk area of the lateral control amount assumed by the vehicle control system 20 are shown. As shown in these figures, if the behavior of the autonomous driving vehicle 2 implemented by the autonomous driving system 10 exceeds the safe driving area, it can be estimated that the autonomous driving system 10 is in a state where it cannot fully consider the risk of an accident.

[0096] It should be noted that in Figure 9 In the example shown, the evaluation of autonomous driving is performed before receiving the override signal. However, the evaluation of autonomous driving may also be performed after receiving the override signal. In this case, the vehicle control system 20 begins or prepares to intervene in autonomous driving upon receiving the override signal. The evaluation of autonomous driving is then performed. If the evaluation results do not confirm the normal operation of the autonomous driving system 10, the vehicle control system 20 continues to intervene in autonomous driving. If the normal operation of the autonomous driving system 10 is confirmed, the vehicle control system 20 ceases intervention in autonomous driving.

[0097] 3. Other Implementation Methods

[0098] In the above-described embodiment, the autonomous driving system 10 transmits an override signal to the vehicle control system 20 when it estimates intervention in autonomous driving by the vehicle control system 20 and when the estimated intervention in autonomous driving is unnecessary. In this case, it is necessary to presuppose that the vehicle control system 20 will intervene in autonomous driving. Therefore, in the autonomous driving vehicle of the present invention, the vehicle control system 20 may notify the autonomous driving system 10 of the intervention in autonomous driving when the vehicle control system 20 intervenes in autonomous driving. Furthermore, the autonomous driving system 10 may transmit an override signal to the vehicle control system 20 when the predicted intervention in autonomous driving is unnecessary. Thus, when the autonomous driving system 10 is operating normally, the override signal is transmitted to the vehicle control system 20 before the predicted intervention in autonomous driving is performed, thereby stopping the intervention in autonomous driving.

Claims

1. A vehicle control system, mounted on a vehicle performing automated driving, which predicts a risk of collision between the vehicle and an obstacle ahead of the vehicle based on information related to the vehicle's surrounding environment, and, when the risk is predicted, intervenes in the automated driving to cause the vehicle to take evasive action to avoid the predicted risk. The vehicle control system is characterized by comprising: at least one memory containing at least one program; and at least one processor coupled to the at least one memory, The at least one processor executes, through execution of the at least one program: communicating with an autonomous driving system that generates a target trajectory for the vehicle and causes the vehicle to travel in a manner that follows the target trajectory through the autonomous driving; receiving an override signal from the autonomous driving system to refuse intervention in the autonomous driving, the override signal being sent by the autonomous driving system to the vehicle control system when the autonomous driving system determines that a movement of the vehicle achieved through the autonomous driving would cause the vehicle control system to intervene in the autonomous driving; diagnosing whether the autonomous driving system is normal or abnormal; and Intervention of the autonomous driving is stopped only when the override signal is received and the autonomous driving system is normal.

2. The vehicle control system according to claim 1, characterized in that: The at least one processor receives a result of self-diagnosis from the autonomous driving system and performs the diagnosis based on the result of the self-diagnosis.

3. The vehicle control system according to claim 1, characterized in that: The at least one processor receives a survival confirmation signal periodically transmitted from the autonomous driving system and performs the diagnosis based on the survival confirmation signal.

4. The vehicle control system according to claim 1, characterized in that: The at least one processor calls the autonomous driving system irregularly or periodically and performs the diagnosis based on a response to the call.

5. The vehicle control system according to claim 1, characterized in that: The at least one processor evaluates the autonomous driving performed by the autonomous driving system and performs the diagnosis based on a result of the evaluation.

6. An autonomous driving vehicle, characterized in that: have: an autonomous driving system that generates a target trajectory and performs autonomous driving in a manner that follows the target trajectory; and a vehicle control system that predicts a risk of collision between the autonomous vehicle and an obstacle in front of the autonomous vehicle based on information related to the surrounding environment, and, when the risk is predicted, intervenes in the autonomous driving by causing the vehicle to take evasive action to avoid the predicted risk. The autonomous driving system executes: when intervention of the autonomous driving by the vehicle control system is not required, that is, when it is determined that the action of the autonomous driving vehicle achieved by the autonomous driving will cause the vehicle control system to intervene in the autonomous driving, sending an override signal to the vehicle control system to refuse intervention in the autonomous driving, The vehicle control system performs: receiving the override signal from the autopilot system; diagnosing whether the autonomous driving system is normal or abnormal; as well as Intervention of the autonomous driving is stopped only when the override signal is received and the autonomous driving system is normal.

7. The autonomous driving vehicle according to claim 6, wherein: The automatic driving system sends the override signal to the vehicle control system when intervention in the automatic driving by the vehicle control system is estimated and the estimated intervention in the automatic driving is not required.

8. The autonomous driving vehicle according to claim 6, wherein: When the vehicle control system intervenes in the automatic driving, the vehicle control system notifies the automatic driving system of the intervention in the automatic driving. The automated driving system sends the override signal to the vehicle control system when no predicted intervention in the automated driving is required.

9. The autonomous driving vehicle according to any one of claims 6 to 8, characterized in that: The automatic driving system performs self-diagnosis to determine whether it is normal or abnormal, and sends the result of the self-diagnosis to the vehicle control system. The vehicle control system receives a result of the self-diagnosis from the automatic driving system and performs the diagnosis based on the result of the self-diagnosis.

10. The autonomous driving vehicle according to any one of claims 6 to 8, characterized in that: The automatic driving system periodically sends a survival confirmation signal to the vehicle control system, The vehicle control system receives the survival confirmation signal from the automatic driving system and performs the diagnosis based on the survival confirmation signal.

11. The autonomous driving vehicle according to any one of claims 6 to 8, characterized in that: The autonomous driving system responds to occasional or regular calls from the vehicle control system, The vehicle control system performs the diagnosis based on the response from the automated driving system.

12. The autonomous driving vehicle according to any one of claims 6 to 8, characterized in that: The vehicle control system evaluates the autonomous driving performed by the autonomous driving system and performs the diagnosis based on a result of the evaluation.

13. A vehicle control method for controlling a vehicle that is automatically driven by an automatic driving system in a manner that follows a target trajectory, wherein: intervening in the autonomous driving by a preventive safety system that predicts a risk of collision with an obstacle in front of the vehicle that the vehicle should avoid based on information about the vehicle's surrounding environment, When the danger is predicted, the autonomous driving is intervened in such a way that the vehicle takes evasive action to avoid the danger. In the vehicle control method, it is determined whether an override signal for refusing intervention in the autonomous driving is received from the autonomous driving system, the override signal being sent by the autonomous driving system when it is determined that the vehicle's movement achieved through the autonomous driving will cause the preventive safety system to intervene in the autonomous driving. diagnosing whether the autonomous driving system is normal or abnormal, If the automatic driving system is abnormal or the override signal is not received from the automatic driving system, intervening in the automatic driving to avoid the predicted danger, When the override signal is received and the automatic driving system is in a normal state, intervention in the automatic driving is stopped.

14. The vehicle control method according to claim 13, characterized in that: A diagnosis of whether the autonomous driving system is normal or abnormal is performed based on at least one of the results of self-diagnosis performed by the autonomous driving system, a survival confirmation signal periodically sent from the autonomous driving system, a response from the autonomous driving system to a call when the autonomous driving system is called irregularly or periodically, and a result of the evaluation of the autonomous driving performed on the autonomous driving system.

Images