A vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario

Abstract

The present invention discloses a vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario. Firstly, an interlocking scenario of autonomous driving vehicles is defined, and the destination planning status of each vehicle is confirmed through vehicle-to-vehicle communication between autonomous driving vehicles. The optimal solution for escape operation is found by traversing different escape driving strategies, and the escape is completed by gradually moving the vehicles to release the interlocking scenario.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario. Background Art

[0002] Nowadays, autonomous driving is developing towards a higher level, and the development of autonomous driving technology is constantly updating and iterating. However, the scenario challenges faced by autonomous driving and how to overcome these challenges are the top priorities for major OEMs and suppliers to develop. With the development and iteration of the industry, they have proposed solutions to various difficult scenarios, such as V2X, etc. This technology can make everything in the entire autonomous driving ecosystem connected, and to a certain extent can solve scenarios that traditional single-vehicle intelligence cannot solve.

[0003] When the traffic lights at the intersection are out of order or there is no traffic signal at the intersection, vehicles are likely to Figure 1 , Figure 2 The vehicle interlocking scenario shown in the figure causes traffic paralysis, greatly affecting travel efficiency. Existing autonomous driving technology makes it difficult for vehicles to escape from this interlocking scenario. Summary of the invention

[0004] The purpose of the present invention is to provide a vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario, so as to achieve rapid escape of the vehicle in an interlocking scenario and avoid traffic congestion.

[0005] In order to solve the above technical problems, the present invention provides a technical solution: a vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario, wherein the interlocking scenario is defined as: multiple vehicles within a certain range, within a number of consecutive interlocking confirmation cycles, the speed of each vehicle is kept at 0 and the trajectory planning control module of each vehicle continuously determines that the vehicle cannot plan and reach the set destination;

[0006] The vehicle escape method is as follows:

[0007] Each vehicle obtains the forward steering movable angle range of its own vehicle, and divides the forward steering movable angle range into several equal parts to obtain a forward steering movable angle sequence;

[0008] Each vehicle obtains the drivable area of ​​its own vehicle under different forward steering movable angles according to the forward steering movable angle sequence of its own vehicle;

[0009] Each vehicle uses the sensor data of the own vehicle to simulate through the calculation unit of the own vehicle, and then simulates the outer edge distance between the own vehicle and the adjacent vehicle in front of the own vehicle in all the drivable areas of the own vehicle; through the vehicle-to-vehicle communication, the simulation results of each vehicle are compared to obtain the maximum outer edge distance corresponding to all the drivable areas of all vehicles, determine the vehicle corresponding to the maximum outer edge distance and the forward steering movable angle of the vehicle, and control the vehicle to perform forward steering at this forward steering movable angle, so that the outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle is the maximum outer edge distance obtained;

[0010] The above operations are repeated in a loop until a vehicle is able to plan a path to its set destination, that is, the interlocking scene is released; then each vehicle plans a path to its own destination and leaves the interlocking scene area in turn.

[0011] According to the above scheme, the interlocking scenario is obtained according to the destination path planning status of other vehicles within a certain range obtained by each vehicle through vehicle-to-vehicle communication.

[0012] According to the above scheme, vehicles communicate with each other through C-V2X.

[0013] According to the above scheme, the outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle is defined as: dividing the outer edge of the adjacent vehicle in front of the vehicle closest to the vehicle into N equal parts, connecting the endpoints of the outer edge and the equal division points with the outer edge corner points closest to the adjacent vehicle in front of the vehicle, summing up the length values ​​of all the connecting lines and dividing them by N+1, and using the quotient obtained as the outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle; wherein N is a constant value.

[0014] According to the above scheme, N=3.

[0015] According to the above scheme, when the vehicle is performing forward turning at a certain forward turning movable angle, obstacle information is monitored in real time. When it is detected that the distance between the obstacle and the vehicle is less than a certain threshold, the forward turning is terminated.

[0016] According to the above scheme, the vehicle monitors obstacle information through cameras and ultrasonic radars.

[0017] According to the above scheme, when a vehicle is turning forward at a certain forward steering angle, the real-time trajectory planning control modules of all vehicles continue to judge the destination path planning status of the vehicle. When there is a vehicle that can plan and reach its set destination, the vehicle leaves the interlocking scene area according to its destination planning path, and stops the vehicle that is turning forward. After the vehicle leaves the interlocking scene area, the remaining vehicles continue to execute the vehicle escape method.

[0018] A computer comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the vehicle escape method based on vehicle-to-vehicle communication in the interlocking scenario described above are implemented.

[0019] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the vehicle escape method based on vehicle-to-vehicle communication in the interlocking scenario described above.

[0020] The beneficial effect of the present invention is that information is shared through vehicle-to-vehicle communication, so that trapped vehicles in an interlocking scenario can be gradually moved within a drivable area, thereby gradually increasing the distance between the trapped vehicles, and ultimately freeing all trapped vehicles in the interlocking scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 (a) and (b) are two interlocking scenarios of the first embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram of calculating the outer edge distance of the first embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of outer edge distance calculation according to the second embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings of the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0025] Embodiment 1:

[0026] For the interlocking scenario in this embodiment, see Figure 1 (a), (b); the vehicles executing the vehicle escape method in the interlocking scenario are vehicle A, vehicle B, vehicle C, and vehicle D shown in the figure. The aforementioned four vehicles are of the same model of autonomous driving models, their respective control logic algorithms are the same, and sensors, controllers and other equipment are in intact / unobstructed / normal working conditions; the four vehicles are connected at the rear to form a "U" shape structure, and the driving directions of the four vehicles are connected in a clockwise or counterclockwise direction. Any vehicle among vehicles A~D is located at a safe distance from another vehicle, and the rear of the four vehicles is followed by other vehicles X.

[0027] Taking vehicle A as an example, when its internal trajectory planning control module determines that the vehicle cannot plan and reach the set destination, it sets the "destination path planning status = invalid bit"; and sends the "vehicle A planning control prediction status = confirming" to the trapped vehicles in the interlocking scenario (i.e., vehicles B, C, and D) through C-V2X; if vehicle A meets:

[0028]

[0029] Then vehicle A meets its interlocking scene confirmation conditions;

[0030] The interlocking scenario confirmation conditions for other vehicles are similar and will not be elaborated here.

[0031] If vehicles A to D meet their respective interlocking scene confirmation conditions within M consecutive interlocking confirmation cycles, it is determined that vehicles A to D are in an interlocking scene; and then the subsequent escape method is executed:

[0032] S1. Each vehicle obtains its own forward steering movable angle range, and divides the forward steering movable angle range into several equal parts to obtain a forward steering movable angle sequence; (taking vehicle A as an example, the forward steering movable angle sequence obtained may be {a 1 ,a 2 ,a 3 ,a 4 ,...,a n}, where a 1 ,a 2 ,a 3 ,a 4 ,...,a n is the current forward steering angle of vehicle A)

[0033] S2. Each vehicle obtains the drivable area of ​​its own vehicle under different forward steering movable angles according to the forward steering movable angle sequence of its own vehicle; (For example: according to {a 1 ,a 2 ,a 3 ,a 4 ,...,a n}Get {A 1 ,A 2 ,A 3 ,A 4 ,...,A n}, where A 1 ,A 2 ,A 3 ,A 4 ,...,A n They are respectively the movable angle a for forward steering 1 ,a 2 ,a 3,a 4 ,...,a n Corresponding drivable area)

[0034] S3, simulate the outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle in all drivable areas of the vehicle; obtain the corresponding maximum outer edge distance in all drivable areas of all vehicles, determine the vehicle corresponding to the maximum outer edge distance and the forward steering movable angle of the vehicle, and control the vehicle to turn forward at this forward steering movable angle, so that the outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle is the obtained maximum outer edge distance; (assuming that the current interlocking scenario is Figure 1 (a) corresponds to, under the premise that vehicles A to D have not moved, first {A 1 ,A 2 ,A 3 ,A 4 ,...,A n}, calculate the outer edge distance between vehicle A and vehicle B at all simulated positions, and obtain the maximum value of the outer edge distance l a_max ; Similarly, obtain the maximum outer edge distance l corresponding to the current vehicles B, C, and D b_max , l c_max , l d_max ; Then select l a_max , l b_max , l c_max , l d_max The maximum value among them is obtained, and the corresponding vehicle is driven forward according to the forward steering movable angle of the maximum outer edge distance; for example, MAX{l a_max , l b_max , l c_max , l d_max}=l a_max , and l a_max The corresponding forward steering angle of vehicle A is a 3 , then control the vehicle to press a 3 The vehicle A and the vehicle B are turned at an angle of l. a_max )

[0035] S4. Repeat all the above operations in a loop until a certain vehicle is able to plan a path to its set destination, that is, the interlocking scene is released; then each vehicle sequentially leaves the interlocking scene area according to its own destination planning path.

[0036] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0037] The acquisition of the above-mentioned forward steering active angle sequence, the acquisition of the drivable area of ​​the vehicle under different forward steering active angles, and the simulated traversal acquisition and comparison of the outer edge distance are all completed by the intelligent driving domain controllers of vehicles A~D.

[0038] Furthermore, the interlocking scenario is obtained according to the destination path planning status of other vehicles within a certain range obtained by each vehicle through vehicle-to-vehicle communication.

[0039] Furthermore, the vehicles communicate with each other through C-V2X. During the vehicle-to-vehicle communication process, each vehicle is both a transmitter and a receiver, and information is broadcast via C-V2X. There is no host or host vehicle in this process. Each vehicle sends its own status and parameters, and at the same time receives the status and parameters of the other three vehicles, and compares them with its own parameters to achieve the optimal solution under the comparison, so as to help the vehicle escape.

[0040] Furthermore, the outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle is defined as: the outer edge of the adjacent vehicle in front of the vehicle closest to the vehicle is divided into three equal parts, the endpoints of the outer edge and the equal division points are respectively connected to the outer edge corner points closest to the adjacent vehicle in front of the vehicle, the length of all the connecting lines is summed up and divided by 4, and the quotient is used as the outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle. Figure 2 The outer edge distance between vehicle A and the vehicle B in front of it is calculated by connecting the outer edge corner point of vehicle A closest to vehicle B with the selected point on the outer edge of vehicle B closest to vehicle A (the selected point includes the endpoint and trisection point of the outer edge of vehicle B), and the lengths of the connecting lines are L and L respectively. 1 , L 2 , L 3 , L 4 , then the outer edge distance between vehicle A and vehicle B is (L 1 +L 2 +L 3 +L 4 ) / 4.

[0041] Furthermore, when the vehicle is turning forward at a certain forward steering angle, obstacle information is monitored in real time through the camera and ultrasonic radar. When it is detected that the distance between the obstacle and the vehicle is less than a certain threshold, the forward steering is terminated.

[0042] Furthermore, when a vehicle is turning forward at a certain forward steering angle, the real-time trajectory planning control modules of all vehicles continue to judge the destination path planning status of the vehicle. When there is a vehicle that can plan and reach its set destination, the vehicle leaves the interlocking scene area according to its destination planning path, and causes the vehicle that is turning forward to stop moving; after the vehicle leaves the interlocking scene area, the remaining vehicles continue to execute the vehicle escape method.

[0043] A computer comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the vehicle escape method based on vehicle-to-vehicle communication in the interlocking scenario described above are implemented.

[0044] A computer-readable storage medium having a computer program stored thereon, characterized in that: when the computer program is executed by a processor, the steps of the vehicle escape method based on vehicle-to-vehicle communication in the interlocking scenario described above are implemented.

[0045] Embodiment 2:

[0046] The difference between this embodiment and the first embodiment is that the outer edge distance is calculated in a different way. The outer edge distance in this embodiment is calculated by a weighted average method. Specifically, the outer edge distance is (d 1 L 1 '+d 2 L 2 '+d 3 L 3 '+d 4 L 4 ') / 4, where d 1 d 2 d 3 d 4 is the weight, L 1 ',L 2 ',L 3 ',L 4 ' is the length of the line between the corner point of vehicle A closest to vehicle B and the endpoint and the three-dividing point of the extended outer edge of vehicle B; the extended outer edge is located between the corner point of vehicle A closest to vehicle B and the outer edge of vehicle B closest to vehicle A, and the extended outer edge and the outer edge of vehicle B closest to vehicle A are equal in length and parallel to each other, and the parallel distance between the two is ΔL (ΔL in this embodiment is 10cm). The setting of the extended outer edge prevents the vehicle from being affected by the smaller weight d 2 d 3 d 4 To improve the escape efficiency of vehicle A, set d 1 =MAX{d 1 ,d 2 ,d3 ,d 4}, the purpose of which is to allow the front of vehicle A to quickly leave the rear of vehicle B.

[0047] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario, characterized in that: The interlocking scenario is defined as: multiple vehicles within a certain range, within a number of consecutive interlocking confirmation cycles, the speed of each vehicle remains at 0 and the trajectory planning control module of each vehicle continues to determine that the vehicle cannot plan and reach the set destination; The vehicle escape method is as follows: Each vehicle obtains the forward steering movable angle range of its own vehicle, and divides the forward steering movable angle range into several equal parts to obtain a forward steering movable angle sequence; Each vehicle obtains the drivable area of ​​its own vehicle under different forward steering movable angles according to the forward steering movable angle sequence of its own vehicle; Each vehicle uses the sensor data of the own vehicle to simulate through the calculation unit of the own vehicle, and then simulates the outer edge distance between the own vehicle and the adjacent vehicle in front of the own vehicle in all the drivable areas of the own vehicle; through the vehicle-to-vehicle communication, the simulation results of each vehicle are compared to obtain the maximum outer edge distance corresponding to all the drivable areas of all vehicles, determine the vehicle corresponding to the maximum outer edge distance and the forward steering movable angle of the vehicle, and control the vehicle to perform forward steering at this forward steering movable angle, so that the outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle is the maximum outer edge distance obtained; The above operations are repeated in a loop until a vehicle is able to plan a path to its set destination, that is, the interlocking scene is released; then each vehicle plans a path to its own destination and leaves the interlocking scene area in turn.

2. The vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario according to claim 1, characterized in that: The interlocking scenario is obtained according to the destination path planning status of other vehicles within a certain range obtained by each vehicle through vehicle-to-vehicle communication.

3. The vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario according to claim 2, characterized in that: Vehicles communicate with each other via C-V2X.

4. The vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario according to claim 1, characterized in that: The outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle is defined as: dividing the outer edge of the adjacent vehicle in front of the vehicle closest to the vehicle into N equal parts, connecting the endpoints of the outer edge and the equal division points with the outer edge corner points closest to the adjacent vehicle in front of the vehicle, summing up the lengths of all the connecting lines and dividing them by N+1, and using the quotient obtained as the outer edge distance between the vehicle and the adjacent vehicle in front of the vehicle; N is a constant value.

5. The vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario according to claim 4, characterized in that: N＝3。 6. The vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario according to claim 1, characterized in that: When the vehicle is turning forward at a certain forward steering angle, obstacle information is monitored in real time. When it is detected that the distance between the obstacle and the vehicle is less than a certain threshold, the forward steering is terminated.

7. The vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario according to claim 6, characterized in that: The vehicle monitors obstacle information through cameras and ultrasonic radar.

8. The vehicle escape method based on vehicle-to-vehicle communication in an interlocking scenario according to claim 1, characterized in that: When a vehicle is turning forward at a certain forward steering angle, the real-time trajectory planning control module of all vehicles continuously determines the destination path planning status of the vehicle. When there is a vehicle that can plan and reach its set destination, the vehicle leaves the interlocking scene area according to its destination planning path and stops the vehicle that is turning forward. After the vehicle leaves the interlocking scene area, the remaining vehicles continue to execute the vehicle escape method.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the vehicle escape method based on vehicle-to-vehicle communication in the interlocking scenario of any one of claims 1-8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle escape method based on vehicle-to-vehicle communication in the interlocking scenario described in any one of claims 1 to 8 are implemented.

Images