Search

EP-4075097-B1 - MULTI-VEHICLE COLLABORATIVE TRAJECTORY PLANNING METHOD, APPARATUS AND SYSTEM, AND DEVICE, STORAGE MEDIUM, AND COMPUTER PROGRAM PRODUCT

EP4075097B1EP 4075097 B1EP4075097 B1EP 4075097B1EP-4075097-B1

Inventors

  • LI, Bai

Dates

Publication Date
20260513
Application Date
20201230

Claims (8)

  1. A method for multi-vehicle collaborative trajectory planning, comprising: determining (S101) a specific number of different multi-vehicle priority schemes for multiple vehicles; determining (S102), by using a sequential planning policy, a respective collaborative planning scheme for each of the multi-vehicle priority schemes, to obtain a specific number of collaborative planning schemes; performing (S103) quality evaluation on each of the specific number of collaborative planning schemes to obtain a respective quality evaluation result, to obtain a specific number of quality evaluation results; and determining (S104) a target collaborative planning scheme from the specific number of collaborative planning schemes according to the specific number of quality evaluation results, characterized in that determining, by using the sequential planning policy, the respective collaborative planning scheme for each of the multi-vehicle priority schemes comprises: for each of the multi-vehicle priority schemes, performing (S402) trajectory planning on each of the multiple vehicles one by one according to a give-way priority sequence of the vehicle in the multi-vehicle priority scheme, to obtain a collaborative planning scheme corresponding to the multi-vehicle priority scheme; determining (S411) a to-be-planned vehicle from the multiple vehicles according to the multi-vehicle priority scheme; determining (S412) a traveling trajectory for the to-be-planned vehicle according to a position of an obstacle in a present environment; adding (S413) the traveling trajectory into a planned trajectory set; and responsive to the to-be-planned vehicle being a last vehicle, determining (S414) all trajectories in the planned trajectory set as the collaborative planning scheme corresponding to the multi-vehicle priority scheme, wherein the traveling trajectory comprises a traveling path and a matching speed during traveling along the traveling path; the obstacle in the present environment comprises a static obstacle and a dynamic obstacle, and wherein determining the traveling trajectory for the to-be-planned vehicle according to the position of the obstacle in the present environment comprises: performing (S421) path planning by using a hybrid A* algorithm according to a position of the static obstacle, to obtain a traveling path of the to-be-planned vehicle; determining (S422) a Space-Time, S-T, scatter diagram corresponding to the dynamic obstacle based on the traveling path and a movement trajectory of the dynamic obstacle; and determining (S423), based on the S-T scatter diagram and by using the A* algorithm, the matching speed when the to-be-planned vehicle travels along the traveling path.
  2. The method of claim 1, further comprising: receiving (S201) a respective present position information and environment perception information that are transmitted by each of the multiple vehicles; determining (S206) a respective target trajectory for each of the multiple vehicles according to the target collaborative planning scheme, to obtain multiple target trajectories; and transmitting (S207) each of the multiple target trajectories to a respective one of the multiple vehicles.
  3. The method of claim 1, wherein determining the specific number of different multi-vehicle priority schemes for the multiple vehicles comprises: starting (S301) a specific number of threads in parallel; randomly determining (S302), through each of the specific number of threads, a respective multi-vehicle priority scheme for the multiple vehicles.
  4. The method of claim 1, wherein performing the trajectory planning on each of the multiple vehicles one by one according to a give-way priority sequence of the vehicle in the multi-vehicle priority scheme, to obtain the collaborative planning scheme corresponding to the multi-vehicle priority scheme further comprises: responsive to the to-be-planned vehicle being not the last vehicle, updating (S415) a vehicle traveling according to the traveling trajectory into the present environment as an obstacle; determining (S416) a vehicle following the to-be-planned vehicle as a new to-be-planned vehicle according to the multi-vehicle priority scheme; determining a traveling trajectory for the new to-be-planned vehicle iteratively according to a position of an obstacle in an updated present environment; and adding the traveling trajectory into the planned trajectory set.
  5. The method of any of claims 1 to 4, wherein the quality evaluation result comprises a respective total mileage of each of the collaborative planning schemes; and wherein performing the quality evaluation on each of the specific number of collaborative planning schemes to obtain the respective quality evaluation result comprises: determining path lengths of vehicles in each of the collaborative planning schemes; and for each of the collaborative planning schemes, accumulating the path lengths of the vehicles in the collaborative planning scheme, to obtain the total mileage of the collaborative planning scheme; and correspondingly, determining the target collaborative planning scheme from the specific number of collaborative planning schemes according to the specific number of quality evaluation results comprises: determining, according to the respective total mileage of each collaborative planning scheme, a collaborative planning scheme of which total mileage satisfies a condition among the specific number of collaborative planning schemes as the target collaborative planning scheme.
  6. A computer device, comprising: a processor; and a memory storing a computer program executable by the processor, wherein the processor, when executing the program, performs the method according to any of claims 1 to 5.
  7. A computer-readable storage medium having stored therein a computer program that, when executed by a processor, causes the processor to perform the method of any of claims 1 to 5.
  8. A computer program product comprising a non-transitory computer-readable storage medium storing a computer program that, when read and executed by a computer, causes the computer to perform the method of any of claims 1 to 5.

Description

CROSS-REFERENCE TO RELATED APPLICATION This application is based upon and claims priority to Chinese Patent Application No. 202010001027.8 filed on January 2, 2020. TECHNICAL FIELD The present disclosure relates to, but is not limited to, the field of automatic driving, and in particular, to a method, apparatus and system for multi-vehicle collaborative trajectory planning, a device, a storage medium, and a computer program product. BACKGROUND With the development of an automatic driving technology, multi-vehicle collaborative trajectory planning plays a very important role in the future. In a main landing scenario of an autonomous vehicle, for example, in scenarios such as multi-vehicle coordinated lane change and formation reconfiguration, collaborative trajectory planning based on multiple vehicles can save space and time, thereby enhancing practical application efficiency. In related art, a multi-vehicle collaborative trajectory planning method has a poor solution quality and a slow solution speed, which is not completely in conformity with actual requirements in the field of automatic driving. Therefore, how to improve the solution quality and solution speed of collaborative trajectory planning is an urgent problem for those skilled in the art. JING SHOUCAI ET AL: "Cooperative Game Approach to Optimal Merging Sequence and on-Ramp Merging Control of Connected and Automated Vehicles", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, IEEE, PISCATAWAY, NJ, USA, discusses a global and optimal coordination of the CAVs in a merging zone. A cooperative multi-player game-based optimization framework and an algorithm are presented to coordinate vehicles and achieve minimum values for the global pay-off conditions. The control scheme derives an optimal merging sequence and an optimal trajectory for each vehicle. WO 2019/186801 A1 discloses a path determination device with a price calculation means that calculates a cost that is incurred when a plurality of mobile bodies move, on the basis of a time loss indicating a temporal loss that occurs when at least some of the plurality of mobile bodies detour around the other mobile bodies. DURING MICHAEL ET AL: "Cooperative decentralized decision making for conflict resolution among autonomous agents", 2014 IEEE INTERNATIONAL SYMPOSIUM ON INNOVATIONS IN INTELLIGENT SYSTEMS AND APPLICATIONS (INISTA) PROCEEDINGS, IEEE, discusses a decentralized decision making algorithm to solve conflicts among autonomous agents. The decentralized decision making algorithm is based on communication among the autonomous agents to find an optimal maneuver combination. SUMMARY In view of this, embodiments of the present disclosure provide a method, apparatus and system for multi-vehicle collaborative trajectory planning, a device, a storage medium, and a computer program product. The technical solutions of the embodiments of the present disclosure are implemented as follows. An embodiment of the present disclosure provides a multi-vehicle collaborative trajectory planning method as defined in claim 1. In some embodiments, the method further includes: receiving a respective present position information and environment perception information that are transmitted by each of the multiple vehicles; determining a respective target trajectory for each vehicle according to the target collaborative planning scheme; and transmitting each of target trajectories to a respective one of the multiple vehicles. In some embodiments, the determining the specific number of different multi-vehicle priority schemes for the multiple vehicles includes: starting a specific number of threads in parallel; and randomly determining, through each of the specific number of threads, a respective vehicle priority scheme for the multiple vehicles. According to the invention, the determining, by using the sequential planning policy, the respective collaborative planning scheme for each multi-vehicle priority scheme includes: for each of the multi-vehicle priority schemes, performing trajectory planning on each of the multiple vehicles one by one according to a give-way priority sequence of the vehicle in the multi-vehicle priority scheme, to obtain a collaborative planning scheme corresponding to the multi-vehicle priority scheme. The performing trajectory planning on each of the multiple vehicles one by one according to the give-way priority sequence of the vehicle in the multi-vehicle priority scheme, to obtain the collaborative planning scheme corresponding to the multi-vehicle priority scheme includes: determining a to-be-planned vehicle from the multiple vehicles according to the multi-vehicle priority scheme; determining a traveling trajectory for the to-be-planned vehicle according to a position of an obstacle in a current environment; adding the traveling trajectory into a planned trajectory set; and responsive to the to-be-planned vehicle being a last vehicle, determining all of trajectories in the planned tr