Tongji University

Peng Hang

Jian Sun

Shiyu Fang

Aijing Kong

The present invention proposes an autonomous driving testing method based on multi-alliance cluster confrontation, aiming to improve the efficiency and accuracy of autonomous driving simulation test, and comprising S—initialization of testing environment of autonomous driving; S—decision-making for dividing background vehicle clusters; S—decision-making for confrontation behaviors of the background vehicles; S—trajectory planning for the background vehicles; and S—looping through the steps S, S, and Suntil cluster confrontation testing tasks are completed. The method of the present invention uses reinforcement learning and alliance games to dynamically generate testing scenarios that are highly confrontational to vehicles being tested, which can find dangerous boundary scenarios for autonomous driving more quickly and improve the efficiency of simulation testing.

Autonomous driving testing method based on multi-coalition swarm confrontation

The present invention relates to an autonomous driving test method based on multi-agent swarm adversarial, a device and a medium. The method includes: deducing a conflict topological relationship graph between a tested autonomous vehicle and an agent; deducing a feasible planning space of the tested autonomous vehicle according to the conflict topological relationship graph; establishing a multi-agent swarm adversarial model based on a potential game under the feasible planning space according to a correlation between an individual reward of the agent and a swarm adversarial test effect of a multi-agent system, and solving and obtaining an optimal adversarial strategy of the multi-agent system against the tested autonomous vehicle, where in the multi-agent swarm adversarial model, an adversarial intensity is introduced, and the adversarial intensity is adaptively adjusted according to an actual response of the tested autonomous vehicle; and repeatedly executing the S-Suntil an adversarial task is completed.

Growing community of inventors

Shanghai, China

Peng Hang