Decision Robustness
[arXiv'22] Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward
We apply MARL to guide traffic participants to construct valuable hazardous scenarios for under-test policies. We run the proposed VDARS method on Baidu Apollo and other types of driving policies (including learning-based and rule-based ones) and discover diverse AV-responsible hazardous scenarios valuable for further improvements of autonomous driving policies.
![[arXiv'22] Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward](/publication.bak/vdars/featured_hu75a404baea997b73e2fba1067a13d170_62183_150x0_resize_q75_h2_lanczos.webp)