Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?

arXiv:2404.07569v1 Announce Type: cross
Abstract: Real-world autonomous driving systems must make safe decisions in the face of rare and diverse traffic scenarios. Current state-of-the-art planners are mostly evaluated on real-world datasets like nuScenes (open-loop) or nuPlan (closed-loop). In particular, nuPlan seems to be an expressive evaluation method since it is based on real-world data and closed-loop, yet it mostly covers basic driving scenarios. This makes it difficult to judge a planner's capabilities to generalize to rarely-seen situations. Therefore, we propose …

abstract art arxiv autonomous autonomous driving autonomous driving systems cs.ai cs.lg cs.ro current datasets decisions diverse driving evaluation face loop motion planning planning safe state systems traffic type world