2 papers
cs.RO2026
Generating Realistic Safety-Critical Scenarios for Vehicle-Pedestrian Interactions
Qingwen Pu, Kun Xie, Yuan Zhu +1
Automated driving system deployment requires rigorous validation across safety-critical vehicle-pedestrian interactions, yet real-world datasets rarely capture high-risk scenarios…
cs.AI2026
A Vision-and-Knowledge Enhanced Large Language Model for Generalizable Pedestrian Crossing Behavior Inference
Qingwen Pu, Kun Xie, Hong Yang +1
Existing paradigms for inferring pedestrian crossing behavior, ranging from statistical models to supervised learning methods, demonstrate limited generalizability and perform inad…