3 papers
eess.SY2026
DRIFT: Driving Risk Inference via Field Transmission for Human-like Autonomous Driving
Zian Wang, Yiming Shu, Zejian Deng +1
Risk fields offer spatially structured alternatives to scalar safety metrics. However, hand-crafted static risk field models struggle with occlusion and topology-driven propagation…
cs.RO2026
Map-Agnostic And Interactive Safety-Critical Scenario Generation via Multi-Objective Tree Search
Wenyun Li, Zejian Deng, Chen Sun
Generating safety-critical scenarios is essential for validating the robustness of autonomous driving systems, yet existing methods often struggle to produce collisions that are bo…
cs.LG2026
Generalizable Trajectory Prediction via Inverse Reinforcement Learning with Mamba-Graph Architecture
Wenyun Li, Wenjie Huang, Zejian Deng +1
Accurate driving behavior modeling is fundamental to safe and efficient trajectory prediction, yet remains challenging in complex traffic scenarios. This paper presents a novel Inv…