collaborators

13 papers

cs.RO2026

Ego-Dynamics-Augmented World Model for Autonomous Driving with Zero-Shot Cross-Chassis Adaptation

Zhidong Wang, Jingsong Liang, Zirui Li +3

World model (WM)-based reinforcement learning enables sample-efficient end-to-end autonomous driving learning by imagining long-horizon trajectories in latent space. However, most…

cs.RO2026

Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving

Cheng Gong, Haoyang Wang, Chao Lu +2

Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based…

cs.RO2026

Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout

Haozhuang Chi, Daosheng Qiu, Hao Su +4

Safe L2/L3 driving automation requires anticipating human-in-the-loop reactions during shared-control transitions. While most driving world models forecast the external environment…

cs.RO2026

IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations

Yuxin Cai, Zongtai Li, Maonan Wang +9

Object navigation requires a robot to search for an unobserved target in an unknown environment by deciding where to explore next under partial observability. Effective search rese…

cs.HC2026

Adaptive Bounded-Rationality Modeling of Early-Stage Takeover in Shared-Control Driving

Jian Sun, Xiyan Jiang, Xiaocong Zhao +3

Human drivers' control quality in the first seconds after a handover is critical to shared-driving safety; potentially unsafe steering or pedal inputs therefore require detection a…

cs.CV2026

Single-Eye View: Monocular Real-time Perception Package for Autonomous Driving

Haixi Zhang, Aiyinsi Zuo, Zirui Li +3

Amidst the rapid advancement of camera-based autonomous driving technology, effectiveness is often prioritized with limited attention to computational efficiency. To address this i…