Showing 2026 · cs.ROShow all
2 papers · 2 filters
cs.RO2026
Cartender: Verifiable Language-Conditioned Driving by Learning the Drives Not Taken
Zhiwen Chen, Benjin Zhu, Yan Xie +1
Every driving scene is logged once, but driving is one-to-many: the scene determines which behaviors are feasible, while an instruction selects among them. A log records only the a…
cs.RO2026
Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations
Zewei Yang, Zengqi Peng, Jun Ma
Parking is a routine yet safety-critical task for autonomous vehicles operating in urban environments. However, cluttered and weakly structured parking spaces, compounded by the in…