Research papers · Posted 2025.03.10 · Preprint
Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception Deficits
Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception Deficits
Overview
LLM-RCO links hazard inference, short-term planning, action verification and safety constraints under partial perception loss. A dedicated deficit dataset and CARLA experiments investigate context-aware responses beyond automatically stopping in every uncertain situation.
Version: v2