A Risk-Sensitive and Uncertainty-Aware Decision-Making and Control Framework for Safe and Robust Autonomous Driving

2026-09-08

AI Summary

为解决复杂交通情况下自动驾驶的安全与鲁棒决策问题，提出了一种基于风险敏感和不确定性感知的决策控制框架RUDC，通过结合分布强化学习与策略不确定性量化来实现。

Abstract

Reinforcement learning (RL) has demonstrated considerable potential for autonomous driving decision-making. However, its deployment in urban autonomous driving, particularly at highly interactive unsignalized intersections, remains challenging, as learned policies may struggle to maintain both safety and robust decision-making in complex traffic situations. Conventional safety-filtering approaches typically employ fixed conservative constraints, which may improve safety at the cost of excessive intervention and degraded traffic efficiency. To address these limitations, we propose a Risk-sensitive and Uncertainty-aware Decision-making and Control (RUDC) framework for safe and robust autonomous driving. RUDC couples risk-sensitive distributional RL with ensemble-based policy uncertainty quantification, jointly accounting for tail risks in return distributions and uncertainty in learned policies. An uncertainty-aware high-order control barrier function (HOCBF)-based safety correction mechanism adaptively adjusts constraint strictness according to policy uncertainty, while a learnable residual predictor compensates for CBF model mismatches and discretization errors. Extensive simulations at unsignalized intersections demonstrate that RUDC achieves a favorable balance among safety, efficiency, and robustness, outperforming representative safe RL baselines under both nominal and challenging OOD and long-tail scenarios while satisfying real-time requirements.

Problem

• Reinforcement Learning
• Autonomous Driving
• Safety
• Robustness
• Unsignalized Intersections

Innovation

• Risk-sensitive distributional RL
• Uncertainty-aware decision-making
• High-order control barrier function (HOCBF)
• Policy uncertainty quantification
• Residual predictor