MARC: Multipolicy and Risk-Aware Contingency Planning for Autonomous Driving

Generating safe and non-conservative behaviors in dense, dynamic environments remains challenging for automated vehicles due to the stochastic nature of traffic participants’ behav- iors and their implicit interaction with the ego vehicle. This letter presents a novel planning framework, Multipolicy And Risk-aware Contingency (MARC) planning, that systematically addresses these challenges by enhancing the multipolicy-based pipelines from both behavior and motion planning aspects. Specifically, MARC realizes a critical scenario set that reflects multiple possible futures conditioned on each semantic-level ego policy. Then, the gener- ated policy-conditioned scenarios are further formulated into a tree-structured representation with a dynamic branchpoint based on the scene-level divergence. Moreover, to generate diverse driv- ing maneuvers, we introduce risk-aware contingency planning, a bi-level optimization algorithm that simultaneously considers multiple future scenarios and user-defined risk tolerance levels. Owing to the more unified combination of behavior and motion planning layers, our framework achieves efficient decision-making and human-like driving maneuvers. Comprehensive experimental results demonstrate superior performance to other strong baselines in various environments.