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

TL;DR

MARC is a novel planning framework for autonomous driving that generates safe, diverse, and human-like behaviors by considering multiple future scenarios and risk levels, improving decision-making in complex environments.

Contribution

The paper introduces MARC, a new multipolicy and risk-aware contingency planning framework that enhances behavior and motion planning for autonomous vehicles in dynamic settings.

Findings

Outperforms baseline methods in diverse environments

Generates human-like driving maneuvers

Efficient decision-making in complex scenarios

Abstract

Generating safe and non-conservative behaviors in dense, dynamic environments remains challenging for automated vehicles due to the stochastic nature of traffic participants' behaviors and their implicit interaction with the ego vehicle. This paper presents a novel planning framework, Multipolicy And Risk-aware Contingency planning (MARC), 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 generated 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 driving 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.