Occlusion-Aware Contingency Safety-Critical Planning for Autonomous Driving

TL;DR

This paper introduces an occlusion-aware planning method for autonomous vehicles that uses reachability analysis and convex optimization to ensure safety and efficiency in dynamic, occluded environments, validated through simulations and real-world tests.

Contribution

It presents a novel real-time planning framework combining reachability, nonlinear programming, and ADMM for safety-critical autonomous driving in occluded scenarios.

Findings

Enhanced safety in occluded intersections

Improved travel efficiency in dynamic environments

Real-time trajectory generation validated in experiments

Abstract

Ensuring safe driving while maintaining travel efficiency for autonomous vehicles in dynamic and occluded environments is a critical challenge. This paper proposes an occlusion-aware contingency safety-critical planning approach for real-time autonomous driving. Leveraging reachability analysis for risk assessment, forward reachable sets of phantom vehicles are used to derive risk-aware dynamic velocity boundaries. These velocity boundaries are incorporated into a biconvex nonlinear programming (NLP) formulation that formally enforces safety using spatiotemporal barrier constraints, while simultaneously optimizing exploration and fallback trajectories within a receding horizon planning framework. To enable real-time computation and coordination between trajectories, we employ the consensus alternating direction method of multipliers (ADMM) to decompose the biconvex NLP problem into low-dimensional convex subproblems. The effectiveness of the proposed approach is validated through simulations and real-world experiments in occluded intersections. Experimental results demonstrate enhanced safety and improved travel efficiency, enabling real-time safe trajectory generation in dynamic occluded intersections under varying obstacle conditions. The project page is available at https://zack4417.github.io/oacp-website/.