Reachability-Based Contingency Planning against Multi-Modal Predictions with Branch MPC

TL;DR

This paper introduces a reachability-based contingency planning framework that efficiently integrates multi-modal traffic predictions into Branch MPC, improving safety and computational efficiency in autonomous driving scenarios.

Contribution

It proposes a novel method to organize multi-modal predictions into driving corridors, reducing complexity while preserving safety in Branch MPC.

Findings

Significantly reduces computational complexity.

Enhances safety and comfort in planning.

Effectively manages multi-modal traffic predictions.

Abstract

This paper presents a novel contingency planning framework that integrates learning-based multi-modal predictions of traffic participants into Branch Model Predictive Control (MPC). Leveraging reachability analysis, we address the computational challenges associated with Branch MPC by organizing the multitude of predictions into driving corridors. Analyzing the overlap between these corridors, their number can be reduced through pruning and clustering while ensuring safety since all prediction modes are preserved. These processed corridors directly correspond to the distinct branches of the scenario tree and provide an efficient constraint representation for the Branch MPC. We further utilize the reachability for determining maximum feasible decision postponing times, ensuring that branching decisions remain executable. Qualitative and quantitative evaluations demonstrate significantly reduced computational complexity and enhanced safety and comfort.