Traffic-Rule-Compliant Trajectory Repair via Satisfiability Modulo Theories and Reachability Analysis

TL;DR

This paper introduces a novel trajectory repair method for automated vehicles that efficiently ensures compliance with traffic rules by combining satisfiability modulo theories with reachability analysis, reducing the need for replanning.

Contribution

It presents a new approach that repairs rule-violating trajectories in real time, avoiding full replanning and improving computational efficiency for automated driving.

Findings

Effective in complex environments with intricate rules

Demonstrates real-time trajectory repair in high-fidelity simulators

Validates approach in real-world scenarios

Abstract

Complying with traffic rules is challenging for automated vehicles, as numerous rules need to be considered simultaneously. If a planned trajectory violates traffic rules, it is common to replan a new trajectory from scratch. We instead propose a trajectory repair technique to save computation time. By coupling satisfiability modulo theories with set-based reachability analysis, we determine if and in what manner the initial trajectory can be repaired. Experiments in high-fidelity simulators and in the real world demonstrate the benefits of our proposed approach in various scenarios. Even in complex environments with intricate rules, we efficiently and reliably repair rule-violating trajectories, enabling automated vehicles to swiftly resume legally safe operation in real time.