Traffic-Rule-Compliant Trajectory Repair via Satisfiability Modulo Theories and Reachability Analysis
This addresses the challenge of ensuring traffic rule compliance for automated vehicles, offering an incremental improvement over existing replanning methods.
The paper tackles the problem of automated vehicles violating traffic rules by proposing a trajectory repair technique instead of replanning from scratch, which reduces computation time and enables real-time, legally safe operation in complex environments.
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.