We use the urban downtown environment with CARLA map ID Town 03 and configure the traffic manager in autopilot mode to simulate realistic urban traffic scenarios.
Traffic rule compliance for automated vehicles is challenging, 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.
Safe Distance Rule: The ego vehicle must maintain a safe distance from vehicles in the same lane, ensuring collision avoidance even in cases of sudden stops by one or more vehicles.
Speed Limit Rule: The ego vehicle must not exceed:
Stop Line Rule: The ego vehicle has to stop with respect to a stop sign
(sign 206) before it enters the intersection at least for a
duration in front of the associated stop line.
|
|
Priority Rule: The ego vehicle is not allowed to enter an intersection if there is
another vehicle with the right of way that will be endangered by the
ego vehicle.
|
|
We use the urban downtown environment with CARLA map ID Town 03 and configure the traffic manager in autopilot mode to simulate realistic urban traffic scenarios.
We integrate our approach into the EDGAR research vehicle, a Volkswagen T7 Multivan equipped with the necessary sensors and hardware for fully autonomous test runs.
