Multilayer Graph-Based Trajectory Planning for Race Vehicles in Dynamic Scenarios
This addresses trajectory planning for autonomous race vehicles in dynamic environments, representing an incremental improvement with domain-specific applications.
The paper tackled the problem of high-speed trajectory planning for race vehicles in dynamic scenarios by proposing a multi-layered graph-based planner that operates at speeds up to 212 km/h, enabling actions like overtaking and handling at friction limits, as demonstrated in simulation and on a real vehicle.
Trajectory planning at high velocities and at the handling limits is a challenging task. In order to cope with the requirements of a race scenario, we propose a far-sighted two step, multi-layered graph-based trajectory planner, capable to run with speeds up to 212~km/h. The planner is designed to generate an action set of multiple drivable trajectories, allowing an adjacent behavior planner to pick the most appropriate action for the global state in the scene. This method serves objectives such as race line tracking, following, stopping, overtaking and a velocity profile which enables a handling of the vehicle at the limit of friction. Thereby, it provides a high update rate, a far planning horizon and solutions to non-convex scenarios. The capabilities of the proposed method are demonstrated in simulation and on a real race vehicle.