Multilayer Graph-Based Trajectory Planning for Race Vehicles in Dynamic Scenarios

TL;DR

This paper introduces a multi-layered graph-based trajectory planning method for race vehicles that can operate at high speeds and handle complex dynamic scenarios, demonstrated in simulation and real-world tests.

Contribution

A novel two-step, multi-layered graph-based trajectory planner capable of high-speed operation and handling non-convex scenarios in racing environments.

Findings

Operates at speeds up to 212 km/h

Generates multiple drivable trajectories for various actions

Validated in simulation and real vehicle tests

Abstract

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.