Robust Tunable Trajectory Repairing for Autonomous Vehicles Using Bernstein Basis Polynomials and Path-Speed Decoupling
Kailin Tong, Selim Solmaz, Martin Horn, Michael C. Stolz, Daniel Watzenig · 2023
Adaptation to changing dynamic situations is yet an open problem for automated driving systems that require robust and efficient solutions. Particularly in the context of motion planning algorithms, this problem is typically addressed by re-planning the whole trajectory or repairing the invalid part. The main drawback of all the current approaches is the increased demand for computational resources, a critical safety issue in automated vehicles. Motivated by this, in this paper we propose a novel and efficient method for trajectory repairing utilizing Bernstein basis polynomials and path-speed decoupling. A robustness metric is introduced to tune the driving behavior. Accurate numerical simulations indicate performance figures typically better than$25ms$for a feasible solution in representative driving scenarios, which was not achievable in other state-of-the-art approaches.