MP-RBFN: Learning-based Vehicle Motion Primitives using Radial Basis Function Networks

TL;DR

This paper presents MP-RBFN, a Radial Basis Function Network-based method that efficiently learns vehicle motion primitives, combining the accuracy of optimal control with the speed of sampling-based planning, suitable for autonomous driving.

Contribution

Introduces MP-RBFN, a novel learning-based approach that integrates RBFNs with motion primitive generation, improving accuracy and inference speed for autonomous vehicle planning.

Findings

Seven times higher accuracy than semi-analytic methods

Low inference times enable real-time planning

Effective integration into sampling-based trajectory planners

Abstract

This research introduces MP-RBFN, a novel formulation leveraging Radial Basis Function Networks for efficiently learning Motion Primitives derived from optimal control problems for autonomous driving. While traditional motion planning approaches based on optimization are highly accurate, they are often computationally prohibitive. In contrast, sampling-based methods demonstrate high performance but impose constraints on the geometric shape of trajectories. MP-RBFN combines the strengths of both by coupling the high-fidelity trajectory generation of sampling-based methods with an accurate description of vehicle dynamics. Empirical results show compelling performance compared to previous methods, achieving a precise description of motion primitives at low inference times. MP-RBFN yields a seven times higher accuracy in generating optimized motion primitives compared to existing semi-analytic approaches. We demonstrate the practical applicability of MP-RBFN for motion planning by integrating the method into a sampling-based trajectory planner. MP-RBFN is available as open-source software at https://github.com/TUM-AVS/RBFN-Motion-Primitives.