Trajectory Planning and Control near the Limits: an Open Experimental Benchmark on the RoboRacer Platform

TL;DR

This paper introduces a comprehensive benchmark framework for trajectory planning and control in high-acceleration autonomous driving maneuvers, implemented on a RoboRacer platform, with open-source code and datasets.

Contribution

It presents a modular benchmarking framework, including a novel neural network for inverse dynamics, and demonstrates its effectiveness through extensive experiments.

Findings

MS-NN improves tracking accuracy and reduces oscillations

Online velocity replanning enhances lap times and safety

Framework is validated on a 1:10-scale RoboRacer platform

Abstract

We present a modular framework to benchmark new and existing methods for trajectory planning and control in high-acceleration maneuvers that push autonomous driving to the limits. Our framework includes time-optimal raceline generation, online time-optimal velocity replanning, geometric path tracking controllers, and a new model-structured neural network (MS-NN) to learn the inverse dynamics for steering control. We deploy our framework on a 1:10-scale RoboRacer platform, using two circuits. Through several ablations with cautious and aggressive racelines, we study the performance of single modules and their combinations. We show that our MS-NN significantly improves tracking accuracy, decreases steering oscillations, and is physically interpretable. Moreover, online velocity replanning improves lap times by compensating for execution errors, and enables the vehicle to safely reach higher speeds and accelerations. To support future research, our code, datasets, videos and results are publicly available at https://roboracer-benchmark.github.io/planning_control_benchmark/.