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

2026-05-19

AI Summary

This work addresses the challenges of trajectory planning and control for autonomous vehicles under extreme driving conditions, such as high-acceleration cornering. The authors propose a modular benchmark framework implemented on a 1:10-scale RoboRacer platform, integrating time-optimal racing line generation, online velocity replanning, a geometric path-tracking controller, and an interpretable Model-Structured Neural Network (MS-NN) designed to learn inverse steering dynamics. By embedding physical priors into its architecture, the MS-NN significantly enhances model interpretability and generalization capability. Experimental results demonstrate that the proposed approach improves trajectory tracking accuracy, suppresses steering oscillations, reduces lap times, and enables safe and stable vehicle operation at higher speeds and lateral accelerations. The associated code, datasets, and demonstration videos are publicly released.

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/.

Problem

• trajectory planning
• control
• autonomous driving
• high-acceleration maneuvers
• limits of handling

Innovation

• model-structured neural network
• online velocity replanning
• trajectory planning
• inverse dynamics learning
• autonomous racing