Spatially-Aware Adaptive Trajectory Optimization with Controller-Guided Feedback for Autonomous Racing

TL;DR

This paper introduces a novel adaptive trajectory optimization framework for autonomous racing that leverages spatial feedback and controller guidance to improve lap times and robustness to varying track conditions.

Contribution

It combines NURBS-based trajectories, CMA-ES optimization, and a Kalman-inspired spatial feedback to adaptively refine trajectories in real-time for autonomous racing.

Findings

Achieves 17.38% lap time reduction in simulation.

Attains 7.60% lap time improvement on real hardware.

Demonstrates robustness to different tire friction conditions.

Abstract

We present a closed-loop framework for autonomous raceline optimization that combines NURBS-based trajectory representation, CMA-ES global trajectory optimization, and controller-guided spatial feedback. Instead of treating tracking errors as transient disturbances, our method exploits them as informative signals of local track characteristics via a Kalman-inspired spatial update. This enables the construction of an adaptive, acceleration-based constraint map that iteratively refines trajectories toward near-optimal performance under spatially varying track and vehicle behavior. In simulation, our approach achieves a 17.38% lap time reduction compared to a controller parametrized with maximum static acceleration. On real hardware, tested with different tire compounds ranging from high to low friction, we obtain a 7.60% lap time improvement without explicitly parametrizing friction. This demonstrates robustness to changing grip conditions in real-world scenarios.