Track-centric Iterative Learning for Global Trajectory Optimization in Autonomous Racing

TL;DR

This paper introduces a track-centric iterative learning framework that optimizes full-horizon trajectories for autonomous racing, incorporating learned dynamics to improve lap times through simulation and real-world data updates.

Contribution

It proposes a novel track-centric approach combining wavelet-based trajectory representation with Bayesian optimization and iterative learning for dynamic updates.

Findings

Achieved up to 20.7% lap time reduction in simulations.

Outperformed existing state-of-the-art methods.

Validated effectiveness through real-world experiments.

Abstract

This paper presents a global trajectory optimization framework for minimizing lap time in autonomous racing under uncertain vehicle dynamics. Optimizing the trajectory over the full racing horizon is computationally expensive, and tracking such a trajectory in the real world hardly assures global optimality due to uncertain dynamics. Yet, existing work mostly focuses on dynamics learning at the tracking level, without updating the trajectory itself to account for the learned dynamics. To address these challenges, we propose a track-centric approach that directly learns and optimizes the full-horizon trajectory. We first represent trajectories through a track-agnostic parametric space in light of the wavelet transform. This space is then efficiently explored using Bayesian optimization, where the lap time of each candidate is evaluated by running simulations with the learned dynamics. This optimization is embedded in an iterative learning framework, where the optimized trajectory is deployed to collect real-world data for updating the dynamics, progressively refining the trajectory over the iterations. The effectiveness of the proposed framework is validated through simulations and real-world experiments, demonstrating lap time improvement of up to 20.7% over a nominal baseline and consistently outperforming state-of-the-art methods.