BayesRace: Learning to race autonomously using prior experience
This work addresses the problem of autonomous racing for developers by providing a model-based framework that learns from sensor data, though it appears incremental as it builds on existing methods.
The paper tackles the challenge of accurately predicting a vehicle's future state in autonomous racing by reducing the effort needed for system identification and control design, demonstrating its approach through experiments on scale autonomous racing simulations.
Autonomous race cars require perception, estimation, planning, and control modules which work together asynchronously while driving at the limit of a vehicle's handling capability. A fundamental challenge encountered in designing these software components lies in predicting the vehicle's future state (e.g. position, orientation, and speed) with high accuracy. The root cause is the difficulty in identifying vehicle model parameters that capture the effects of lateral tire slip. We present a model-based planning and control framework for autonomous racing that significantly reduces the effort required in system identification and control design. Our approach alleviates the gap induced by simulation-based controller design by learning from on-board sensor measurements. A major focus of this work is empirical, thus, we demonstrate our contributions by experiments on validated 1:43 and 1:10 scale autonomous racing simulations.