Guaranteeing constraint satisfaction is challenging in imitation learning (IL), particularly in tasks that require operating near a system's handling limits. Traditional IL methods, such as Behavior Cloning (BC), often struggle to enforce constraints, leading to suboptimal performance in high-precision tasks. In this paper, we present a simple approach to incorporating safety into the IL objective. Through simulations, we empirically validate our approach on an autonomous racing task with both full-state and image feedback, demonstrating improved constraint satisfaction and greater consistency in task performance compared to BC.
@article{arxiv.2503.07737,
title = {A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing},
author = {Shengfan Cao and Eunhyek Joa and Francesco Borrelli},
journal= {arXiv preprint arXiv:2503.07737},
year = {2025}
}