Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection

TL;DR

MPC-SafeGIL enhances imitation learning safety by injecting adversarial disturbances during demonstrations, enabling robust recovery behaviors and improving safety in high-dimensional robotic systems.

Contribution

It introduces a scalable MPC-based disturbance injection method to improve safety in imitation learning without relying on analytical models or interactive experts.

Findings

Improved safety in quadruped locomotion tasks

Enhanced task performance in visuomotor navigation

Successful real-world quadrotor experiments

Abstract

Imitation Learning has provided a promising approach to learning complex robot behaviors from expert demonstrations. However, learned policies can make errors that lead to safety violations, which limits their deployment in safety-critical applications. We propose MPC-SafeGIL, a design-time approach that enhances the safety of imitation learning by injecting adversarial disturbances during expert demonstrations. This exposes the expert to a broader range of safety-critical scenarios and allows the imitation policy to learn robust recovery behaviors. Our method uses sampling-based Model Predictive Control (MPC) to approximate worst-case disturbances, making it scalable to high-dimensional and black-box dynamical systems. In contrast to prior work that relies on analytical models or interactive experts, MPC-SafeGIL integrates safety considerations directly into data collection. We validate our approach through extensive simulations including quadruped locomotion and visuomotor navigation and real-world experiments on a quadrotor, demonstrating improvements in both safety and task performance. See our website here: https://leqiu2003.github.io/MPCSafeGIL/