Salvato in:
Dettagli Bibliografici
Autori principali: Qiu, Le, Ciftci, Yusuf Umut, Bansal, Somil
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.03129
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911092958035968
author Qiu, Le
Ciftci, Yusuf Umut
Bansal, Somil
author_facet Qiu, Le
Ciftci, Yusuf Umut
Bansal, Somil
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2508_03129
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection
Qiu, Le
Ciftci, Yusuf Umut
Bansal, Somil
Robotics
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/
title Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection
topic Robotics
url https://arxiv.org/abs/2508.03129