SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ciftci, Yusuf Umut, Chiu, Darren, Feng, Zeyuan, Sukhatme, Gaurav S., Bansal, Somil
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917840690348032
author Ciftci, Yusuf Umut
Chiu, Darren
Feng, Zeyuan
Sukhatme, Gaurav S.
Bansal, Somil
author_facet Ciftci, Yusuf Umut
Chiu, Darren
Feng, Zeyuan
Sukhatme, Gaurav S.
Bansal, Somil
contents Behavior cloning (BC) is a widely-used approach in imitation learning, where a robot learns a control policy by observing an expert supervisor. However, the learned policy can make errors and might lead to safety violations, which limits their utility in safety-critical robotics applications. While prior works have tried improving a BC policy via additional real or synthetic action labels, adversarial training, or runtime filtering, none of them explicitly focus on reducing the BC policy's safety violations during training time. We propose SAFE-GIL, a design-time method to learn safety-aware behavior cloning policies. SAFE-GIL deliberately injects adversarial disturbance in the system during data collection to guide the expert towards safety-critical states. This disturbance injection simulates potential policy errors that the system might encounter during the test time. By ensuring that training more closely replicates expert behavior in safety-critical states, our approach results in safer policies despite policy errors during the test time. We further develop a reachability-based method to compute this adversarial disturbance. We compare SAFE-GIL with various behavior cloning techniques and online safety-filtering methods in three domains: autonomous ground navigation, aircraft taxiing, and aerial navigation on a quadrotor testbed. Our method demonstrates a significant reduction in safety failures, particularly in low data regimes where the likelihood of learning errors, and therefore safety violations, is higher. See our website here: https://y-u-c.github.io/safegil/
format Preprint
id arxiv_https___arxiv_org_abs_2404_05249
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems
Ciftci, Yusuf Umut
Chiu, Darren
Feng, Zeyuan
Sukhatme, Gaurav S.
Bansal, Somil
Robotics
Machine Learning
Systems and Control
Behavior cloning (BC) is a widely-used approach in imitation learning, where a robot learns a control policy by observing an expert supervisor. However, the learned policy can make errors and might lead to safety violations, which limits their utility in safety-critical robotics applications. While prior works have tried improving a BC policy via additional real or synthetic action labels, adversarial training, or runtime filtering, none of them explicitly focus on reducing the BC policy's safety violations during training time. We propose SAFE-GIL, a design-time method to learn safety-aware behavior cloning policies. SAFE-GIL deliberately injects adversarial disturbance in the system during data collection to guide the expert towards safety-critical states. This disturbance injection simulates potential policy errors that the system might encounter during the test time. By ensuring that training more closely replicates expert behavior in safety-critical states, our approach results in safer policies despite policy errors during the test time. We further develop a reachability-based method to compute this adversarial disturbance. We compare SAFE-GIL with various behavior cloning techniques and online safety-filtering methods in three domains: autonomous ground navigation, aircraft taxiing, and aerial navigation on a quadrotor testbed. Our method demonstrates a significant reduction in safety failures, particularly in low data regimes where the likelihood of learning errors, and therefore safety violations, is higher. See our website here: https://y-u-c.github.io/safegil/
title SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems
topic Robotics
Machine Learning
Systems and Control
url https://arxiv.org/abs/2404.05249