Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Zishuo, Loo, Joel, Hsu, David
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.24680
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909053306798080
author Wang, Zishuo
Loo, Joel
Hsu, David
author_facet Wang, Zishuo
Loo, Joel
Hsu, David
contents While imitation learning (IL) has enabled successful visual navigation in many common environments, IL policies are prone to unpredictable failures under out-of-distribution (OOD) scenarios. This necessitates failure-resilient policies, which not only detect failures, but also recognise their sources and recover from them autonomously. We propose InFeR, a general framework for building IL policies with informed failure resilience without failure or recovery demonstrations. InFeR retrains an IL policy with a Variational Information Bottleneck (VIB) loss to structure its latent space for OOD failure detection. It applies a visual explainability technique, Grad-CAM, to localise an image region as the source of failure and inform a heuristic policy for recovery. All these are achieved without requiring additional training data. Real-world experiments show that InFeR enables informed failure recovery across two different policy architectures, yielding robust long-range navigation in complex environments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24680
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle InFeR: Informed Failure Resilience in Learned Visual Navigation Control
Wang, Zishuo
Loo, Joel
Hsu, David
Robotics
While imitation learning (IL) has enabled successful visual navigation in many common environments, IL policies are prone to unpredictable failures under out-of-distribution (OOD) scenarios. This necessitates failure-resilient policies, which not only detect failures, but also recognise their sources and recover from them autonomously. We propose InFeR, a general framework for building IL policies with informed failure resilience without failure or recovery demonstrations. InFeR retrains an IL policy with a Variational Information Bottleneck (VIB) loss to structure its latent space for OOD failure detection. It applies a visual explainability technique, Grad-CAM, to localise an image region as the source of failure and inform a heuristic policy for recovery. All these are achieved without requiring additional training data. Real-world experiments show that InFeR enables informed failure recovery across two different policy architectures, yielding robust long-range navigation in complex environments.
title InFeR: Informed Failure Resilience in Learned Visual Navigation Control
topic Robotics
url https://arxiv.org/abs/2510.24680