InFeR: Informed Failure Resilience in Learned Visual Navigation Control

TL;DR

InFeR is a framework that enhances learned visual navigation policies by enabling autonomous failure detection and recovery using explainability and information bottleneck techniques, without extra training data.

Contribution

It introduces a novel approach combining Variational Information Bottleneck and Grad-CAM for failure resilience in imitation learning-based navigation.

Findings

InFeR improves failure detection accuracy in out-of-distribution scenarios.

The framework enables autonomous failure recovery in real-world navigation tasks.

InFeR enhances robustness of policies across different architectures.

Abstract

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.