让视觉导航模型自动识别并修复异常，无需额外训练数据。
InFeR: Informed Failure Resilience in Learned Visual Navigation Control
- 用变分信息瓶颈重构隐空间，实现对异常的精准检测。
- 通过梯度图定位失败源，指导模型自主恢复行动。
- 无需失败或恢复样本，适用于多种导航架构。
虽然模仿学习（IL）在常见环境中实现了成功的视觉导航，但在分布外（OOD）场景下，其策略容易出现不可预测的失败。这需要具备故障自愈能力的策略，不仅能检测失败，还需识别原因并自主恢复。我们提出InFeR，一种无需失败或恢复演示即可构建具备知情故障容错能力的IL策略的通用框架。InFeR通过引入变分信息瓶颈（VIB）损失对IL策略进行再训练，以结构化其隐空间，实现对分布外失败的检测；同时采用可视化解释技术Grad-CAM定位图像中导致失败的区域，并据此指导启发式策略完成恢复。所有过程均不依赖额外训练数据。真实世界实验表明，InFeR可在两种不同策略架构上实现知情故障恢复，在复杂环境中支持鲁棒的长距离导航。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。