Explaining Navigation Decisions: Stage-Aware Visual Attribution for Vision-Language Navigation
The paper proposes a stage-aware attribution framework for Vision-Language Navigation to improve explainability.
The paper addresses the issue of instruction-stage insensitivity in existing explainability methods for Vision-Language Navigation.
Before reading this…
Applications
- →robotics
- →natural language processing
To understand this paper, make sure you know these concepts first:
- Vision-Language Modelsfind papers →
- Vision-Language Navigationfind papers →
Abstract
More Like ThisAs Vision-Language Models (VLMs) increasingly enable robots to follow language instructions, understanding their navigation decisions becomes important for reliable deployment. Existing explainability methods overlook a key challenge in Vision-Language Navigation (VLN): evidence for the current action may be distributed across historical and current observations and associated with different instruction stages. We identify instruction-stage insensitivity, where existing methods produce similar explanations despite changes across different navigation stages. To address this issue, we propose a stage-aware attribution framework for VLN. We first construct action-conditioned temporal instruction--visual attributions across observations. These attributions are projected into instruction space to estimate stage associations, which guide the aggregation of relevant historical evidence for refining the current explanation. An instruction-guided spatial filter further suppresses isolated responses while preserving compact, instruction-relevant regions. Experiments across multiple VLN policies and benchmarks show improved attribution quality over existing methods. We further demonstrate that our method acts as a diagnostic tool for analyzing failure cases, and validate its applicability to real-world navigation on a Unitree G1 robot.