NeFut Logo NeFut
Admin Login

[CS.AI] VTM-Nav: Hierarchical Visual-Topological Memory for Cross-Episode Navigation

Published at: 2026-07-18 22:00 Last updated: 2026-07-22 01:24
#algorithm #AI #Open Source

Abstract

Object-goal navigation requires an embodied agent to locate and reach an instance of a specified object category in an indoor environment. Recent training-free approaches leverage vision-language models (VLMs) for open-vocabulary semantic reasoning, but are typically evaluated under an episodic protocol that resets all scene-specific state after each episode. We introduce Cross-Episode Object-Goal Navigation, in which an agent repeatedly operates in the same scene, retains only self-acquired experience, and keeps its model parameters fixed.

To support experience reuse, we present VTM, a training-free VLM navigation framework with a persistent hierarchical Visual-Topological Memory. The VTM organizes scene knowledge at room and object levels and retrieves relevant experience through coarse-to-fine matching, providing memory as soft guidance only when it agrees with current observations. A conservative execution guard further mitigates oscillations, blocked motions, and premature stopping.

Under a controlled same-scene protocol, we evaluate VTM-Nav on three benchmarks: HM3D v0.1, HM3D v0.2, and MP3D, comparing it with a strengthened WMNav baseline augmented with cross-episode textual memory, while keeping the VLM backbone and action pipeline identical. VTM-Nav achieves the best performance across all three benchmarks, demonstrating the effectiveness and robustness of structured visual-topological experience reuse across datasets.

Blogger's Review: The introduction of VTM-Nav marks a significant advancement in the field of goal navigation. The innovative visual-topological memory mechanism not only enhances the model's adaptability but also significantly improves navigation capabilities in complex environments. This success may drive further research into intelligent agents in dynamic settings.

Original Source: https://arxiv.org/abs/2607.14514

[h] Back to Home