T2Nav Algebraic Topology Aware Temporal Graph Memory and Loop Detection for ZeroShot Visual Navigation

TL;DR

T2Nav is a zero-shot visual navigation system that uses graph-based reasoning with integrated visual data, enabling flexible, efficient, and robust navigation in unknown environments without additional training.

Contribution

It introduces T2Nav, a novel graph-based zero-shot navigation approach that incorporates visual information directly into the environment graph for improved reasoning.

Findings

Effective obstacle avoidance and loop detection.

Handles goal specification via reference images.

Adapts efficiently to unseen environments.

Abstract

Deploying autonomous agents in real world environments is challenging, particularly for navigation, where systems must adapt to situations they have not encountered before. Traditional learning approaches require substantial amounts of data, constant tuning, and, sometimes, starting over for each new task. That makes them hard to scale and not very flexible. Recent breakthroughs in foundation models, such as large language models and vision language models, enable systems to attempt new navigation tasks without requiring additional training. However, many of these methods only work with specific input types, employ relatively basic reasoning, and fail to fully exploit the details they observe or the structure of the spaces. Here, we introduce T2Nav, a zeroshot navigation system that integrates heterogeneous data and employs graph-based reasoning. By directly incorporating visual information into the graph and matching it to the environment, our approach enables the system to strike a good balance between exploration and goal attainment. This strategy allows robust obstacle avoidance, reliable loop closure detection, and efficient path planning while eliminating redundant exploration patterns. The system demonstrates flexibility by handling goals specified using reference images of target object instances, making it particularly suitable for scenarios in which agents must navigate to visually similar yet spatially distinct instances. Experiments demonstrate that our approach is efficient and adapts well to unknown environments, moving toward practical zero-shot instance-image navigation capabilities.