RAGNav: A Retrieval-Augmented Topological Reasoning Framework for Multi-Goal Visual-Language Navigation

TL;DR

RAGNav is a novel framework that combines topological and semantic reasoning with retrieval mechanisms to improve multi-goal vision-language navigation, addressing spatial hallucinations and planning drift.

Contribution

It introduces a Dual-Basis Memory system with topological and semantic structures, enabling better spatial reasoning and target screening in multi-goal VLN tasks.

Findings

Achieves state-of-the-art performance on complex multi-goal navigation tasks.

Enhances inter-target reachability reasoning and sequential planning efficiency.

Reduces semantic noise and spatial hallucinations in navigation.

Abstract

Vision-Language Navigation (VLN) is evolving from single-point pathfinding toward the more challenging Multi-Goal VLN. This task requires agents to accurately identify multiple entities while collaboratively reasoning over their spatial-physical constraints and sequential execution order. However, generic Retrieval-Augmented Generation (RAG) paradigms often suffer from spatial hallucinations and planning drift when handling multi-object associations due to the lack of explicit spatial modeling.To address these challenges, we propose RAGNav, a framework that bridges the gap between semantic reasoning and physical structure. The core of RAGNav is a Dual-Basis Memory system, which integrates a low-level topological map for maintaining physical connectivity with a high-level semantic forest for hierarchical environment abstraction. Building on this representation, the framework introduces an anchor-guided conditional retrieval and a topological neighbor score propagation mechanism. This approach facilitates the rapid screening of candidate targets and the elimination of semantic noise, while performing semantic calibration by leveraging the physical associations inherent in the topological neighborhood.This mechanism significantly enhances the capability of inter-target reachability reasoning and the efficiency of sequential planning. Experimental results demonstrate that RAGNav achieves state-of-the-art (SOTA) performance in complex multi-goal navigation tasks.