Topological graph links language and navigation for robot movement
A Topological Representation with Object-Path Graphs for Open-Vocabulary Instance Navigation
Robotics
Summary
Getting robots to follow spoken instructions inside buildings can be tricky because they need to understand both language and where they are. This paper presents a new way to help robots navigate by linking objects and paths in a simple graph that combines language understanding with map information. The authors built a system that plans routes and moves the robot using this graph without needing a detailed map. They tested it in virtual environments and real robots to show it works well for finding objects by name and navigating efficiently.
What this means in practice
- •For robotics engineers: Use a combined object-path graph to navigate robots indoors following natural language commands without dense 3D maps.
- •For indoor delivery services: Implement robot navigation systems that find objects or locations by name in complex indoor environments using lightweight topological graphs.$Commercial implications: Enables commercial indoor robots to deliver and locate items efficiently without expensive mapping setups.
Authors
Linwei Zheng, Daojie Peng, Bingtao Wang, Haoang Li, Jun Ma
Abstract
Vision-language navigation requires embodied agents to navigate environments using natural language instructions and visual observations. Existing approaches typically decompose navigation into sequential language-guided decisions or rely on online exploration without prior environmental knowledge. Scene graph representations offer compact semantic memory but remain decoupled from downstream navigation, which still depends on dense metric maps. To close this gap, we propose an object--path graph that unifies open-vocabulary semantic reasoning with topological navigation. The proposed representation jointly supports semantic grounding, graph-based localization, and navigation within a single lightweight topological framework. Building on this graph, we introduce a navigation strategy that combines global path planning with local inter-node execution through lightweight node localization and semantic visual servoing, enabling navigation directly over the graph without dense metric reconstruction. Experiments on HM3D and Replica demonstrate competitive performance in open-vocabulary object grounding through the proposed hierarchical graph structure, while achieving effective navigation performance. Real-world robot experiments further validate the practicality of the proposed framework.