aiqbench analysis
This research introduces an object-path graph framework that unifies semantic reasoning with topological navigation, allowing embodied agents to move through environments using natural language without relying on dense metric maps. By integrating global path planning with local visual servoing directly over the graph structure, the method achieves competitive performance in open-vocabulary grounding and real-world robot experiments. The approach represents a significant step forward in decoupling semantic understanding from heavy geometric reconstruction for autonomous navigation tasks.
A Topological Representation with Object-Path Graphs for Open-Vocabulary Instance Navigation
arXiv:2609.24189v1 Announce Type: new 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.
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.
Robotics (cs.RO)
arXiv:2609.24189 [cs.RO]
(or arXiv:2609.24189v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.24189 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 250 words
Related coverage
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta Engineering · Jul 15, 2026
Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments
arXiv · Aug 7, 2026
DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding
arXiv · Sep 16, 2026
Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
arXiv · Jun 3, 2026