SSTG-Nav: Metric-Grounded Spatial-Semantic Topological Graphs for Reusable Object Navigation
Not on the map. Why?
Abstract (arXiv)
Service robots operating for months in the same homes, offices, and facilities should become more reliable with experience instead of searching familiar space from scratch for every request. Yet ObjectNav is predominantly formulated as one-shot exploration, leaving a central deployment challenge unresolved: recognizing an object does not identify a reachable place to stop, and one confident map error can terminate the task. We introduce SSTG-Nav, a reusable metric-semantic memory that turns a one-time survey into actionable object goals, consolidates evidence across viewpoints, and retains spatially distinct recovery standoffs. On 1,000 HM3D-v2 episodes across 36 scenes, our goal-independent topology achieves a 99.4% geometric success ceiling. Holding semantic responses fixed, metric grounding raises SR/SPL from 0.835/0.560 to 0.920/0.603, and source-aware fusion reaches 0.926/0.586. Fusion-aware Top-3 recovery raises Success@1/2/3 to 0.928/0.965/0.975 and reaches 0.601 SPL@3. Model, field-of-view, density, and corruption controls identify where these gains originate, and a ROS2/Nav2 realization demonstrates the complete reusable query-to-execution pipeline. Together, the results establish pre-exploration as a powerful practical regime for dependable, repeated semantic navigation.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 32 references that are in the map. First posted on arXiv 1 Aug 2026.
Builds on
26 of 32 references.
References · 26
- 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
- 2023OpenMask3D: Open-Vocabulary 3D Instance Segmentationcited by 289
- 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigationcited by 205
- 2022Robot Operating System 2: Design, Architecture, and Uses In The Wildcited by 199
- 2022ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddingscited by 178
- 2022CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memorycited by 165
- 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 157
- 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 150
- 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigationcited by 127
- 2023L3MVN: Leveraging Large Language Models for Visual Target Navigationcited by 120
- 2024SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigationcited by 109
- 2023Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skillcited by 77
14 more
- 2020The Marathon 2: A Navigation Systemcited by 70
- 2025UniGoal: Towards Universal Zero-shot Goal-oriented Navigationcited by 57
- 2022Topological Semantic Graph Memory for Image-Goal Navigationcited by 45
- 2025WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigationcited by 43
- 2024CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMscited by 33
- 2025ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusioncited by 30
- 2024GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidancecited by 23
- 2025LOVON: Legged Open-Vocabulary Object Navigatorcited by 11
- 2022Online Learning of Reusable Abstract Models for Object Goal Navigationcited by 9
- 2025TopoNav: Topological Graphs as a Key Enabler for Advanced Object Navigationcited by 6
- 2024Context-Aware Replanning with Pre-explored Semantic Map for Object Navigationcited by 2
- 2025FOM-Nav: Frontier-Object Maps for Object Goal Navigationcited by 1
- 2026TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigationcited by 1
- 2026ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Controlcited by 1
Built on by
Not cited yet.