# Topological Semantic Graph Memory for Image-Goal Navigation

arXiv: https://arxiv.org/abs/2209.08274 · HTML: https://mlsanity.com/paper/2209.08274/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2022.

## Built on by (most cited first, 30 of 45)

- [3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning](https://mlsanity.com/paper/2411.17735/) (2024)
- [SACSoN: Scalable Autonomous Control for Social Navigation](https://mlsanity.com/paper/2306.01874/) (2023)
- [GaussNav: Gaussian Splatting for Visual Navigation](https://mlsanity.com/paper/2403.11625/) (2024)
- [Learning Generalizable Feature Fields for Mobile Manipulation](https://mlsanity.com/paper/2403.07563/) (2024)
- [Prioritized Semantic Learning for Zero-shot Instance Navigation](https://mlsanity.com/paper/2403.11650/) (2024)
- [RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation](https://mlsanity.com/paper/2405.05792/) (2024)
- [General Place Recognition Survey: Towards Real-World Autonomy](https://mlsanity.com/paper/2405.04812/) (2024)
- [FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation](https://mlsanity.com/paper/2310.07473/) (2023)
- [Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation](https://mlsanity.com/paper/2402.17587/) (2024)
- [MemoNav: Working Memory Model for Visual Navigation](https://mlsanity.com/paper/2402.19161/) (2024)
- [REGNav: Room Expert Guided Image-Goal Navigation](https://mlsanity.com/paper/2502.10785/) (2025)
- [IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation](https://mlsanity.com/paper/2508.00823/) (2025)
- [Exploitation-Guided Exploration for Semantic Embodied Navigation](https://mlsanity.com/paper/2311.03357/) (2023)
- [Multiview Scene Graph](https://mlsanity.com/paper/2410.11187/) (2024)
- [LoopNav: Benchmarking Spatial Consistency in World Models](https://mlsanity.com/paper/2505.22976/) (2025)
- [One-4-All: Neural Potential Fields for Embodied Navigation](https://mlsanity.com/paper/2303.04011/) (2023)
- [TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals](https://mlsanity.com/paper/2509.08699/) (2025)
- [Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation](https://mlsanity.com/paper/2409.10071/) (2024)
- [TopoNav: Topological Navigation for Efficient Exploration in Sparse Reward Environments](https://mlsanity.com/paper/2402.04061/) (2024)
- [SIGN: Safety-Aware Image-Goal Navigation for Autonomous Drones via Reinforcement Learning](https://mlsanity.com/paper/2508.12394/) (2025)
- [ObjectReact: Learning Object-Relative Control for Visual Navigation](https://mlsanity.com/paper/2509.09594/) (2025)
- [Feudal Networks for Visual Navigation](https://mlsanity.com/paper/2402.12498/) (2024)
- [LiteVLoc: Map-Lite Visual Localization for Image Goal Navigation](https://mlsanity.com/paper/2410.04419/) (2024)
- [OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism](https://mlsanity.com/paper/2603.14371/) (2026)
- [Personalized Embodied Navigation for Portable Object Finding](https://mlsanity.com/paper/2403.09905/) (2024)
- [NOLO: Navigate Only Look Once](https://mlsanity.com/paper/2408.01384/) (2024)
- [Image-Goal Navigation Using Refined Feature Guidance and Scene Graph Enhancement](https://mlsanity.com/paper/2503.10986/) (2025)
- [Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation](https://mlsanity.com/paper/2510.08553/) (2025)
- [Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents](https://mlsanity.com/paper/2604.19034/) (2026)
- [A Landmark-Aware Visual Navigation Dataset](https://mlsanity.com/paper/2402.14281/) (2024)

## Abstract (arXiv)

A novel framework is proposed to incrementally collect landmark-based graph memory and use the collected memory for image goal navigation. Given a target image to search, an embodied robot utilizes semantic memory to find the target in an unknown environment. % The semantic graph memory is collected from a panoramic observation of an RGB-D camera without knowing the robot's pose. In this paper, we present a topological semantic graph memory (TSGM), which consists of (1) a graph builder that takes the observed RGB-D image to construct a topological semantic graph, (2) a cross graph mixer module that takes the collected nodes to get contextual information, and (3) a memory decoder that takes the contextual memory as an input to find an action to the target. On the task of image goal navigation, TSGM significantly outperforms competitive baselines by +5.0-9.0% on the success rate and +7.0-23.5% on SPL, which means that the TSGM finds efficient paths. Additionally, we demonstrate our method on a mobile robot in real-world image goal scenarios.