# Graph-MambaNav: Spatial-Temporal Graph Mamba Leveraging Object-Relation Knowledge for Object-Goal Navigation

arXiv: https://arxiv.org/abs/2608.13723 · HTML: https://mlsanity.com/paper/2608.13723/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [RoboTHOR: An Open Simulation-to-Real Embodied AI Platform](https://mlsanity.com/paper/2004.06799/) (2020)
- [Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2402.00789/) (2024)
- [Visual Semantic Navigation using Scene Priors](https://mlsanity.com/paper/1810.06543/) (2018)
- [RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation](https://mlsanity.com/paper/2406.04339/) (2024)
- [Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning](https://mlsanity.com/paper/1812.00971/) (2018)
- [Learning Object Relation Graph and Tentative Policy for Visual Navigation](https://mlsanity.com/paper/2007.11018/) (2020)
- [VTNet: Visual Transformer Network for Object Goal Navigation](https://mlsanity.com/paper/2105.09447/) (2021)
- [Visual Navigation with Spatial Attention](https://mlsanity.com/paper/2104.09807/) (2021)
- [Hierarchical Object-to-Zone Graph for Object Navigation](https://mlsanity.com/paper/2109.02066/) (2021)
- [STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model](https://mlsanity.com/paper/2403.12418/) (2024)
- [Unbiased Directed Object Attention Graph for Object Navigation](https://mlsanity.com/paper/2204.04421/) (2022)
- [MTIL: Encoding Full History with Mamba for Temporal Imitation Learning](https://mlsanity.com/paper/2505.12410/) (2025)
- [Aligning Knowledge Graph with Visual Perception for Object-goal Navigation](https://mlsanity.com/paper/2402.18892/) (2024)

## Abstract (arXiv)

Object-goal navigation requires an agent to reason over object relationships and prioritize target-relevant objects for efficient decision making in unseen environments. While existing graph-based methods incorporate target-awareness at the feature or attention level, they remain permutation-invariant and lack an explicit mechanism to control information propagation order, limiting their ability to model target-dependent importance and long-range dependencies. In contrast, Graph-Mamba highlights that node prioritization through sequence ordering is critical for effective global reasoning. In this work, we investigate the node prioritization mechanism in Graph-Mamba and study its role in object navigation. We propose Graph-MambaNav, a target-aware spatial-temporal graph encoding framework that introduces a heuristic ordering over objects based on their relevance to the target, allowing more informative objects to be processed later to aggregate richer context. Both node ordering and edge weights are initialized from LLM-derived commonsense object relationships, providing a unified prior for structured reasoning. A spatial module integrates local message passing with global GraphMamba-based selective scanning, while a temporal module applies Mamba-based sequence modeling over object-wise temporal orders, allowing selective aggregation of historical context for long-range temporal reasoning. Experiments on AI2-THOR and RoboTHOR demonstrate improved navigation performance with generalization, and additional real-world robot deployment further validates the effectiveness of our proposed approach.