# Graph Attention Memory for Visual Navigation

arXiv: https://arxiv.org/abs/1905.13315 · HTML: https://mlsanity.com/paper/1905.13315/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2019.

## Built on by (most cited first, 3 of 3)

- [Graph Convolutional Memory using Topological Priors](https://mlsanity.com/paper/2106.14117/) (2021)
- [UAS Navigation in the Real World Using Visual Observation](https://mlsanity.com/paper/2208.12125/) (2022)
- [UAS Visual Navigation in Large and Unseen Environments via a Meta Agent](https://mlsanity.com/paper/2503.15781/) (2025)

## Abstract (arXiv)

Visual navigation in complex environments is inefficient with traditional reactive policy or general-purposed recurrent policy. To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module. The memory construction module builds the topological graph based on supervised learning by taking the exploration prior. Then, guided attention features are extracted with the graph attention module. Finally, the deep reinforcement learning based control module makes decisions based on visual observations and guided attention features. Detailed convergence analysis of GAM is presented in this paper. We evaluate GAM-based navigation system in two complex 3D environments. Experimental results show that the GAM-based navigation system significantly improves learning efficiency and outperforms all baselines in average success rate.