# Semantic Environment Atlas for Object-Goal Navigation

arXiv: https://arxiv.org/abs/2410.09081 · HTML: https://mlsanity.com/paper/2410.09081/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 34 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [Cognitive Mapping and Planning for Visual Navigation](https://mlsanity.com/paper/1702.03920/) (2017)
- [Learning Exploration Policies for Navigation](https://mlsanity.com/paper/1903.01959/) (2019)
- [Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks](https://mlsanity.com/paper/1903.03878/) (2019)
- [Learning to Navigate in Cities Without a Map](https://mlsanity.com/paper/1804.00168/) (2018)
- [Neural Map: Structured Memory for Deep Reinforcement Learning](https://mlsanity.com/paper/1702.08360/) (2017)
- [Auxiliary Tasks and Exploration Enable ObjectNav](https://mlsanity.com/paper/2104.04112/) (2021)
- [No RL, No Simulation: Learning to Navigate without Navigating](https://mlsanity.com/paper/2110.09470/) (2021)
- [Learning Object Relation Graph and Tentative Policy for Visual Navigation](https://mlsanity.com/paper/2007.11018/) (2020)
- [Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks](https://mlsanity.com/paper/2108.01176/) (2021)
- [Bayesian Relational Memory for Semantic Visual Navigation](https://mlsanity.com/paper/1909.04306/) (2019)
- [Topological Semantic Graph Memory for Image-Goal Navigation](https://mlsanity.com/paper/2209.08274/) (2022)
- [A Behavioral Approach to Visual Navigation with Graph Localization Networks](https://mlsanity.com/paper/1903.00445/) (2019)
- [Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation](https://mlsanity.com/paper/2007.09841/) (2020)
- [Hierarchical Object-to-Zone Graph for Object Navigation](https://mlsanity.com/paper/2109.02066/) (2021)
- [Visual Memory for Robust Path Following](https://mlsanity.com/paper/1812.00940/) (2018)
- [Embodied Visual Recognition](https://mlsanity.com/paper/1904.04404/) (2019)
- [EMPNet: Neural Localisation and Mapping Using Embedded Memory Points](https://mlsanity.com/paper/1907.13268/) (2019)
- [Online Learning of Reusable Abstract Models for Object Goal Navigation](https://mlsanity.com/paper/2203.02583/) (2022)

## Abstract (arXiv)

In this paper, we introduce the Semantic Environment Atlas (SEA), a novel mapping approach designed to enhance visual navigation capabilities of embodied agents. The SEA utilizes semantic graph maps that intricately delineate the relationships between places and objects, thereby enriching the navigational context. These maps are constructed from image observations and capture visual landmarks as sparsely encoded nodes within the environment. The SEA integrates multiple semantic maps from various environments, retaining a memory of place-object relationships, which proves invaluable for tasks such as visual localization and navigation. We developed navigation frameworks that effectively leverage the SEA, and we evaluated these frameworks through visual localization and object-goal navigation tasks. Our SEA-based localization framework significantly outperforms existing methods, accurately identifying locations from single query images. Experimental results in Habitat scenarios show that our method not only achieves a success rate of 39.0%, an improvement of 12.4% over the current state-of-the-art, but also maintains robustness under noisy odometry and actuation conditions, all while keeping computational costs low.