# Object Memory Transformer for Object Goal Navigation

arXiv: https://arxiv.org/abs/2203.14708 · HTML: https://mlsanity.com/paper/2203.14708/

## Key facts

- Cited by 19 papers in the map (data through 7 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 23 of 23)

- [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)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [Semi-parametric Topological Memory for Navigation](https://mlsanity.com/paper/1803.00653/) (2018)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [Visual Semantic Navigation using Scene Priors](https://mlsanity.com/paper/1810.06543/) (2018)
- [Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks](https://mlsanity.com/paper/1903.03878/) (2019)
- [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)
- [Control of Memory, Active Perception, and Action in Minecraft](https://mlsanity.com/paper/1605.09128/) (2016)
- [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)
- [Memory Augmented Control Networks](https://mlsanity.com/paper/1709.05706/) (2017)
- [Active Object Perceiver: Recognition-guided Policy Learning for Object Searching on Mobile Robots](https://mlsanity.com/paper/1807.11174/) (2018)

## Built on by (most cited first, 19 of 19)

- [Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation](https://mlsanity.com/paper/2303.03480/) (2023)
- [Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation](https://mlsanity.com/paper/2502.14254/) (2025)
- [Search for or Navigate to? Dual Adaptive Thinking for Object Navigation](https://mlsanity.com/paper/2208.00553/) (2022)
- [Transformers in Reinforcement Learning: A Survey](https://mlsanity.com/paper/2307.05979/) (2023)
- [Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation](https://mlsanity.com/paper/2302.01520/) (2023)
- [Switching Head-Tail Funnel UNITER for Dual Referring Expression Comprehension with Fetch-and-Carry Tasks](https://mlsanity.com/paper/2307.07166/) (2023)
- [Multi-goal Audio-visual Navigation using Sound Direction Map](https://mlsanity.com/paper/2308.00219/) (2023)
- [TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability](https://mlsanity.com/paper/2404.08353/) (2024)
- [Select2Plan: Training-Free ICL-Based Planning through VQA and Memory Retrieval](https://mlsanity.com/paper/2411.04006/) (2024)
- [TransFusionOdom: Interpretable Transformer-based LiDAR-Inertial Fusion Odometry Estimation](https://mlsanity.com/paper/2304.07728/) (2023)
- [Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidance](https://mlsanity.com/paper/2308.12845/) (2023)
- [Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigation](https://mlsanity.com/paper/2312.03327/) (2023)
- [Learning to Terminate in Object Navigation](https://mlsanity.com/paper/2309.16164/) (2023)
- [ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination](https://mlsanity.com/paper/2512.17435/) (2025)
- [AERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object Navigation](https://mlsanity.com/paper/2603.17712/) (2026)
- [Leveraging Unknown Objects to Construct Labeled-Unlabeled Meta-Relationships for Zero-Shot Object Navigation](https://mlsanity.com/paper/2405.15222/) (2024)
- [Efficient Strategy Learning by Decoupling Searching and Pathfinding for Object Navigation](https://mlsanity.com/paper/2406.14103/) (2024)
- [Collision-Aware Object-Goal Visual Navigation via Two-Stage Deep Reinforcement Learning](https://mlsanity.com/paper/2502.13498/) (2025)
- [GRIP: A Unified Framework for Grid-Based Relay and Co-Occurrence-Aware Planning in Dynamic Environments](https://mlsanity.com/paper/2510.10865/) (2025)

## Abstract (arXiv)

This paper presents a reinforcement learning method for object goal navigation (ObjNav) where an agent navigates in 3D indoor environments to reach a target object based on long-term observations of objects and scenes. To this end, we propose Object Memory Transformer (OMT) that consists of two key ideas: 1) Object-Scene Memory (OSM) that enables to store long-term scenes and object semantics, and 2) Transformer that attends to salient objects in the sequence of previously observed scenes and objects stored in OSM. This mechanism allows the agent to efficiently navigate in the indoor environment without prior knowledge about the environments, such as topological maps or 3D meshes. To the best of our knowledge, this is the first work that uses a long-term memory of object semantics in a goal-oriented navigation task. Experimental results conducted on the AI2-THOR dataset show that OMT outperforms previous approaches in navigating in unknown environments. In particular, we show that utilizing the long-term object semantics information improves the efficiency of navigation.