mlsanityData to 7 Oct 2026

Memory-Augmented Reinforcement Learning for Image-Goal Navigation

arXiv 2101.05181 ↗First posted 13 Jan 2021cs.CV cs.AI cs.ROcited by 64

Not on the map. Why?

Abstract (arXiv)

In this work, we present a memory-augmented approach for image-goal navigation. Earlier attempts, including RL-based and SLAM-based approaches have either shown poor generalization performance, or are heavily-reliant on pose/depth sensors. Our method is based on an attention-based end-to-end model that leverages an episodic memory to learn to navigate. First, we train a state-embedding network in a self-supervised fashion, and then use it to embed previously-visited states into the agent's memory. Our navigation policy takes advantage of this information through an attention mechanism. We validate our approach with extensive evaluations, and show that our model establishes a new state of the art on the challenging Gibson dataset. Furthermore, we achieve this impressive performance from RGB input alone, without access to additional information such as position or depth, in stark contrast to related work.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 36 of its 45 references that are in the map. First posted on arXiv 13 Jan 2021.

Builds on

36 of 45 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  3. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  4. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  5. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  6. 2018On Evaluation of Embodied Navigation Agentscited by 526
  7. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 477
  8. 2020Reinforcement Learning with Augmented Datacited by 452
  9. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 421
  10. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
  11. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  12. 2017Embodied Question Answeringcited by 335
24 more
  1. 2020Learning to Explore using Active Neural SLAMcited by 308
  2. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 240
  3. 2017Cognitive Mapping and Planning for Visual Navigationcited by 209
  4. 2018Semi-parametric Topological Memory for Navigationcited by 203
  5. 2020Neural Topological SLAM for Visual Navigationcited by 193
  6. 2016Learning to Navigate in Complex Environmentscited by 192
  7. 2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 188
  8. 2018Visual Semantic Navigation using Scene Priorscited by 127
  9. 2019Learning Exploration Policies for Navigationcited by 113
  10. 2018Episodic Curiosity through Reachabilitycited by 109
  11. 2019Scene Memory Transformer for Embodied Agents in Long-Horizon Taskscited by 106
  12. 2018Learning to Navigate in Cities Without a Mapcited by 103
  13. 2017Neural Map: Structured Memory for Deep Reinforcement Learningcited by 88
  14. 2019Bayesian Relational Memory for Semantic Visual Navigationcited by 48
  15. 2020Semantic Curiosity for Active Visual Learningcited by 44
  16. 2019A Behavioral Approach to Visual Navigation with Graph Localization Networkscited by 40
  17. 2017Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Taskscited by 37
  18. 2020Learning to plan with uncertain topological mapscited by 29
  19. 2020EgoMap: Projective mapping and structured egocentric memory for Deep RLcited by 23
  20. 2018Active Neural Localizationcited by 18
  21. 2018Visual Memory for Robust Path Followingcited by 16
  22. 2019EMPNet: Neural Localisation and Mapping Using Embedded Memory Pointscited by 9
  23. 2020Learning to Visually Navigate in Photorealistic Environments Without any Supervisioncited by 6
  24. 2020MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic Navigationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 11; 2023: 15; 2024: 17; 2025: 14; 2026: 3.

64 papers.

Sort:

By area:

  1. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
  2. 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?cited by 215
  3. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  4. 2022ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddingscited by 177
  5. 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigationcited by 126
  6. 2023Scaling Data Generation in Vision-and-Language Navigationcited by 115
  7. 2022Offline Visual Representation Learning for Embodied Navigationcited by 74
  8. 2024Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphscited by 72
  9. 2023OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNavcited by 68
  10. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 66
  11. 2021No RL, No Simulation: Learning to Navigate without Navigatingcited by 63
  12. 2024Theia: Distilling Diverse Vision Foundation Models for Robot Learningcited by 56
38 more
  1. 2023Navigating to Objects Specified by Imagescited by 50
  2. 2021Coupling Vision and Proprioception for Navigation of Legged Robotscited by 46
  3. 2022Retrospectives on the Embodied AI Workshopcited by 46
  4. 2024Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generationcited by 44
  5. 2023Learning Navigational Visual Representations with Semantic Map Supervisioncited by 40
  6. 2024Prioritized Semantic Learning for Zero-shot Instance Navigationcited by 30
  7. 2022Last-Mile Embodied Visual Navigationcited by 25
  8. 2023FGPrompt: Fine-grained Goal Prompting for Image-goal Navigationcited by 21
  9. 2023Selective Visual Representations Improve Convergence and Generalization for Embodied AIcited by 19
  10. 2022VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangementcited by 18
  11. 2024Zero-shot Object Navigation with Vision-Language Models Reasoningcited by 18
  12. 2022Active Audio-Visual Separation of Dynamic Sound Sourcescited by 16
  13. 2023End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenoncited by 16
  14. 2024Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigationcited by 15
  15. 2024MemoNav: Working Memory Model for Visual Navigationcited by 13
  16. 2025Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Taskscited by 13
  17. 2024Human-inspired Perspectives: A Survey on AI Long-term Memorycited by 12
  18. 2025REGNav: Room Expert Guided Image-Goal Navigationcited by 12
  19. 2025Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answeringcited by 12
  20. 2023PlaceNav: Topological Navigation through Place Recognitioncited by 11
  21. 2024Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Controlcited by 11
  22. 2024GOMAA-Geo: GOal Modality Agnostic Active Geo-localizationcited by 11
  23. 2025NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistantscited by 11
  24. 2025From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learningcited by 11
  25. 2023AutoNeRF: Training Implicit Scene Representations with Autonomous Agentscited by 10
  26. 2025Safety of Embodied Navigation: A Surveycited by 9
  27. 2024Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigationcited by 6
  28. 2023Visual Hindsight Self-Imitation Learning for Interactive Navigationcited by 5
  29. 2025Mobile Robot Navigation Using Hand-Drawn Maps: A Vision Language Model Approachcited by 5
  30. 2022Aerial View Localization with Reinforcement Learning: Towards Emulating Search-and-Rescuecited by 4
  31. 2024Feudal Networks for Visual Navigationcited by 4
  32. 2021Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistencycited by 3
  33. 2024Situated Instruction Followingcited by 3
  34. 2024NOLO: Navigate Only Look Oncecited by 3
  35. 2025Image-Goal Navigation Using Refined Feature Guidance and Scene Graph Enhancementcited by 3
  36. 2026Notes-to-Self: Scratchpad Augmented VLAs for Memory Dependent Manipulation Taskscited by 3
  37. 2024Causality-Aware Transformer Networks for Robotic Navigationcited by 2
  38. 2025RANa: Retrieval-Augmented Navigationcited by 2

50 most cited of 64 All 64 (JSON)