mlsanityData to 14 Oct 2026

No RL, No Simulation: Learning to Navigate without Navigating

arXiv 2110.09470 ↗First posted 18 Oct 2021cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

Most prior methods for learning navigation policies require access to simulation environments, as they need online policy interaction and rely on ground-truth maps for rewards. However, building simulators is expensive (requires manual effort for each and every scene) and creates challenges in transferring learned policies to robotic platforms in the real-world, due to the sim-to-real domain gap. In this paper, we pose a simple question: Do we really need active interaction, ground-truth maps or even reinforcement-learning (RL) in order to solve the image-goal navigation task? We propose a self-supervised approach to learn to navigate from only passive videos of roaming. Our approach, No RL, No Simulator (NRNS), is simple and scalable, yet highly effective. NRNS outperforms RL-based formulations by a significant margin. We present NRNS as a strong baseline for any future image-based navigation tasks that use RL or Simulation.

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). Builds on 37 of its 48 references that are in the map. First posted on arXiv 18 Oct 2021.

Builds on

37 of 48 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2017Proximal Policy Optimization Algorithmscited by 15,215
  5. 2017Graph Attention Networkscited by 8,923
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  7. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  8. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  9. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  10. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  11. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  12. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
25 more
  1. 2018On Evaluation of Embodied Navigation Agentscited by 547
  2. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 481
  3. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  4. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 366
  5. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 362
  6. 2020Learning to Explore using Active Neural SLAMcited by 316
  7. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 244
  8. 2020Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learningcited by 215
  9. 2017Cognitive Mapping and Planning for Visual Navigationcited by 212
  10. 2018Semi-parametric Topological Memory for Navigationcited by 209
  11. 2020Neural Topological SLAM for Visual Navigationcited by 195
  12. 2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 194
  13. 2018Visual Semantic Navigation using Scene Priorscited by 128
  14. 2019Learning Exploration Policies for Navigationcited by 116
  15. 2020Occupancy Anticipation for Efficient Exploration and Navigationcited by 106
  16. 2018Learning to Navigate in Cities Without a Mapcited by 104
  17. 2020ViNG: Learning Open-World Navigation with Visual Goalscited by 80
  18. 2021Memory-Augmented Reinforcement Learning for Image-Goal Navigationcited by 66
  19. 2020Semantic Visual Navigation by Watching YouTube Videoscited by 60
  20. 2019Bayesian Relational Memory for Semantic Visual Navigationcited by 48
  21. 2019A Behavioral Approach to Visual Navigation with Graph Localization Networkscited by 40
  22. 2020Sparse Graphical Memory for Robust Planningcited by 31
  23. 2020Learning to plan with uncertain topological mapscited by 29
  24. 2019Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigationcited by 13
  25. 2017DeepNav: Learning to Navigate Large Citiescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 20; 2023: 14; 2024: 17; 2025: 10; 2026: 4.

65 papers.

Sort:

By area:

  1. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  2. 2022GNM: A General Navigation Model to Drive Any Robotcited by 171
  3. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 169
  4. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 150
  5. 2022Habitat-Matterport 3D Semantics Datasetcited by 110
  6. 2022Navigating to Objects in the Real Worldcited by 106
  7. 2024GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigationcited by 94
  8. 2022When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?cited by 89
  9. 2022Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environmentscited by 86
  10. 2022Offline Visual Representation Learning for Embodied Navigationcited by 75
  11. 2023OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNavcited by 70
  12. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 67
38 more
  1. 2022Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instancescited by 55
  2. 2023Renderable Neural Radiance Map for Visual Navigationcited by 51
  3. 2023Navigating to Objects Specified by Imagescited by 51
  4. 2024GaussNav: Gaussian Splatting for Visual Navigationcited by 49
  5. 2022Retrospectives on the Embodied AI Workshopcited by 46
  6. 2023Learning Navigational Visual Representations with Semantic Map Supervisioncited by 43
  7. 2024CityWalker: Learning Embodied Urban Navigation from Web-Scale Videoscited by 41
  8. 2024DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulationcited by 32
  9. 2024Prioritized Semantic Learning for Zero-shot Instance Navigationcited by 31
  10. 2022Phone2Proc: Bringing Robust Robots Into Our Chaotic Worldcited by 26
  11. 2022Last-Mile Embodied Visual Navigationcited by 25
  12. 2022PEANUT: Predicting and Navigating to Unseen Targetscited by 22
  13. 2023FGPrompt: Fine-grained Goal Prompting for Image-goal Navigationcited by 22
  14. 2022Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RLcited by 21
  15. 2023Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Groundingcited by 18
  16. 2023Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Trainingcited by 18
  17. 2024NeRFs in Robotics: A Surveycited by 16
  18. 2024SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Expertscited by 16
  19. 2024Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigationcited by 15
  20. 2022Finding Fallen Objects Via Asynchronous Audio-Visual Integrationcited by 14
  21. 2024MemoNav: Working Memory Model for Visual Navigationcited by 13
  22. 2026Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Explorationcited by 13
  23. 2025REGNav: Room Expert Guided Image-Goal Navigationcited by 12
  24. 2023MOPA: Modular Object Navigation with PointGoal Agentscited by 11
  25. 2025NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistantscited by 11
  26. 2025IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigationcited by 11
  27. 2023AutoNeRF: Training Implicit Scene Representations with Autonomous Agentscited by 10
  28. 2023Exploitation-Guided Exploration for Semantic Embodied Navigationcited by 9
  29. 2023One-4-All: Neural Potential Fields for Embodied Navigationcited by 7
  30. 2026CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigationcited by 6
  31. 2022Learning-Augmented Model-Based Planning for Visual Explorationcited by 5
  32. 2025SIGN: Safety-Aware Image-Goal Navigation for Autonomous Drones via Reinforcement Learningcited by 5
  33. 2025ObjectReact: Learning Object-Relative Control for Visual Navigationcited by 5
  34. 2024Feudal Networks for Visual Navigationcited by 4
  35. 2025VL-Nav: Neuro-Symbolic Reasoning-based Vision-Language Navigationcited by 4
  36. 2022Layout-aware Dreamer for Embodied Referring Expression Groundingcited by 3
  37. 2024NOLO: Navigate Only Look Oncecited by 3
  38. 2025Image-Goal Navigation Using Refined Feature Guidance and Scene Graph Enhancementcited by 3

50 most cited of 65 All 65 (JSON)