mlsanityData to 14 Oct 2026

Rapid Exploration for Open-World Navigation with Latent Goal Models

arXiv 2104.05859 ↗First posted 12 Apr 2021cs.RO cs.AI cs.LGcited by 121

Not on the map. Why?

Cited by 31 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We describe a robotic learning system for autonomous exploration and navigation in diverse, open-world environments. At the core of our method is a learned latent variable model of distances and actions, along with a non-parametric topological memory of images. We use an information bottleneck to regularize the learned policy, giving us (i) a compact visual representation of goals, (ii) improved generalization capabilities, and (iii) a mechanism for sampling feasible goals for exploration. Trained on a large offline dataset of prior experience, the model acquires a representation of visual goals that is robust to task-irrelevant distractors. We demonstrate our method on a mobile ground robot in open-world exploration scenarios. Given an image of a goal that is up to 80 meters away, our method leverages its representation to explore and discover the goal in under 20 minutes, even amidst previously-unseen obstacles and weather conditions. Please check out the project website for videos of our experiments and information about the real-world dataset used at https://sites.google.com/view/recon-robot.

Key facts. Cited by 121 papers in the map (data through 14 Oct 2026). Builds on 51 of its 70 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

51 of 70 references.

References · 51

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  4. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  5. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  6. 2018Exploration by Random Network Distillationcited by 993
  7. 2016Deep Variational Information Bottleneckcited by 930
  8. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  9. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  10. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  11. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 362
  12. 2019Learning Latent Plans from Playcited by 316
38 more
  1. 2020Learning to Explore using Active Neural SLAMcited by 316
  2. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 276
  3. 2018Provably Efficient Maximum Entropy Explorationcited by 242
  4. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 215
  5. 2018Semi-parametric Topological Memory for Navigationcited by 209
  6. 2020Neural Topological SLAM for Visual Navigationcited by 195
  7. 2019Efficient Exploration via State Marginal Matchingcited by 188
  8. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 178
  9. 2019Skew-Fit: State-Covering Self-Supervised Reinforcement Learningcited by 174
  10. 2019Goal-conditioned Imitation Learningcited by 162
  11. 2015Incentivizing Exploration In Reinforcement Learning With Deep Predictive Modelscited by 154
  12. 2019Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learningcited by 114
  13. 2018Episodic Curiosity through Reachabilitycited by 109
  14. 2019Training Agents using Upside-Down Reinforcement Learningcited by 107
  15. 2020C-Learning: Learning to Achieve Goals via Recursive Classificationcited by 103
  16. 2020BADGR: An Autonomous Self-Supervised Learning-Based Navigation Systemcited by 102
  17. 2020Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learningcited by 102
  18. 2019Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneckcited by 101
  19. 2016Revisiting Active Perceptioncited by 94
  20. 2018Temporal Difference Models: Model-Free Deep RL for Model-Based Controlcited by 89
  21. 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 85
  22. 2020ViNG: Learning Open-World Navigation with Visual Goalscited by 80
  23. 2018CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learningcited by 79
  24. 2019InfoBot: Transfer and Exploration via the Information Bottleneckcited by 78
  25. 2018Deep Imitative Models for Flexible Inference, Planning, and Controlcited by 76
  26. 2017PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planningcited by 69
  27. 2020World Model as a Graph: Learning Latent Landmarks for Planningcited by 69
  28. 2018Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translationcited by 50
  29. 2020Semantic Curiosity for Active Visual Learningcited by 45
  30. 2018Meta Reinforcement Learning with Latent Variable Gaussian Processescited by 44
  31. 2019Contextual Imagined Goals for Self-Supervised Robotic Learningcited by 40
  32. 2019Scaling Local Control to Large-Scale Topological Navigationcited by 37
  33. 2019Learning to Reach Goals via Iterated Supervised Learningcited by 26
  34. 2020Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planningcited by 26
  35. 2020Hallucinative Topological Memory for Zero-Shot Visual Planningcited by 25
  36. 2019Policy Continuation with Hindsight Inverse Dynamicscited by 22
  37. 2021Success Weighted by Completion Time: A Dynamics-Aware Evaluation Criteria for Embodied Navigationcited by 22
  38. 2018Approximate Bayesian inference in spatial environmentscited by 8

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 15; 2023: 16; 2024: 10; 2025: 31; 2026: 48.

121 papers.

Sort:

By area:

  1. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 439
  2. 2024Navigation World Modelscited by 272
  3. 2023NoMaD: Goal Masked Diffusion Policies for Navigation and Explorationcited by 248
  4. 2023ViNT: A Foundation Model for Visual Navigationcited by 222
  5. 2022GNM: A General Navigation Model to Drive Any Robotcited by 171
  6. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 158
  7. 2023HIQL: Offline Goal-Conditioned RL with Latent States as Actionscited by 141
  8. 2023Large Language Models for Robotics: A Surveycited by 133
  9. 2022Deep Hierarchical Planning from Pixelscited by 101
  10. 2023Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planningcited by 89
  11. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  12. 2025Vid2World: Crafting Video Diffusion Models to Interactive World Modelscited by 76
38 more
  1. 2023SACSoN: Scalable Autonomous Control for Social Navigationcited by 61
  2. 2022ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hintscited by 58
  3. 2023QUAR-VLA: Vision-Language-Action Model for Quadruped Robotscited by 56
  4. 2023Navigating to Objects Specified by Imagescited by 51
  5. 2024GaussNav: Gaussian Splatting for Visual Navigationcited by 49
  6. 2025NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidancecited by 49
  7. 2026Learning Latent Action World Models In The Wildcited by 47
  8. 2025What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?cited by 43
  9. 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learningcited by 38
  10. 2025OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigationcited by 38
  11. 2024End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answeringcited by 37
  12. 2026Beyond Language Modeling: An Exploration of Multimodal Pretrainingcited by 37
  13. 2023Contrastive Difference Predictive Codingcited by 36
  14. 2024Autonomous Improvement of Instruction Following Skills via Foundation Modelscited by 32
  15. 2022Offline Reinforcement Learning for Visual Navigationcited by 29
  16. 2022How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversabilitycited by 27
  17. 2022Phone2Proc: Bringing Robust Robots Into Our Chaotic Worldcited by 26
  18. 2022Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Taskscited by 25
  19. 2025NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigationcited by 25
  20. 2025Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Modelscited by 25
  21. 2026ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigationcited by 25
  22. 2024A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoalscited by 23
  23. 2025A Survey of Interactive Generative Videocited by 23
  24. 2022Multi-Object Navigation with dynamically learned neural implicit representationscited by 21
  25. 2022ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentationcited by 19
  26. 2021Understanding the World Through Actioncited by 17
  27. 2022Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networkscited by 17
  28. 2023FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicingcited by 17
  29. 2025Dual Goal Representationscited by 16
  30. 2024GHIL-Glue: Hierarchical Control with Filtered Subgoal Imagescited by 15
  31. 2025XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representationscited by 15
  32. 2025Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresightcited by 14
  33. 2025Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generationcited by 14
  34. 2026Walk through Paintings: Egocentric World Models from Internet Priorscited by 14
  35. 2022Learning Robotic Navigation from Experience: Principles, Methods, and Recent Resultscited by 13
  36. 2025Exploring Embodied Multimodal Large Models: Development, Datasets, and Future Directionscited by 13
  37. 2025Learning to Drive Anywhere with Model-Based Reannotationcited by 13
  38. 2024FlowNav: Combining Flow Matching and Depth Priors for Efficient Navigationcited by 12

50 most cited of 121 All 121 (JSON)