mlsanityData to 14 Oct 2026

Semi-parametric Topological Memory for Navigation

arXiv 1803.00653 ↗First posted 1 Mar 2018cs.LG cs.AI cs.CVcited by 209

Not on the map. Why?

Cited by 22 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce a new memory architecture for navigation in previously unseen environments, inspired by landmark-based navigation in animals. The proposed semi-parametric topological memory (SPTM) consists of a (non-parametric) graph with nodes corresponding to locations in the environment and a (parametric) deep network capable of retrieving nodes from the graph based on observations. The graph stores no metric information, only connectivity of locations corresponding to the nodes. We use SPTM as a planning module in a navigation system. Given only 5 minutes of footage of a previously unseen maze, an SPTM-based navigation agent can build a topological map of the environment and use it to confidently navigate towards goals. The average success rate of the SPTM agent in goal-directed navigation across test environments is higher than the best-performing baseline by a factor of three. A video of the agent is available at https://youtu.be/vRF7f4lhswo

Key facts. Cited by 209 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 50; 2022: 48; 2023: 27; 2024: 26; 2025: 27; 2026: 31.

209 papers.

Sort:

By area:

  1. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  2. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
  3. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 439
  4. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
  5. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  6. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 253
  7. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 238
  8. 2023ViNT: A Foundation Model for Visual Navigationcited by 222
  9. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 193
  10. 2022GNM: A General Navigation Model to Drive Any Robotcited by 171
  11. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 150
  12. 2023HIQL: Offline Goal-Conditioned RL with Latent States as Actionscited by 141
38 more
  1. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 132
  2. 2021Rapid Exploration for Open-World Navigation with Latent Goal Modelscited by 121
  3. 2022Navigating to Objects in the Real Worldcited by 106
  4. 2021ManipulaTHOR: A Framework for Visual Object Manipulationcited by 102
  5. 2021Structured Scene Memory for Vision-Language Navigationcited by 95
  6. 2023Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planningcited by 89
  7. 2023METRA: Scalable Unsupervised RL with Metric-Aware Abstractioncited by 86
  8. 2024Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphscited by 73
  9. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 67
  10. 2023Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agentscited by 67
  11. 2024OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Modelscited by 67
  12. 2024ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigationcited by 67
  13. 2021Memory-Augmented Reinforcement Learning for Image-Goal Navigationcited by 66
  14. 2021The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AIcited by 65
  15. 2021No RL, No Simulation: Learning to Navigate without Navigatingcited by 65
  16. 2023SACSoN: Scalable Autonomous Control for Social Navigationcited by 61
  17. 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 58
  18. 2022ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hintscited by 58
  19. 2025Horizon Reduction Makes RL Scalablecited by 57
  20. 2024Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Makingcited by 56
  21. 2021RobustNav: Towards Benchmarking Robustness in Embodied Navigationcited by 54
  22. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 52
  23. 2021VTNet: Visual Transformer Network for Object Goal Navigationcited by 51
  24. 2021Coupling Vision and Proprioception for Navigation of Legged Robotscited by 51
  25. 2023Navigating to Objects Specified by Imagescited by 51
  26. 2021Scene-Intuitive Agent for Remote Embodied Visual Groundingcited by 49
  27. 2024GaussNav: Gaussian Splatting for Visual Navigationcited by 49
  28. 2024Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robotscited by 48
  29. 2021Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learningcited by 47
  30. 2022Retrospectives on the Embodied AI Workshopcited by 46
  31. 2023Learning Navigational Visual Representations with Semantic Map Supervisioncited by 43
  32. 2024CityWalker: Learning Embodied Urban Navigation from Web-Scale Videoscited by 41
  33. 2022Continuous Scene Representations for Embodied AIcited by 39
  34. 2025OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigationcited by 38
  35. 2021Hierarchical Few-Shot Imitation with Skill Transition Modelscited by 37
  36. 2021Move2Hear: Active Audio-Visual Source Separationcited by 35
  37. 2021Hierarchical Object-to-Zone Graph for Object Navigationcited by 34
  38. 2022Episodic Memory Question Answeringcited by 32

50 most cited of 209 All 209 (JSON)