mlsanityData to 7 Oct 2026

Bayesian Relational Memory for Semantic Visual Navigation

arXiv 1909.04306 ↗First posted 10 Sep 2019cs.CV cs.LG cs.ROcited by 48

Not on the map. Why?

Abstract (arXiv)

We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to navigate towards. BRM takes the form of a probabilistic relation graph over semantic entities (e.g., room types), which allows (1) capturing the layout prior from training environments, i.e., prior knowledge, (2) estimating posterior layout at test time, i.e., memory update, and (3) efficient planning for navigation, altogether. We develop a BRM agent consisting of a BRM module for producing sub-goals and a goal-conditioned locomotion module for control. When testing in unseen environments, the BRM agent outperforms baselines that do not explicitly utilize the probabilistic relational memory structure

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 12; 2023: 7; 2024: 4; 2025: 3; 2026: 5.

48 papers.

Sort:

By area:

  1. 2021Structured Scene Memory for Vision-Language Navigationcited by 95
  2. 2024Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrappingcited by 89
  3. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 66
  4. 2021Memory-Augmented Reinforcement Learning for Image-Goal Navigationcited by 64
  5. 2021No RL, No Simulation: Learning to Navigate without Navigatingcited by 63
  6. 2021VTNet: Visual Transformer Network for Object Goal Navigationcited by 50
  7. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 50
  8. 2023Navigating to Objects Specified by Imagescited by 50
  9. 2021Visual Navigation with Spatial Attentioncited by 43
  10. 2024Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Tracescited by 40
  11. 2022Continuous Scene Representations for Embodied AIcited by 39
  12. 2021Move2Hear: Active Audio-Visual Source Separationcited by 35
36 more
  1. 2021Hierarchical Object-to-Zone Graph for Object Navigationcited by 34
  2. 2021Vision-Language Navigation: A Survey and Taxonomycited by 33
  3. 2022SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement with Multi-Scale Perceptioncited by 32
  4. 2022Episodic Memory Question Answeringcited by 32
  5. 2022Towards Versatile Embodied Navigationcited by 26
  6. 2022Reasoning with Scene Graphs for Robot Planning under Partial Observabilitycited by 25
  7. 2021Learning Efficient Multi-Agent Cooperative Visual Explorationcited by 19
  8. 2023Selective Visual Representations Improve Convergence and Generalization for Embodied AIcited by 19
  9. 2023Modeling Dynamic Environments with Scene Graph Memorycited by 18
  10. 2022Navigating to Objects in Unseen Environments by Distance Predictioncited by 15
  11. 2021Environment Predictive Coding for Embodied Agentscited by 12
  12. 2025Memory-Centric Embodied Question Answeringcited by 12
  13. 2021Agent-Centric Relation Graph for Object Visual Navigationcited by 10
  14. 2023Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigationcited by 8
  15. 2024Aligning Knowledge Graph with Visual Perception for Object-goal Navigationcited by 8
  16. 2021Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graphcited by 7
  17. 2021Lifelong Topological Visual Navigationcited by 7
  18. 2022A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Searchcited by 6
  19. 2025ObjectReact: Learning Object-Relative Control for Visual Navigationcited by 5
  20. 2022Spatial Relation Graph and Graph Convolutional Network for Object Goal Navigationcited by 3
  21. 2022A General Purpose Supervisory Signal for Embodied Agentscited by 3
  22. 2023ReVoLT: Relational Reasoning and Voronoi Local Graph Planning for Target-driven Navigationcited by 3
  23. 2023Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidancecited by 3
  24. 2021Deep Learning for Embodied Vision Navigation: A Surveycited by 2
  25. 2021Graph Convolutional Memory using Topological Priorscited by 1
  26. 2022Movement Analytics: Current Status, Application to Manufacturing, and Future Prospects from an AI Perspectivecited by 1
  27. 2026Memory-Guided View Refinement for Dynamic Human-in-the-loop EQAcited by 1
  28. 2026Semantic Audio-Visual Navigation in Continuous Environmentscited by 1
  29. 2021Symmetry-aware Neural Architecture for Embodied Visual Navigationcited by 0
  30. 2022Predicting Topological Maps for Visual Navigation in Unexplored Environmentscited by 0
  31. 2023Pseudo-Trilateral Adversarial Training for Domain Adaptive Traversability Predictioncited by 0
  32. 2024Semantic Environment Atlas for Object-Goal Navigationcited by 0
  33. 2025UAS Visual Navigation in Large and Unseen Environments via a Meta Agentcited by 0
  34. 2026Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Inductioncited by 0
  35. 2026PixelLoop: Shortcut Topological Navigation with Pixel-Level Loopscited by 0
  36. 2026RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigationcited by 0