mlsanityData to 14 Oct 2026

Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks

arXiv 1903.03878 ↗First posted 9 Mar 2019cs.LG cs.CV cs.ROcited by 107

Not on the map. Why?

Abstract (arXiv)

Many robotic applications require the agent to perform long-horizon tasks in partially observable environments. In such applications, decision making at any step can depend on observations received far in the past. Hence, being able to properly memorize and utilize the long-term history is crucial. In this work, we propose a novel memory-based policy, named Scene Memory Transformer (SMT). The proposed policy embeds and adds each observation to a memory and uses the attention mechanism to exploit spatio-temporal dependencies. This model is generic and can be efficiently trained with reinforcement learning over long episodes. On a range of visual navigation tasks, SMT demonstrates superior performance to existing reactive and memory-based policies by a margin.

Key facts. Cited by 107 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 23; 2022: 29; 2023: 16; 2024: 18; 2025: 8; 2026: 12.

107 papers.

Sort:

By area:

  1. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  2. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
  3. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  4. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 193
  5. 2022Open-vocabulary Queryable Scene Representations for Real World Planningcited by 160
  6. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 150
  7. 2023Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functionscited by 131
  8. 2024MOKA: Open-World Robotic Manipulation through Mark-Based Visual Promptingcited by 129
  9. 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 119
  10. 2022Navigating to Objects in the Real Worldcited by 106
  11. 2021Structured Scene Memory for Vision-Language Navigationcited by 95
  12. 2024Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphscited by 73
38 more
  1. 2024ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigationcited by 67
  2. 2021Memory-Augmented Reinforcement Learning for Image-Goal Navigationcited by 66
  3. 2022Video Transformers: A Surveycited by 63
  4. 2021Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completioncited by 58
  5. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 51
  6. 2021VTNet: Visual Transformer Network for Object Goal Navigationcited by 51
  7. 2021Learning to Map for Active Semantic Goal Navigationcited by 50
  8. 2021Scene-Intuitive Agent for Remote Embodied Visual Groundingcited by 49
  9. 2022Retrospectives on the Embodied AI Workshopcited by 46
  10. 2022Masked Autoencoding for Scalable and Generalizable Decision Makingcited by 45
  11. 2022On Transforming Reinforcement Learning by Transformer: The Development Trajectorycited by 36
  12. 2021Hierarchical Object-to-Zone Graph for Object Navigationcited by 34
  13. 2022Uncertainty-driven Planner for Exploration and Navigationcited by 33
  14. 2022Episodic Memory Question Answeringcited by 32
  15. 2021Core Challenges in Embodied Vision-Language Planningcited by 30
  16. 2022AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environmentscited by 26
  17. 2022Towards Versatile Embodied Navigationcited by 26
  18. 2022Phone2Proc: Bringing Robust Robots Into Our Chaotic Worldcited by 26
  19. 2022Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learningcited by 22
  20. 2022EgoEnv: Human-centric environment representations from egocentric videocited by 22
  21. 2023FGPrompt: Fine-grained Goal Prompting for Image-goal Navigationcited by 22
  22. 2022Multi-Object Navigation with dynamically learned neural implicit representationscited by 21
  23. 2022Learning Active Camera for Multi-Object Navigationcited by 21
  24. 2022Object Memory Transformer for Object Goal Navigationcited by 20
  25. 2021Learning Efficient Multi-Agent Cooperative Visual Explorationcited by 19
  26. 2021Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agentscited by 19
  27. 2021Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigationcited by 17
  28. 2021Shaping embodied agent behavior with activity-context priors from egocentric videocited by 17
  29. 2024OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representationcited by 17
  30. 2022Active Audio-Visual Separation of Dynamic Sound Sourcescited by 16
  31. 2022Navigating to Objects in Unseen Environments by Distance Predictioncited by 16
  32. 2023End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenoncited by 16
  33. 2021Teaching Autoregressive Language Models Complex Tasks By Demonstrationcited by 15
  34. 2024Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Resetcited by 15
  35. 2025COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigationcited by 15
  36. 2023CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environmentscited by 14
  37. 2023Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulationcited by 14
  38. 2026Gated Memory Policy: In-Context Memorization and Adaptationcited by 14

50 most cited of 107 All 107 (JSON)