mlsanityData to 7 Oct 2026

Online Learning of Reusable Abstract Models for Object Goal Navigation

arXiv 2203.02583 ↗First posted 4 Mar 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a novel approach to incrementally learn an Abstract Model of an unknown environment, and show how an agent can reuse the learned model for tackling the Object Goal Navigation task. The Abstract Model is a finite state machine in which each state is an abstraction of a state of the environment, as perceived by the agent in a certain position and orientation. The perceptions are high-dimensional sensory data (e.g., RGB-D images), and the abstraction is reached by exploiting image segmentation and the Taskonomy model bank. The learning of the Abstract Model is accomplished by executing actions, observing the reached state, and updating the Abstract Model with the acquired information. The learned models are memorized by the agent, and they are reused whenever it recognizes to be in an environment that corresponds to the stored model. We investigate the effectiveness of the proposed approach for the Object Goal Navigation task, relying on public benchmarks. Our results show that the reuse of learned Abstract Models can boost performance on Object Goal Navigation.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 34 of its 53 references that are in the map. First posted on arXiv 4 Mar 2022.

Builds on

34 of 53 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  3. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  4. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  5. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  6. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  7. 2018On Evaluation of Embodied Navigation Agentscited by 526
  8. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 477
  9. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 421
  10. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
  11. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  12. 2017Embodied Question Answeringcited by 335
22 more
  1. 2020Learning to Explore using Active Neural SLAMcited by 308
  2. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 240
  3. 2017Cognitive Mapping and Planning for Visual Navigationcited by 209
  4. 2020Neural Topological SLAM for Visual Navigationcited by 193
  5. 2016Learning to Navigate in Complex Environmentscited by 192
  6. 2020Rearrangement: A Challenge for Embodied AIcited by 153
  7. 2019Scene Memory Transformer for Embodied Agents in Long-Horizon Taskscited by 106
  8. 2016Playing FPS Games with Deep Reinforcement Learningcited by 95
  9. 2018Visual Representations for Semantic Target Driven Navigationcited by 89
  10. 2020Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigationcited by 71
  11. 2017MINOS: Multimodal Indoor Simulator for Navigation in Complex Environmentscited by 66
  12. 2018RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentationcited by 65
  13. 2017Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundarycited by 58
  14. 2020Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Viewscited by 57
  15. 2018Learning Plannable Representations with Causal InfoGANcited by 56
  16. 2018PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Makingcited by 51
  17. 2016Towards Deep Symbolic Reinforcement Learningcited by 42
  18. 2019Learning First-Order Symbolic Representations for Planning from the Structure of the State Spacecited by 38
  19. 2019Learning to Navigate Using Mid-Level Visual Priorscited by 25
  20. 2019Unsupervised Grounding of Plannable First-Order Logic Representation from Imagescited by 24
  21. 2020Exploiting Scene-specific Features for Object Goal Navigationcited by 20
  22. 2018Incremental learning abstract discrete planning domains and mappings to continuous perceptionscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 4; 2025: 1; 2026: 1.

9 papers.

  1. 2022Navigating to Objects in the Real Worldcited by 104
  2. 2025UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agentscited by 31
  3. 2024TANGO: Training-free Embodied AI Agents for Open-world Taskscited by 26
  4. 2023MOPA: Modular Object Navigation with PointGoal Agentscited by 11
  5. 2022Exploiting Proximity-Aware Tasks for Embodied Social Navigationcited by 6
  6. 2024Following the Human Thread in Social Navigationcited by 4
  7. 2024Personalized Embodied Navigation for Portable Object Findingcited by 3
  8. 2024Semantic Environment Atlas for Object-Goal Navigationcited by 0
  9. 2026SSTG-Nav: Metric-Grounded Spatial-Semantic Topological Graphs for Reusable Object Navigationcited by 0