mlsanityData to 14 Oct 2026

Semantic Environment Atlas for Object-Goal Navigation

arXiv 2410.09081 ↗First posted 5 Oct 2024cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce the Semantic Environment Atlas (SEA), a novel mapping approach designed to enhance visual navigation capabilities of embodied agents. The SEA utilizes semantic graph maps that intricately delineate the relationships between places and objects, thereby enriching the navigational context. These maps are constructed from image observations and capture visual landmarks as sparsely encoded nodes within the environment. The SEA integrates multiple semantic maps from various environments, retaining a memory of place-object relationships, which proves invaluable for tasks such as visual localization and navigation. We developed navigation frameworks that effectively leverage the SEA, and we evaluated these frameworks through visual localization and object-goal navigation tasks. Our SEA-based localization framework significantly outperforms existing methods, accurately identifying locations from single query images. Experimental results in Habitat scenarios show that our method not only achieves a success rate of 39.0%, an improvement of 12.4% over the current state-of-the-art, but also maintains robustness under noisy odometry and actuation conditions, all while keeping computational costs low.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 34 references that are in the map. First posted on arXiv 5 Oct 2024.

Builds on

28 of 34 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2017Mask R-CNNcited by 7,277
  4. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  5. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  6. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  7. 2018On Evaluation of Embodied Navigation Agentscited by 547
  8. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  9. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 362
  10. 2020Learning to Explore using Active Neural SLAMcited by 316
  11. 2017Cognitive Mapping and Planning for Visual Navigationcited by 212
  12. 2019Learning Exploration Policies for Navigationcited by 116
16 more
  1. 2019Scene Memory Transformer for Embodied Agents in Long-Horizon Taskscited by 107
  2. 2018Learning to Navigate in Cities Without a Mapcited by 104
  3. 2017Neural Map: Structured Memory for Deep Reinforcement Learningcited by 90
  4. 2021Auxiliary Tasks and Exploration Enable ObjectNavcited by 74
  5. 2021No RL, No Simulation: Learning to Navigate without Navigatingcited by 65
  6. 2020Learning Object Relation Graph and Tentative Policy for Visual Navigationcited by 64
  7. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 52
  8. 2019Bayesian Relational Memory for Semantic Visual Navigationcited by 48
  9. 2022Topological Semantic Graph Memory for Image-Goal Navigationcited by 45
  10. 2019A Behavioral Approach to Visual Navigation with Graph Localization Networkscited by 40
  11. 2020Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigationcited by 34
  12. 2021Hierarchical Object-to-Zone Graph for Object Navigationcited by 34
  13. 2018Visual Memory for Robust Path Followingcited by 16
  14. 2019Embodied Visual Recognitioncited by 9
  15. 2019EMPNet: Neural Localisation and Mapping Using Embedded Memory Pointscited by 9
  16. 2022Online Learning of Reusable Abstract Models for Object Goal Navigationcited by 9

Built on by

Not cited yet.