mlsanityData to 14 Oct 2026

Search for or Navigate to? Dual Adaptive Thinking for Object Navigation

arXiv 2208.00553 ↗First posted 1 Aug 2022cs.AI cs.ROcited by 20

Not on the map. Why?

Abstract (arXiv)

"Search for" or "Navigate to"? When finding an object, the two choices always come up in our subconscious mind. Before seeing the target, we search for the target based on experience. After seeing the target, we remember the target location and navigate to. However, recently methods in object navigation field almost only consider using object association to enhance "search for" phase while neglect the importance of "navigate to" phase. Therefore, this paper proposes the dual adaptive thinking (DAT) method to flexibly adjust the different thinking strategies at different navigation stages. Dual thinking includes search thinking with the object association ability and navigation thinking with the target location ability. To make the navigation thinking more effective, we design the target-oriented memory graph (TOMG) to store historical target information and the target-aware multi-scale aggregator (TAMSA) to encode the relative target position. We assess our methods on the AI2-Thor dataset. Compared with the state-of-the-art (SOTA) method, our method reports 10.8%, 21.5% and 15.7% increase in success rate (SR), success weighted by path length (SPL) and success weighted by navigation efficiency (SNE), respectively.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 1 Aug 2022.

Builds on

34 of 49 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  7. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  8. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  9. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  10. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  11. 2018On Evaluation of Embodied Navigation Agentscited by 547
  12. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
22 more
  1. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  2. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  3. 2017Embodied Question Answeringcited by 336
  4. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  5. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 244
  6. 2019Understanding and Improving Layer Normalizationcited by 217
  7. 2016Learning to Navigate in Complex Environmentscited by 198
  8. 2020RoboTHOR: An Open Simulation-to-Real Embodied AI Platformcited by 193
  9. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 150
  10. 2018Visual Semantic Navigation using Scene Priorscited by 128
  11. 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 119
  12. 2018Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learningcited by 93
  13. 2020Learning Object Relation Graph and Tentative Policy for Visual Navigationcited by 64
  14. 2021VTNet: Visual Transformer Network for Object Goal Navigationcited by 51
  15. 2020SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigationcited by 44
  16. 2022Continuous Scene Representations for Embodied AIcited by 39
  17. 2021Hierarchical Object-to-Zone Graph for Object Navigationcited by 34
  18. 2022Zero-shot object goal visual navigationcited by 31
  19. 2022Object Memory Transformer for Object Goal Navigationcited by 20
  20. 2022Unbiased Directed Object Attention Graph for Object Navigationcited by 18
  21. 2021Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledgecited by 10
  22. 2021Learning Embeddings that Capture Spatial Semantics for Indoor Navigationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 6; 2025: 2; 2026: 7.

20 papers.

Sort:

By area:

  1. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  2. 2024CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMscited by 33
  3. 2023A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigationcited by 18
  4. 2023Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigationcited by 8
  5. 2023PASTS: Progress-Aware Spatio-Temporal Transformer Speaker For Vision-and-Language Navigationcited by 8
  6. 2025RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Modelscited by 4
  7. 2023Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidancecited by 3
  8. 20263DGSNav: Enhancing Vision-Language Model Reasoning for Object Navigation via Active 3D Gaussian Splattingcited by 3
  9. 2023Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigationcited by 2
  10. 2025ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learningcited by 2
  11. 2026TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigationcited by 1
  12. 2026A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigationcited by 1
8 more
  1. 2024Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigationcited by 0
  2. 2024Temporal-Spatial Object Relations Modeling for Vision-and-Language Navigationcited by 0
  3. 2024Leveraging Unknown Objects to Construct Labeled-Unlabeled Meta-Relationships for Zero-Shot Object Navigationcited by 0
  4. 2024Efficient Strategy Learning by Decoupling Searching and Pathfinding for Object Navigationcited by 0
  5. 2026Visual Marker Search for Autonomous Drone Landing in Diverse Urban Environmentscited by 0
  6. 2026AION: Aerial Indoor Object-Goal Navigation Using Dual-Policy Reinforcement Learningcited by 0
  7. 2026SR-Nav: Spatial Relationships Matter for Zero-shot Object Goal Navigationcited by 0
  8. 2026EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigationcited by 0