mlsanityData to 7 Oct 2026

Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation

arXiv 2302.01520 ↗First posted 3 Feb 2023cs.RO cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together. Based on the MAD paradigm, we design a multiple thinking (MT) model that leverages distinct thinking to abstract various meta-abilities. Our method decouples meta-abilities from three aspects: input, encoding, and reward while employing the multiple thinking collaboration (MTC) module to promote mutual cooperation between thinking. MAD introduces a novel qualitative and quantitative interpretability system for object navigation. Through extensive experiments on AI2-Thor and RoboTHOR, we demonstrate that our method outperforms state-of-the-art (SOTA) methods on both typical and zero-shot object navigation tasks.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 34 of its 52 references that are in the map. First posted on arXiv 3 Feb 2023.

Builds on

34 of 52 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  5. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  6. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
  7. 2018On Evaluation of Embodied Navigation Agentscited by 526
  8. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  9. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 421
  10. 2020Learning to Explore using Active Neural SLAMcited by 308
  11. 2021Simple but Effective: CLIP Embeddings for Embodied AIcited by 191
  12. 2020RoboTHOR: An Open Simulation-to-Real Embodied AI Platformcited by 190
22 more
  1. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 187
  2. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 149
  3. 2018Visual Semantic Navigation using Scene Priorscited by 127
  4. 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 118
  5. 2018Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learningcited by 91
  6. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 66
  7. 2020Learning Object Relation Graph and Tentative Policy for Visual Navigationcited by 62
  8. 2021VTNet: Visual Transformer Network for Object Goal Navigationcited by 50
  9. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 50
  10. 2021Scene-Intuitive Agent for Remote Embodied Visual Groundingcited by 49
  11. 2019Bayesian Relational Memory for Semantic Visual Navigationcited by 48
  12. 2020SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigationcited by 43
  13. 2021Hierarchical Object-to-Zone Graph for Object Navigationcited by 34
  14. 2021The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Designcited by 33
  15. 2022Zero-shot object goal visual navigationcited by 29
  16. 2020What they do when in doubt: a study of inductive biases in seq2seq learnerscited by 20
  17. 2022Object Memory Transformer for Object Goal Navigationcited by 19
  18. 2022Search for or Navigate to? Dual Adaptive Thinking for Object Navigationcited by 19
  19. 2022Unbiased Directed Object Attention Graph for Object Navigationcited by 17
  20. 2021A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applicationscited by 14
  21. 2021Towards Optimal Correlational Object Searchcited by 14
  22. 2022Zero-shot Active Visual Search (ZAVIS): Intelligent Object Search for Robotic Assistantscited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 5; 2025: 2.

8 papers.

  1. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  2. 2025Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparitiescited by 24
  3. 2023A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigationcited by 18
  4. 2024MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigationcited by 6
  5. 2024Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigationcited by 0
  6. 2024Leveraging Unknown Objects to Construct Labeled-Unlabeled Meta-Relationships for Zero-Shot Object Navigationcited by 0
  7. 2024Efficient Strategy Learning by Decoupling Searching and Pathfinding for Object Navigationcited by 0
  8. 2025GRIP: A Unified Framework for Grid-Based Relay and Co-Occurrence-Aware Planning in Dynamic Environmentscited by 0