mlsanityData to 7 Oct 2026

Auxiliary Tasks and Exploration Enable ObjectNav

arXiv 2104.04112 ↗First posted 8 Apr 2021cs.CV cs.ROcited by 73

Not on the map. Why?

Abstract (arXiv)

ObjectGoal Navigation (ObjectNav) is an embodied task wherein agents are to navigate to an object instance in an unseen environment. Prior works have shown that end-to-end ObjectNav agents that use vanilla visual and recurrent modules, e.g. a CNN+RNN, perform poorly due to overfitting and sample inefficiency. This has motivated current state-of-the-art methods to mix analytic and learned components and operate on explicit spatial maps of the environment. We instead re-enable a generic learned agent by adding auxiliary learning tasks and an exploration reward. Our agents achieve 24.5% success and 8.1% SPL, a 37% and 8% relative improvement over prior state-of-the-art, respectively, on the Habitat ObjectNav Challenge. From our analysis, we propose that agents will act to simplify their visual inputs so as to smooth their RNN dynamics, and that auxiliary tasks reduce overfitting by minimizing effective RNN dimensionality; i.e. a performant ObjectNav agent that must maintain coherent plans over long horizons does so by learning smooth, low-dimensional recurrent dynamics. Site: https://joel99.github.io/objectnav/

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Builds on 28 of its 41 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

28 of 41 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  6. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  7. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  8. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  9. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  10. 2018On Evaluation of Embodied Navigation Agentscited by 526
  11. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 421
  12. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
16 more
  1. 2016Learning to Navigate in Complex Environmentscited by 192
  2. 2018Learning by Playing - Solving Sparse Reward Tasks from Scratchcited by 164
  3. 2020Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learningcited by 101
  4. 2018Visual Representations for Semantic Target Driven Navigationcited by 89
  5. 2018RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentationcited by 65
  6. 2020Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Viewscited by 57
  7. 2020An Exploration of Embodied Visual Explorationcited by 56
  8. 2020Auxiliary Tasks Speed Up Learning PointGoal Navigationcited by 52
  9. 2019Environmental drivers of systematicity and generalization in a situated agentcited by 50
  10. 2020SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigationcited by 43
  11. 2018Neural Predictive Belief Representationscited by 39
  12. 2019Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamicscited by 38
  13. 2020How recurrent networks implement contextual processing in sentiment analysiscited by 11
  14. 2020Probing Emergent Semantics in Predictive Agents via Question Answeringcited by 9
  15. 2020The geometry of integration in text classification RNNscited by 9
  16. 2020How to Train PointGoal Navigation Agents on a (Sample and Compute) Budgetcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 13; 2023: 13; 2024: 22; 2025: 15; 2026: 8.

73 papers.

Sort:

By area:

  1. 2021Simple but Effective: CLIP Embeddings for Embodied AIcited by 191
  2. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 162
  3. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 149
  4. 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigationcited by 126
  5. 2024SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigationcited by 106
  6. 2022Navigating to Objects in the Real Worldcited by 104
  7. 2024GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigationcited by 93
  8. 2022Offline Visual Representation Learning for Embodied Navigationcited by 74
  9. 2023OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNavcited by 68
  10. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 66
  11. 2024RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulationcited by 48
  12. 20223D-Aware Object Goal Navigation via Simultaneous Exploration and Identificationcited by 46
38 more
  1. 2024CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMscited by 32
  2. 2022Stubborn: A Strong Baseline for Indoor Object Navigationcited by 31
  3. 2025UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agentscited by 31
  4. 2024TANGO: Training-free Embodied AI Agents for Open-world Taskscited by 26
  5. 2022Last-Mile Embodied Visual Navigationcited by 25
  6. 2025NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigationcited by 23
  7. 2022PEANUT: Predicting and Navigating to Unseen Targetscited by 22
  8. 2023Selective Visual Representations Improve Convergence and Generalization for Embodied AIcited by 19
  9. 2022Ask4Help: Learning to Leverage an Expert for Embodied Taskscited by 18
  10. 2024Zero-shot Object Navigation with Vision-Language Models Reasoningcited by 18
  11. 2022Unbiased Directed Object Attention Graph for Object Navigationcited by 17
  12. 2023Object Goal Navigation with Recursive Implicit Mapscited by 16
  13. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  14. 2024SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Expertscited by 16
  15. 2024Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigationcited by 15
  16. 2024Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaborationcited by 14
  17. 2024Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language Modelscited by 12
  18. 2023MOPA: Modular Object Navigation with PointGoal Agentscited by 11
  19. 2025NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistantscited by 11
  20. 2023Exploitation-Guided Exploration for Semantic Embodied Navigationcited by 9
  21. 2025ForesightNav: Learning Scene Imagination for Efficient Explorationcited by 9
  22. 2022Multi-Robot Active Mapping via Neural Bipartite Graph Matchingcited by 8
  23. 2022What do navigation agents learn about their environment?cited by 8
  24. 2023Co-NavGPT: Multi-Robot Cooperative Visual Semantic Navigation Using Vision Language Modelscited by 8
  25. 2024Aligning Knowledge Graph with Visual Perception for Object-goal Navigationcited by 8
  26. 2025WoMAP: World Models For Embodied Open-Vocabulary Object Localizationcited by 8
  27. 2025PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memorycited by 8
  28. 2023Learning with a Mole: Transferable latent spatial representations for navigation without reconstructioncited by 6
  29. 2024Perception Matters: Enhancing Embodied AI with Uncertainty-Aware Semantic Segmentationcited by 6
  30. 2024IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigationcited by 6
  31. 2023Probable Object Location (POLo) Score Estimation for Efficient Object Goal Navigationcited by 4
  32. 2025CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graphcited by 4
  33. 2025Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal Navigationcited by 3
  34. 20263DGSNav: Enhancing Vision-Language Model Reasoning for Object Navigation via Active 3D Gaussian Splattingcited by 3
  35. 2023Interactive Semantic Map Representation for Skill-based Visual Object Navigationcited by 2
  36. 2023Visual Semantic Navigation with Real Robotscited by 2
  37. 2024A Landmark-Aware Visual Navigation Datasetcited by 2
  38. 2024Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigationcited by 2

50 most cited of 73 All 73 (JSON)