mlsanityData to 7 Oct 2026

RobustNav: Towards Benchmarking Robustness in Embodied Navigation

arXiv 2106.04531 ↗First posted 8 Jun 2021cs.CV cs.ROcited by 52

Not on the map. Why?

Abstract (arXiv)

As an attempt towards assessing the robustness of embodied navigation agents, we propose RobustNav, a framework to quantify the performance of embodied navigation agents when exposed to a wide variety of visual - affecting RGB inputs - and dynamics - affecting transition dynamics - corruptions. Most recent efforts in visual navigation have typically focused on generalizing to novel target environments with similar appearance and dynamics characteristics. With RobustNav, we find that some standard embodied navigation agents significantly underperform (or fail) in the presence of visual or dynamics corruptions. We systematically analyze the kind of idiosyncrasies that emerge in the behavior of such agents when operating under corruptions. Finally, for visual corruptions in RobustNav, we show that while standard techniques to improve robustness such as data-augmentation and self-supervised adaptation offer some zero-shot resistance and improvements in navigation performance, there is still a long way to go in terms of recovering lost performance relative to clean "non-corrupt" settings, warranting more research in this direction. Our code is available at https://github.com/allenai/robustnav

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 49 of its 68 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

49 of 68 references.

References · 49

  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. 2017Mask R-CNNcited by 7,259
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  7. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  8. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  9. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  10. 2019Solving Rubik's Cube with a Robot Handcited by 699
  11. 2018On Evaluation of Embodied Navigation Agentscited by 526
  12. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 477
37 more
  1. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
  2. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 421
  3. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
  4. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  5. 2017Embodied Question Answeringcited by 335
  6. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  7. 2020Learning to Explore using Active Neural SLAMcited by 308
  8. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 293
  9. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 240
  10. 2020Understanding and Improving Fast Adversarial Trainingcited by 213
  11. 2017Cognitive Mapping and Planning for Visual Navigationcited by 209
  12. 2018Semi-parametric Topological Memory for Navigationcited by 203
  13. 2020RoboTHOR: An Open Simulation-to-Real Embodied AI Platformcited by 190
  14. 2019Self-Monitoring Navigation Agent via Auxiliary Progress Estimationcited by 173
  15. 2017IQA: Visual Question Answering in Interactive Environmentscited by 154
  16. 2020Self-Supervised Policy Adaptation during Deploymentcited by 121
  17. 2019Benchmarking the Robustness of Semantic Segmentation Modelscited by 111
  18. 2018Episodic Curiosity through Reachabilitycited by 109
  19. 2020Occupancy Anticipation for Efficient Exploration and Navigationcited by 104
  20. 2019Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learningcited by 102
  21. 2019Look, Listen, and Act: Towards Audio-Visual Embodied Navigationcited by 95
  22. 2020Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifierscited by 93
  23. 2018Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learningcited by 91
  24. 2020An empirical investigation of the challenges of real-world reinforcement learningcited by 75
  25. 2020AllenAct: A Framework for Embodied AI Researchcited by 54
  26. 2020Auxiliary Tasks Speed Up Learning PointGoal Navigationcited by 52
  27. 2020Data-efficient Domain Randomization with Bayesian Optimizationcited by 43
  28. 2019PyRobot: An Open-source Robotics Framework for Research and Benchmarkingcited by 39
  29. 2019Environment Probing Interaction Policiescited by 39
  30. 2020Bi-directional Domain Adaptation for Sim2Real Transfer of Embodied Navigation Agentscited by 33
  31. 2019SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigationcited by 29
  32. 2019Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?cited by 25
  33. 2020Identifying Statistical Bias in Dataset Replicationcited by 24
  34. 2020Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshopcited by 22
  35. 2019Single Episode Policy Transfer in Reinforcement Learningcited by 17
  36. 2020Generating Automatic Curricula via Self-Supervised Active Domain Randomizationcited by 7
  37. 2015Self-calibration of a differential wheeled robot using only a gyroscope and a distance sensorcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 7; 2023: 16; 2024: 9; 2025: 8; 2026: 5.

52 papers.

Sort:

By area:

  1. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  2. 2021Simple but Effective: CLIP Embeddings for Embodied AIcited by 191
  3. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  4. 20223D Common Corruptions and Data Augmentationcited by 120
  5. 2023AerialVLN: Vision-and-Language Navigation for UAVscited by 117
  6. 2021Learning to Map for Active Semantic Goal Navigationcited by 47
  7. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 47
  8. 2023Learning Navigational Visual Representations with Semantic Map Supervisioncited by 40
  9. 2024BadRobot: Jailbreaking Embodied LLM Agents in the Physical Worldcited by 40
  10. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  11. 2023Emergence of Maps in the Memories of Blind Navigation Agentscited by 31
  12. 2021Core Challenges in Embodied Vision-Language Planningcited by 30
38 more
  1. 2024SPIN: Simultaneous Perception, Interaction and Navigationcited by 27
  2. 2022Last-Mile Embodied Visual Navigationcited by 25
  3. 2022Phone2Proc: Bringing Robust Robots Into Our Chaotic Worldcited by 24
  4. 2021Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigationcited by 20
  5. 2024Zero-shot Object Navigation with Vision-Language Models Reasoningcited by 18
  6. 2023End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenoncited by 16
  7. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  8. 2023Adaptive Coordination in Social Embodied Rearrangementcited by 14
  9. 2023Benchmarking Robustness in Neural Radiance Fieldscited by 13
  10. 2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
  11. 2023SkyScenes: A Synthetic Dataset for Aerial Scene Understandingcited by 12
  12. 2025From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learningcited by 11
  13. 2023CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigationcited by 10
  14. 2023Exploitation-Guided Exploration for Semantic Embodied Navigationcited by 9
  15. 2022What do navigation agents learn about their environment?cited by 8
  16. 2021An in-depth experimental study of sensor usage and visual reasoning of robots navigating in real environmentscited by 6
  17. 2021Towards Disturbance-Free Visual Mobile Manipulationcited by 6
  18. 2023Learning with a Mole: Transferable latent spatial representations for navigation without reconstructioncited by 6
  19. 2024LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environmentscited by 6
  20. 2024Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigationcited by 6
  21. 2024Learning to navigate efficiently and precisely in real environmentscited by 5
  22. 2024Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agentscited by 5
  23. 2021Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistencycited by 3
  24. 2022MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agentscited by 3
  25. 2023Moving Forward by Moving Backward: Embedding Action Impact over Action Semanticscited by 3
  26. 2024Multi-Object Navigation in real environments using hybrid policiescited by 3
  27. 2025RoHOI: Robustness Benchmark for Human-Object Interaction Detectioncited by 3
  28. 2022Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learningcited by 2
  29. 2024Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performancecited by 2
  30. 2025RANa: Retrieval-Augmented Navigationcited by 2
  31. 2025What does really matter in image goal navigation?cited by 2
  32. 2025Kinaema: a recurrent sequence model for memory and pose in motioncited by 2
  33. 2026ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Modelscited by 2
  34. 2023AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Imagescited by 1
  35. 2025Harnessing Input-Adaptive Inference for Efficient VLNcited by 1
  36. 2026RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agentscited by 1
  37. 2023Core Challenges in Embodied Vision-Language Planningcited by 0
  38. 2026Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoningcited by 0

50 most cited of 52 All 52 (JSON)