mlsanityData to 7 Oct 2026

NavTrust: Benchmarking Trustworthiness for Embodied Navigation

arXiv 2603.19229 ↗First posted 19 Mar 2026cs.RO cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

There are two major categories of embodied navigation: Vision-Language Navigation (VLN), where agents navigate by following natural language instructions; and Object-Goal Navigation (OGN), where agents navigate to a specified target object. However, existing work primarily evaluates model performance under nominal conditions, overlooking the potential corruptions that arise in real-world settings. To address this gap, we present NavTrust, a unified benchmark that systematically corrupts input modalities, including RGB, depth, and instructions, in realistic scenarios and evaluates their impact on navigation performance. To our best knowledge, NavTrust is the first benchmark that exposes embodied navigation agents to diverse RGB-Depth corruptions and instruction variations in a unified framework. Our extensive evaluation of seven state-of-the-art approaches reveals substantial performance degradation under realistic corruptions, which highlights critical robustness gaps and provides a roadmap toward more trustworthy embodied navigation systems. Furthermore, we systematically evaluate four distinct mitigation strategies to enhance robustness against RGB-Depth and instruction corruptions. Our base models include Uni-NaVid and ETPNav. We deployed them on a real mobile robot and observed improved robustness to corruptions. The project website is: https://navtrust.github.io/.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 41 references that are in the map. First posted on arXiv 19 Mar 2026.

Builds on

34 of 41 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  7. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  8. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  9. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 579
  10. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 429
  11. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 401
  12. 2020Learning to Explore using Active Neural SLAMcited by 308
22 more
  1. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 222
  2. 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agentscited by 213
  3. 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigationcited by 201
  4. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 165
  5. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 146
  6. 2021Waypoint Models for Instruction-guided Navigation in Continuous Environmentscited by 125
  7. 2023L3MVN: Leveraging Large Language Models for Visual Target Navigationcited by 118
  8. 2022EnvEdit: Environment Editing for Vision-and-Language Navigationcited by 83
  9. 2024PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Taskscited by 78
  10. 2021Auxiliary Tasks and Exploration Enable ObjectNavcited by 73
  11. 2021Physics-based Noise Modeling for Extreme Low-light Photographycited by 67
  12. 2021RobustNav: Towards Benchmarking Robustness in Embodied Navigationcited by 52
  13. 2025WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigationcited by 42
  14. 2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
  15. 2024Prioritized Semantic Learning for Zero-shot Instance Navigationcited by 30
  16. 2024Mind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigationcited by 11
  17. 2025On the robustness of multimodal language model towards distractionscited by 9
  18. 2025View Invariant Learning for Vision-Language Navigation in Continuous Environmentscited by 6
  19. 2024Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attackscited by 5
  20. 2023Robust Navigation with Cross-Modal Fusion and Knowledge Transfercited by 2
  21. 2024ON as ALC: Active Loop Closing Object Goal Navigationcited by 1
  22. 2024Noise Analysis and Modeling of the PMD Flexx2 Depth Camera for Robotic Applicationscited by 1

Built on by

Not cited yet.