NavTrust: Benchmarking Trustworthiness for Embodied Navigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Huaide, Chaudhary, Yash, Wang, Yuping, Wang, Zehao, Sharma, Raghav, Mehta, Manan, Zhou, Yang, Sun, Lichao, Fan, Zhiwen, Tu, Zhengzhong, Li, Jiachen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912974593064960
author Jiang, Huaide
Chaudhary, Yash
Wang, Yuping
Wang, Zehao
Sharma, Raghav
Mehta, Manan
Zhou, Yang
Sun, Lichao
Fan, Zhiwen
Tu, Zhengzhong
Li, Jiachen
author_facet Jiang, Huaide
Chaudhary, Yash
Wang, Yuping
Wang, Zehao
Sharma, Raghav
Mehta, Manan
Zhou, Yang
Sun, Lichao
Fan, Zhiwen
Tu, Zhengzhong
Li, Jiachen
contents 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 instructions 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19229
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NavTrust: Benchmarking Trustworthiness for Embodied Navigation
Jiang, Huaide
Chaudhary, Yash
Wang, Yuping
Wang, Zehao
Sharma, Raghav
Mehta, Manan
Zhou, Yang
Sun, Lichao
Fan, Zhiwen
Tu, Zhengzhong
Li, Jiachen
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Systems and Control
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 instructions 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.
title NavTrust: Benchmarking Trustworthiness for Embodied Navigation
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Systems and Control
url https://arxiv.org/abs/2603.19229