Zero-Shot Sim-to-Real 6-DoF Pose Estimation for Underwater Vehicles Based on Uncertainty-Guided Dense Correspondence
IEEE Transactions on Robotics · 2026 · 42 · 2691-2707
DOI: 10.1109/tro.2026.3701577 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2026. Verfasst von Qingbo Wei und 6 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Gefördert von: Liaoning Revitalization Talents Program.
Abstract (Originalsprache)
Accurate 6-DoF relative pose estimation is essential for multi-autonomous underwater vehicle (AUV) cooperative tasks. However, pose-annotated underwater data are difficult to obtain, limiting learning-based methods. In this article, we present ZUPose, a monocular pose estimator trained entirely on synthetic data and deployed directly in real underwater scenes. A key challenge is prediction noise introduced by the sim-to-real gap and underwater optical degradation. To address it, we adopt an algorithm-data co-design strategy. At the algorithm level, we develop an uncertainty-guided dense-correspondence framework in which the network jointly predicts dense correspondences and per-pixel uncertainty under a Laplace-based probabilistic formulation. The predicted uncertainty acts as a learned scale parameter to model correspondence noise and guide pose optimization. At the data level, we construct a physics-guided simulation pipeline to model underwater optical degradation and generate diverse synthetic images. In real turbid water, ZUPose achieves translation and rotation errors of 6.7 cm and 7.7$^\circ$, with both reduced by about half compared with the best-performing baseline. The method remains stable under overexposure and long-range observation, and dual-AUV navigation experiments further validate its practical viability.
Förderung
- Liaoning Revitalization Talents Program
Zitieren
APA
Wei, Q., Yang, Y., Zhou, X., Hu, Z., Fan, C., Zheng, Q., & Wang, Z. (2026). Zero-Shot Sim-to-Real 6-DoF Pose Estimation for Underwater Vehicles Based on Uncertainty-Guided Dense Correspondence. IEEE Transactions on Robotics, 42, 2691-2707. https://doi.org/10.1109/tro.2026.3701577
Vancouver
Wei Q, Yang Y, Zhou X, Hu Z, Fan C, Zheng Q, et al. Zero-Shot Sim-to-Real 6-DoF Pose Estimation for Underwater Vehicles Based on Uncertainty-Guided Dense Correspondence. IEEE Transactions on Robotics. 2026;42:2691-2707. doi:10.1109/tro.2026.3701577
BibTeX
@article{Wei2026,
author = {Wei, Qingbo and Yang, Yi and Zhou, Xingqun and Hu, Zhiqiang and Fan, Chuanzhi and Zheng, Quan and Wang, Zhichao},
title = {Zero-Shot Sim-to-Real 6-DoF Pose Estimation for Underwater Vehicles Based on Uncertainty-Guided Dense Correspondence},
journal = {IEEE Transactions on Robotics},
year = {2026},
volume = {42},
pages = {2691--2707},
doi = {10.1109/tro.2026.3701577}
}
EUVIMED