EUVIMEDEUVIMED entdecken
Crossref

Open‐Set Fault Diagnosis for Autonomous Underwater Vehicles Via Prototype Learning and Adaptive Mahalanobis Gating

Daxiong Ji, Lie Xu, Ye Pu, Marcelo H. Ang, Yan Zhi Tan

Journal of Field Robotics · 2026-12 · 43 (8) · 5240-5259

DOI: 10.1002/rob.70295 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Field Robotics, online erschienen am 08.07.2026. Verfasst von Daxiong Ji und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable fault diagnosis is essential for the safe operation of autonomous underwater vehicles (AUVs) in uncertain and dynamic environments. However, conventional closed‐set diagnosis methods are unable to handle previously unseen fault conditions, while existing open‐set techniques often struggle with low‐frequency, highly coupled multivariate telemetry. This paper proposes ProtoNet‐MDAG, a prototype‐based open‐set diagnosis framework for AUV fault recognition. Specifically, a dilated multi‐scale encoder is developed to extract discriminative temporal features from low‐frequency sensor streams, and a variance‐penalized prototypical learning strategy is introduced to enforce compact and well‐structured known‐class manifolds in the latent space. Based on this representation, an adaptive Mahalanobis distance gating mechanism is constructed to perform statistically calibrated open‐set rejection. Experimental results on a Haizhe AUV and a BlueROV‐class underwater robotic platform show that the proposed method achieves 97.19% and 89.12% accuracy, respectively. The results demonstrate strong unknown‐state rejection on the Haizhe AUV and competitive known‐class recognition on the BlueROV‐class platform, while also revealing that platform‐dependent distribution shift can weaken unknown‐state rejection in more heterogeneous operating conditions. Robustness tests on the Haizhe dataset further show that the framework remains stable under representative telemetry perturbations. These results demonstrate that the proposed framework provides an effective and reliable solution for open‐set fault diagnosis in underwater robotic systems.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Ji, D., Xu, L., Pu, Y., Ang, M. H., & Tan, Y. Z. (2026). Open‐Set Fault Diagnosis for Autonomous Underwater Vehicles Via Prototype Learning and Adaptive Mahalanobis Gating. Journal of Field Robotics, 43(8), 5240-5259. https://doi.org/10.1002/rob.70295

Vancouver

Ji D, Xu L, Pu Y, Ang MH, Tan YZ. Open‐Set Fault Diagnosis for Autonomous Underwater Vehicles Via Prototype Learning and Adaptive Mahalanobis Gating. Journal of Field Robotics. 2026;43(8):5240-5259. doi:10.1002/rob.70295

BibTeX
@article{Ji2026,
  author = {Ji, Daxiong and Xu, Lie and Pu, Ye and Ang, Marcelo H. and Tan, Yan Zhi},
  title = {Open‐Set Fault Diagnosis for Autonomous Underwater Vehicles Via Prototype Learning and Adaptive Mahalanobis Gating},
  journal = {Journal of Field Robotics},
  year = {2026},
  volume = {43},
  number = {8},
  pages = {5240--5259},
  doi = {10.1002/rob.70295}
}
Kostenlos starten →