Detection of unanticipated faults for autonomous underwater vehicles using online topic models
Bellingham, James G.
MetadataShow full item record
KeywordAutonomous underwater vehicle (AUV); Autonomy; Fault detection and diagnosis; Topic modeling
For robots to succeed in complex missions, they must be reliable in the face of subsystem failures and environmental challenges. In this paper, we focus on autonomous underwater vehicle (AUV) autonomy as it pertains to self‐perception and health monitoring, and we argue that automatic classification of state‐sensor data represents an important enabling capability. We apply an online Bayesian nonparametric topic modeling technique to AUV sensor data in order to automatically characterize its performance patterns, then demonstrate how in combination with operator‐supplied semantic labels these patterns can be used for fault detection and diagnosis by means of a nearest‐neighbor classifier. The method is evaluated using data collected by the Monterey Bay Aquarium Research Institute's Tethys long‐range AUV in three separate field deployments. Our results show that the proposed method is able to accurately identify and characterize patterns that correspond to various states of the AUV, and classify faults at a high rate of correct detection with a very low false detection rate.
© The Author(s), 2017. This article is distributed under the terms of the Creative Commons Attribution License. The definitive version was published in Journal of Field Robotics 35 (2018): 705-716, doi:10.1002/rob.21771.
Suggested CitationArticle: Raanan, Ben-Yair, Bellingham, James G., Zhang, Yanwu, Kemp, Mathieu, Kieft, Brian, Singh, Hanumant, Girdhar, Yogesh, "Detection of unanticipated faults for autonomous underwater vehicles using online topic models", Journal of Field Robotics 35 (2018): 705-716, DOI:10.1002/rob.21771, https://hdl.handle.net/1912/10498
The following license files are associated with this item:
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 International
Showing items related by title, author, creator and subject.
Verification of a six-degree of freedom simulation model for the REMUS autonomous underwater vehicle Prestero, Timothy (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2001-09)Improving the performance of modular, low-cost autonomous underwater vehicles (AUVs) in such applications as long-range oceanographic survey, autonomous docking, and shallow-water mine countermeasures requires improving ...
Eustice, Ryan M. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2005-06)This thesis describes a vision-based, large-area, simultaneous localization and mapping (SLAM) algorithm that respects the low-overlap imagery constraints typical of autonomous underwater vehicles (AUVs) while exploiting ...
Efficient control based on a verified model for an autonomous underwater vehicle : a case study of Autonomous Benthic Explorer Anderson, Jamie M. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1992-02)The Autonomous Benthic Explorer (ABE) is an unmanned underwater vehicle being developed for scientific study of the deep ocean sea:floor. ABE will be completely autonomous from the surface which means that the lifetime ...