Open Access Repository

Teach-and-repeat path following for an autonomous underwater vehicle

Downloads

Downloads per month over past year

King, PD ORCID: 0000-0001-9436-0936, Vardy, A and Forrest, AL ORCID: 0000-0002-7853-9765 2018 , 'Teach-and-repeat path following for an autonomous underwater vehicle' , Journal of Field Robotics , pp. 1-16 , doi: 10.1002/rob.21776.

[img] PDF
ROB-17-0049-R1...pdf | Document not available for request/download
Full text restricted until 8 March 2019.

Abstract

This paper presents a teach-and-repeat path-following method for an autonomous underwater vehicle (AUV) navigating long distances in environments where external navigation aides are denied. This method utilizes sonar images to construct a series of reference views along a path,stored as a topological map. The AUV can then renavigate along this path, either to return to the start location or to repeat the route. Utilizing unique assumptions about the sonar image-generation process, this system exhibits robust image-matching capabilities, providing observations to a discrete Bayesian filter that maintains an estimate of progress along the path. Image-matching also provides an estimate of offset from the path, allowing the AUV to correct its heading and effectively close the gap. Over a series of field trials, this system demonstrated online control of an AUV in the ocean environment of Holyrood Arm, Newfoundland and Labrador, Canada. The system was implemented on an International Submarine Engineering Ltd. Explorer AUV and per-formed multiple path completions over both a 1 and 5 km track. These trials illustrated an AUV operating in a fully autonomous mode, in which navigation was driven solely by sensor feedback and adaptive control. Path-following performance was as desired, with the AUV maintaining close offset to the path.

Item Type: Article
Authors/Creators:King, PD and Vardy, A and Forrest, AL
Keywords: navigation, autonomy, AUV, sonar, computer vision
Journal or Publication Title: Journal of Field Robotics
Publisher: John Wiley & Sons, Inc.
ISSN: 1556-4959
DOI / ID Number: 10.1002/rob.21776
Copyright Information:

Copyright 2018 Wiley Periodicals

Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page
TOP