Peter King
University of Tasmania

“Teach and repeat path following for an autonomous underwater vehicle”

Department of Computer Science
Thursday, June 21, 2018, 11:00 a.m., Room EN-2022

---

Abstract

This talk 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 path that the AUV can use to re-navigate, 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.

Over a series of field trials, this system demonstrated online control of an AUV in the oceanenvironment, 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.

This work will see application for AUVs operating in unexplored environments, such as beneath ice shelves.