To main content

AUV Pipeline Following using Reinforcement Learning

Abstract

This paper analyzes the application of several reinforcement learning techniques for continuous state and action spaces to pipeline following for an autonomous underwater vehicle (AUV). Continuous space SARSA is compared to the actor-critic CACLA algorithm, and is also extended into a supervised reinforcement learning architecture. A novel exploration method using the skew-normal stochastic distribution is proposed, and evidence towards advantages in the case of tabula rasa exploration is presented. Results are validated on a realistic simulator of the AUV, and confirm the applicability of reinforcement learning to optimize pipeline following behavior.
Read the publication

Category

Academic chapter

Language

English

Author(s)

Affiliation

  • SINTEF Digital / Mathematics and Cybernetics
  • Norwegian University of Science and Technology
  • Western Norway University of Applied Sciences

Year

2010

Publisher

VDE Verlag GmbH

Book

Proceedings for the joint conference of ISR 2010, 41st International Symposium on Robotics, ROBOTIK 2010, 6th German Conference on Robotics

ISBN

9783800732739

Page(s)

310 - 317

View this publication at Norwegian Research Information Repository