Online Direct Policy Search for Thruster Failure Recovery in Autonomous Underwater Vehicles

Post date: May 29, 2016 9:33:50 PM

Seyed Reza Ahmadzadeh, Matteo Leonetti, Petar Kormushev

Reference:

Seyed Reza Ahmadzadeh, Matteo Leonetti, Petar Kormushev, "Online Direct Policy Search for Thruster

Failure Recovery in Autonomous Underwater Vehicles", In Proc. 6th Intl Workshop on Evolutionary and

Reinforcement Learning for Autonomous Robot Systems (ERLARS 2013), 12th European Conf. on

Artificial Life (ECAL 2013), Taormina, Italy, 2-9 Sept. 2013.

Bibtex Entry:

@INPROCEEDINGS{ahmadzadeh2013online, TITLE={Online Direct Policy Search for Thruster Failure Recovery in Autonomous Underwater Vehicles}, AUTHOR={Ahmadzadeh, Seyed Reza and Leonetti, Matteo and Kormushev, Petar}, BOOKTITLE={6th International workshop on Evolutionary and Reinforcement Learning for Autonomous Robot System (ERLARS)}, YEAR={2013}, MONTH={September}, ADDRESS={Taormina, Italy} }

Abstract:

Autonomous underwater vehicles are prone to various factors that may lead a mission to fail and

cause unrecoverable damages. Even robust controllers cannot make sure that the robot is able to

navigate to a safe location in such situations. In this paper we propose an online learning method

for reconfiguring the controller, which tries to recover the robot and survive the mission using

the current asset of the system. The proposed method is framed in the reinforcement learning

setting, and in particular as a model-based direct policy search approach. Since learning on a

damaged vehicle would be impossible owing to time and energy constraints, learning is performed on

a model which is identified and kept updated online. We evaluate the applicability of our method

with different policy representations and learning algorithms, on the model of the Girona500

autonomous underwater vehicle.