Title :
Design of semi-decentralized control laws for distributed-air-jet micromanipulators by reinforcement learning
Author :
Matignon, Laëtitia ; Laurent, Guillaume J. ; Fort-Piat, Nadine Le
Author_Institution :
FEMTOST, Univ. de Franche-Comte, Besancon, France
Abstract :
Recently, a great deal of interest has been developed in learning in multi-agent systems to achieve decentralized control. Machine learning is a popular approach to find controllers that are tailored exactly to the system without any prior model. In this paper, we propose a semi-decentralized reinforcement learning control approach in order to position and convey an object on a contact-free MEMS-based distributed-manipulation system. The experimental results validate the semi-decentralized reinforcement learning method as a way to design control laws for such distributed systems.
Keywords :
distributed control; jets; learning (artificial intelligence); micromanipulators; micromechanical devices; multi-agent systems; MEMS based distributed manipulation system; distributed air jet micromanipulators; distributed systems; machine learning; multi agent systems; reinforcement learning; semi decentralized control laws; semi decentralized reinforcement learning control; Actuators; Control systems; Distributed control; Electrodes; Machine learning; Micromanipulators; Microvalves; Multiagent systems; Open loop systems; Sorting;
Conference_Titel :
Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on
Conference_Location :
St. Louis, MO
Print_ISBN :
978-1-4244-3803-7
Electronic_ISBN :
978-1-4244-3804-4
DOI :
10.1109/IROS.2009.5353902
