Publication

Feasible control of complex systems using automatic learning

Conference Article

Conference

International Conference on Informatics in Control, Automation and Robotics (ICINCO)

Edition

2nd

Pages

284-287

Doc link

http://www.icinco.org/Abstracts/2005/ICINCO2005_Abstracts.htm

File

Download the digital copy of the doc pdf document

Abstract

Robotic applications often involve dealing with complex dynamic systems. In these cases coping with control requirements with conventional techniques is hard to achieve and a big effort has to be done in the design and tuning of the control system. An alternative to conventional control techniques is the use of automatic learning systems that could learn control policies automatically, by means of the experience. But the amount of experience required in complex problems is intractable unless some generalization is performed. Many learning techniques have been proposed to deal with this challenge but the applicability of them in a complex control task is still difficult because of their bad learning convergence or insufficient generalization. In this work a new learning technique, that exploits a kind of generalization called categorization, is used in a complex control task. The results obtained show that it is possible to learn, in short time and with good convergence, a control policy that outperforms a classical PID control tuned for the specific task of controlling a manipulator with high inertia and variable load.

Categories

control theory, generalisation (artificial intelligence), intelligent robots, learning (artificial intelligence).

Author keywords

robot control, reinforcement learning, categorization

Scientific reference

A. Agostini and E. Celaya. Feasible control of complex systems using automatic learning, 2nd International Conference on Informatics in Control, Automation and Robotics, 2005, Barcelona, Espanya, pp. 284-287, 2005, INSTICC.