Learning cooperative assembly with the graph representation of a state-action space

Author

Ferch, Markus ; Höchsmann, Matthias ; Zhang, Jianwei

Author_Institution

Tech. Comput. Sci., Bielefeld Univ., Germany

Volume

1

fYear

2002

fDate

2002

Firstpage

990

Abstract

In this paper, we present a method for two robot manipulators to learn cooperative assembly tasks. A learning algorithm based on trial end error is used to find a sequence for each robot to assemble the goal aggregate. It is shown that a distributed learning method based on a Markov decision process is able to learn the sequences for the involved robots. A novel state-action graph is used to store the reinforcement values of the learning process. The approach is designed in a way that not only exact matches but also similar aggregates are accepted by the system.

Keywords

Markov processes; assembling; cooperative systems; graph theory; industrial manipulators; learning (artificial intelligence); multi-robot systems; state-space methods; Markov decision process; aggregate model; approximate graph matching; cooperative assembly task learning; distributed learning method; learning process reinforcement values; robot manipulators; sequence learning; state-action space graph representation; trial end error learning algorithm; Aggregates; Cameras; Cognitive robotics; Computer science; Manipulator dynamics; Orbital robotics; Robot vision systems; Robotic assembly; Space technology; State-space methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Robots and Systems, 2002. IEEE/RSJ International Conference on

Print_ISBN

0-7803-7398-7

Type

conf

DOI

10.1109/IRDS.2002.1041519

Filename

1041519