Using neuroevolution for optimal impedance control

Author

De Gea, Jose ; Kirchner, Frank

Author_Institution

Robot. Group, Univ. of Bremen, Bremen

fYear

2008

fDate

15-18 Sept. 2008

Firstpage

1063

Lastpage

1066

Abstract

This paper describes the use of evolutionary algorithms to find an optimal solution for the parameters of an impedance controller represented as an artificial neural network (ANN). An impedance controller with force tracking capabilities has been evolved using evolutionary strategies which control the forces between a robotic manipulator and the environment. Simulation results show the controllerpsilas performance using a model of a two-link robot arm and a Hunt-Crossley non-linear model of the environment.

Keywords

electric impedance; electric variables control; evolutionary computation; force control; manipulators; neurocontrollers; nonlinear control systems; optimal control; Hunt-Crossley nonlinear model; artificial neural network; evolutionary algorithms; force control; force tracking capabilities; neuroevolution; optimal impedance control; robotic manipulator; two-link robot arm; Artificial neural networks; Control systems; Force control; Force measurement; Genetic mutations; Impedance; Intelligent robots; Manipulator dynamics; Neural networks; Optimal control;

fLanguage

English

Publisher

ieee

Conference_Titel

Emerging Technologies and Factory Automation, 2008. ETFA 2008. IEEE International Conference on

Conference_Location

Hamburg

Print_ISBN

978-1-4244-1505-2

Electronic_ISBN

978-1-4244-1506-9

Type

conf

DOI

10.1109/ETFA.2008.4638525

Filename

4638525