Automatic generation of nonlinear optimal control laws for broom balancing using evolutionary programming

Author

Chellapilla, Kumar

Author_Institution

Dept. of Electr. & Comput. Eng., California Univ., San Diego, La Jolla, CA, USA

fYear

1998

fDate

4-9 May 1998

Firstpage

195

Lastpage

200

Abstract

The paper explores the use of mutatian operators with evolutionary programming (EP) to automatically generate time optimal “bang-bang” type control laws for the three dimensional broom balancing (inverted pendulum) problem. EP produces a time optimal nonlinear control strategy that takes the state variables as input and determines the direction of the “bang-bang” force to be applied. Preliminary results indicate that the control laws generated are capable of generalizing over previously unseen input states and compare well with nonlinear control laws that were generated using other evolutionary computation methods

Keywords

bang-bang control; nonlinear control systems; optimal control; optimisation; 3D broom balancing problem; automatic nonlinear optimal control law generation; bang-bang force direction; bang-bang type control laws; broom balancing; evolutionary computation methods; evolutionary programming; inverted pendulum problem; mutatian operators; state variables; time optimal nonlinear control strategy; unseen input states; Automatic control; Automatic generation control; Automatic programming; Control systems; Cost function; Evolutionary computation; Force control; Genetic mutations; Genetic programming; Optimal control;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on

Conference_Location

Anchorage, AK

Print_ISBN

0-7803-4869-9

Type

conf

DOI

10.1109/ICEC.1998.699500

Filename

699500