Generation of evaluation function for robot force control using genetic programming

Kazuo Kiguchi, Keigo Watanabe, Kiyotaka Izumi, Toshio Fukuda

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Force control is one of the most important and fundamental tasks of robot manipulators. It is known that a neuro-fuzzy control method is one of the best control methods for robot force control. Usually, the neuro-fuzzy controller is trained to minimize the error function. However, unexpected response such as overshooting or oscillation might occur as far as only the control error is evaluated, since the dynamics of the robot and the environment is not reflected in the evaluation function. In this paper, we propose an effective evaluation function generation method using genetic programming. The effectiveness of the proposed method was evaluated by simulation.

Original languageEnglish
Pages2767-2771
Number of pages5
Publication statusPublished - Dec 1 2001
Externally publishedYes
EventJoint 9th IFSA World Congress and 20th NAFIPS International Conference - Vancouver, BC, Canada
Duration: Jul 25 2001Jul 28 2001

Other

OtherJoint 9th IFSA World Congress and 20th NAFIPS International Conference
CountryCanada
CityVancouver, BC
Period7/25/017/28/01

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Fingerprint Dive into the research topics of 'Generation of evaluation function for robot force control using genetic programming'. Together they form a unique fingerprint.

  • Cite this

    Kiguchi, K., Watanabe, K., Izumi, K., & Fukuda, T. (2001). Generation of evaluation function for robot force control using genetic programming. 2767-2771. Paper presented at Joint 9th IFSA World Congress and 20th NAFIPS International Conference, Vancouver, BC, Canada.