• Title/Summary/Keyword: Kyushu

Search Result 1,143, Processing Time 0.03 seconds

A Simple Robust Tracking Controller for Robot Manipulators Using Joint Position Measurements Contaminated by Noises

  • Wada, Makoto;Oya, Masahiro;Sagara, Shinichi;Kobayashi, Toshihiro
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2001.10a
    • /
    • pp.147.2-147
    • /
    • 2001
  • In this paper we develop a new robust trajectory tracking control scheme without using joint velocity. The proposed controller doesn´t employ adaptation, Therefore, the construction of the controller becomed very simple. Moreover, by using numerical simulation, we make sure the effectiveness of the proposed controller in the presence of quantization errors.

  • PDF

An Optimization Method Wsing Simulated Annealing for Universal Learning Network

  • Murata, Junichi;Tajiri, Akihito;Hirasawa, Kotaro;Ohbayashi, Masanao
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1995.10a
    • /
    • pp.183-186
    • /
    • 1995
  • A method is presented for optimization of Universal Learning Networks (ULN), where, together with gradient method, Simulated Annealing (SA) is employed to elude local minima. The effectiveness of the method is shown by its application to control of a crane system.

  • PDF

Neural network structure design using genetic algorithm

  • Murata, Junichi;Tanaka, Kei;Koga, Masaru;Hirasawa, Kotaro
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1995.10a
    • /
    • pp.187-190
    • /
    • 1995
  • A method is proposed which searches for optimal structures of Neural Networks (NN) using Genetic Algorithm (GA). The purpose of the method lies in not only finding an optimal NN structure but also leading us to the goal of self-organized control system that acquires its structure and its functionality by itself depending on its environment.

  • PDF

Control of a magnetic levitation system via feedback error learning

  • Hao, Shuang-Hui;Yang, Zi-Jiang;Tsuji, Teruo
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1993.10b
    • /
    • pp.345-350
    • /
    • 1993
  • This paper presents an on-line feedback error learning control algorithm for a magnetic levitation system. It will be shown that even in the case of abrupt changes of the system parameters and disturbanes, the control performance is still very satisfactory.

  • PDF