Intelligent power assistant manipulator usable for diseaster

Yingda Dai, Masami Konishi, Jun Imai

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This paper presents experiments on assistant manipulator system for solving the problem of rescue activities. A dynamic neural network model was implemented in a humanoid robot manipulator, based on the recurrent neural network model (RNN model) evaluated by agent parts. The proposed robot manipulator system with dual 2-dof robot arms, can be tele-operated by human and are able to move cooperatively. Human operates the master arm that enlarge the action of human, and the slave arm based on the agent system follows the master cooperatively. Each joints of the manipulator are respectively provided a learning method to optimize its movement by training RNN model. The experiments showed that the proposed RNN model can regenerate each pattern synchronously with the master manipulator after the robot multiple trajectory movement. And the simulation results show the effectiveness of the approach, and that the proposed RNN model can successfully learn the inverse dynamics of robot manipulators, performing accurate tracking for a general trajectory.

Original languageEnglish
Title of host publication2006 SICE-ICASE International Joint Conference
Number of pages6
Publication statusPublished - Dec 1 2006
Event2006 SICE-ICASE International Joint Conference - Busan, Korea, Republic of
Duration: Oct 18 2006Oct 21 2006

Publication series

Name2006 SICE-ICASE International Joint Conference


Other2006 SICE-ICASE International Joint Conference
Country/TerritoryKorea, Republic of


  • Agent system
  • Cooperative motion control
  • Master-slave manipulator
  • Power assistant
  • Recurrent neural network (RNN)

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering


Dive into the research topics of 'Intelligent power assistant manipulator usable for diseaster'. Together they form a unique fingerprint.

Cite this