PENS Repository

A Study of Interactive Genetic Algorithm for Human-Friendly Trajectory Generation of a Robot Arm

Sulistijono, Indra Adji and Kubota, Naoyuki (2003) A Study of Interactive Genetic Algorithm for Human-Friendly Trajectory Generation of a Robot Arm. Machine Intelligence & Robotic Control (MIROC), 5 (4). pp. 129-135. ISSN 1345-2681

This is the latest version of this item.

[img]
Preview
PDF (Journal of Machine Intelligence & Robotic Control (MIROC)) - Published Version
Available under License Creative Commons Public Domain Dedication.

Download (2769Kb) | Preview

    Abstract

    This work deals with human-friendly trajectory generation of a robot arm. Various methods for the trajectory generation have been proposed so far, but robots must deal with environments including human operators. In this situation, the robot should take a suitable action/motion to the individual operator. This work applies an interactive genetic algorithm for the trajectory generation using human evaluation. Basically human evaluation is very important for generating robotic behavior, but the detail of the human evaluation is not clear. Therefore, the robot must estimate human evaluation through the optimization process, and use a state-value function used often in reinforcement learning. Furthermore, the effectiveness of the proposed method through some experiments of the robot arm will be discussed.

    Item Type: Article
    Uncontrolled Keywords: human-friendly arm robot, interactive genetic algorithm, human evaluation, state value function
    Subjects: T Technology > TJ Mechanical engineering and machinery
    Divisions: Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
    Depositing User: Dr.Eng. Indra Adji Sulistijono
    Date Deposited: 21 Mar 2012 09:10
    Last Modified: 29 Mar 2012 14:22
    URI: http://repo.pens.ac.id/id/eprint/1653

    Available Versions of this Item

    Actions (login required)

    View Item