Nonlinear Intelligent Control of Two Link Robot Arm by Considering Human Voluntary Components

Sensors

Yuanhong Xu¹  Shotaro Kubota¹  Mingcong Deng¹ 

[1] Department of Electrical and Electronic Engineering (The Graduate School of Engineering), Tokyo University of Agriculture and Technology, 2-24-16 Nakacho, Tokyo 184-8588, Japan;

关键词: nonlinear intelligent control;    support vector regression;    feedforward control;    human arm viscoelastic;   

DOI  :  10.3390/s22041424

来源: DOAJ

【 摘 要 】

This paper proposes a nonlinear intelligent control of a two link robot arm by considering human voluntary components. In general, human arm viscoelastic properties are regulated in different manners according to various task requirements. The viscoelasticity consists of joint stiffness and viscosity. The research of the viscoelasticity can improve the development of industrial robots, rehabilitation and sports etc. So far, some results have been shown using filtered human arm viscoelasticity measurements. That is, human motor command is removed. As a result, the dynamics of human voluntary component during movements is omitted. In this paper, based on the feedforward characteristics of human multi joint arm, a model is obtained by considering human voluntary components using a support vector regression technique. By employing the learned model, a nonlinear intelligent control of two link robot arm is proposed. Experimental results confirm the effectiveness of this proposal.

【 授权许可】

Unknown