Abstract
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.
Highlights
In recent years, in the medical and welfare fields, human resources with appropriate skills are required for treatment/surgical support for patients and long-term care for the elderly
In this research, we propose a feedforward controller based on Support Vector Regression (SVR), which is one of machine learning methods
In order to confirm the effectiveness of the proposed SVR-based feedforward controller, it is effective to compare the experimental results of the feedforward controller based on the dynamic model without the feedforward controller with the experimental results of the proposed method
Summary
In the medical and welfare fields, human resources with appropriate skills are required for treatment/surgical support for patients and long-term care for the elderly. Multi-joint viscoelastic properties are attracting attention as an elucidation of human motion control principles. Human arm multi-joint viscoelasticity is the characteristic of the arm joint when the human arm comes into contact with the outside world. It is thought that humans perform the desired movement by adjusting the multi-joint viscoelasticity so that the operating environment interacts with the arm and the object. Learning the work is learning the work procedure, and learning how to control the viscoelastic properties of the above-mentioned musculoskeletal system and contact with the outside world. Exploring the mechanism of adjusting the joint mechanical impedance of the musculoskeletal system is to elucidate the motor control principle of the brain that controls complex multi-joint movements, quantitatively understands the deterioration of movements caused by nerve and muscle disorders, and has human-friendly mechanical interfaces. It can be said that it is an important issue in the development of [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
