Abstract
Abstract Due to the increased complexity of the dynamics of robots with joint flexibility, many conventional robot control strategies are incapable to solve this problem effectively. To overcome this difficulty, a neural controller based on iterative learning has been proposed for the control of a flexible joint robot in this paper. The controller design is based the fact that most industrial robots perform repetitive tasks. The neural network for this purpose is trained as an inverse dynamic model of a flexible joint robot and is implemented as a feedforward controller. Our modifications of the back-propagation neural network [11] are employed in this study and result in a much better learning efficiency. A case study of a two-link flexible joint robot demonstrated that the proposed iterative neural learning controller can reduce the tracking errors after a few learning steps. Also, the proposed neural learning has advantages of easy implementation and requiring very little on-line computation.
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.
