As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Multiple point manufacturing problems of multi-DOF robots involve a series of inverse solutions to be solved in the joint space. Along with the increment of the manufacturing points, the inverse problem becomes more complex. In particular, the convergence is poor if all the joint variables locating the vast manufacturing points are directly encoded in the evolutionary optimization method. Therefore, partial optimization methods combined with a specific solution flow are proposed for the solver in the paper. Because of the multimodal characteristics, this paper uses a niche method, the Twin-space Crowding (TSC) method, to cooperate with the genetic algorithm (GA) to avoid the evolutionary premature condition. In order to verify the solution capability, the experiments are set up to adopt two different approaches to explore the manufacturing manipulations of industry robots. From the result, the proposed bidirectional reference manipulation (BRM) approach performs much better compared to the point-by-point inverse approach.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.