Abstract
Error analysis and compensation of positioning is one of the basic problems for robot control. There are some limitations to study the error compensation either from the perspective of vision system or mechanism of the robot. Therefore, this paper studied the error compensation from both aspects with BP neural network model. Firstly, aiming at the depth values obtained by the vision system, a depth error database was established and based on BP neural network the depth error was effectively compensated within 5mm in MATLAB simulation. Secondly, aiming at the mechanism of a robot prototype the error compensation simulation based on BP neural network in MATLAB was carried out, and the simulation result showed that the error was within ±1mm after compensation. Thirdly, the correlative positioning error was defined and its error compensation simulation was carried out in MATLAB with the BP neural networks of the vision system and the mechanism; the simulation results showed that the correlative positioning error was approximately zero in this study. Finally, the error compensation of the robot mechanism based on the BP neural network was carried out on the robot prototype HNrobot2, and the experiment results showed that the positioning error was by 60% less, which was within 5mm.
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.
