Position-based visual servoing of manipulator using model predictive control

View at publisher Summarise with VIRAT
Authors: Juan Wang, Sibin Zhang, Yutong Du, Peng Li
Cited by: 0
References: 27

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In order to solve the problem of acquiring the position of the target and tracking control of the target, this paper designs a visual servo system for manipulator position based on model predictive control. First, the initial camera position value is obtained by solving the relative position relationship between the camera and the target by the Perspective-n-Point algorithm. Second, the Levenberg–Marquardt algorithm is adopted to reduce the influence of noise and other factors on measurement accuracy. It is adopted to optimize the camera position by minimizing the reprojection error. Third, considering the motion space constraints during the movement of the manipulator, the model predictive control method is employed to solve the visual servo control problem with constraints. The monocular vision system is used to measure the position of the end of the manipulator and the target to provide feedback for the model predictive control. Finally, the simulation experiment is provided to verify the validity and effectiveness of the proposed method.

Fields of Study & Subjects

Advanced Vision and Imaging Advanced Control Systems Optimization Robot Manipulation and Learning

Publication details

Journal / source
Transactions of the Institute of Measurement and Control
Publication date
25 March 2026
Language
EN