Repetitive Motion Planning of Kinematically Redundant Manipulators Using LVI-based Primal-Dual Neural Network

• Published in: 2007 International Conference on Mechatronics and Automation pp. 3138 - 3143
• Main Authors: Yunong Zhang, Xuanjiao Lv, Zhi Yang, Zhonghua Li
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2007
• Subjects: Automation; drift-free; joint physical limits; kine-matically redundant manipulators; Kinematics; Linear programming; LVI-based primal-dual neural network; Manipulator dynamics; Mechatronics; Motion planning; Neural networks; Quadratic programming; repetitive motion planning; Robots; Sun
• ISBN: 9781424408276; 142440827X
• ISSN: 2152-7431
• DOI: 10.1109/ICMA.2007.4304063

In this paper, a primal-dual neural network based on linear variational inequalities (LVI) is presented for online repetitive motion planning of kinematically redundant manipulators. To do this, a drift-free criterion is exploited. In addition, the physical constraints such as joint limits and joint velocity limits are incorporated into the problem formulation of such a scheme. The scheme is finally reformulated as a quadratic programming (QP) problem. As a QP real-time solver, the LVI-based primal-dual neural network is designed based on the QP-LVI conversion and Karush-Kuhn-Tucker (KKT) conditions. With simple piecewise-linear dynamics and global (exponential) convergence to optimal solutions, it can handle general QP and linear programming (LP) problems in the same inverse-free manner. The repetitive motion planning scheme and the LVI-based primal-dual neural network are simulated based on PA 10 robot manipulator with effectiveness demonstrated.