Distributed Recurrent Neural Networks for Cooperative Control of Manipulators: A Game-Theoretic Perspective

• Published in: IEEE transaction on neural networks and learning systems Vol. 28; no. 2; pp. 415 - 426
• Main Authors: Shuai Li, Jinbo He, Yangming Li, Rafique, Muhammad Usman
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computer simulation; Control stability; Cooperative Behavior; Cooperative control; Distributed control; dual neural network; End effectors; Game Theory; kinematic resolution; Kinematics; Manipulator dynamics; Manipulators; neural network; Neural networks; Neural Networks (Computer); Optimization; recurrent neural network; Recurrent neural networks; Redundancy; redundant manipulator; Robot arms
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2016.2516565

This paper considers cooperative kinematic control of multiple manipulators using distributed recurrent neural networks and provides a tractable way to extend existing results on individual manipulator control using recurrent neural networks to the scenario with the coordination of multiple manipulators. The problem is formulated as a constrained game, where energy consumptions for each manipulator, saturations of control input, and the topological constraints imposed by the communication graph are considered. An implicit form of the Nash equilibrium for the game is obtained by converting the problem into its dual space. Then, a distributed dynamic controller based on recurrent neural networks is devised to drive the system toward the desired Nash equilibrium to seek the optimal solution of the cooperative control. Global stability and solution optimality of the proposed neural networks are proved in the theory. Simulations demonstrate the effectiveness of the proposed method.