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

TLDR

The study aims to extend recurrent neural network control from single to multiple manipulators for cooperative kinematic coordination. The authors formulate the coordination as a constrained game, derive an implicit Nash equilibrium in dual space, and design a distributed RNN controller that drives the manipulators toward that equilibrium. Global stability and optimality of the proposed neural networks are proven theoretically, and simulations confirm their effectiveness.

Abstract

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.