Processing math: 50%
Decentralized Tracking Optimization Control for Partially Unknown Fuzzy Interconnected Systems via Reinforcement Learning Method | IEEE Journals & Magazine | IEEE Xplore

Decentralized Tracking Optimization Control for Partially Unknown Fuzzy Interconnected Systems via Reinforcement Learning Method


Abstract:

In this article, a novel parallel tracking control optimization algorithm is first proposed for partially unknown fuzzy interconnected systems. In the existing standard o...Show More

Abstract:

In this article, a novel parallel tracking control optimization algorithm is first proposed for partially unknown fuzzy interconnected systems. In the existing standard optimal tracking control, the bounded or nonasymptotic stable reference trajectory will lead the feedback control not converging to zero, which causes the performance index infinite and invalid. By using the precompensation technique, in this article, the working feedback control is considered as a reconstructed dynamic with the virtual control and a new augmented fuzzy interconnected tracking system is built, thus that the performance index is valid for optimal control. Then, combining the integral reinforcement learning (RL) method and decentralized control design, the novel integral RL parallel algorithm is first developed to solve the tracking controls for interconnected systems, which relax the requirements of exact matrices information A_i^k and B_i^k during the solving process. Both the convergence and stability of the designed control optimization scheme are guaranteed by theorems. Finally, the new parallel tracking algorithm for interconnected systems is verified through the dual-manipulator coordination system and simulation results demonstrate the effectiveness.
Published in: IEEE Transactions on Fuzzy Systems ( Volume: 29, Issue: 4, April 2021)
Page(s): 917 - 926
Date of Publication: 13 January 2020

ISSN Information:

Funding Agency:


I. Introduction

During the recent decades, artificial intelligence and learning control algorithms have received significantly increasing attention and become one key issue of programmers and engineers from commercial and research fields [1]–[3]. Along with the environmental interactions in operational strategies, reinforcement learning (RL) technique can calculate the optimized policy with respect to the performance evaluation, and overcome the crucial problem, curse of dimensionality, in the traditional dynamic programming theory [4]–[6]. Based on the superiority and essence of RL methods, the adaptive dynamic programming (ADP) or integral RL technique is developed and widely applied in optimal control designs [7]–[10], which maps the relationship of control policies and performance index. However, it is still on preliminary stage and more considerable attention should be paid to implementing the RL techniques into challenging problems from engineering applications.

References

References is not available for this document.