Design of fuzzy system-fuzzy neural network-backstepping control for complex robot system

In this study, the control problem of complex robot system with uncertainties and disturbances is addressed. Fuzzy system-fuzzy neural network-backstepping control (FS-FNN-BSC) system is proposed, which can guarantee the accurate, stable and efficient control. First, the general dynamics model of robot is introduced briefly. Then, the design procedure of backstepping control (BSC) technique is presented, to make the best of the advantages of fuzzy system (FS) and fuzzy neural network (FNN) and compromise the accuracy and efficiency, the FS is adopted to approximate the modeling information, and the FNN is utilized to approximate and predict the non-modeling information, and the FS-FNN-BSC system is constructed. Moreover, based on the Lyapunov stability theorem, the stability of the FS-FNN-BSC is proved. To illustrate the correctness, practicality and generality of the proposed control method, the FS-FNN-BSC system is applied to the series robot (KUKA robot) and the parallel robot (Delta robot). And the superiority of the proposed FS-FNN-BSC strategy is highlighted by quantitative comparison with the existing intelligent control methods. (C) 2020 Elsevier Inc. All rights reserved.

Automated summary

This study addresses the control problem of complex robot systems with uncertainties and disturbances using the FS-FNN-BSC system, which guarantees accurate, stable and efficient control. By utilizing fuzzy system and fuzzy neural network technologies, modeling and non-modeling information is approximated and predicted, respectively. The stability of the FS-FNN-BSC system is proved based on the Lyapunov stability theorem, and its superiority is demonstrated through quantitative comparison with existing intelligent control methods on the series and parallel robots.