A Fuzzy Cascaded Proportional-Derivative Controller for Under-actuated Flexible Joint Manipulators Using Bayesian Optimization

Abstract: This paper proposes a novel fuzzy cascaded Proportional-Derivative (PD) controller for under-actuated single-link flexible joint manipulators. The original flexible joint system is considered as two coupled $2^{nd}$-order sub-systems. The proposed controller is composed of two cascaded PD controllers and two fuzzy logic regulators (FLRs). The first (virtual) PD controller is used to generate desired control input that stabilizes the first $2^{nd}$-order sub-system. Solving the equation by considering the coupling terms as design variables, the reference signal is generated for the second sub-system. Then through simple compensation design, together with the second PD controller, the cascaded PD controller is derived. In order to further improve the performance, two FLRs are implemented that adaptively tune the parameters of PD controllers. Under natural assumptions, the cascaded fuzzy PD controller is proved to possess locally asymptotic stability. All the offline tuning processes are completed data-efficiently by Bayesian Optimization. The results in simulation illustrate the stability and validity of our proposed method. Besides, the idea of cascaded PD controller presented here may be extended as a novel control method for other under-actuated systems, and the stability analysis renders a new perspective towards the stability proof of all other fuzzy-enhanced PID controllers.