Stable adaptive controller design of robotic manipulators via neuro-fuzzy dynamic inversion

A stable adaptive controller design approach via neuro-fuzzy (NF) dynamic inversion is developed for the trajectory tracking of the robotic manipulator which can be identified in the Takagi-Sugeno (T-S) fuzzy framework with both structure and parameters identified through input/output (I/O) data from the robot control process. The dynamic NF (DNF) system aims to approximate the whole robot dynamics rather than its nonlinear components as is done by static neural networks (NNs). The dynamic inversion introduced for the controller design is constructed by the DNF system and will help the NF controller design because it does not require the assumption that the robot states should be on a compact set. The system stability and the convergence of tracking errors are guaranteed by Lyapunov stability theory, and the learning algorithm for the DNF system is obtained thereby. Finally, simulation studies are carried out to show the viability and effectiveness of the proposed control approach.