Data-Driven Adaptive Modelling and Control for a Class of Discrete-Time Robotic Systems Based on a Generalized Jacobian Matrix Initialization

Data technology advances have increased in recent years, especially for robotic systems, order to apply data-driven modelling and control computations by only considering the input output signals’ relationship. For a approach, system is considered unknown. Thus, initialization values of play an important role obtain suitable estimation. This paper presents methodology initialize model using pseudo-Jacobian matrix algorithm estimate mobile manipulator robot. Once obtained, law proposed robot end-effector position tasks. To this end, novel neuro-fuzzy network as law, which needs update one parameter minimize error avoids chattering phenomenon. In addition, general stability analysis guarantees convergence estimation errors tuning closed-loop design parameters. The simulations results validate performance control.