Adaptive Neural Task Space Control for Robot Manipulators With Unknown and Closed Control Architecture Under Random Vibrations

Robot manipulators are now used in various domains and environments, where they can be subjected to random vibrations. Random vibrations mainly affect the torque control signal, a controller is therefore required designed for stabilization purposes. However, security or intellectual property protection reasons, most commercialized robots manufactured with unknown inaccessible interface such that user only design position/velocity controller. This paper proposes an adaptive task-space velocity free from inner controller’s structure exhibiting stochastic deterministic disturbances rejection deal these issues. To controller, exploits fact controllers use feedback term, it considers other terms as functions vector. cope disturbances, demonstrated excitation matrix linearly parameterized, therefore, direct method constructed. Using radial basis function neural network (RBF NN), indirect developed uncertainties. Through Lyapunov theory, proves all closed-loop signals bounded probability. The effectiveness of proposed approach further through simulation comparisons.