Fuzzy learning grasping force controller for manipulator hand

A fuzzy set adaptive and learning control algorithm is developed. it is applied to grasping force control for a manipulator hand powered by a transistor PWM converter-fed servomotor. This robust manipulator hand can grip every object stably despite differences in compliance. This controller is applicable to systems whose dynamics changes time-variantly. The learning algorithm implemented `off-line´ is derived on the basis of sliding mode control. It gives strong error convergence properties proved by using the Lyapunov stability theorem, since it does not contain integrators as conventional adaptive mechanisms do