Η∞ Adaptive Neural Network Position/force Learning Control of Rled Manipulators

A new robust learning controller for simultaneous position/force control of constrained uncertain rigid-link electrically-driven (RLED) manipulators is presented. In the controller, a robust nonlinear control design and the direct adaptive neural networks (NN) technique are integrated together. Firstly, NN devices are used to adaptively learn those RLED manipulator’s structured/unstructured uncertain dynamics and the uncertainties with environmental modelling. Then, the unfavorable effects on the tracking performance due to the approximation errors of NN devices are attenuated to a prescribed level by the embedded nonlinear control. Via a tuning function like design, each unknown mapping, in the system model used, can be learned by only one set of NN devices. This thrift usage of NN devices is a very desired feature in reducing hardware implementation cost. ∞ H