A robust position/force learning controller of manipulators via nonlinear H infinity control and neural networks

A new robust learning controller for simultaneous position and force contro l of uncertain constrained manipulators is presented, Using models of the m anipulator dynamics and environmental constraint, a task-space reduced-orde r position dynamics and an algebraic description for the interacting force between the manipulator and its environment are constructed. Based on this treatment, the robust nonlinear H infinity control approach and direct adap tive neural network (NN) technique are then integrated together. The role o f NN devices is to adaptively learn those manipulators' structured/unstruct ured uncertain dynamics as well as the uncertainties with environmental mod elling. Then, the effects on tracking performance attributable to the appro ximation errors of NN devices are attenuated to a prescribed level by the e mbedded nonlinear H infinity control. Whenever the adopted NN devices have the potential to effectively approximate those nonlinear mappings which are to be learned, then this new control scheme can be ultimately less conserv ative than its counterpart H infinity only position/force tracking control scheme. This is shown analytically in the form of theorem. Finally, a simul ation study for a constrained two-link planar manipulator is given. Simulat ion results indicate that the proposed adaptive H infinity NN position/forc e tracking controller performs better in both force and position tracking t asks than its counterpart H infinity only position/force tracking control s cheme.