Control of Flexible-link Manipulators Using Neural Networks addresses the difficulties that arise in controlling the end-point of a manipulator that has a significant amount of structural flexibility in its links. The non-minimum phase characteristic, coupling effects, nonlinearities, parameter variations and unmodeled dynamics in such a manipulator all contribute to these difficulties. Control strategies that ignore these uncertainties and nonlinearities generally fail to provide satisfactory closed-loop performance. This monograph develops and experimentally evaluates several intelligent (neural network based) control techniques to address the problem of controlling the end-point of flexible-link manipulators in the presence of all the aforementioned difficulties. To highlight the main issues, a very flexible-link manipulator whose hub exhibits a considerable amount of friction is considered for the experimental work. Four different neural network schemes are proposed and implemented on the experimental test-bed. The neural networks are trained and employed as online controllers.

This monograph is concerned with the development and implementation of nonlinear mathematical techniques for feedback control and shape design of robot manipulators whose links have considerable structural flexibility. Several nonlinear control and observation techniques are studied and implemented by simulations and experiments in a laboratory setup. These techniques include integral manifolds in singular perturbation theory, nonlinear input-output decoupling, nonlinear observers and sliding control.
The study of dynamic properties and control techniques for flexible-link manipulators can also be a framework for designing the mechanical shape and material of these systems such that improved properties can be achieved in order to facilitate the control problem. Therefore, structural shape optimization is considered as a means of improving the dynamic behaviour of flexible-link manipulators.