ABSTRACT
This chapter explores the issue of force/position control for limited reconfigurable manipulators. By combining the advantages of the model-dependent controller with the radial basis function (RBF) neural network-based controller, the authors advance a brand-new control strategy for limited reconfigurable manipulators. The application of a neural network-based controller can increase the inefficiency of the model-based control method. With the addition of an adaptive compensator to the controller, the neural network compensates for system uncertainties and handles the impacts of friction terms, external disturbances, network reconstruction error, and more. The Lyapunov approach takes advantage of the online learning of a neural network weights to ensure system stability and error convergence. The simultaneous force and the joint tracking have progressed extremely slowly as a result of the suggested approach. As a result, we see that, while maintaining the boundedness of the restricted force tracking and the asymptotic convergence of the joint tracking errors, both of these tracks also converge to the appropriate values when various constraints are applied to various configurations.
