Neural network control of mobile manipulators

In this paper, a novel neural-net (NN) based control methodology is developed for the motion control of mobile manipulators subject to kinematic constraints. The dynamics of the mobile manipulator is assumed to be unknown and is to be identified by the NN online estimators. No preliminary learning stage of NN weight matrices is required. The controller is capable of disturbance-rejection in the presence of unknown bounded disturbances. Closed-loop stability of the control system and convergence of the NN learning processes are both guaranteed. Experimental tests on a two-DOE manipulator arm illustrate that the proposed control is significantly better than conventional robust control