Adaptive robust neural control of a two-manipulator system holding a rigid object with inaccurate base frame parameters

The problem of self-tuning control with a two-manipulator system holding a rigid object in the presence of inaccurate translational base frame parameters is addressed. An adaptive robust neural controller is proposed to cope with inaccurate translational base frame parameters, internal force, modeling uncertainties, joint friction, and external disturbances. A radial basis function neural network is adopted for all kinds of dynamical estimation, including undesired internal force. To validate the effectiveness of the proposed approach, together with simulation studies and analysis, the position tracking errors are shown to asymptotically converge to zero, and the internal force can be maintained in a steady range. Using an adaptive engine, this approach permits accurate online calibration of the relative translational base frame parameters of the involved manipulators. Specialized robust compensation is established for global stability. Using a Lyapunov approach, the controller is proved robust in the face of inaccurate base frame parameters and the aforementioned uncertainties.