Neuro-Adaptive Compliant Force/Motion Control of Uncertain Constrained Wheeled Mobile Manipulators

In this paper, neuro-adaptive force/motion control of mobile manipulators in the presence of unknown dynamic model and uncertain constraints is studied. The working surface is deformable, and the geometric and physical model of the surface is unknown. All contact forces are nonlinear and difficult to model. A neuro-based control with robust force/motion tracking performance for constrained robot manipulators is proposed. The control law is based on the philosophy of the parallel approach in two decoupled subspaces and utilizes an adaptive scheme to deal with the uncertain environmental constraints, disturbances, and unknown robotic dynamics. The wheeled mobile base is utilized to avoid the system's singularity. Stability conditions for control parameters are derived. Simulation results are presented to show the effectiveness of the proposed control, which performs better compared with model-based control.