Adaptive Neural Networked Based Impedance Control of Mobile Manipulators with Uncertainties

This paper introduces a novel impedance controller for mobile manipulators that ensures safe interaction with uncertain environments without requiring force information. Dynamics uncertainties are compensated by employing adapative radial basis function neural networks (RBFNN). Redundancy of mobile manipulators is managed to perform subtasks alongside tracking control without compromising performance. Stability analysis guarantee the uniformly ultimately boundedness of tracking errors during interaction with the environment and asymptotic convergence to zero in free motion. Numerical simulation is provided to validate the efficacy of the proposed method.