Force/position mracking for a robotic finger in compliant contact with a surface using neuro-adaptive control

In this work, the problem of force/position tracking for a robotic finger in compliant contact with a surface under non-parametric uncertainties is considered. In particular, structural uncertainties are assumed to characterize the compliance model as well as the robot dynamic model. A novel neuroadaptive controller is proposed that exploits the approximation capabilities of the linear in the weights neural networks and the uniform ultimate boundedness of force and position error is proved. Simulation results illustrate the performance of the proposed controller.