Force control strategy and test research of underwater dexterous hand

Abstract

The contract force between the fingertip and object need to be controlled when the underwater dexterous hand grasp the object. The original impedance control method lacks robustness because of the inaccurate dynamic model, position error and unknown stiffness of the object, thus, the position-based neural network impedance control method was studied. The effect of position error was analyzed, the neural network was adopted to compensate the uncertainty of finger dynamics, object position and stiffness one by one, and compensation strategy was deduced in detail. Compensator adopted forward feedback neural network with three layers, and updating rules was obtained based on BP arithmetic and Delta learning rule. Finally, the tests of single finger force control were carried out to verify the compensation effect in these three conditions. The results show that the position-based neural network impedance control is a robust method, and this method is fit to the control system of the underwater dexterous hand.