Robot manipulator hybrid control for an unknown environment using visco-elastic neural networks

Robot manipulators are expected to perform more sophisticated tasks under unlimited environment. In order to realize these tasks, the robot manipulators have to be flexible enough to work in an unknown environment. In this paper, we propose an effective adaptive neural network feedback controller for hybrid position/force control of robot manipulators for an unknown environment by applying new types of neurons which possess visco-elastic properties. The unexpected overshooting and oscillation caused by the unknown and/or unmodeled dynamics of a robot manipulator and an environment can be decreased efficiently by the proposed visco-elastic neurons. The effectiveness of the proposed visco-elastic neural network controllers is evaluated by simulation with the model of a 3-DOF direct-drive planar robot manipulator.