Adaptive neural network control of bilateral teleoperation with time delay

This paper proposes a novel architecture for bilateral teleoperation with a master and slave nonlinear robotic systems under constant communication delays. We basically extend the passivity based coordination architecture to improve position and force tracking and consequently transparency in the face of offset in initial conditions, environmental contacts and unknown parameters such as friction coefficient. This structure provides robust stability against constant delay and guarantee position and force tracking. The proposed controller employ a stable neural network in each side to approximate unknown nonlinear functions in the robot dynamics, thereby overcoming some limitation of adaptive control and guarantee good performance. An adaptation algorithm is developed to train the NN controller in order to stabilize the whole system. Furthermore, it is demonstrate that the tracking error of desired trajectory and NN weights are bounded. Simulation results show that NN controller tracking performance is superior to conventional coordination controller tracking performance.