Adaptive force/ position control for dual-arm system based on neural network radial basis function without using a force sensor

Abstract

The paper has developed an adaptive algorithm using neural network for controlling dual-arm robotic system in stable holding a rectangle object and moving it to track the desired trajectories. Firstly, an overall dynamic of the system including the dual-arm robot and the object is derived based on Euler-Lagrangian principle. Then based on the dynamics, a controller has proposed to achieve the desired trajectories of the holding object. A radial basis neural network has been applied to compensate uncertainties of system parameters. The adaptive learning algorithm has been derived owning to Lyapunov stability principle to guarantee asymptotical convergence of the closed loop system. Besides, force control at contact point is implemented without the measurements of forces and moments at contact points. Finally, simulation work on Matlab has been carried out to confirm the accuracy and the effectiveness of the proposed controller.