This paper proposes a back-stepping and neural network hybrid control method for mobile platform and slider of mobile robot used in shipbuilding welding. The kinematics model of the robot is built firstly, and then a motion controller is designed based on the model and back-stepping method. Stability of the controller is proved through use of Liapunov theory. For improving the tracking precision and anti-interference performance of the controller, a neural network is designed to identify the kinematical model of the robot and to adjust the control coefficients in real time based on the tracking errors. The simulation and experiments have been done to verify the effectiveness of the proposed controllers. © 2011 Published by Elsevier Ltd.
Gao, Y., Zhang, H., & Ye, Y. (2011). Back-stepping and neural network control of a mobile robot for curved weld seam tracking. In Procedia Engineering (Vol. 15, pp. 38–44). https://doi.org/10.1016/j.proeng.2011.08.009