Abstract—The paper deals with the design of a controller using neural networks to track the motion trajectory for a differential mobile robot considering the wheels' lateral and longitudinal slip components. The proposed control algorithm is an adaptive controller using neural networks to online adjust the parameters of the Backstepping controller according to the robot's reference model and trajectory. In this method, the neural network is required to find the characteristics of the kinematic and dynamic model and use it to determine the parameters for the Backstepping controller, thereby increasing the trajectory tracking performance and reducing error and index to compensate for the gains of the backstepping controller. The Lyapunov criteria is used to assess the closed system's stability. The Wheeled Mobile Robot (WMR) algorithm is built on a very flexible microcontroller architecture, and the software supports Robot Operating System (ROS) robot programming. Simulation results with Matlab/Simulink reveal that the effectiveness of the proposed controller exhibits a steady state and position deviation of the right and left wheels is accordingly 0.0021 m and respectively 0.003 m and the angular velocity tracking error in the right and left wheels of the control method is 0.006 rad/s. Experimental results have verified outstanding efficiency with the most significant control error of only about 0.0053 m in the environment around the room with many curves and 0.0021 m in the corridor environment when testing with Proportional Integral Derivative (PID)-Backstepping Neural Network (NN) controller compared with PID controller, PID-Backstepping controller.

Keywords—Wheeled Mobile Robot (WMR), backstepping controller, PID-Backstepping, Neural Network (NN), Model Robot Operating System (ROS)

Cite: Vo Thu Hà and Thân Thị Thương, "Neural-Backstepping Adaptive Control for Nonlinear Motion of Sliding Mobile Robots," International Journal of Mechanical Engineering and Robotics Research, Vol. 14, No. 3, pp. 323-339, 2025. doi: 10.18178/ijmerr.14.3.323-339

Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).