Image-Based Trajectory Tracking Control for Wheeled Mobile Robots with ADP

In this paper, a visual servoing approach based on approximate dynamic programming (ADP) is developed for the trajectory tracking control of mobile robots. First, according to the current image, the desired image and reference image sequence of coplanar feature points are captured by the onboard camera, and the current pose information and desired pose information of the mobile robot can be reconstructed by homography technology. Then, the open-loop system errors are defined by translation and rotation. In order to design the optimal controller for this system, the appropriate control input transformation is adopted. Therefore, a visual servoing approach based on ADP is proposed to achieve the trajectory tracking task for the mobile robot. A critic neural network (NN) structure is used to learn the time-varying solution, namely the optimal value function, of the Hamilton–Jacobi–Bellman (HJB) equation. Since the existence of time-varying terms, which is different from many existing works, the HJB equation is time-varying. Therefore, a NN with time-varying weight structure is designed to approximate the time-dependent value function of the HJB equation. Finally, it is proved that the approach proposed in this paper guarantees that the closed-loop system is uniformly ultimately bounded.