The challenge in addressing uncalibrated visual servoing (VS) control of robot manipulators with unstructured environments is to obtain appropriate interaction matrix and keep the image features in the field of view (FOV), especially when the non-Gaussian noise disturbance exists in the VS process. In this paper, a hybrid control algorithm which combines bidirectional extreme learning machine (B-ELM) with smooth variable structure filter (SVSF) is proposed to estimate interaction matrix and tackle visibility constraints. For VS, the nonlinear mapping between image features and interaction matrix is approximated using the B-ELM learning. To increase the capability of anti-interference, the SVSF is employed to re-estimate interaction matrix. A constraint function presenting feature coordinates and region boundaries is given and added to the velocity controller, which drags image features away from the restricted region and ensures the smoothness of the velocities. Since the camera and robot model parameters are not required in developing the control strategy, the servoing task can be fulfilled flexibly and simply. Simulation and experimental results on a conventional 6-degree-of-freedom manipulator verify the effectiveness of the proposed method.

This paper investigates a feature tracking control method for visual servoing (VS) manipulators adaptive dynamic programming (ADP)-based the unknown dynamics. The major superiority of ADP-based optimal control lies in that the visual tracking problem is converted to the feature tracking error control with optimal cost function. Moreover, an adaptive neural network observer is developed to approximate the entire uncertainties, which are utilized to construct an improved cost function. By establishing a critic neural network, the Hamilton–Jacobi–Bellman (HJB) equation is solved, and the approximate optimal error control policy is derived. The closed-loop VS manipulator system is verified to be ultimately uniformly bounded with the developed ADP-based feature tracking control strategy according to the Lyapunov theory. Finally, simulation results under various situations demonstrate that the proposed method achieves higher tracking accuracy than other methods, as well as satisfies energy optimal requirements.

In this paper, a decentralized robust control method of modular robot manipulator (MRM) is proposed under the situation of physical human-robot interaction (pHRI). Different from the traditional human-robot interaction control method that relies on the precise dynamic model and centralized control scheme, the decentralized robust control method is proposed based on the human motion intention, which is estimated through radial basis function neural network (RBFNN). By only using local dynamic information of each joint, a decentralized robust controller is designed to deal with various model uncertainties and joint trajectory tracking problems. Based on Lyapunov theory, the asymptotic stability of the closed-loop robotic system is verified. Finally, the effectiveness of the proposed method is verified by experiments.

Aiming at the precise positioning problem of cigarette filter box cartoning machine in the process of pushing the production line, a new type of push mechanism control system is designed. The fuzzy control theory is combined with the PID controller, and the PID parameters are adaptively adjusted by fuzzy control. It can improve system response speed and control accuracy. The results show that the improved push mechanism can realize the flexible filter rod packing, and the positioning accuracy is better than 0.1mm, which improves the packing quality of the filter box cartoning machine.

An adaptive dynamic programming (ADP) technique is investigated to figure out the problem of image feature tracking control of constrained visual servoing (VS) manipulators system. The complete camera-manipulator dynamic model can be established through the mapping relationship between image feature and manipulator position. The control inputs in the VS manipulators system are taken as a constrained case, and the performance index function is considered to cooperate with sliding mode function. On the basis of ADP technique, a critic neural network (NN) is constructed to derive the Hamilton-Jacobi-Bellman (HJB) equation. Furthermore, the near-optimal control policy is obtained. The Lyapunov theory illustrates that the feature tracking of input-constrained VS manipulators system is ultimately uniformly bounded (UUB). Numerical simulation examples are given to certify the validity of the developed approach.