Abstract
In some environments where manual work cannot be carried out, snake manipulators are instead used to improve the level of automatic work and ensure personal safety. However, the structure of the snake manipulator is diverse, which renders it difficult to establish an environmental model of the control system. It is difficult to obtain an ideal control effect by using the traditional manipulator control method. In view of this, this paper proposes a data-driven snake manipulator control algorithm. After collecting data, the algorithm uses the strong learning and decision-making ability of the deep deterministic strategy gradient to learn these system data. A data-driven controller based on the deep deterministic policy gradient was trained in order to solve the manipulator system control problem when the control system environment model is uncertain or even unknown. The data of simulation experiments show that the control algorithm has good stability and accuracy in the case of model uncertainty.
Highlights
Existing manipulator control theory can be divided into three categories: (1) Accurate mathematical models are required, such as optimal control strategies, linear or nonlinear control strategies, and pole assignment methods
Aiming at the trajectory tracking control problem caused by uncertainty and disturbance of the manipulator, Vu proposed a robust adaptive control strategy based on a fuzzy wavelet neural network system with dynamic structure
The contribution of this paper is to propose a data-driven snake manipulator control strategy to solve the control problem of snake manipulators in some complex environments
Summary
Existing manipulator control theory can be divided into three categories: (1) Accurate mathematical models are required, such as optimal control strategies, linear or nonlinear control strategies, and pole assignment methods. Jung proposed an improved sliding mode control method based on an RBF neural network to solve the problem of nonlinear function gain selection of a sliding mode controller and the uncertainty of the three-link manipulator model [6]. The method of establishing the environment object and agent of the DDPG control system is introduced in detail This mainly includes the two-link dynamic model of the serpentine manipulator, Q network design, and action network design. The simulation experiment of this method was designed, and the simulation results verify the feasibility of the method This method avoids the complicated task of establishing the manipulator model and improves the stability and accuracy of the control system.The data-driven control algorithm uses the existing motion data of the serpentine robot.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
