Abstract
In order to solve the joint chattering problem of the manipulator in the process of motion, a novel dynamics model is established based on the dynamics model of the manipulator, by fitting parameters of the neural network and combining with the estimated value of the inertia matrix. We proposed a neural network adaptive control method with a time-varying constraint state based on the dynamics model of estimation. We design the control law, establish the Lyapunov function equation and the asymmetric term, and derive the convergence of the control law. According to the joint state tracking results of the manipulator, the angular displacement, angular velocity, angular acceleration, input torque, and disturbance fitting of the manipulator are analyzed by using the Simulink and Gazebo. The simulation results show that the proposed method can effectively suppress the chattering amplitude under the environment disturbances.
Highlights
With the development of artificial intelligence, robots are more and more popular, so the design and research of the redundant manipulator control system have become an important research direction in the robotics field [1]
Model errors, and unknown disturbances, the trajectory at the end-effector of the manipulator will have obvious deviation, so the control of trajectory motion is important. e implementation methods include the adaptive control that achieves better end-effector trajectory tracking characteristics in the robot dynamics [4, 5], neural network control that has universal approximation to any nonlinear functions [6,7,8], and the fuzzy control strategy that is widely used in artificial intelligence [9]
These control algorithms have achieved a lot of research results. e PD control in adaptive control shows that the PD model can be used to compensate the sliding mode control law when the manipulator is not affected by the friction and external influence. e neural network adaptive control shows that the neural network control with Gaussian radial basis function as the excitation function in the hidden layer has the advantages of good stability, unique approximation, no local minimum, and fast network convergence
Summary
With the development of artificial intelligence, robots are more and more popular, so the design and research of the redundant manipulator control system have become an important research direction in the robotics field [1]. E implementation methods include the adaptive control that achieves better end-effector trajectory tracking characteristics in the robot dynamics [4, 5], neural network control that has universal approximation to any nonlinear functions [6,7,8], and the fuzzy control strategy that is widely used in artificial intelligence [9]. At present, these control algorithms have achieved a lot of research results. Combined with timevarying constrained output states, a neural network adaptive control algorithm with time-varying output constraints is proposed without the complex manipulator dynamics model.
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.
