PD Control of a Manipulator with Gravity and Inertia Compensation Using an RBF Neural Network
- PDF / 2,415,614 Bytes
- 10 Pages / 594.77 x 793.026 pts Page_size
- 8 Downloads / 204 Views
ISSN:1598-6446 eISSN:2005-4092 http://www.springer.com/12555
PD Control of a Manipulator with Gravity and Inertia Compensation Using an RBF Neural Network Yueyuan Zhang, Dongeon Kim, Yudong Zhao, and Jangmyung Lee* Abstract: Dynamic compensation can improve the accuracy of trajectory tracking for industrial manipulators. For irregularly shape or flexible manipulators, however, it is difficult to measure the position of the center of mass (COM) so that its dynamic model cannot be expressed explicitly. This paper proposes a proportional derivative (PD) controller with radial basis function neural network based gravity and inertia compensation (RBFNN-GIC). The RBFNN is utilized to estimate the gravity disturbance and to enable identification of COM to calculate the compensated inertia term. The proposed strategy based on the dynamic model can be used on any robot arm whose COM, gravity and inertia are difficult to obtain. To demonstrate the optimization and effectiveness of proposed PD controller, comparative experiments between the proposed control scheme and the traditional data-fitting method least mean square method (LMS) are conducted on a 3 degree of freedom (DOF) robotic manipulator. Keywords: Gravity and inertia compensation, least mean square method, PD controller, RBF neural network.
1.
INTRODUCTION
Robot arms are widely used in the fields of industrial manufacturing, medical treatment, entertainment services, military, semiconductor manufacturing and space exploration. The primary goal of robot control is to make the end-effector track a desired time-varying trajectory. Improved controller performance can elaborate the working efficiency and operation accuracy of the robot without costly redesign of drive system components [1–3]. However, some problems in the control process of manipulators remain unsolved. During movement, the generated control torque of the controller is mostly utilized to compensate for the gravity, inertia, and friction which are nonlinear disturbances such that high-precision and highspeed trajectory tracking performance can be achieved [4]. On the one hand, with no gravity compensation if the manipulator is powered on, it will fall due to its own gravity, which will cause severe damage to the structure of the manipulator. In addition, at the initial instant of path tracking, the manipulator must first overcome its own gravity and then gradually approach the reference trajectory [5–7]. On the other hand, the inertial term will considerably affect the tracking result when unexpected instructions are given to the robot [8, 9]. If the robot relies only on the closed-loop system to overcome gravity and inertial torque, the PD (Proportional Derivative) control gain must
be increased. However, in this case the increased gain may cause oscillations. Therefore, eliminating the effect of gravity and inertial terms will shorten the response time and will improve dynamic performance for more rapid and accurate control. David and Robles designed a PID (Proportional Integral Derivative) contro
Data Loading...
