Computed Torque-NN-GWO Dynamic Hybrid Control of Manipulator Robotic Arm

Robotics involves designing, simulating, and controlling robots for various industries and daily tasks. Manipulator arm robots are precisionoriented industrial robots designed for one-plane movement. Planar robotic manipulators are used in cargo loading, assembly lines, handling radioactive materials, and military applications. In this study theoretical analysis of manipulator robot kinematics using Denavit-Hartenberg notation and the Euler-Lagrange method for a three-degree of freedom (3-DOF) system, requiring an advanced controller for accurate control. A new hybrid controller, Computed Torque Control-Neural-Network -Grey Wolf Optimization (CTC-NNGWO), is proposed for path planning of 3-DOF MR. It uses kinematics and dynamic models, computes torque magnitudes of stepper motors, and denormalizes output values from NN. MATLAB programming is used for the simulation of the theoretical result. A comparison study of CTC-NN-GWO and CTC-PSO found that CTC-NN-GWO outperforms CTC-PSO in minimizing path planning errors, the maximal value of the error of joint angular position 𝑒𝜃1 is (0.29 rad), whereas 𝑒𝜃2 and 𝑒𝜃3 are approximately (0.15 rad) and (0.07 rad), respectively, also, reducing torque magnitudes, improving the performance of 3-DOF MR. Index Terms— Manipulator robotic, Grey wolf, Neural network, Path planning, Computed torque.