Intelligent optimization algorithms for control error compensation and task scheduling for a robotic arm

Abstract

A task scheduling and error control optimization method for robotic arms was developed. The arm’s accuracy after optimization with particle swarm optimization, artificial bee colony, grey wolf optimizer, the genetic algorithm, differential evolution algorithm, and the bat algorithm was compared to identify the best optimization method. Task scheduling was optimized by identifying the optimal paths to each target object. The method can control positioning error, enabling the robotic arm to reach its target coordinates with the smallest error despite being affected by interference during navigation. The proposed method was verified in virtual environments with varying target objects at different locations. The estimation results and convergence speed of each algorithm were compared to identify the most accurate algorithm. The proposed method could be used to improve the task scheduling and error control of robotic arms. The method could also be used in combination with algorithms in accordance with the requirements of practical scenarios.