Modifications of Fully Resampled PSO in the Inverse Kinematics of Robot Manipulators

Inverse kinematics involves calculating joint configurations for a robot manipulator to perform tasks. To solve this problem, various approaches have been proposed, including meta-heuristics methods, which are not specific to a manipulator class and do not require matrix inversion. Particle Swarm Optimization (PSO) is a commonly used meta-heuristic due to its simplicity and effectiveness, but it is prone to local minima. In response to this challenge, several PSO variants have been introduced, incorporating strategies such as multiple populations, adaptive parameters, and particle resampling. This paper focuses on the variant Fully Resample PSO (FRPSO), which performs full particle resampling in each iteration. The study investigates how the number of joints and FRPSO parameters impact its performance. Additionally, the paper proposes a novel extension to FRPSO called Modified-FRPSO. The novel approach involves one less parameter compared to the original method, simplifying the process of fine-tuning the performance of FRPSO. Furthermore, the experiments conducted in environments with obstacles indicate that the new approach outperforms the original FRPSO and PSO in terms of convergence rate and average number of iterations.