<![CDATA[This study investigates the application of metaheuristic algorithms to solve the inverse kinematics (IK) problem in robotic manipulators, which is often challenging for high-degree-of-freedom systems. The research contribution is the comparative evaluation of four recent metaheuristic algorithms—Ant Colony Optimization, Mayfly Optimization Algorithm, Stochastic Paint Optimizer, and Ant Lion Optimizer—across different robot configurations. A kinematic analysis was conducted on three robotic arms: a 4-DOF SCARA, a 6-DOF ABB IRB 1600, and the dual-arm 15-DOF Motoman SDA20D/12L. For each manipulator, the end-effector pose was optimized by solving the IK problem using the selected algorithms. A total of 30 random target positions were tested within the operational space to ensure diversity in pose challenges; while not exhaustive, this sampling provides statistically informative trends. We evaluate each algorithm based on the number of optimal solutions obtained, the precision of the computed joint configurations, and execution time. The results indicate that the Mayfly Optimization Algorithm consistently delivered the highest precision with relatively low execution time across all robot types. In contrast, the Ant Lion Optimizer showed inconsistent performance in higher-DOF settings. Unlike traditional Jacobian-based or analytical IK methods, metaheuristics offer flexibility in handling complex, nonlinear systems without requiring gradient information. These findings provide practical insight for selecting suitable algorithms in real-world robotic applications.]]>
Copyrights © 2025
