Genetic Algorithms for Optimal Grasping in Automated 3D-Printed Part Extraction

This article presents a novel approach to automate the extraction of 3D printed parts using genetic algorithms for optimal grasp planning. The method addresses a key challenge in additive manufacturing: the automated removal of printed objects. Using information from the G-code file, our algorithm determines the most effective grasping pose for a robotic arm equipped with a two-finger gripper. The system considers multiple factors including collision avoidance, contact quality, and part geometry to optimize the grasp location. The solution was implemented using an industrial manipulator and integrated with a commercial 3D printer through a custom ROS 2 package. Experimental results demonstrate the effectiveness of our approach on simple geometries, successfully extracting printed parts without human intervention. While the method has certain limitations, this study lays the foundation for fully autonomous 3D printing workflows. Our research contributes to the broader goal of developing adaptive and self-sufficient manufacturing systems, paving the way for more efficient and flexible production processes in industry 4.0 environments.