Application and Optimal Design of a Soft Robotic Gripper for Grasping Objects of Arbitrary Shape

Automation of waste sorting operations using robotic systems marks a significant advance in ecological development. The use of robotic arms with elastic grippers offers advantages over conventional grippers, which require a pre-defined regular shape, composition, and mass of the handled objects. To successfully grasp and manipulate irregularly shaped objects, it is necessary to define the optimal design of an elastic robotic gripper tailored to the sorted items. This paper presents a method for evaluating robotic fingers with four different configurations operating with seven types of known and regular-shaped objects. An external pneumatic control system for the robotic arm and a predefined robot trajectory during testing were used, involving various translational and rotational movements, spatial perturbations, and strong centrifugal forces. Additionally, an interactive inspection of the gripping was conducted using a seven-step scoring system, examining the impact of the object's mass, orientation, position, and center of mass change on the gripping outcome. It was concluded that the robotic gripper with three elastic fingers achieved the best overall results in testing the grip quality of objects with and without added mass, scoring 0.86 out of a maximum of 1. Meanwhile, the four-fingered gripper performed best in tests assessing the impact of position changes, orientation, and center of mass, with scores of 0.54, 0.61, and 1, respectively.