This study presents the development and evaluation of a multi-fingered, biomimetic robotic gripper. This gripper is designed to handle delicate, soft agricultural produce. To address this, an eye-in-hand vision system supports a multi-view look-and-grasp strategy, capturing object geometry from several angles to assess optimal grasp planning. Besides, a digital twin environment is used to simulate and evaluate candidate grasp configurations. The most stable configuration is validated in a physical setup using a Universal Robots UR3 arm. Results demonstrate the gripper’s ability to achieve steady, damage-free grasps on strawberries as well as its versatility across various objects, including ping pong balls, plush toys, sushi, and Takoyaki. By showing how hybrid actuation and digital simulation can enhance robotic harvesting reliability and adaptability, this work advances precision agricultural robotics contributing to reduced post-harvest losses and improved food security in alignment with UN sustainable development goal 2 (zero hunger).
Siripin et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: