In recent years, roboticists around the world have designed various robotic grippers that can grasp and manipulate different types of objects. The most effective grippers for tackling real-world manual tasks, especially complex object manipulation tasks, are often those inspired by human hands.
Despite their good performance, many humanoid robotic hands rely on advanced and sometimes expensive mechanisms and sophisticated programming tools. This could limit their large-scale deployment, as it makes them impractical for the development of energy-efficient and cost-effective robots.
Researchers at Purdue University and the Massachusetts Institute of Technology (MIT) have recently developed a simpler yet apparently equally effective robotic gripper. The gripper, presented in an article published on the site arXiv The preprint server has proven effective at tackling complex object manipulation tasks, despite having fewer degrees of freedom (DOF) than grippers inspired by human hands.
“Conventional high depth of field (DOF) and dexterous robotic hands can perform complex hand manipulation tasks, but are non-trivial for programming/control due to their complex mechanisms,” Yu She, co-author of the paper, told Tech Xplore.
“In contrast, traditional single-degree-of-freedom parallel-jaw robotic grippers are easy to program/control, but are limited to gripping tasks and are difficult to perform in manual manipulation. Our team aims to design a gripper that bridges the gap between these two types of grippers.”
The new gripper developed by She and colleagues has 5 degrees of freedom. Although its simple design makes it easy to control via programming tools, the gripper can still perform human-like hand manipulations, relying on sensory data recorded by an integrated vision-based touch sensor.
The newly designed gripper essentially consists of two fingers attached to a gripper base. The team also mounted a small vision-based tactile sensor on top of the gripper’s left finger.
“The gripper base provides one degree of freedom for closing and opening the gripper,” she explained. “Each finger is equipped with a linear actuator and a rotary servo motor, resulting in a total of five degrees of freedom for the gripper. The gripper fingers are made from PLA material using 3D printing. A mini tactile sensor based on GelSight vision is mounted on the left fingertip, providing information about the geometry, orientation, and grip force of the gripped object.”
The distinctive feature of the gripper developed by She and her colleague is that, although its movements can be easily controlled, it can nevertheless achieve a high level of dexterity during hand manipulation tasks by combining its 5 degrees of freedom.
The researchers evaluated the gripper in a series of initial real-world experiments and found that it could manipulate more complex objects than most simple grippers, with a few degrees of freedom. The gripper could actually perform two types of object manipulation, called singulation and scooping. For example, it could mimic the human motion of rubbing sand particles stuck between the surface of an object and one’s fingers, an action humans might perform when picking up seashells on the beach.
“We demonstrate that a gripper with fewer degrees of freedom than a humanoid robotic hand can successfully perform complex manual manipulation tasks,” she said. “This reduction in complexity can lead to simpler controller design and more robust, cost-effective and energy-efficient robotic solutions that are easier to implement and maintain.”
The gripper robot developed by this research team could soon be refined and applied to other complex object-handling tasks. Its underlying design could also inspire the development of other similar robotic systems for object handling that are both cost-effective and efficient.
“We now plan to use the developed tactile gripper to accomplish more complex manipulation tasks that are currently beyond the capabilities of other robotic grippers,” she added. “These tasks include, but are not limited to, the manipulation of deformable linear objects.”
More information:
Yuhao Zhou et al., Hand-held singulation and pick-up manipulation with a 5-degree-of-freedom tactile gripper, arXiv (2024). DOI: 10.48550/arxiv.2408.00610
arXiv
© 2024 Science X Network
Quote: Simplified robotic gripper can still tackle complex object-handling tasks (2024, August 17) retrieved August 18, 2024 from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.