真空驱动的多材料混合软夹爪的应用:从RoboSoft操作挑战赛中学到的经验教训。

Applications of a vacuum-actuated multi-material hybrid soft gripper: lessons learnt from RoboSoft manipulation challenge.

作者信息

Dontu Saikrishna, Kanhere Elgar, Stalin Thileepan, Dharmawan Audelia Gumarus, Hegde Chidanand, Su Jiangtao, Chen Xiaodong, Magdassi Shlomo, Soh Gim Song, Valdivia Y Alvarado Pablo

机构信息

Digital Manufacturing and Design Centre, Singapore University of Technology and Design, Singapore, Singapore.

Singapore-HUJ Alliance for Research and Enterprise (SHARE), The Smart Grippers for Soft Robotics (SGSR) Programme, Campus for Research Excellence and Technological Enterprise (CREATE), Singapore, Singapore.

出版信息

Front Robot AI. 2024 May 28;11:1356692. doi: 10.3389/frobt.2024.1356692. eCollection 2024.

Abstract

Soft grippers are garnering increasing attention for their adeptness in conforming to diverse objects, particularly delicate items, without warranting precise force control. This attribute proves especially beneficial in unstructured environments and dynamic tasks such as food handling. Human hands, owing to their elevated dexterity and precise motor control, exhibit the ability to delicately manipulate complex food items, such as small or fragile objects, by dynamically adjusting their grasping configurations. Furthermore, with their rich sensory receptors and hand-eye coordination that provide valuable information involving the texture and form factor, real-time adjustments to avoid damage or spill during food handling appear seamless. Despite numerous endeavors to replicate these capabilities through robotic solutions involving soft grippers, matching human performance remains a formidable engineering challenge. Robotic competitions serve as an invaluable platform for pushing the boundaries of manipulation capabilities, simultaneously offering insights into the adoption of these solutions across diverse domains, including food handling. Serving as a proxy for the future transition of robotic solutions from the laboratory to the market, these competitions simulate real-world challenges. Since 2021, our research group has actively participated in RoboSoft competitions, securing victories in the Manipulation track in 2022 and 2023. Our success was propelled by the utilization of a modified iteration of our Retractable Nails Soft Gripper (RNSG), tailored to meet the specific requirements of each task. The integration of sensors and collaborative manipulators further enhanced the gripper's performance, facilitating the seamless execution of complex grasping tasks associated with food handling. This article encapsulates the experiential insights gained during the application of our highly versatile soft gripper in these competition environments.

摘要

软抓手因其能够灵活适应各种物体,特别是易碎物品,而无需精确的力控制,正日益受到关注。这一特性在非结构化环境和诸如食品处理等动态任务中尤为有益。人类的手由于其高度的灵活性和精确的运动控制,能够通过动态调整抓握方式,巧妙地操纵复杂的食品,如小型或易碎物品。此外,人类的手拥有丰富的感觉受体和手眼协调能力,能提供有关质地和形状因素的宝贵信息,从而在食品处理过程中能无缝地进行实时调整,以避免损坏或溢出。尽管人们通过涉及软抓手的机器人解决方案进行了大量努力来复制这些能力,但要达到人类的表现水平仍然是一项艰巨的工程挑战。机器人竞赛是拓展操纵能力边界的宝贵平台,同时也能为这些解决方案在包括食品处理在内的不同领域的应用提供见解。这些竞赛模拟现实世界的挑战,可作为机器人解决方案从实验室向市场未来过渡的代表。自2021年以来,我们的研究团队积极参加了RoboSoft竞赛,并在2022年和2023年的操纵赛道上取得了胜利。我们的成功得益于对可伸缩钉软抓手(RNSG)的改进版本的运用,该版本是根据每项任务的具体要求量身定制的。传感器和协作操纵器的集成进一步提升了抓手性能,有助于无缝执行与食品处理相关的复杂抓取任务。本文总结了我们高度通用的软抓手在这些竞赛环境中的应用经验。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3e69/11165351/fa2c52c4b5f5/frobt-11-1356692-g001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索