ERI: Tool Grasping Compliance and Stability of Underactuated Hands in Model-Mediated Telemanipulation

该奖项全部或部分由《2021年美国救援计划法案》（公法117-2）资助。这项工程研究启动（ERI）资助支持将贡献与制造过程相关的新知识的研究，促进科学进步，促进国家繁荣。机械手以精度高、重复性好著称。它们已广泛应用于定义明确的全自动工业环境中。然而，特别的、高度不确定的和复杂的操作任务仍然需要现场人员的在场和协助。许多此类任务都存在危险和具有挑战性的环境，例如在大流行期间工厂运营的情况。该项目旨在通过使员工具备远程操作操作任务的多功能和灵巧能力来增强员工的能力。将为劳动力开发一种新的模型介导的远程操作框架，以扩展他们的物理范围，他们的动手操作灵活性和他们的态势感知智能，从本地到远程站点。这些先进的远程操作技术将对社会和经济产生重大影响，有助于为劳动力提供安全的制造工作环境。从教育的角度来看，该项目通过激励和培养服务不足社区的学生在高中和大学阶段从事科学、技术、工程和数学（STEM）职业，促进了工程教育的多样性。该项目旨在开发增强的远程操作方法，以弥补目前在远程操作操作任务中使用抓取工具的差距，例如，用抓取螺丝刀紧固螺钉。本课题的主要研究目标是研究力控制造任务中刀具抓取的顺应性和稳定性，并探索其在模型介导的远程操作中的应用。首先，利用来自手部传感器（关节角度和本体感觉）和腕部力和扭矩传感器的联合反馈，开发了一个框架来估计欠驱动机器人手的刀具抓取顺应性矩阵。然后，利用估计的柔度来推断抓取状态和稳定性，并制定新的力控制策略。最后，将刀具抓取信息整合到模型介导的远程操作中，设计并实现了一种新的抓取通知虚拟夹具触觉辅助。因此，可以为用户驱动的远程操作任务提供完整的解决方案。该项目由跨部门机器人基础研究项目支持，由工程（ENG）和计算机与信息科学与工程（CISE）联合管理和资助。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).This Engineering Research Initiation (ERI) grant supports research that will contribute new knowledge related to a manufacturing process, promoting the progress of science, and advancing national prosperity. Robot manipulators are known for high precision and repeatability. They have been widely used in well-defined and fully automated industrial settings. However, ad-hoc, highly uncertain, and complex manipulation tasks still require on-site presence and assistance from human crew. Many such tasks present hazardous and challenging environments, such as in the case of factory operations during a pandemic. This project aims to empower the workforce by enabling their versatile and dexterous capabilities for remotely operated manipulation tasks. A novel model-mediated telemanipulation framework will be developed for the workforce, to extend their physical reach, their hands-on manipulation dexterity, and their situational awareness intelligence, from local to a remote site. These advanced telemanipulation technologies will have substantial impact on society and the economy, helping facilitate safe manufacturing working environments for the workforce. From an educational perspective, this project promotes diversity in engineering education by inspiring and preparing students in under-served communities for science, technology, engineering, and mathematics (STEM) careers at the high school and college levels.This project seeks to develop enhanced teleoperation methods to bridge the current gaps of using grasped tools in remotely operated manipulation tasks, such as, fastening a screw with a grasped screwdriver. The key research objective of this project is to investigate tool grasping compliance and stability in force-controlled manufacturing tasks and explore its usage in model-mediated telemanipulation. First, a framework is developed for estimating tool grasping compliance matrices of underactuated robotic hands using combined feedback from hand sensors (joint angles and proprioception) and wrist-mounted force and torque sensors. Then, the estimated compliance is used to infer grasping status and stability and to develop novel force control strategies. Finally, the tool grasping information is incorporated in model-mediated telemanipulation to design and implement a novel grasping-informed virtual fixture haptic assistance. Thereby, a complete solution for user-driven remotely operated manipulation tasks can be delivered.This project is supported by the cross-directorate Foundational Research in Robotics program, jointly managed and funded by the Directorates for Engineering (ENG) and Computer and Information Science and Engineering (CISE).This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.