CAREER: Synergy-based Human Machine Interfaces

职业：基于协同的人机界面

• 批准号: 2053498
• 负责人: Ramana Vinjamuri
• 金额: $ 41.36万
• 依托单位: University of Maryland Baltimore County
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-22 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2053498&HistoricalAwards=false
• 关键词: CAREER; Synergy; based; Human; Machine

With a brain controlled exoskeleton, an individual with spinal cord injury performed a symbolic-kickoff of for the World Cup in Brazil in 2014. Human-machine interfaces have not only become popular technologies but have become the hope of many individuals for restoring their lost limb function. Decades of research went into making the interface between the human and the machine seamless, but scientists were unable to effectively address the inherent challenges, namely, complexity, adaptability and variability. To overcome the above challenges, it is critical to computationally understand and quantitatively characterize how humans control their senses and motor abilities. Biomimetically inspired models can help to understand this process, and can enable efficient control of the machine. The human hand has many dimensions and is an ideal testbed to understand sensorimotor control while interacting with computers and other machines. Hence the goal of this project is to design and develop biomimetic models that control the human hand and extend these models to the control of multidimensional machines. The societal impacts of the proposed project will be the development of new designs of artificial limbs for individuals with disabilities that are as close to natural in their functions. The educational and outreach impacts of the project will create opportunities for students and working engineers to learn the importance of human machine interfaces. The project will facilitate mentored international research and educational opportunities for students. The hands-on modules developed as an outflow of the proposed research will ignite interest in science and technology among students at all levels, particularly women and underrepresented minorities.The means by which the central nervous system effortlessly controls the high dimensional human hand is still an unsolved mystery. To address this high dimensional control problem, many bioinspired motor control models have been proposed, one of which is based on synergies. According to this model, instead of controlling individual motor units, central nervous system simplifies the control using coordinated control of groups of motor units called synergies. However, there are several unanswered questions today. Where are synergies present? What is their role in motor control and motor learning? To answer these fundamental questions, this project takes a holistic and comprehensive approach. It combines the concepts of human motor control, computational neuroscience, machine learning and validation with noninvasive human experiments. The research objectives of this project are: to model the generation of synergies in human hand movements and validate the model with noninvasive human experiments using computational models, electroencephalography and transcranial magnetic stimulation, to model the behavior and the role of synergies in motor learning and to apply these synergies in multidimensional machine control and machine-assisted learning.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.

2014年，一名脊髓损伤的人用大脑控制的外骨骼为巴西世界杯进行了象征性的开球。人机界面不仅成为一种流行的技术，而且成为许多人恢复失去的肢体功能的希望。几十年来，科学家们一直在研究如何使人机界面无缝对接，但却无法有效地解决其固有的挑战，即复杂性、适应性和可变性。为了克服上述挑战，至关重要的是计算理解和定量表征人类如何控制他们的感觉和运动能力。仿生学启发的模型可以帮助理解这一过程，并可以使机器的有效控制。人的手有很多维度，是一个理想的测试平台，了解感觉运动控制，同时与计算机和其他机器的互动。因此，这个项目的目标是设计和开发控制人手的仿生模型，并将这些模型扩展到多维机器的控制。拟议项目的社会影响将是为残疾人开发新的假肢设计，使其功能接近自然。该项目的教育和推广影响将为学生和在职工程师创造机会，让他们了解人机界面的重要性。该项目将为学生提供国际研究指导和教育机会。作为拟议研究的外流而开发的实践模块将激发各级学生，特别是妇女和代表性不足的少数民族对科学和技术的兴趣。中枢神经系统毫不费力地控制高维人手的方法仍然是一个未解之谜。为了解决这个高维控制问题，许多仿生运动控制模型已经被提出，其中一个是基于协同效应的。根据该模型，中枢神经系统不再控制单个运动单元，而是通过协同控制称为协同作用的运动单元群来简化控制。然而，今天仍有几个悬而未决的问题。协同效应体现在哪里？它们在运动控制和运动学习中的作用是什么？为了回答这些基本问题，该项目采用了整体和综合的方法。它结合了人类运动控制，计算神经科学，机器学习和非侵入性人体实验验证的概念。该项目的研究目标是：模拟人类手部运动中协同作用的产生，并利用计算模型、脑电图和经颅磁刺激等非侵入性人体实验验证该模型，模拟协同作用在运动学习中的行为和作用，并将这些协同作用应用于多维机器控制和机器辅助学习。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。

项目成果

Finding Robust Low Dimensional Features for Sleep Detection Using EEG Data

使用脑电图数据寻找用于睡眠检测的稳健低维特征

• DOI: 10.1109/icdsca56264.2022.9988155
• 发表时间: 2022
• 期刊: 2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA
• 作者: Mao, Helen X.;Widjaja, Joseph;Guo, Yifan;Yin, Jijun;Vinjamuri, Ramana
• 通讯作者: Vinjamuri, Ramana

Dynamical Synergies in Multidigit Hand Prehension

多指手握持中的动态协同作用

• DOI: 10.1109/embc48229.2022.9871888
• 发表时间: 2022
• 期刊: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC
• 作者: Pei, Dingyi;Olikkal, Parthan;Adali, Tulay;Vinjamuri, Ramana
• 通讯作者: Vinjamuri, Ramana