CPS: Synergy: Sensor Network-Based Lower-Limb Prosthetic Optimization and Control

CPS：协同：基于传感器网络的下肢假肢优化和控制

• 批准号: 1446737
• 负责人: Ou Bai
• 金额: $ 90.19万
• 依托单位: Virginia Commonwealth University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-12-01 至 2015-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1446737&HistoricalAwards=false
• 关键词: CPS; Synergy; Sensor; Network; Based

More than one million people including many wounded warfighters from recent military missions are living with lower-limb amputation in the United States. This project will design wearable body area sensor systems for real-time measurement of amputee's energy expenditure and will develop computer algorithms for automatic lower-limb prosthesis optimization. The developed technology will offer a practical tool for the optimal prosthetic tuning that may maximally reduce amputee's energy expenditure during walking. Further, this project will develop user-control technology to support user's volitional control of lower-limb prostheses. The developed volitional control technology will allow the prosthesis to be adaptive to altered environments and situations such that amputees can walk as using their own biological limbs. An optimized prosthesis with user-control capability will increase equal force distribution on the intact and prosthetic limbs and decrease the risk of damage to the intact limb from the musculoskeletal imbalance or pathologies. Maintenance of health in these areas is essential for the amputee's quality of life and well-being. Student participation is supported.This research will advance Cyber-Physical Systems (CPS) science and engineering through the integration of sensor and computational technologies for the optimization and control of physical systems. This project will design body area sensor network systems which integrate spatiotemporal information from electromyography (EMG), electroencephalography (EEG) and inertia measurement unit (IMU) sensors, providing quantitative, real-time measurements of the user's physical load and mental effort for personalized prosthesis optimization. This project will design machine learning technology-based, automatic prosthesis parameter optimization technology to support in-home prosthesis optimization by users themselves. This project will also develop an EEG-based, embedded computing-supported volitional control technology to support user?s volitional control of a prosthesis in real-time by their thoughts to cope with altered situations and environments. The technical advances from this project will provide wearable and wireless body area sensing solutions for broader applications in healthcare and human-CPS interaction applications. The explored computational methods will be broadly applicable for real-time, automatic target recognition from spatiotemporal, multivariate data in CPS-related communication and control applications. This synergic project will be implemented under multidisciplinary team collaboration among computer scientists and engineers, clinicians and prosthetic industry engineers. This project will also provide interdisciplinary, CPS relevant training for both undergraduate and graduate students by integrating computational methods with sensor network, embedded processors, human physical and mental activity recognition, and prosthetic control.

在美国，包括最近军事任务中受伤的战士在内的100多万人患有下肢截肢。该项目将设计可穿戴的身体区域传感器系统，用于实时测量截肢者的能量消耗，并将开发自动优化下肢假肢的计算机算法。所开发的技术将为最佳假肢调整提供实用工具，可以最大限度地减少截肢者行走时的能量消耗。此外，本项目将开发用户控制技术，以支持用户对下肢假肢的意志控制。发达的意志控制技术将使假肢能够适应变化的环境和情况，例如截肢者可以像使用自己的生物四肢一样行走。一个具有用户控制能力的优化假肢将增加完整肢体和假肢上的均匀力分布，降低肌肉骨骼失衡或病理对完整肢体损伤的风险。维持这些部位的健康对截肢者的生活质量和福祉至关重要。支持学生参与。这项研究将通过集成传感器和计算技术来优化和控制物理系统，从而推进信息物理系统（CPS）科学和工程。该项目将设计身体区域传感器网络系统，该系统集成了来自肌电（EMG）、脑电图（EEG）和惯性测量单元（IMU）传感器的时空信息，为个性化假肢优化提供用户身体负荷和脑力的定量、实时测量。本项目将设计基于机器学习技术的义肢参数自动优化技术，支持用户自行在家进行义肢优化。该项目还将开发一种基于脑电图的嵌入式计算支持的意志控制技术，以支持用户？通过他们的思想实时控制假肢，以应对变化的情况和环境。该项目的技术进步将为医疗保健和人类- cps交互应用中的更广泛应用提供可穿戴和无线身体区域传感解决方案。所探索的计算方法将广泛适用于cps相关通信和控制应用中从时空、多变量数据中实时、自动识别目标。这个协同项目将在计算机科学家和工程师、临床医生和假肢工业工程师之间的多学科团队合作下实施。该项目还将通过将计算方法与传感器网络、嵌入式处理器、人类身心活动识别和假肢控制相结合，为本科生和研究生提供跨学科的CPS相关培训。