CRII: CHS: Enabling Safe and Adaptive Robot-aided Gait Training through Biomechanical Characterization and Learning from Demonstration

CRII:CHS:通过生物力学表征和从演示中学习,实现安全和自适应机器人辅助步态训练

基本信息

  • 批准号:
    1756031
  • 负责人:
  • 金额:
    $ 17.5万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2018
  • 资助国家:
    美国
  • 起止时间:
    2018-09-01 至 2023-08-31
  • 项目状态:
    已结题

项目摘要

The unprecedented growth in the elderly population is generating a high demand for gait rehabilitation due to age-related neurological diseases. To address this urgent need various assistive robots have been developed to improve gait training outcomes, and impedance control (controlling the force of resistance to external motions that are produced by the environment) has been widely employed in these robots to ensure safe human-robot interaction. However, it is difficult to personalize the virtual impedance for such robots due to the complex nature of human neurological and musculoskeletal dynamics. On the other hand, a physical therapist can provide adaptive assistance to a patient at the correct moment in a gait cycle based on real-time sensory feedback and clinical experience. Inspired by this observation, one could imagine designing an assistive robot control system by learning from therapists' demonstrations, but such a purely data-driven approach could lead to significantly degraded performance with new gait patterns, which creates safety risks for users. This research will develop a hybrid assistive robot control approach, which integrates model-based impedance control with machine learning from therapists' behaviors so that the resultant robot assistance is safe yet adaptive. Project outcomes will include a novel algorithm framework for physical human-robot collaboration that exhibits both performance guarantees due to the model-based control and intelligent adaptation resulting from robot learning. The new technology will have a wide range of applications in many other safety-critical human-robot collaboration scenarios, including collaborative manufacturing, (semi) autonomous driving, and service robots. The broader impacts of the work will be further enhanced by tight integration of the research with educational activities including new modules in existing robotics classes, research opportunities for undergraduate students from underrepresented groups, and internships for local high-school students. The scientific contribution of the work will include: 1) integration of heterogeneous wearable sensor data to build the robot learning model from therapists' demonstrations, and human knee impedance characterization to build the robot impedance control model; 2) a robot planning approach based on a fusion of learning from demonstration and impedance control, with the weights determined by the degree of confidence in the robot learning model; and 3) automatic requests for new demonstration data and incorporation of subject feedback to refine both the robot learning and impedance control models. Performance of the approach will be assessed in biomechanical simulations, in lab tests with healthy subjects, and in a pilot study with stroke and Parkinson's disease patients. It is envisioned that project outcomes will make assistive robots highly intelligent so that a therapist could work with multiple patients simultaneously and even remotely, which could significantly reduce both the therapists' labor intensity and cost of rehabilitation training for patients.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.
老年人口的空前增长正在产生对步态康复的高需求,这是由于与年龄相关的神经系统疾病。 为了满足这一迫切需求,各种辅助机器人已经被开发出来,以改善步态训练的结果,阻抗控制(控制由环境产生的外部运动的阻力)已被广泛应用于这些机器人,以确保安全的人机交互。 然而,由于人类神经系统和肌肉骨骼动力学的复杂性质,很难个性化这种机器人的虚拟阻抗。 另一方面,物理治疗师可以根据实时感觉反馈和临床经验,在步态周期的正确时刻为患者提供自适应辅助。 受这一观察的启发,人们可以想象通过从治疗师的演示中学习来设计辅助机器人控制系统,但这种纯粹的数据驱动方法可能会导致新步态模式的性能显著下降,从而为用户带来安全风险。本研究将开发一种混合辅助机器人控制方法,该方法将基于模型的阻抗控制与从治疗师的行为中进行的机器学习相结合,从而使所得到的机器人辅助安全而自适应。 项目成果将包括一个新的算法框架,用于物理人机协作,该框架既具有基于模型的控制的性能保证,又具有机器人学习产生的智能适应。 这项新技术将在许多其他安全关键的人机协作场景中有广泛的应用,包括协同制造、(半)自动驾驶和服务机器人。 通过将研究与教育活动紧密结合,包括现有机器人课程的新模块,代表性不足的本科生的研究机会以及当地高中生的实习机会,将进一步增强这项工作的更广泛影响。 本研究的科学贡献包括:1)整合不同种类的可穿戴传感器数据,从治疗师的示范中建立机器人学习模型,并利用人类膝盖阻抗特性建立机器人阻抗控制模型; 2)基于示范学习和阻抗控制融合的机器人规划方法,其权重由机器人学习模型的置信度确定;以及3)自动请求新的演示数据并结合受试者反馈以改进机器人学习和阻抗控制模型。 该方法的性能将在生物力学模拟、健康受试者的实验室测试以及中风和帕金森病患者的试点研究中进行评估。 预计项目成果将使辅助机器人高度智能化,治疗师可以同时甚至远程与多名患者合作,这将大大降低治疗师的劳动强度和患者康复训练的成本。该奖项反映了NSF的法定使命,并通过使用基金会的智力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

期刊论文数量(8)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Invariant Extended Kalman Filtering for Human Motion Estimation with Imperfect Sensor Placement
  • DOI:
    10.23919/acc53348.2022.9867745
  • 发表时间:
    2022-05
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Zenan Zhu;S. M. R. Sorkhabadi;Yan Gu;Wenlong Zhang
  • 通讯作者:
    Zenan Zhu;S. M. R. Sorkhabadi;Yan Gu;Wenlong Zhang
Assessment of Human Dynamic Gait Stability With a Lower Extremity Assistive Device
Design and Evaluation of an Invariant Extended Kalman Filter for Trunk Motion Estimation With Sensor Misalignment
用于传感器失准躯干运动估计的不变扩展卡尔曼滤波器的设计和评估
  • DOI:
    10.1109/tmech.2022.3175988
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Zhu, Zenan;Sorkhabadi, Seyed Mostafa;Gu, Yan;Zhang, Wenlong
  • 通讯作者:
    Zhang, Wenlong
Robotic Shoe: An Ankle Assistive Device for Gait Plantar Flexion Assistance
机械鞋:一种用于步态跖屈辅助的踝关节辅助装置
  • DOI:
    10.1115/dmd2020-9058
  • 发表时间:
    2020
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Schaller, Marcus;Sorkhabadi, Seyed Mostafa;Zhang, Wenlong
  • 通讯作者:
    Zhang, Wenlong
Automatic virtual impedance adaptation of a knee exoskeleton for personalized walking assistance
  • DOI:
    10.1016/j.robot.2019.01.013
  • 发表时间:
    2019-04-01
  • 期刊:
  • 影响因子:
    4.3
  • 作者:
    Chinimilli, Prudhvi Tej;Qiao, Zhi;Zhang, Wenlong
  • 通讯作者:
    Zhang, Wenlong
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Wenlong Zhang其他文献

Short-term changes in simulated inundation frequency differentially affect inorganic nitrogen, nitrification, and denitrification in estuarine marshes
模拟淹没频率的短期变化对河口沼泽无机氮、硝化作用和反硝化作用的影响存在差异
  • DOI:
    10.1016/j.ecolind.2019.105571
  • 发表时间:
    2019-12
  • 期刊:
  • 影响因子:
    6.9
  • 作者:
    Weifang Hu;Wenlong Zhang;Linhai Zhang;Xianbiao Lin;Chuan Tong;Derrick Y.F. Lai;Yuemin Chen;Congsheng Zeng
  • 通讯作者:
    Congsheng Zeng
An adaptive rate control scheme for multi-screen sharing system based on H.264/SVC
基于H.264/SVC的多屏共享系统自适应码率控制方案
Trophic interactions regulate microbial responses to environmental conditions and partially counteract nitrogen transformation potential in urban river bends
营养相互作用调节微生物对环境条件的反应并部分抵消城市河湾的氮转化潜力
  • DOI:
    10.1016/j.jenvman.2022.116889
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    8.7
  • 作者:
    Haolan Wang;Wenlong Zhang;Yi Li;Yu Gao;Nan Yang;Lihua Niu;Huanjun Zhang;Longfei Wang
  • 通讯作者:
    Longfei Wang
Towards Untethered Soft Pneumatic Exosuits Using Low-Volume Inflatable Actuator Composites and a Portable Pneumatic Source
使用小容量充气致动器复合材料和便携式气动源的无束缚软气动外装
  • DOI:
    10.1109/lra.2020.2986744
  • 发表时间:
    2020
  • 期刊:
  • 影响因子:
    5.2
  • 作者:
    Saivimal Sridar;Souvik Poddar;Yida Tong;Panagiotis Polygerinos;Wenlong Zhang
  • 通讯作者:
    Wenlong Zhang
The role of microbial communities on primary producers in aquatic ecosystems: Implications in turbidity stress resistance
微生物群落对水生生态系统初级生产者的作用:对浊度胁迫抵抗力的影响
  • DOI:
    10.1016/j.envres.2022.114353
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    8.3
  • 作者:
    Wenlong Zhang;Pengcheng Zhou;Shenyang Pan;Yi Li;Li Lin;Lihua Niu;Longfei Wang;Huanjun Zhang
  • 通讯作者:
    Huanjun Zhang

Wenlong Zhang的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Wenlong Zhang', 18)}}的其他基金

Collaborative Research: SLES: Safe Distributional-Reinforcement Learning-Enabled Systems: Theories, Algorithms, and Experiments
协作研究:SLES:安全的分布式强化学习系统:理论、算法和实验
  • 批准号:
    2331781
  • 财政年份:
    2023
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
CCRI: Planning-C: Developing a Minecraft-based Testbed for Evaluating Human-AI Teaming Research
CCRI:Planning-C:开发基于 Minecraft 的测试平台,用于评估人类-人工智能团队研究
  • 批准号:
    2213827
  • 财政年份:
    2022
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
I-Corps: Wearable Soft Robotic Glove for Hand Assistance and Rehabilitation
I-Corps:用于手部辅助和康复的可穿戴软机器人手套
  • 批准号:
    2132714
  • 财政年份:
    2021
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
CAREER: Facilitating Human Interaction with Assistive Robots Through Intent Signaling and Inference
职业:通过意图信号和推理促进人类与辅助机器人的交互
  • 批准号:
    1944833
  • 财政年份:
    2020
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
NRI: FND: Scalable and Customizable Intent Inference and Motion Planning for Socially-Adept Autonomous Vehicles
NRI:FND:适用于社交自动驾驶车辆的可扩展和可定制的意图推理和运动规划
  • 批准号:
    1925403
  • 财政年份:
    2019
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
EAGER: Distributed Iterative Control of Soft Robotic Arms
EAGER:软机械臂的分布式迭代控制
  • 批准号:
    1800940
  • 财政年份:
    2018
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant

相似国自然基金

基于CHS-DRGs和诊疗全流程大数据挖掘的子宫肌瘤手术“主路径+支路径”的复合临床路径模式研究
  • 批准号:
  • 批准年份:
    2025
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
CHS-DRG模式下ICU老年患者CRE医院感染防控对策研究
  • 批准号:
  • 批准年份:
    2024
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
威尼斯镰刀菌中几丁质合成关键基因Chs调控菌丝体结构与蛋白消 化特性的机制研究
  • 批准号:
  • 批准年份:
    2024
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
PLA/GO/CHS导电分层缓释给药系统治疗长节段周围神经损伤的研究
  • 批准号:
  • 批准年份:
    2024
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
旁系同源CHS在柑橘黄酮类及花色苷合成通路中差异化调控的分子机制
  • 批准号:
    32302507
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
Chs 基因对红曲色素和桔霉素合成代谢的调控作用
  • 批准号:
    2021JJ31146
  • 批准年份:
    2021
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
红曲霉关键chs基因调控红曲色素和桔霉素合成的作用机制
  • 批准号:
  • 批准年份:
    2021
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
除虫菊CHS合成酶及其互作蛋白协同调控除虫菊酯合成代谢的催化机制解析
  • 批准号:
    31902051
  • 批准年份:
    2019
  • 资助金额:
    23.0 万元
  • 项目类别:
    青年科学基金项目
先进CHS结构柔性复合负极材料的可控制备及其储能构效关系研究
  • 批准号:
    61574122
  • 批准年份:
    2015
  • 资助金额:
    64.0 万元
  • 项目类别:
    面上项目

相似海外基金

CARDIOVASCULAR HEALTH STUDY (CHS) - TASK AREA C, STUDY CLOSEOUT
心血管健康研究 (CHS) - 任务领域 C,研究收尾
  • 批准号:
    10974001
  • 财政年份:
    2023
  • 资助金额:
    $ 17.5万
  • 项目类别:
CHS: Medium: Collaborative Research: Augmenting Human Cognition with Collaborative Robots
CHS:媒介:协作研究:用协作机器人增强人类认知
  • 批准号:
    2343187
  • 财政年份:
    2023
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Continuing Grant
CRII: CHS: RUI: Computational models of humans for studying and improving Human-AI interaction
CRII:CHS:RUI:用于研究和改善人机交互的人类计算模型
  • 批准号:
    2218226
  • 财政年份:
    2022
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
CHS: Smal: AI-Human Collaboration in Autonomous Vehicles for Safety and Security
CHS:Smal:自动驾驶汽车中的人工智能与人类协作以确保安全
  • 批准号:
    2245055
  • 财政年份:
    2022
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
CHS: Small: Towards Next-Generation Large-Scale Nonlinear Deformable Simulation
CHS:小型:迈向下一代大规模非线性变形模拟
  • 批准号:
    2244651
  • 财政年份:
    2022
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
CRII: CHS: Developing Youth Data Literacies through a Visual Programming Environment
CRII:CHS:通过可视化编程环境培养青少年数据素养
  • 批准号:
    2230291
  • 财政年份:
    2022
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
CHS: Medium: Collaborative Research: Empirically Validated Perceptual Tasks for Data Visualization
CHS:媒介:协作研究:数据可视化的经验验证感知任务
  • 批准号:
    2236644
  • 财政年份:
    2022
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
CRII: CHS: Harnessing Machine Learning to Improve Human Decision Making: A Case Study on Deceptive Detection
CRII:CHS:利用机器学习改善人类决策:欺骗检测案例研究
  • 批准号:
    2125113
  • 财政年份:
    2021
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
CHS: Small: Guiding future design of affect-aware cyber-human systems through the investigation of human reactions to machine errors
CHS:小型:通过研究人类对机器错误的反应来指导情感感知网络人类系统的未来设计
  • 批准号:
    2151464
  • 财政年份:
    2021
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Standard Grant
CHS: Small: Developing and Validating a Physically Accurate Light-Scattering Model for the Rendering of Bird and Other Dinosaur Feathers
CHS:小型:开发和验证用于渲染鸟类和其他恐龙羽毛的物理精确光散射模型
  • 批准号:
    2007974
  • 财政年份:
    2021
  • 资助金额:
    $ 17.5万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了