检索结果-内蒙古大学图书馆

Advanced Centroid State Estimation and Instability Detection Framework Leveraging UKF and AdvSAE-LSTM

IEEE Sensors Journal 2025年

作者： Mao, Han Zhu, Aibin Tu, Yao Song, Jiyuan Zheng, Chunli Li, Meng Xu, Peng Shi, Lei Liu, Yang Li, Xiao Guan, Zhenpeng Xi'an Jiaotong University Institute of Robotics and Intelligent Systems Shaanxi Key Laboratory of Intelligent Robots Xi'an710049 China Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System Xi'an710049 China Xi'an Jiaotong University School of Energy and Power Engineering Xi'an710049 China Xi'an Jiaotong University School of Mechanical Engineering Xi'an710049 China Xi'an Jiaotong University Honghui Hospital Xi'an710000 China Xi'an Jiaotong University Department of Sports Xi'an710049 China Xi'an Jiaotong University Second Affiliated Hospital Department of General Surgery Xi'an710004 China Fourth Medical Center of PLA General Hospital Department of Rehabilitation Senior Department of Orthopedics Beijing100048 China Sports Medicine and Rehabilitation National Clinical Research Center for Orthopedics Beijing100048 China Peking University Shougang Hospital Orthopedics Department Beijing100144 China

With the growing aging population, fall detection has become a significant research focus in recent years. However, most existing studies have not effectively improved the accuracy of centroid state estimation in human instability, particularly in terms of multi-source information fusion. To address this, we propose a centroid state estimation method based on the Unscented Kalman Filter (UKF), integrating data from the five-link model and trunk IMU sensors, significantly enhancing both the accuracy and robustness of centroid state estimation. Experimental results demonstrate that the proposed method achieves estimation errors of 0.0099 m and 0.0226 m/s for centroid displacement and velocity in the x-direction, and 0.0006 m and 0.0099 m/s in the y-direction, indicating high accuracy. To overcome the reliance of traditional supervised learning methods on large amounts of labeled data for instability state estimation, we propose an unsupervised learning-based instability state estimation method, featuring the AdvSAE-LSTM model. Data from different sensors are preprocessed and independent training datasets are constructed, after which the feature maps from each sensor are concatenated to form a global feature map. Compared to baseline methods, the proposed approach significantly improves instability state detection performance. Specifically, when the SAS threshold is set to 0.02, both the False Positive Rate (FPR) and False Negative Rate (FNR) are 0%, with a detection delay of only 77.16 ms, achieving highly efficient and accurate estimation of human instability states. © 2025 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Feasibility of integrating FES grasp assistance with a task-oriented robot-assisted therapy environment: A case study

Feasibility of integrating FES grasp assistance with a task-...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Dominic E. Nathan Michelle J. Johnson John McGuire Zablocki VA Medical Center Rehabilitation Robotics and Research and Design Laboratory Milwaukee WI USA Department of Biomedical Engineering Marquette University Milwaukee WI USA Department of Physical Medicine and Rehabilitation Medical College Milwaukee WI USA

Reaching-to-grasp is a vital skill to be relearned following stroke. Robotic aided stroke rehabilitation reduces motor impairment but has is limited in improving ADL function. We present a case study examining the feasibility of a custom developed glove to provide grasp assistance in a robotic therapy environment dedicated to the practice of real activities, ADLER. The case study consists of three subjects, a high functioning, and a low functioning stroke subject and a healthy subject. Results suggest that the glove system was able to providing grasp-assistance and that it was capable of collecting grasp aperture information during reach to grasp activities.

关键词： Robots Medical treatment rehabilitation robotics Apertures Feedback Biomedical engineering Biomechatronics USA Councils Haptic interfaces Head

来源：评论

学校读者我要写书评

暂无评论

A task-oriented, trajectory planner: Could it train stroke survivors to move normally on ADLs?

A task-oriented, trajectory planner: Could it train stroke s...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Rohit Ruparel Michelle J. Johnson Rehabilitation Robotics and Research and Design Laboratory Milwaukee WI USA Department of Biomedical Engineering Marquette University Milwaukee WI USA Design Lab Clement J. Zablocki Veterans Affairs Medical Center Milwaukee WI USA Department of Physical Medicine and Rehabilitation Medical College Milwaukee WI USA

When real objects are used in therapy their presence affects movement kinematics and hence the trajectories themselves. We examine the effectiveness of a trajectory planning algorithm to model the natural curving wrist movements observed in real life functional tasks. The fifth order minimum jerk model that incorporates curvature is used as a starting point for the model. The model was further developed and modified using observed data from able-bodied individuals. The model will be implemented as a trajectory planning tool for the ADLER environment where it could be used to train stroke survivors during functional tasks. We assessed differences between predicted and actual movements for medium to high functional stroke survivors on a drink task for several variables such as peak velocity, total displacement, movement smoothness, etc. We found that the model was capable of predicting movements smoothness and total displacement but not peak velocities in the horizontal or vertical planes of movement. Our next steps would be to improve and implement the model in the ADLER environment for stroke rehabilitation.

关键词： Medical treatment rehabilitation robotics Trajectory Kinematics Wrist Extremities Educational institutions Biomedical engineering Robots Biomechatronics

来源：评论

学校读者我要写书评

暂无评论

Methods for Evaluating Interlimb Coordination for Bimanual Robotic Therapy after Stroke

Methods for Evaluating Interlimb Coordination for Bimanual R...

引用

IEEE International Conference on rehabilitation robotics (ICORR)

作者： Sarah Wang Michelle J Johnson Rehabilitation Robotics Research and Design Laboratory Zablocki VA Medical Center Milwaukee WI USA Department of Biomedical Engineering Marquette University Milwaukee WI USA Department of Physical Medicine and Rehabilitation Medical College Milwaukee WI USA

Deficits in interlimb coordination(IC) contribute to the functional disability in stroke patients. Addressing IC deficits after stroke has been somewhat overlooked in the realm of robotic bilateral stroke interventions. Our goal is to develop a robotic therapy protocol to improve IC for bimanual tasks and to assess changes in IC due to therapy. We evaluated the metrics of phase difference (PD), goal synchronization (GS), task completion time (TCT), % movement overlap (%MO) to determine which are most sensitive to IC on both symmetric and asymmetric bimanual functional tasks (e.g., drink and feed). We assessed IC for able-bodied and strokes. We showed PD, TCT, and %MO to be sensitive to differences in IC across subject groups. PD was more sensitive in the symmetrical task while TCT and %MO were more sensitive in the asymmetrical task. Creating a robotic intervention with these metrics will enable us to explore the efficacy of addressing coordination deficits after stroke.

关键词： Robot kinematics Medical treatment rehabilitation robotics Mutual coupling Robot sensing systems Biomedical engineering Protocols Feeds Medical robotics Arm

来源：评论

学校读者我要写书评

暂无评论

design of a Grasp Assistive Glove for ADL-focused, Robotic Assisted Therapy after Stroke

Design of a Grasp Assistive Glove for ADL-focused, Robotic A...

引用

IEEE International Conference on rehabilitation robotics (ICORR)

作者： Dominic E. Nathan Michelle J. Johnson Rehabilitation Robotics Research and Design Laboratory Zablocki VA Medical Center Milwaukee WI USA Department of Biomedical Engineering Marquette University Milwaukee WI USA Department of Physical Medicine and Rehabilitation Medical College Milwaukee WI USA

Reaching to grasp is an essential process in our everyday lives. Individual who suffer a stroke experience major deficits in this ability leading to compromised activities of daily living (ADL), employment, and social interaction. Robotic aided therapy is at the forefront of stroke rehabilitation, however not many systems support functional goal oriented therapy using real world objects. We are interested in designing a grasp assistive component for our ADL-focused robotic therapy environment. This paper reports on the glove development and a static validation study to determine the accuracy and repeatability of the glove in the measurement of joint angles of the thumb and index fingers and grasp aperture, which is the distance between the fingers. Our results showed no significant differences between the glove and a hand-held goniometer for the measured joint angles and the derived grasp aperture. The results suggest that the glove is repeatable and has the potential to measure in vivo grasp aperture during a functional tasks. Our next steps are to complete a dynamic validation study and integrate the glove with our robotic environment.

关键词： Robots Medical treatment rehabilitation robotics Biomedical measurements Employment Goniometers Fingers Apertures Biomedical engineering Thumb

来源：评论

学校读者我要写书评

暂无评论

Development of ADLER: The Activities of Daily Living Exercise Robot

Development of ADLER: The Activities of Daily Living Exercis...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： M.J. Johnson K.J. Wisneski J. Anderson D. Nathan R.O. Smith Department of Biomedical Engineering Olin Engineering Center Marquette University Milwaukee WI USA Department of Physical Medicine & Rehabilitation Medical College Milwaukee WI USA Rehabilitation Robotics Research and Design Laboratory Medical College Milwaukee WI USA Rehabilitation Research Design and Disability Laboratory University of Wisconsin Milwaukee Milwaukee WI USA

Robot-assisted therapy devices are being used in the physical and neurological rehabilitation of persons after stroke, which is the leading cause of disability among adults in the United States. Motor gains after robot-assisted therapy may not transfer to functioning on activities of daily living. It is conceivable that carryover after training may be improved through the use of training activities that are patient-centered, engaging and focused on daily living activities. We have developed the activities of daily living exercise robot (ADLER) stroke training environment to test this idea. This environment permits the consistent and repeated practice of daily living tasks such as drinking. This paper describes the ADLER training system

关键词： Robots rehabilitation robotics Medical treatment Medical robotics robotics and automation Educational institutions Biomedical engineering Orbital robotics design engineering Testing

来源：评论

学校读者我要写书评

暂无评论

Should Object Function Matter during Modeling of Functional Reach-to-Grasp Tasks in Robot-Assisted Therapy?

Should Object Function Matter during Modeling of Functional ...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

Recent literature support the idea of using an intense, task-oriented, stroke rehabilitation to promote motor learning and cerebral reorganization. Supporting a task-oriented, robot-assisted therapy approach requires better understanding of the components of real tasks and the limitations and benefits of current trajectory models. We set out to understand natural reach-to-grasp kinematics as it relates to various functional bilateral and unilateral tasks so as to better map this information to a robotic reach-to-grasp therapy systems. To do so, we investigated the influence of arm use and object functionality on four reaching kinematics in reach-to-grasp daily living tasks. We compared our results with the minimum jerk trajectory model used in robot-assisted therapy with the goal of understanding how best to support these real movements in a robotic environment. Eight neurologically intact, right handed subjects participated in the motion analysis study. They completed unilateral and bilateral reaching to objects in the same location with the same orientation, and with handles of the same size and shape. We discuss our results in terms of the minimum jerk model, which is typically used in robot-assisted trajectory planning. Our results showed significant differences in peak velocities, movement time and total displacement across tasks and across arm use conditions

关键词： Medical treatment Robot kinematics rehabilitation robotics Trajectory Shape Biomedical engineering Acceleration Cities and towns USA Councils Motion analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：