This paper presents the design concept of an Instrumented Compliant Anatomical Palmar Mechanism (I-CAPM), which leverages the deformable curvatures of compliant beams to reconstruct the palm's displacement and force fields during grasping. The I-CAPM models the human palm using eight cantilever beams, with four beams converging at the thumb knuckle and the remainder individually connecting to the finger knuckles, emulating the human hand's oblique, transverse, and longitudinal arches. To enable independent analysis, each decoupled cantilever is embedded with a strain sensor array, allowing for field reconstruction on a single beam level. This architecture simplifies computational modeling and facilitates robust strain field reconstruction, deformation analysis, and real-time force perception. The methodology for characterizing the displacement and force fields of the beams is numerically illustrated and validated using commercial finite-element analysis (FEA). © 2025 IEEE.

This article presents a multi-DOF motion sensing system consisting of a permanent magnet (PM) and a magnetic tensor sensor (MTS) comprising a 3 x 3 array of three-axis digital magnetic flux density (MFD) sensors, and the methods to measure their relative MTS-PM position/orientation in a 3-D space. The design enables redundant differential measurements of MFD vectors and gradient tensor components to account for the singularities due to matrix inversion, providing a basis to explore different methods for multi-DOF estimation of the PM position/pose. Formulated as a two-stage linear least-square (LS) problem to take advantage of the dipole simplicity and exploit its physics revealed by its inverse model to guide the design of a fully connected artificial neural network (ANN) to account for the MTS measurement noise and un-modeled factors, a prototype multi-MTS system capable of 5-DOF motion measurements is developed and evaluated experimentally along with a study analyzing the parametric effects on the estimation accuracy; both stationary and moving sensor scenarios are considered. Enhanced with a fully connected ANN, an accuracy within a root-mean-square error (RMSE) of 40 mu m spatial position and 0.1 degrees pose can be uniquely obtained without subtracting a predetermined geomagnetic field in both fixed and moving multi-MTS scenarios, representing a significant improvement over the (0.5 mm, 1 degrees) RMSE of the single-MTS.

This article offers an impedance sensing method taking advantage of the conductivity changes due to muscle contraction to estimate muscle-driven joint torques through a convolutional neural network (CNN), where the input images are derived from a finite set of boundary voltage measurements. Guided by a physical model combining the forearm biomechanics and the muscle electric field along with the CNN criteria considering the receptive fields (RFs), the effects of two image formats [for quasi-static (QS) and dynamic (DYN) states] on the CNN performance are experimentally studied on eight human subjects' forearms using a prototype impedance sensing system. By comparing the CNN-estimated torques with that measured on a haptic device, the findings verify that the impedance-based method can estimate the joint torques driven by both the deep and superficial muscles within 9% errors of the three degrees-of-freedom wrist torque and 10% error of the gripping torque and that it is feasible to share data among a similar group to reduce data collection and time when training a CNN for uses on a new subject.

This article presents a three-degree-of-freedom (3-DOF) magnetic sensor, referred to here as a pantographic exoskeleton (PGE) sensor, for monitoring in real time the internal human-joint motion in the sagittal plane. With two sets of embedded magnetic sensors and a permanent magnet, the PGE wearable on a healthy leg or lower extremity exoskeleton (LEE) independently measures the 2-DOF translations and the joint angle. Two sensor estimation methods, which are the model-based and the artificial neural network (ANN), are experimentally analyzed in the presence of measurement noise. As an illustration, the PGE sensors are evaluated for sit-to-stand (STS) exercises, where the real-time measurements are verified by comparing with the joint angles determined by a commercial VICON motion capture system, and the translational deviations measured on a 4-DOF platform manipulated to follow a specified internal motion trajectory of an ankle joint during STS. With the ANNs appropriately trained to account for measurement noise, the PGE sensors can track the joint angles while measuring the internal motions of both legs with or without the LEE demonstrating that the PGE sensor has the potential to serve as an indicator of stroke rehabilitation where patients lack force perception and suffer an increased risk of falls due to the weak affected leg.

随着机电一体化和计算机技术的发展,越来越多的学者将目光投向医疗康复领域。在我国,脑卒中患者的发病率居高不下,发病年龄呈现越来越低的趋势,大多患者在紧急治疗后出现偏瘫、行动困难的状况,最佳康复手段是由护理师协助完成长期训练任务,由于康复护理资源的缺乏,很多患者不得不选择居家静养,错过最佳康复期。本文根据他们的实际需求,设计一款用于下肢康复训练的多功能轮椅,通过支撑人体重力的方式辅助使用者完成坐站转换,通过肌肉训练恢复肌力,刺激受损神经组织的恢复。首先以健康青年人为研究对象,利用Vicon运动捕捉系统采集人体主动完成坐站转换过程中的运动数据,使用Open Sim计算运动中的关节角和关节力矩。通过分析计算结果,将减重支撑作为减轻下肢负担的核心,确定骨盆作为轮椅作用对象,坐骨结节作为主要受力点,使用圆弧对坐骨结节轨迹进行拟合,作为轮椅末端执行器的设计标准。基于人体运动轨迹和偏瘫康复方法,完成多功能轮椅的设计。在结构设计方面,多功能轮椅提供抬腿、仰背和坐站转换三种功能,以轮椅式结构为框架便于患者的移动。辅助站立结构采用电动推杆和平行连杆作为执行机构,还原拟合的圆弧轨迹,同时末端执行器始终水平,保证身体平衡。在控制方面,使用PC建立人机交互界面,PC通过USBCAN模块与驱动器通信,对电机的转速和电流（力矩）进行控制,以实现被动训练和半主动训练两种模式,用于康复的不同时期。将三维结构模型导入骨骼肌肉模型形成耦合模型,将电动推杆运动和人机交互力作为仿真输入,进行逆运动学耦合仿真分析。结果表明,轮椅辅助模式具有良好的舒适性,耦合仿真中关节力矩明显降低,可以降低从坐到站过程中下肢关节负担,验证结构设计合理性。最后,根据设计制作实物样机,通过辅助坐站转换实验,分析其性能状况。实验中,多功能轮椅能够帮助实验对象平稳完成从坐到站动作,足底压力明显降低。通过Open Sim进行生物力学分析,结果显示,和人体主动完成坐站转换相比,辅助站立实验中关节力矩和肌肉力明显下降,减轻了患者下肢关节和肌肉负担。因此可以得出结论,轮椅辅助站立设计在坐站转换中起到一定辅助作用,可以做进一步的临床研究。

城市地铁、火车站、机场等公共场所具有人员密集程度高、客流量大等特点,它们是犯罪潜逃甚至恐怖分子袭击的重要场所,这些场合对智能视觉监控技术的需求日益增加,人体步态作为一种具有非接触、非侵犯性、难以伪装和模仿及可远距离检测等特点的新型生物特征,其在交通公共安全领域中将发挥无可替代的作用。在人工智能快速发展的推动下,基于步态的身份识别技术也有了新的突破,但技术上还存在着因服饰改变、外携物品、视角问题、步行速度等带来的挑战以及不能做到实时处理,使得基于步态的身份识别与监控系统无法大面积投入使用。本文针对多视角下的服饰改变、携带物等协变量导致身份识别不理想的问题,以深度学习技术为基础,提出基于人体行走特征矢量图的步态识别方法,主要工作如下:（1）针对步态识别任务多数要求能实时处理在室外较复杂环境的情况,提出基于基础网络为Mobilenet的人体姿态估计算法OpenPose进行人体行走特征矢量图的获取,即首先使用YOLOV3网络结合步态轮廓高宽比方法对数据集进行步态平均周期的提取,以此作为步态时空网络的超参数timestep的设置,之后剔除与步态识别任务无贡献的头部PAFs且进行数据标准化,最后将PAFs按照时间序列进行堆叠,则形成了本文提出的人体行走特征矢量图。在CASIA-B部分数据集进行了实验,实验结果表明,这种方法获得的特征描述既保留丰富的时空信息又避免了冗余信息不利于时空网络的特征学习、模型的训练,能较好解决服饰改变、携带物等协变量引发的识别困难的问题。（2）针对现有的步态特征学习与识别算法对多视角下的服饰改变、携带物等协变量问题导致算法鲁棒性差的问题进行了创新,设计了一种能较好解决多视角下的服饰改变、有携带物影响的神经网络,即把人体行走步态矢量图作为输入的步态时空网络,该时空网络是基于残差学习模块学习步态空间特征和基于LSTM学习步态时间特征的特征学习与识别网络,在网络末端Softmax层进行分类判决。（3）组建了18个视角下的三种步行状态（普通、服饰改变、携带物）的室外数据库,且在数据库进行了多视角下同状态和跨状态实验,验证了基于人体行走特征矢量图的步态识别方法的适用性及鲁棒性。最后,在上述算法研究的基础上,利用Tensorflow、OpenCV、PyQt设计和实现了基于人体行走特征矢量图的身份识别系统,并使用该系统在自建数据库中完成了步态识别测试,取得了较好的效果,说明所提方法能有效提升多视角下考虑服饰改变、携带物的算法识别率和鲁棒性。

This paper presents a design method based on distributed current source (DCS) that discretizes the permanent magnets (PMs) and electromagnets (EMs) into elemental current sources and derives the magnetic field and current-force models for design analyses of a 3-degree-of-freedom (3-DOF) planar motor with redundant inputs. The DCS models have been verified by comparing them with exact solutions and commercial finite element analysis (FEA). The results show that the DCS models are accurate (within 2.5% of exact solutions) and computationally efficient (a three-order improvement over FEA). As an illustration, the analytically derived DCS models are employed to analyze the geometrical constraints and parametric effects on the PM/EM layout and forces/torque performance of a 3-DOF planar motor. Using singular value decomposition, two designs are numerically evaluated. With the closed-form DCS models, the loci of the best/worst manipulability ellipsoids are graphically presented. © 2023 IEEE.

脑-接口技术（Brain Computer Interface,BCI）是指从人的大脑建立一条与外部辅助设备联系的通路以达到利用外部辅助设备完成大脑想要完成的任务,近些年来被广泛的研究并应用在医疗康复等众多领域。BCI技术主要目标是帮助患者进行恢复训练,甚至替代某些严重损伤的肢体。但是BCI的发展并不能满足实际的需求,其存在背景噪声较大导致信噪比较低、信号采集比较困难、由被试间差异等影响导致分类结果比较低等问题,所以目前BCI技术更多的是在研究阶段,距真正应用在生活中还存在一定的距离。本文基于脑电信号的研究基础,设计并开展针对右下肢不便患者的运动想象脑电信号（Electroencephalogram,EEG）采集实验,其目的是通过对信号的分析实现对不同任务的识别,从而给外部设备输出相关控制指令。主要工作内容如下:（1）基于对BCI系统前期的分析研究,本文基于Unity与Kinect技术设计并搭建了虚拟现实的实验平台,并将其分为训练实验部分和采集实验部分。阐述了运动想象脑电信号的产生机理、特点以及按照幅值大小进行了分类。（2）EEG信号特性分析。首先对采集的EEG信号进行预处理,并利用带通滤波以及独立成分分析（Independent Component Analysis,ICA）等方法去除噪声得到较为干净的信号。其次选择三通道数据,并分析脑电信号的时频特性确定选择三通道数据存在事件相关去同步（Event-Related Desynchronization,ERD）现象从而证实了选择数据的可分析性。同时由于不同被试之间存在生理差异,所以选择不同患者的最佳时频段作为后期的研究数据。最后利用公共空间模式（Common Spatial Pattern,CSP）的方法提取脑电信号的特征并分析特征值的可分性。（3）针对脑电信号分类效果不佳的现状,本文选择了PSO-SVM方法和改进的卷积神经网络（Convolutional Neural Network,CNN）方法对脑电信号进行分类。首先利用支持向量机（Support Vector Machine,SVM）方法对CSP提取的特征进行分类识别,同时利用粒子群优化算法（Particle Swarm Optimization,PSO）寻找SVM最优参数。其次设计了十层的CNN模型,并引用批量归一化（Batch Normalization,BN）以消除运算过程出现的梯度消失问题,结果表明BN-CNN模型在收敛速度和分类效果方面有较好的提升,同时分析了Dropout参数对BN-CNN网络的影响。最后对本文选择的两种算法的实验结果进行分析,表明改进后的BN-CNN网络在识别结果上更优。

This article offers an image processing method to optimize the design of a three-level color machine vision algorithm illustrated in the context of presenting a whole chicken carcass for subsequent handling, which overcomes some common problems in image segmentation, feature identification, and pose estimation for classifying, identifying, and locating poultry meat products. First, artificial color contrast and principal component analysis are optimized to enhance the contrast between similar colors to extract targeted regions more effectively. Second, the boundaries of poultry products are mostly smooth curves that are proposed as features for object recognition. Third, image feature points are found using template matching, from which the object (size, location, and pose) can be accurately determined. The algorithm simplifies the complex edges of a poultry product into a finite number of arc-centers, which greatly improves the efficiency/accuracy of the matching for part-presentation. Evaluated with 100 randomly posed samples, the algorithm has a success rate of 93%. The 7% failures were primarily due to missing points, which can be eliminated by incorporating more template points.

Illustrated in the context of home-based stroke rehabilitation, this paper presents the design and development of magnetic flexonic sensor nodes (FSNs) with configurable parameters for simultaneous sensing of normal forces and displacement. The FSN is composed of a magnetic sensor in flexible elements that can be embedded in wearable devices and rapid-prototyped at a low cost to facilitate distributed force sensing applications. As an illustration, a shoe insole with 19 embedded FSN for monitoring the plantar force distribution and arch height has been designed, prototyped, and experimentally evaluated by comparing it with a commercial dynamometric platform. The FSN-embedded insole directly measures the arch height and captures the transients of the plantar forces in five different zones in real-time. Because of the simplicity and low cost, FSNs have the potential to facilitate fabricating low-cost sensing systems, for example, for home-based stroke rehabilitation where the insole stiffness and arch height of the embeddable electronic sensors can be configured according to the patient's specific abnormal plantar distribution to adapt to different range and distribution and wearable configuration during different rehabilitation state. © 2016 IEEE.