考虑跖趾关节运动的踏板式步行康复机器人运动规划

基于人正常步行时足部的运动特征,提出了一种利用机械约束即能实现步行时踝关节和跖趾关节运动姿态模拟的踏板式步行康复机器人,帮助老年人及偏瘫患者进行步行康复训练.通过分析步行时跖趾关节的背屈过程,对前踏板的运动姿态进行规划,并以此确定了约束导轨的轨迹.按照人正常平地步行过程对步行训练时双侧踏板的运动时序进行了规划,并根据步行时的时相分布关系规划了双侧曲柄的转速.利用MATLAB软件建立步行康复机器人的运动学仿真模型,验证了运动规划的可行性,说明该步行康复机器人可以模拟正常人步行时的步态及踝关节和跖趾关节的运动姿态,能够满足步行康复训练的要求.     

仿人机器人动态步行控制综述

综述了仿人机器人动态步行的研究历史和研究现状。归纳了动态步行的特点,分析了动态步行稳定性判定方法,介绍了基于ZMP的姿态稳定判据和基于庞加莱映射（Poincaré Map）的步态稳定判据。总结了仿人机器人学习适应复杂地面环境步行的方法,概述了动态步行控制实现的典型解决方案,指出了动态步行控制中待解决的问题,并探讨了未来的发展方向。     

速度受限的全方向康复步行训练机器人Backstepping补偿跟踪控制

全方向康复步行训练机器人需要跟踪医生指定的训练轨迹、针对运动过程中速度过快而影响康复者安全性问题,提出一种基于Backstepping补偿方法的速度受限型控制器设计方案,目的是保证康复者的安全训练.通过限制实际运动速度的幅值,并根据所提出轨迹跟踪误差和速度跟踪误差的实时补偿方法,实现了全方向康复步行训练机器人在安全速度下的轨迹跟踪.基于李亚普诺夫稳定性理论和LaSalle不变性原理,证明了补偿误差系统和跟踪误差系统的渐近稳定性.通过仿真结果对比分析,表明了所提控制器设计方法的有效性和可行性.     

人机不确定条件下康复步行训练机器人的部分记忆迭代学习限速控制

为了提高康复步行训练机器人的跟踪精度及安全性,提出了一种带有运动速度约束和部分记忆信息的自适应迭代学习控制方法,目的是抑制人机不确定性及速度突变对系统跟踪性能的影响.在考虑人机不确定性的基础上,建立了康复步行训练机器人的动力学模型.提出了基于模型预测的速度约束方法,通过限制每个轮子的运动速度,约束了机器人的实际运动速度.进一步,利用受约束的运动速度建立了动力学跟踪误差系统,提出了具有部分记忆信息的自适应迭代学习控制器设计方法,并验证了跟踪误差系统的稳定性.仿真对比分析和实验研究结果表明,文中提出的控制方法能抑制人机不确定性并使康复者在安全速度下完成步行训练.     

一种类人机器人步行鲁棒控制器

提出了一种应用于类人步行机器人研究平台的鲁棒控制算法,当机器人在步行过程中受到一定程度的 外界冲力等干扰时,它可以使机器人自主达到动态平衡,而且该算法具有一定的实时性．通过一个九连杆的仿人平 面机械系统,分析了机器人步行的动态过程;应用科氏力向量等建立起机器人步行的动力学模型,通过非线性补偿, 得出其渐近稳定控制的约束性条件;进而构造出理想的李亚普诺夫函数,并应用遗传算法进行参数优化,设计出具 备一定实时性能的鲁棒控制算法;仿真计算出机器人各个关节的角位移误差,其零力矩点（ZMP）始终在支撑脚的 范围内,重心轨迹在地面的投影基本位于正弦曲线上．将该算法应用于实际的类人步行机器人行走控制中,实验证 明,在受到一定程度的外扰影响时,该机器人可在短执行周期内自主达到动态平衡．     

双足机器人预观控制的ZMP补偿步行模式研究

针对双足机器人的稳定行走,提出了一种预观控制的零力距点（ZMP）补偿步行模式在线生成方法。利用实际ZMP与目标ZMP之间的未来误差信息,基于预观控制计算机器人行走过程中质心的补偿量,事先调整质心轨迹来改变步态。最终使实际ZMP更好地跟踪目标值。12自由度的双足机器人动力学仿真验证了所提出方法的有效性,而且机器人能在一定程度不平整地面上实现稳定行走。     

下肢康复机器人离散自适应控制的研究

康复训练是脑卒中、脊髓损伤患者主要的治疗手段.机器人辅助步行训练是近年来广泛应用的下肢康复训练方式.针对具有步态自适应功能的下肢康复机器人,提出了一种柔顺协调控制方法.基于非线性逆系统解耦理论,系统分解为几个独立的二阶积分系统.在解耦子系统中,采用阻抗和自适应控制来进行步态轨迹的规划和跟踪.最后,在Matlab-Adams联合仿真系统中对设计的控制器进行仿真并验证算法的正确性.     

飞行员静息态脑功能度中心度特征研究

度中心度的实质是计算单个体素与全脑所有体素之间的脑功能网络连接强度,使用度中心度分析方法对飞行员与地面职业者进行分析,探讨飞行员与地面职业者大脑功能差异的脑区。选取26名飞行员作为飞行组和24名地面职业者作为对照组,采集RS-fMRI数据,计算出相对应的DC值,然后在组间差异区间内对两组DC值做双样本t检验,最后定位差异脑区,并进一步分析差异脑区与飞行时长之间的相关性。通过数据处理发现飞行组左侧辅助运动区的DC值（P<0.001）相较于地面组有明显的增高,且该值与飞行时长呈显著正相关（双尾检验,r=0.450, P=0.027）。飞行员在静息态下左侧辅助运动区的功能活动与普通职业者之间存在明显差异。该区域与运动前准备阶段中的信息筛选、运动起始等功能有关,因此,结果可能意味着经过系统化的飞行训练,飞行员在信息筛选、运动起始等方面的能力有所提高。     

面向人脸年龄估计的深度融合神经网络

目的 为了提高人脸图像年龄估计的精度,提出一种端对端可训练的深度神经网络模型来进行人脸年龄估计。方法 该网络模型由多个卷积神经网络（CNN）和一个深度置信网络（DBN）堆叠而成,称为深度融合网络（DFN）。首先使用多个并联的CNN提取人脸图像多个区域的外观特征,将得到的特征进行串接输入一个DBN网络进行非线性融合。为了实现DFN的端到端的整体训练,提出一种逐网络迭代训练（INWT）的机制。为了降低过拟合效应,那些对应人脸局部图像的CNN经过多次迭代迁移学习实现面向人脸年龄估计任务的训练。完成对DFN中所有CNN和DBN的预训练后,再进行全网络端到端的整体精调。结果 在两个人脸年龄图像库MORPHⅡ和FG-NET上对本文方法进行测试,实验结果显示基于DFN的人脸年龄估计方法能在两个人脸图像库中分别取得平均绝对误差（MAE）等于3.42和4.14的估计精度,与目前主流的年龄估计算法,如基于浅层学习的CA-SVR方法（两个数据库上取得的MAE分别等于5.88和4.75）,基于深度学习的DeepRank+方法（MORPHⅡ数据库上取得的MAE为3.49）和Deep-CS-LBMFL方法（FG-NET数据库上取得的MAE为4.22）等相比,估计精确度明显提高。结论 本文提出基于深度融合网络的人脸年龄估计方法与当前大部分基于深度神经网络的主流算法相比具有明显的优势。     

网络机器人研究与发展分析

0.前言 90年代后期,丰田双足步行机器人P2和索尼AIB0等对机器人热潮起到了推波助澜的作用;日本和韩国在2004年都推出了下一步国家信息化战略,分别称作u—Japan和u—Korea。日本政府的u—Japan计划着力发展泛在网络（Ubiquitous Network,简称UN）和相关产业,希望由此催生新一代信息科技革命。     

下肢康复机器人系统设计与协调控制算法

脑卒中、脊髓损伤、下肢退行性关节疾病等神经系统疾病会导致肢体功能障碍,需要进行有针对性和重复性的训练.本文设计了一款可以切换坐、立、躺三种模式的轮椅式下肢康复机器人,在机器人站立姿态的主动步行训练模式下,解算人体前进速度映射轮椅式底盘电机速度,实现了下肢功能障碍患者步态训练与机器人轮椅式车体的协调控制.实验结果表明,下肢外骨骼行走的速度曲线和轮椅式车体的速度曲线基本一致,实现人与机器人的协调控制.     

Initial System Evaluation of an Overground Rehabilitation Gait Training Robot (NaTUre-gaits)

For decades, robotic devices have been suggested to enhance motor recovery by replicating clinical manual-assisted training. This paper presents an overground gait rehabilitation robot, which consists of a pair of robotic orthoses, the connected pelvic arm in parallel and a mounted mobile platform. The overground walking incorporates pelvic control together with active joints on the lower limb. As a preliminary evaluation, system trials have been conducted on healthy subjects and a spinal cord injury (SCI) subject, respectively. Electromyography signals were recorded from muscles of the lower limb for each subject. Three experiments were carried out: (i) health volunteers walking at self-preferred walking speed, (ii) a SCI subject walking with the help of three helpers and (iii) the same SCI subject walking with the assistance provided by the gait device. In the experiment, the muscle activation of overground walking was compared between the manual-assisted and robotic-assisted methods. The initial results show that the performance of the device can provide impact-less overground walking and it is comparable to the performance obtained by manual assistance in gait rehabilitation training.     

理疗师交互下的下肢康复训练机器人个性化步态规划方法

针对偏瘫患者的个体差异及病况差异,提出了一种理疗师交互下的下肢康复训练机器人步态规划方法,在理疗师-减重悬吊式康复训练机器人-患者三者共存的复杂环境中,理疗师穿戴主控外骨骼直接行走实现步态时空参数规划,并融入理疗师的医学经验及对患者的评估.首先,基于旋量理论建立运动学模型,实现理疗师空间与机器人空间的运动映射;然后,统一规划机器人关节运动轨迹、减重机构重心调整轨迹及跑步机步速.最后,通过理疗师步态参数的实时采集、运动映射实验及机器人轨迹跟踪实验,验证了步态时空规划方法的有效性.结果表明,髋、膝关节规划角度在人体关节活动范围内,速度变化平稳,关节轨迹规划和重心调整规划均符合人体行走的生理特性.理疗师的参与实现了渐进康复训练中的个性化步态规划.     

一种下肢康复机器人步态的生成与调节方法

针对下肢康复外骨骼机器人康复训练参考步态的标准化设计,对平地行走、上楼梯和下楼梯等不同情境下的步态轨迹的设计问题进行研究,提出了由无线惯性传感器采集人体步态,利用基于关键点的步态生成与调节方法,得到了融合过渡过程的参考步态曲线.利用得到的参考步态曲线指导下肢康复外骨骼式机器人辅助人体在平地行走、上楼梯和下楼梯等情景下进...     

A test of two training interventions to prevent work-related musculoskeletal disorders of the upper extremity

We investigated, on behalf of a large electronics manufacturer, two types of worker training interventions for their efficacy in preventing unnecessary muscle tension and the symptoms of work-related musculoskeletal disorders. The first intervention, Muscle Learning Therapy (MLT), used electromyographic (sEMG) feedback and operant conditioning to decrease muscle tension during complex work tasks. The second intervention used adult learning and cognitive behavioral techniques in small group discussion to advance the worker's capabilities for symptom and stress management and problem-solving. Workers were randomly assigned to a control group or one of the two treatment conditions. Prior to training, baseline data were collected using symptom diaries and sEMG recordings of the trapezius and forearm muscles of the left and right arms. The training interventions were conducted for 6 weeks with reinforcement training provided at 18 and 32 weeks post-baseline. Follow-up data were collected after the initial 6-week training period and at 32 weeks, prior to the reinforcement training. Symptom outcomes demonstrated significant differences at 6 weeks, increasing in severity for the control group and declining modestly for the educational group, with little change for the MLT group. These differences were not maintained at further follow-up. The MLT group was consistently effective in reducing muscle tension in the trapezius areas after 6 and 32 weeks, and was partially effective for the forearms. Further testing is recommended of these training interventions, especially with the inclusion of strategic, periodic reinforcement of the worker's learning.     

基于姿态估计与GRU网络的人体康复动作识别

康复锻炼是脑卒中患者的重要治疗方式,为提高康复动作识别的准确率与实时性,更好地辅助患者在居家环境中进行长期康复训练,结合姿态估计与门控循环单元(GRU)网络提出一种人体康复动作识别算法Pose-AMGRU。采用OpenPose姿态估计方法从视频帧中提取骨架关节点,经过姿态数据预处理后得到表达肢体运动的关键动作特征,并利用注意力机制构建融合三层时序特征的GRU网络实现人体康复动作分类。实验结果表明,该算法在KTH和康复动作数据集中的识别准确率分别为98.14%和100%,且在GTX1060显卡上的运行速度达到14.23frame/s,具有较高的识别准确率与实时性。     

Machine learning approach to model sport training

The aim of this study was to use a machine learning approach combining fuzzy modeling with an immune algorithm to model sport training, in particular swimming. A proposed algorithm mines the available data and delivers the results in a form of a set of fuzzy rules “IF (fuzzy conditions) THEN (class)”. Fuzzy logic is a powerful method to cope with continuous data, to overcome problem of overlapping class definitions, and to improve the rule comprehensibility. Sport training is modeled at the level of microcycle and training unit by 12 independent attributes. The data was collected in two months (February-March 2008), among swimmers from swimming sections in Wroc?aw, Poland. The swimmers had minimum of 7 years of training and reached the II class level in swimming classification from 2005 to 2008. The goal of the performed experiments was to find the rules answering the question - how does the training unit influence swimmer’s feelings while being in water the next day? The fuzzy rules were inferred for two different scales of the class to be predicted. The effectiveness of the learned set of rules reached 68.66%. The performance, in terms of classification accuracy, of the proposed approach was compared with traditional classifier schemes. The accuracy of the result of compared methods is significantly lower than the accuracy of fuzzy rules obtained by a method presented in this study (paired t-test, P < 0.05).     

Reality-based practice under pressure improves handgun shooting performance of police officers

The current study examined whether reality-based practice under pressure may help in preventing degradation of handgun shooting performance under pressure for police officers. Using a pre–post–test design, one group of nine police officers practised handgun shooting under pressure evoked by an opponent who also fired back using marking (coloured soap) cartridges. The control group (n = 8) practised handgun shooting on standard cardboard targets instead of real opponents. Within a fortnight after the pre-test, both groups received three training sessions of 1 h, in which each person fired a total of 72 rounds. During the pre- and post test each participant took 30 shots without pressure (cardboard targets) and 30 shots under additional pressure (with an opponent firing back). While during the pre-test both groups performed worse in front of an opponent firing back compared to the cardboard targets, after the training sessions shooting performance of the experimental group no longer deteriorated with an opponent while performance of the control group was equally harmed as during the pre-test. These results indicate that training exercises involving increased pressure can acclimatize shooting performance of ordinary police officers to those situations with elevated pressure that they may encounter during their police work.     

Effects of intermittent hypoxic training on aerobic and anaerobic performance

The aim of the present study was to determine whether short-term intermittent hypoxic training would enhance sea level aerobic and anaerobic performance over and above that occurring with equivalent sea level training. Over a 4-week period, two groups of eight moderately trained team sports players performed 30 min of cycling exercise three times per week. One group trained in normobaric hypoxia at a simulated altitude of 2750 m (F(I)O2= 0.15), the other group trained in a laboratory under sea level conditions. Each training session consisted of ten 1-min bouts at 80% maximum workload maintained for 2 min (Wmax) during the incremental exercise test at sea level separated by 2-min active recovery at 50% Wmax. Training intensities were increased by 5% after six training sessions and by a further 5% (of original Wmax) after nine sessions. Pre-training assessments of VO(2max), power output at onset of 4 mM blood lactate accumulation (OBLA), Wmax and Wingate anaerobic performance were performed on a cycle ergometer at sea level and repeated 4-7 d following the training intervention. Following training there were significant increases (p < 0.01) in VO(2max) (7.2 vs. 8.0%), Wmax (15.5 vs. 17.8%), OBLA (11.1 vs. 11.9%), mean power (8.0 vs. 6.5%) and peak power (2.9 vs. 9.3%) in both the hypoxic and normoxic groups respectively. There were no significant differences between the increases in any of the above-mentioned performance parameters in either training environment (p > 0.05). In addition, neither haemoglobin concentration nor haematocrit were significantly changed in either group (p > 0.05). It is concluded that acute exposure of moderately trained subjects to normobaric hypoxia during a short-term training programme consisting of moderate- to high-intensity intermittent exercise has no enhanced effect on the degree of improvement in either aerobic or anaerobic performance. These data suggest that if there are any advantages to training in hypoxia for sea level performance, they would not arise from the short-term protocol employed in the present study.     

Does training in the cold improve cold performance?

Despite the well-described physiological response to cold, little is known about how to best train persons to perform motor tasks in cold conditions. It is unclear if principles of training specificity would apply to motor skill training when cold because cold exposure reduces tactile sensitivity and cognitive function, which may reduce rather than enhance training efficacy. The purpose of this study is to determine whether training in the cold facilitates performance in the cold. To do this, we investigated the effect of cold or thermoneutral training on performance of the Grooved Pegboard Task. Twenty persons (11M, 9F, mean age 31.2 ± 5.44 years) visited the lab on two separate days and were randomly assigned to either a cold (5M, 5F) or thermoneutral (6M, 4F) training group. On day one, participants were tested at baseline and then performed 20 repetitions of the task according to their respective group assignment. Prior to each task repetition during training, the cold training group immersed their hand in cold water (2 °C) while the thermoneutral group immersed their hand in thermoneutral water (34 °C). Following training, participants were tested once again (immediate retention test). During testing, participants performed the task twice; once after immersing their hands in cold water and once after immersing their hands in thermoneutral water. On day two, delayed retention tests were performed. Time to completion and number of errors were recorded during testing. There were no differences in time to completion at delayed retention tests between thermoneutral and cold-trained groups (p = 0.434). The incidence of errors was significantly less in the cold-trained group than the thermoneutral training group at delayed retention testing (p = 0.035). The main finding of this study was that dexterity but not speed was improved by cold training. Further research is required but the findings presented here suggest that industries that require motor tasks in the cold could benefit from training employees in cold conditions.