Modern conflicts demand substantial physical and psychological exertion,often resulting in fatigue and diminished combat or operational readiness.Several exoskeletons have been developed recently to address these chal...Modern conflicts demand substantial physical and psychological exertion,often resulting in fatigue and diminished combat or operational readiness.Several exoskeletons have been developed recently to address these challenges,presenting various limitations that affect their operational or everyday usability.This article evaluates the performance of a dual-purpose passive ankle exoskeleton developed for the reduction of metabolic costs during walking,seeking to identify a force element that could be applied to the target population.Based on the 6-min walk test,twenty-nine subjects participated in the study using three different force elements.The results indicate that it is possible to reduce metabolic expenditure while using the developed exoskeleton.Additionally,the comfort and range of motion results verify the exoskeleton's suitability for use in uneven terrain and during extended periods.Nevertheless,the choice of the force element should be tailored to each user,and the control system should be adjustable to optimise the exoskeleton's performance.展开更多
下肢外骨骼需要通过识别穿戴者的运动意图为穿戴者日常活动提供助力,然而当前的研究很少关注能够提供新受试者意图信息的下肢运动模式预测.为此,本文提出了一种基于多传感器信息融合和迁移学习的下肢运动模式预测方法.本文首先设计了一...下肢外骨骼需要通过识别穿戴者的运动意图为穿戴者日常活动提供助力,然而当前的研究很少关注能够提供新受试者意图信息的下肢运动模式预测.为此,本文提出了一种基于多传感器信息融合和迁移学习的下肢运动模式预测方法.本文首先设计了一个下肢运动模式预测模型,采用长短时记忆单元(Long-Short Term Memory,LSTM)提取表面肌电信号(surface ElectroMyoGraphy,sEMG)中的模式特征,然后将sEMG的模式特征与关节角度特征融合预测下肢运动模式.考虑到受试者之间的生理信号差异,本文设计的迁移学习策略分两步训练预测模型,第一步在源域受试者数据集上预训练模型,第二步冻结sEMG模式特征提取器的网络权值,并在目标域数据集上微调全连接层.实验采集了受试者自由行走和穿戴外骨骼行走的数据.通过预测时间长度为100 ms的实验可以得出,所提出的方法分别能够有效提升新受试者自由行走状态下和穿戴外骨骼行走时9.53%和8.29%的运动模式预测准确率.实验结果表明,所提出方法可通过提升新受试者运动模式预测准确率,从而保障下肢外骨骼可靠的人体运动意图感知.展开更多
针对国内康复设备缺乏及其对儿童腿型适应性不足的现状,设计了一款用于脑瘫儿童下肢康复的台架式外骨骼机器人。脑瘫作为一种常见的儿童疾病,常导致“蹲伏步态”等不同程度的步态异常,本文针对此步态进行康复机器人设计。该结构由外骨...针对国内康复设备缺乏及其对儿童腿型适应性不足的现状,设计了一款用于脑瘫儿童下肢康复的台架式外骨骼机器人。脑瘫作为一种常见的儿童疾病,常导致“蹲伏步态”等不同程度的步态异常,本文针对此步态进行康复机器人设计。该结构由外骨骼机器人和助行器小车组成,拥有4个主动自由度,能进行多角度调节和伸缩,满足不同儿童腿型的需求。控制系统采用主从分布式架构,结合KMP(kernelized movement primitive)算法实现了个性化轨迹的匹配和自适应步态的规划。实验结果表明,该康复设备机械结构和控制系统运行可靠,同时具备良好的轨迹跟踪能力,可有效提高脑瘫儿童的步态稳定性。展开更多
基金the Portuguese Army,through CINAMIL,within project ELITE2-Enhancement LITe ExoskeletonFoundation for Science and Technology (FCT),through IDMEC,under LAETA,project UIDB/50022/2020 for supporting this research。
文摘Modern conflicts demand substantial physical and psychological exertion,often resulting in fatigue and diminished combat or operational readiness.Several exoskeletons have been developed recently to address these challenges,presenting various limitations that affect their operational or everyday usability.This article evaluates the performance of a dual-purpose passive ankle exoskeleton developed for the reduction of metabolic costs during walking,seeking to identify a force element that could be applied to the target population.Based on the 6-min walk test,twenty-nine subjects participated in the study using three different force elements.The results indicate that it is possible to reduce metabolic expenditure while using the developed exoskeleton.Additionally,the comfort and range of motion results verify the exoskeleton's suitability for use in uneven terrain and during extended periods.Nevertheless,the choice of the force element should be tailored to each user,and the control system should be adjustable to optimise the exoskeleton's performance.
文摘下肢外骨骼需要通过识别穿戴者的运动意图为穿戴者日常活动提供助力,然而当前的研究很少关注能够提供新受试者意图信息的下肢运动模式预测.为此,本文提出了一种基于多传感器信息融合和迁移学习的下肢运动模式预测方法.本文首先设计了一个下肢运动模式预测模型,采用长短时记忆单元(Long-Short Term Memory,LSTM)提取表面肌电信号(surface ElectroMyoGraphy,sEMG)中的模式特征,然后将sEMG的模式特征与关节角度特征融合预测下肢运动模式.考虑到受试者之间的生理信号差异,本文设计的迁移学习策略分两步训练预测模型,第一步在源域受试者数据集上预训练模型,第二步冻结sEMG模式特征提取器的网络权值,并在目标域数据集上微调全连接层.实验采集了受试者自由行走和穿戴外骨骼行走的数据.通过预测时间长度为100 ms的实验可以得出,所提出的方法分别能够有效提升新受试者自由行走状态下和穿戴外骨骼行走时9.53%和8.29%的运动模式预测准确率.实验结果表明,所提出方法可通过提升新受试者运动模式预测准确率,从而保障下肢外骨骼可靠的人体运动意图感知.
文摘针对国内康复设备缺乏及其对儿童腿型适应性不足的现状,设计了一款用于脑瘫儿童下肢康复的台架式外骨骼机器人。脑瘫作为一种常见的儿童疾病,常导致“蹲伏步态”等不同程度的步态异常,本文针对此步态进行康复机器人设计。该结构由外骨骼机器人和助行器小车组成,拥有4个主动自由度,能进行多角度调节和伸缩,满足不同儿童腿型的需求。控制系统采用主从分布式架构,结合KMP(kernelized movement primitive)算法实现了个性化轨迹的匹配和自适应步态的规划。实验结果表明,该康复设备机械结构和控制系统运行可靠,同时具备良好的轨迹跟踪能力,可有效提高脑瘫儿童的步态稳定性。
