Online adaptive neural control of a robotic lower limb prosthesis.
Online adaptive neural control of a robotic lower limb prosthesis.
复制标题
DOI：
10.1088/1741-2552/aa92a8
复制
发表时间：
2018-03
影响因子：
4
通讯作者：
Hargrove LJ
中科院分区：
文献类型：
--
作者：
Spanias JA;Simon AM;Finucane SB;Perreault EJ;Hargrove LJ
本研究的目的是开发和评估一种自适应意图识别算法，该算法可以在下肢截肢者带着机器人假肢行走时不断学习并整合他们的神经信息（通过肌电图[EMG]获得）。我们提出了一种动力下肢假体，它被配置为从嵌入式机械传感器获取用户的神经信息和动力学/运动学信息，并识别和响应用户的意图。我们对8名经股截肢者进行了数天的实验。当使用动力膝关节/踝关节假体的受试者完成各种活动（如在平地、楼梯和坡道上行走）时，收集肌电图和机械传感器数据。我们的自适应意图识别算法自动将假肢转换为不同的运动模式，并不断更新用户在移动过程中的神经数据模型。尽管神经信号在不断变化，我们提出的算法仍能在数天内准确、一致地识别用户的意图。该算法在多个实验会话中包含了96.31%[0.91%]（平均值，[标准误差]）的神经信息，并且优于我们的算法的非自适应版本-错误率相对降低了6.66%[3.16%]。这项研究表明，我们的自适应意图识别算法能够在长时间的使用中整合神经信息，使辅助机器人设备能够以低错误率准确地响应用户的意图。
The purpose of this study was to develop and evaluate an adaptive intent recognition algorithm that continuously learns to incorporate a lower limb amputee’s neural information (acquired via electromyography [EMG]) as they ambulate with a robotic leg prosthesis. We present a powered lower limb prosthesis that was configured to acquire the user’s neural information and kinetic/kinematic information from embedded mechanical sensors, and identify and respond to the user’s intent. We conducted an experiment with eight transfemoral amputees over multiple days. EMG and mechanical sensor data were collected while subjects using a powered knee/ankle prosthesis completed various ambulation activities such as walking on level ground, stairs, and ramps. Our adaptive intent recognition algorithm automatically transitioned the prosthesis into the different locomotion modes and continuously updated the user’s model of neural data during ambulation. Our proposed algorithm accurately and consistently identified the user’s intent over multiple days, despite changing neural signals. The algorithm incorporated 96.31% [0.91%] (mean, [standard error]) of neural information across multiple experimental sessions, and outperformed non-adaptive versions of our algorithm—with a 6.66% [3.16%] relative decrease in error rate. This study demonstrates that our adaptive intent recognition algorithm enables incorporation of neural information over long periods of use, allowing assistive robotic devices to accurately respond to the user’s intent with low error rates.
登录
查看更多内容
影响因子：
5.1
作者：
Hargrove LJ;Simon AM;Lipschutz R;Finucane SB;Kuiken TA
通讯作者：
Kuiken TA
影响因子：
5.1
作者：
Hargrove, Levi;Englehart, Kevin;Hudgins, Bernard
通讯作者：
Hudgins, Bernard
影响因子：
4.6
作者：
Lawson, Brian Edward;Varol, Huseyin Atakan;Goldfarb, Michael
通讯作者：
Goldfarb, Michael
DOI：
10.1109/tnsre.2012.2225640
发表时间：
2013-05-01
影响因子：
4.9
作者：
Lawson, Brian Edward;Varol, Huseyin Atakan;Goldfarb, Michael
通讯作者：
Goldfarb, Michael
DOI：
10.1109/tnsre.2010.2087360
发表时间：
2011-02-01
影响因子：
4.9
作者：
Sup, Frank;Varol, Huseyin Atakan;Goldfarb, Michael
通讯作者：
Goldfarb, Michael