助行器智能转弯意图感知和摔倒检测

doi:10.3969/j.issn.1006-9771.2023.07.016

《中国康复理论与实践》 ›› 2023, Vol. 29 ›› Issue (7): 849-855.doi: 10.3969/j.issn.1006-9771.2023.07.016

助行器智能转弯意图感知和摔倒检测

孙志杰¹, 郭欣¹, 兰陟²^,³^,⁴, 王强²^,³^,⁴()

1.河北工业大学，天津市 300401
2.国家康复辅具研究中心，北京市 100176
3.北京市老年功能障碍康复辅助技术重点实验室，北京市 100176
4.民政部康复辅具技术与系统重点实验室，北京市 100176

收稿日期:2023-03-29 修回日期:2023-06-03 出版日期:2023-07-25 发布日期:2023-08-30
通讯作者: 王强(1982-)，男，硕士，高级工程师。E-mail： yebif@163.com
作者简介:孙志杰(1999-)，男，汉族，河北沧州市人，硕士研究生，主要研究方向：康复辅具、智能助行器。
基金资助:
国家重点研发计划项目(2020YFC2007502);xml:lang="en"National Key Research and Development Program of China(2020YFC2007502)

Turn intention perception and fall detection for smart walkers

SUN Zhijie¹, GUO Xin¹, LAN Zhi²^,³^,⁴, WANG Qiang²^,³^,⁴()

1. Hebei University of Technology, Tianjin 300401, China
2. National Research Center for Rehabilitation Technical Aids, Beijing 100176, China
3. Beijing Key Laboratory of Rehabilitation Technical Aids for Old-age Disability, Beijing 100176, China
4. Key Laboratory of Rehabilitation Aids Technology and System of the Ministry of Civil Affairs, Beijing 100176, China

Received:2023-03-29 Revised:2023-06-03 Published:2023-07-25 Online:2023-08-30
Contact: WANG Qiang, E-mail： yebif@163.com

摘要/Abstract

摘要：

目的提高助行器智能抗摔倒功能，加强安全保障。

方法在助行器两侧手柄上放置压力传感器，手动标注对应的运行意图标签，使用支持向量机(SVM)分类器进行模型预测，预测助行器的行驶意图，得到混淆矩阵。在使用者腰部佩带陀螺仪，助行器上安装激光传感器，通过陀螺仪检测角速度和角加速度，激光传感器测量距离，两者结合检测使用者摔倒情况。

结果 SVM建立的分类器模型能成功预测助行器的直行、左转和右转3种状态。当合角速度> 100°/s、合角加速度> 1.3 G、Z轴角加速度> 0.7 G或< 0.2 G、距离> 600 mm或< 300 mm，提示使用者摔倒。

结论本研究设计的助行器可以感知使用者的转弯意图，并检测使用者摔倒情况。

关键词: 助行器机器人, 转弯意图感知, 摔倒检测

Abstract:

Objective To improve the anti-fall capacity and safety of the smart walkers.

Methods Two pressure sensors were placed on the handles on both sides of the walker. The confusion matrix was obtained, the corresponding operational intent labels were manually labeled, using a support vector machine (SVM) classifier for model prediction to predict the travel intent of the users. The user wore a gyroscope and the walker was equipped with a laser sensor, to measure the angular velocity, angular acceleration and the distance data, respectively, to detect the user's fall.

Results The classifier model established by SVM successfully predicted three operating states of the walker, namely straight ahead, left turning and right turning. The user's fall was detected by the sudden change of the following data: the combined angular velocity was greater than 100°/s, the combined angular acceleration was greater than 1.3 G, the angular acceleration of Z-axis was greater than 0.7 G or less than 0.2 G, and the distance was greater than 600 mm or less than 300 mm.

Conclusion The improvement of the walker can predict the turn intention of the user, and detect the user's fall.

Key words: walking aid robot, turn intention perception, fall detection

中图分类号:

R496

孙志杰, 郭欣, 兰陟, 王强. 助行器智能转弯意图感知和摔倒检测[J]. 《中国康复理论与实践》, 2023, 29(7): 849-855.

SUN Zhijie, GUO Xin, LAN Zhi, WANG Qiang. Turn intention perception and fall detection for smart walkers[J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(7): 849-855.

图/表 5

参考文献 26

[1]	石栋, 张克华, 徐彪. 独居老人云智能跌倒实时检测系统的开发[J]. 计算机工程与应用, 2016, 52(19): 259-264.
	SHI D, ZHANG K H, XU B. Development of cloud intelligent real-time fall detection system for the aged population[J]. Comput Eng Appl, 2016, 52(19): 259-264.
[2]	乔美生, 王忠. MEMS传感器技术在人体摔倒检测中的应用[J]. 电声技术, 2017, 41(4): 156-160.
	QIAO M S, WANG Z. Application of MEMS technology in human fall detection[J]. Audio Eng, 2017, 41(4): 156-160.
[3]	陈玮, 周晴, 曹桂涛. 基于SVM和阈值分析法的摔倒检测系统[J]. 计算机应用与软件, 2017, 34(7): 182-187.
	CHEN W, ZHOU Q, CAO G T. Fall detection system based on SVM and threshold analysis[J]. Comput Appl Software, 2017, 34(7): 182-187.
[4]	杨志勇, 王俊杰, 金磊. 基于SE-CNN的人体摔倒检测方法[J]. 计算机工程, 2022, 48(6): 270-277. doi: 10.19678/j.issn.1000-3428.0061833
	YANG Z Y, WANG J J, JIN L. Human fall detection method based on SE-CNN[J]. Comput Eng, 2022, 48(6): 270-277. doi: 10.19678/j.issn.1000-3428.0061833
[5]	彭亚平, 贺乾格, 柯希垚, 等. 一种基于加速度传感器的摔倒检测腰带[J]. 电子测量技术, 2018, 41(11): 117-120.
	PENG Y P, HE Q G, KE X Y, et al. Fall detection belt based on acceleration sensor[J]. Electron Measur Technol, 2018, 41(11): 117-120.
[6]	CAO B. Deep learning using for fall detection on the rehabilitation walking-aid robot[C]. 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2019.
[7]	汤引生, 谢楠, 何建强. 基于三轴加速度传感器的老年人摔倒检测算法的设计与实现[J]. 微型电脑应用, 2019, 35(2): 42-44.
	TANG Y S, XIE N, HE J Q. Design and implementation of senile fall detection algorithm based on triaxial accelerometer[J]. Microcomput Appl, 2019, 35(2): 42-44.
[8]	PALMERINI L, KLENK J, BECKER C, et al. Accelerometer-based fall detection using machine learning: training and testing on real-world falls[J]. Sensors (Basel, Switzerland), 2020, 20(22): E6479.
[9]	AMARA M I, AKKOUCHE A, BOUTELLAA E, et al. A smartphone application for fall detection using accelerometer and ConvLSTM network[C]. The 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH), 2021.
[10]	周立鹏, 孟利民, 周磊, 等. 基于BP神经网络的摔倒检测算法[J]. 计算机科学, 2020, 47(S1): 242-246.
	ZHOU L P, MENG L M, ZHOU L, et al. Fall detection algorithm based on BP neural network[J]. Comput Sci, 2020, 47(S1): 242-246.
[11]	LEE D W, JUN K, NAHEEM K, et al. Deep neural network-based double-check method for fall detection using IMU-L sensor and RGB camera data[J]. IEEE Access, 2021, PP(99): 1.
[12]	刘鹏, 卢潭城, 吕愿愿, 等. 基于MEMS三轴加速度传感器的摔倒检测[J]. 传感技术学报, 2014, 27(4): 570-574.
	LIU P, LU T C, LÜ Y Y, et al. MEMS Tri-axial accelerometer based fall detection[J]. Chin J Sensors Actuators, 2014, 27(4): 570-574.
[13]	OZCAN K, VELIPASALAR S. Wearable camera- and accelerometer-based fall detection on portable devices[J]. IEEE Embed Syst Lett, 2016, 8(1): 6-9.
[14]	NUTSATHAPORN C, CHOMKOKARD S, WONGKOKUA W, et al. Human fall prediction and detection using low price IMU sensor[C]. IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE), 2022.
[15]	丁茜, 赵晓东, 吴鑫俊, 等. 基于RBF核的多分类滑塌易发性评价模型[J]. 中国安全科学学报, 2022, 32(3): 194-200. doi: 10.16265/j.cnki.issn1003-3033.2022.03.026
	DING X, ZHAO X D, WU X J, et al. Landslide susceptibility assessment model based on mulfi-class SVM with RBF kernel[J]. Chin Safety Sci J, 2022, 32(3): 194-200.
[16]	李宝胜, 秦传东. 基于粒子群优化的SVM多分类的电动车价格预测研究[J]. 计算机科学, 2020, 47(S2): 421-424.
	LI B S, QIN C D. Study on electric vehicle price prediction based on PSO-SVM multi-classification method[J]. Comput Sci, 2020, 47(S2): 421-424.
[17]	CORTES C, VAPNIK V. Support-vector networks[J]. Mach Learn, 1995, 20(3): 273-297.
[18]	BAI F, LIU R. Improved nonparallel hyperplanes support vector machines for multi-class classification[C]. IEEE 23rd International Conference on Digital Signal Processing (DSP), 2018.
[19]	唐奇, 王红瑞, 许新宜, 等. 基于混合核函数SVM水文时序模型及其应用[J]. 系统工程理论与实践, 2014, 34(2): 521-529. doi: 10.12011/1000-6788(2014)2-521
	TANG Q, WANG H R, XU X Y, et al. Hydrological time series model based on SVM with mixed kernel function and its application[J]. Syst Eng Theory Prac, 2014, 34(2): 521-529.
[20]	CORTES C, MOHRI M, ROSTAMIZADEH A. Multi-class classification with maximum margin multiple kernel[C]. International Conference on Machine Learning, 2013.
[21]	YANAGAIMOTO H, HASHIMOTO K. Review Rating prediction with Gaussian process classification[C]. 14th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP), 2019.
[22]	ARDJANI F, SADOUNI K. Optimization of SVM multiclass by particle swarm (PSO-SVM)[J]. Int J Modern Educ Comput Sci, 2010, 2(2): 32-38.
[23]	CLARKE K, ARIYARATHNA T, KUMARI S. Concept-to-implementation of new threshold-based fall detection sensor[C]. IEEE Region 10 Conference (TENCON), 2021.
[24]	HIROTA K, MURAKAMI T. IMU sensor based human motion detection and its application to braking control of electric wheeled walker for fall-prevention[J]. IEEJ J Industry Appl, 2016, 5(4): 347-354.
[25]	张玉叶. 基于多传感器数据融合的助行机器人防摔倒技术研究[J]. 现代电子技术, 2015, 38(14): 36-38.
	ZHANG Y Y. Research on walking aid robot technology based on multi-sensor data fusion to prevent elders from falling down[J]. Modern Electron Technique, 2015, 38(14): 36-38.
[26]	ISUFI E, LOUKAS A, SIMONETTO A, et al. Autoregressive moving average graph filtering[J]. IEEE Transactions on Signal Processing, 2016, 65(2): 274-288. doi: 10.1109/TSP.2016.2614793

助行器智能转弯意图感知和摔倒检测

Turn intention perception and fall detection for smart walkers

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 26

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	邱服冰, 杨亚茹. 深圳市公共体育场馆无障碍设施建设与辅助技术应用[J]. 《中国康复理论与实践》, 2023, 29(12): 1465-1472.
[2]	张恒瑞, 孟昭莉, 崔配, 王瑞怡. 不同头戴式虚拟现实对人体平衡与姿势控制的影响[J]. 《中国康复理论与实践》, 2023, 29(11): 1359-1364.
[3]	蔡华年, 费思先, 张忆晨, 孙青, 郭帅, 宋韬. 基于导纳控制的双边康复机器人运动辅助分析[J]. 《中国康复理论与实践》, 2023, 29(9): 1104-1109.
[4]	张意彬, 吕杰, 喻洪流. 基于模糊逻辑算法的智能膝关节假肢步态相位识别[J]. 《中国康复理论与实践》, 2023, 29(8): 896-902.
[5]	闫媚, 江华, 董理权, 柳博飞, 贺炜洁, 吴小高, 郭智洋. 中国辅助技术的需求、供给和满意度研究：基于快速辅助技术评估数据[J]. 《中国康复理论与实践》, 2023, 29(4): 373-380.
[6]	朱长建, 郑邵骑, 贡智兵, 柯旭, 赵有鹏. 基于三自由度模型的电动轮椅操纵稳定性优化与仿真[J]. 《中国康复理论与实践》, 2023, 29(4): 381-389.
[7]	于文强, 侯俞彤, 黄承兰, 杨云霄, 鲁德志, 王彩萍, 王金武. 3D打印脊柱侧凸矫形器的矫正效果[J]. 《中国康复理论与实践》, 2023, 29(4): 390-395.
[8]	潘海鸿, 李泰薇, 刘远才, 卢美铭, 陈琳. 简易滑动式腿部康复设备机构设计与分析[J]. 《中国康复理论与实践》, 2023, 29(4): 396-401.
[9]	张意彬, 李剑峰, 喻洪流. 一种智能膝关节假肢及其步态对称性评价[J]. 《中国康复理论与实践》, 2023, 29(4): 402-407.
[10]	王芳, 杨涛, 何耀广, 曹子君, 刘国庆, 胡军, 张建国, 樊瑜波. 基于糖尿病患者步态周期足底压力的变刚度鞋垫设计[J]. 《中国康复理论与实践》, 2023, 29(4): 408-415.
[11]	黄承兰, 侯俞彤, 杨云霄, 曾红, 张子砚, 赵文宽, 王赞博, 单春雷, 戴尅戎, 蔡斌, 王金武. 3D打印矫形鞋垫在扁平足中应用的系统综述[J]. 《中国康复理论与实践》, 2023, 29(4): 416-422.
[12]	单新颖,俞梦孙. 下肢截肢患者运动表象的脑电功率谱改变[J]. 《中国康复理论与实践》, 2022, 28(11): 1360-1364.
[13]	林高,张道辉,赵新刚. 适应患者个体差异的上肢康复机器人直接示教技术[J]. 《中国康复理论与实践》, 2022, 28(10): 1231-1240.
[14]	朱旭,刘静,董泽萍,仇大伟. 基于表面肌电图手势动作意图识别的系统综述[J]. 《中国康复理论与实践》, 2022, 28(9): 1032-1038.
[15]	张文波,瞿畅,周建萍,张小萍,张啸天. 基于Azure Kinect骨骼追踪的腕关节活动度测量方法[J]. 《中国康复理论与实践》, 2022, 28(8): 981-988.