Motion Forecasting Network (MoFCNet): IMU-Based Human Motion Forecasting for Hip Assistive Exoskeleton
文献类型:期刊论文
作者 | Zhang, Xingxuan1; Zhang, Haojian1,2; Hu, Jianhua1; Deng, Jieren1,2; Wang, Yunkuan1 |
刊名 | IEEE ROBOTICS AND AUTOMATION LETTERS |
出版日期 | 2023-09-01 |
卷号 | 8期号:9页码:5783-5790 |
ISSN号 | 2377-3766 |
关键词 | Intention recognition prosthetics and exoskeletons human motion forecasting |
DOI | 10.1109/LRA.2023.3300279 |
通讯作者 | Zhang, Haojian(zhanghaojian2014@ia.ac.cn) |
英文摘要 | Accurate recognition of human pose and prediction of human motion intention are essential for exoskeleton robots to provide effective assistance. In recent years, inertial measurement units (IMUs) have been widely used to estimate human pose due to their stability and economy. However, physical sensors are inherently subject to time delay relative to human movement, which makes it challenging to meet the demand for real-time control of power-assisted exoskeletons. To address this issue, we propose a data-driven approach called motion forecasting network (MoFCNet) that leverages historical IMU readings to forecast the 3D pose of human in future frames. Our approach consists of two stages, state variables forecasting and pose regression. In stage I, we forecast the IMU data, joint positions and velocities. In stage II, we regress the future human poses from the forecasting results of stage I. Besides, we design a basic stack that can be applied to both stages. The mean joint rotation error on DIP-IMU and TotalCapture datasets are 10.34 and 16.11 degrees, respectively. When focusing solely on the first frame of the prediction results, these errors decrease to 9.13 and 14.50 degrees. Experimental results indicate that our method not only outperforms the forecasting baseline methods but also achieves comparable performance to the sparse IMU-based human pose estimation algorithm. |
WOS关键词 | INTENTION |
WOS研究方向 | Robotics |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:001045412800008 |
源URL | [http://ir.ia.ac.cn/handle/173211/53954] |
专题 | 中科院工业视觉智能装备工程实验室 |
通讯作者 | Zhang, Haojian |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Xingxuan,Zhang, Haojian,Hu, Jianhua,et al. Motion Forecasting Network (MoFCNet): IMU-Based Human Motion Forecasting for Hip Assistive Exoskeleton[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2023,8(9):5783-5790. |
APA | Zhang, Xingxuan,Zhang, Haojian,Hu, Jianhua,Deng, Jieren,&Wang, Yunkuan.(2023).Motion Forecasting Network (MoFCNet): IMU-Based Human Motion Forecasting for Hip Assistive Exoskeleton.IEEE ROBOTICS AND AUTOMATION LETTERS,8(9),5783-5790. |
MLA | Zhang, Xingxuan,et al."Motion Forecasting Network (MoFCNet): IMU-Based Human Motion Forecasting for Hip Assistive Exoskeleton".IEEE ROBOTICS AND AUTOMATION LETTERS 8.9(2023):5783-5790. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。