智能系统学报2025，Vol.20Issue(2)：407-415,9.DOI:10.11992/tis.202403025
面向下肢外骨骼的运动意图识别算法研究
Motion intention recognition algorithms for lower limb exoskeleton
牛苗赫 1雷飞2
作者信息
- 1. 北京工业大学 都柏林国际学院,北京 100020
- 2. 北京工业大学 信息科学技术学院,北京 100020
- 折叠
摘要
Abstract
The rapid advancement of artificial intelligence and sensing technology has highlighted the potential of lower-limb exoskeleton technology in assisted walking and motion assistance.Decoding human motion intention using sur-face myoelectric(sEMG)signals is essential for achieving coordination and unification of human-machine motion.However,owing to the spatiotemporal differences and nonlinear dynamics of sEMG signals,existing methods have lim-itations,such as single feature capture and low recognition accuracy.A motion intention perception model based on a multiscale convolutional neural network is proposed to solve these problems.The model uses multiple differential con-volution blocks to extract the temporal and spatial scale features of sEMG signals.It utilizes a multi-layer deep network to capture the nonlinear dynamic features of sEMG signals.The recognition accuracy of this model for the offline EMG database is 94%,and that of the whole-foot off-ground motion category is 98%.The average recognition accuracy of this model is more than 90%in the experiment of online motion intention recognition using a lower-limb exoskeleton,which verifies its effectiveness in the field of lower limb exoskeleton intention recognition.关键词
下肢外骨骼/助力行走/表面肌电信号/人机运动/多尺度/卷积神经网络/感知模型/意图识别Key words
lower limb exoskeleton/assisted walking/surface electromyography signals/human-machine movement/multi-scale/convolutional neural network/perceptual model/intention recognition分类
信息技术与安全科学引用本文复制引用
牛苗赫,雷飞..面向下肢外骨骼的运动意图识别算法研究[J].智能系统学报,2025,20(2):407-415,9.
