Research On Human Lower Limb Motion Intention Detection And Prediction Based On EMG

With the flourish of the lower limb exoskeleton robot technology,its role in the daily assistance,military and medical rehabilitation fields has become increasingly prominent.Due to the high correlation between electromyography(EMG)and human motion,human-robot interaction of exoskeleton based on EMG signals has the advantage of understanding human motion intentions autonomously.In this paper,aimed at the upper layer control of lower limb exoskeleton robot,a human lower limb motion intention detection and prediction system based on EMG signals was proposed,this system includes the motion intention pattern recognition model,the lower limb joint angle prediction model and the online verification experiment.Through the verification of offline experiments based on data set proposed in this paper and on-site online experiments,the accuracy and real-time requirements of the control signals required by the exoskeleton upper control system are achieved.Based on the previous research of motion pattern recognition based on EMG signals and continuous joint angle estimation,this paper summarized some outstanding problems and established the research direction of this paper.At the same time,previous research provides a lot of reference for this paper.By means of analyzing physiological characteristics of EMG signals and the gait of the lower limbs,an offline lower limb multi-channel signals data set containing five lower limb motion patterns was established using wireless myoelectric electrodes which integrated with inertial measurement unit(IMU)and foot pressure sensors.It contains 9 lower limb muscles,corresponding original EMG and IMU signals,multiple EMG signal features and IMU signal features.This data set was used for model training and testing in offline experiments,as well as basic model parameter training in online experiments.Referring to the related research,three machine learning algorithms are selected as the reference algorithms of the motion pattern recognition model.The lower limb motion intention detection and prediction system proposed in this paper includes a motion pattern recognition model and a lower limb joint angle prediction model corresponding to different motion patterns.According to the data characteristics of the dataset in this paper,the motion pattern recognition model is applied to the parameter preset of multi-classification problem,and the recognition accuracy of EMG signal features,IMU signal features and the fusion features of the two were studied.At the same time,based on the three recognition models,the number of muscle channels required to maintain the high recognition accuracy of the model,the corresponding muscle combination method under this number was studied,and the required number and combination of EMG signal characteristics were simplified,and finally established.The motion pattern recognition model motion pattern and the subset of the simplest and best features required for recognition.At the same time,based on the three recognition models,the number of muscle channels required to maintain the high recognition accuracy of the model,and the corresponding muscle combination mode under the number are studied,the required number and combination of EMG signal features are simplified.At the same time,based on the three recognition models,the number of muscle channels required to maintain the high recognition accuracy of the model,and the corresponding muscle combination mode under the number are studied,and the required number and combination of EMG signal features are simplified.A motion pattern recognition model and a subset of the simplest and best features required for recognition were established.According to the physiological basis of electromechanical delay(EMD),the lower limb joint angle prediction scheme and the selection of four prediction time lengths were determined.The EMG signal feature extractor and predictor are established based on the long short-term memory neural network.The two are combined to form the lower limb joint angle prediction model,which can accurately predict the joint angle under different prediction times.Comparing with the traditional EMG signal time domain features and machine learning regression algorithm in different prediction time,the superiority of the lower limb joint angle prediction model proposed in this paper is confirmed.In order to prove the reliability of the online experiment of the motion intention detection and prediction system,based on the model established by offline data set,the data collected on-site and the transfer learning are used to optimize the offline trained model parameters,then the parameter optimized model was imported to the portable artificial intelligence computing card,the EMG and IMU are collected and used online by using the wireless electromyography electrode and its SDK module.The accuracy and real-time test of the proposed model were tested through the motion intention pattern recognition experiment,the lower limb joint angle prediction experiment and the realtime experiment of the motion intention detection and prediction system.Finally,the effectiveness and reliability of the lower limb motion intention detection and prediction system proposed for the upper-layer exoskeleton control is proved.