下肢康复机器人的训练控制与监测研究

Research on training control and monitoring of lower limb rehabilitation robot

针对下肢术后康复训练需求,设计并开发了一种基于嵌入式控制器和远程控制架构的下肢康复机器人控制与监测系统,实现了下肢康复机器人的主动/被动训练模式控制、运动姿态与肌电信号采集、WIFI通讯、安全保护等功能,通过应用随机森林机器学习算法和线性回归算法实现了训练过程的识别与分析。实验结果表明:所研制的下肢康复机器人控制与监测系统可以通过安卓进行便携控制,并能通过训练过程中的监测信号,实现对训练过程的智能分析。同时可知,随机森林算法相对线性回归算法在运动识别方面更有优势,这对训练过程的自动监测和智能化控制具有积极意义。

Aiming at the needs of lower limb rehabilitation training after surgery,a control and monitoring system of lower limb rehabilitation robot was designed and developed based on embedded controller and remote control architecture,which realizes the functions of active and passive training control mode,motion posture and EMG acquisition,WIFI communication and safety protection of the lower limb rehabilitation robot.The recognition and analysis of training process were completed by using random forest machine learning algorithm and linear regression algorithm.The experimental results show that the developed control and monitoring system can realize the intelligent analysis of the training process through the portable control of the Android terminal and the monitoring signals.In the experiment,the random forest algorithm has more advantages than the linear regression algorithm in motion recognition,which has positive significance for the automatic monitoring and intelligent control of the training process.