基于小腿表面肌电的智能机器人协同控制方法

作为人机交互的核心内容之一,面向机器人控制的步态识别拥有广泛的应用前景。提出一种基于小腿表面肌电信号的智能移动机器人控制方法。通过优化互信息的最大相关最小冗余算法(MRMR),实现对前进、后退、左转、右转等4种步态分类识别,并建立一套移动机器人同步控制系统。使用表面肌电信号(sEMG)作为输入信息,对人步态动作进行分类识别,并转化为对机器人运动进行控制的信息,从而实现人与智能移动机器人的实时协同交互。通过采集8名受试者前进、后退、左转、右转行走时的小腿表面肌电信号,并实时控制智能机器人的运动。结果表明,在少量的训练条件下,该方法的步态识别准确率可达88%。基于此方法搭建的移动机器人协同控制系统,具有较强的实时控制能力以及较高的控制准确度。基于小腿表面肌电的智能机器人协同控制方法具有良好的应用前景,未来或可广泛应用于人机运动协调机器人控制等领域。

Cooperative Intelligent Robot Control Method Using Leg Surface EMG Signals

As a significant aspect of human-computer interaction, gait recognition technology has a broad prospect in robot control area. A method for intelligent robot cooperative control system was proposed by using single leg surface EMG-based gait recognition technology. The system achieved the classification and recognition among four different gaits (moving forward, moving backward, turning left and turning right) by using mutual information based minimal-redundancy-maximal-relevance (MRMR) algorithm, and built up a synchronous robot control system. Surface EMG (sEMG) signals were collected from 8 subjects to classify and recognize the gait, and then the recognition result was used to control the robot synchronous motion. The results of the experiment showed that the recognition accuracy of the system reached to 88%. Based on the proposed approach, a robot synchronous control system with good synchronous controlling performance and high controlling accuracy was built. In concusion, the leg EMG signal based robot cooperative control technology has the application potentials in the areas of civilian equipment control and human-computer interaction in the future.