基于手势识别的采摘机器人智能控制系统

Intelligent Control System of Picking Robot Based on Visual Gesture Recognition

为了减少采摘机器人采摘误差、提高其工作效率,首先介绍了肌电信号采集处理和手势识别算法、然后设计了系统的整体框架,最后阐述了采摘机器人机械手执行机构和驱动结构的控制原理。测试结果表明:与LDA、SVM算法相比,ANN算法手势识别时间更短、识别准确度更高,能够大大提高采摘效率和成熟果实准确度,具有一定的现实意义。

In order to reduce the picking error and improve the efficiency of the picking robot,it first introduces the EMG signal acquisition and processing and gesture recognition algorithm,then introduces the overall framework of the system,and finally introduces the control principle of the actuator and driving structure of the picking robot manipulator.The test results show that it has shorter gesture recognition time and higher recognition accuracy compared with LDA and SVM,ANN algorithm,which has certain practical significance to greatly improve the picking efficiency and the accuracy of mature fruits.