Using Deep Learning Technology to Realize the Automatic Control Program of Robot Arm Based on Hand Gesture Recognition

In this study, the robot arm control, computer vision, and deep learning technologies are combined to realize an automatic control program. There three functional modules in program, i.e., hand gesture recognition module, communication module. The module records user’s images recognize gestures’ features using YOLOv4 algorithm. results transmitted by Finally, received commands analyzed executed With proposed engineers can interact with through gestures, teach record trajectory simple movements, call different scripts satisfy motion requirements actual production environment.