Robot imitation of human arm via Artificial Neural Network

摘要

In this study, a robot arm that can imitate human arm is designed and presented. The potentiometers are located to the joints of the human arm in order to detect movements of human gestures, and data were collected by this way. The collected data named as “movement of human arm” are classified by the help of Artificial Neural Network (ANN). The robot performs its movements according to the classified movements of the human. Real robot and real data are used in this study. Obtained results show that the learning application of imitating human action via the robot was successfully implemented. With this application, the platforms of robot arm in an industrial environment can be controlled more easily; on the other hand, robotic automation systems which have the capability of making a standard movements of a human can become more resistant to the errors.