Recently, many studies are being conducted to use an EMG signal, which is one of biological signals, as an engineering device, and researches for utilizing the EMG signal as an input device of a human-machine interface have been actively conducted. In this paper, an intuitive method for recognizing human motion and controlling movement of robot is proposed. An 8 channel real-time EMG measurement device that can be worn on a human 's arm is used for human motion recognition, and an artificial neural network-based pattern recognition algorithm is applied. The human wrist motion using the EMG signal is distinguished, and the robot is controlled to move in five states: the initial state, forward, backward, left turn, and right turn. The recognition accuracy of each operation is more than 98%, and it is verified through experiments that intuitive control of robot movement is possible.