Adaptive handshaking between humans and robots, using imitation: Based on gender-detection and person recognition

In this paper a method for handshaking between robots and humans is introduced. In this method the robot tunes handshaking based on personal characteristics of the person who interacts with it. The characteristics which are considered in this research are gender and familiarity. Handshaking mode changes according to the value of these factors. This adaptation can help social robots, including assistive robots, to interact with humans like humans. It is worthy to mention that the way by which the robot handshake with people has been taught to the robot using OFTM based imitation. OFTM is a one-shot learning method which enables robots to imitate humans only by one demonstration. As this method is fast and real-time, the robot can learn handshaking quickly in the real world. As this robot is able to tune its behavior during its interaction with others, and based on its learning rate which enables the robot learn new behaviors quickly, it can interact with people more fluently and human-like. This method is applied on a service robot with seventeen degrees of freedom.