Natural Interface Using Pointing Behavior for Human–Robot Gestural Interaction

Abstract

In this paper, we focus on using pointing behavior for a natural interface. Recently, robots that fit into the human community have been needed. A gestural interface is important for use with these robots. Gestural recognition has already been studied for use in a human-machine interface. We investigated to find a system that recognizes users' intentions by using their gestural information in particular situations. Therefore, we constructed a system based on interpersonal communication that uses pointing gestures as information. Our aim is not to calculate accurately the point indicated by a user. The system recognizes objects or the pointing direction and decides its own action by automatically considering context. In addition, we report three experiments with this pointing behavior. In the first experiment, a user instructed the robot to follow a specified route. In the second, the user moved a robot or an object by using a virtual room interface. In the third, the user pointed out a specific parking space in which the system was to park a car