Human–Robot Interaction and Cooperation Through People Detection and Gesture Recognition

In this paper, we propose a system that performs human–robot interaction in order to carry out a cooperation between a robot and a person. The system is based on people detection and gesture recognition. Human beings are detected using a technique that combines face and legs detection from data provided by a camera and a laser range finder. Besides that the gesture recognition method allows the person to choose the kind of help he/she wants. In this work, the cooperative tasks the robot can perform are to guide the user up to a desired place in the work environment, to carry a load together with or for a person, to follow a person or navigate to a place to get something the user wants. Many experiments were performed and two of them (person guidance and navigation up to a predefined place carrying an object) will be shown in this paper with the purpose of validating the proposed system.