Abstract
This paper proposes a new concept of "fourth-person sensing" for service robots. The proposed concept combines wearable cameras (the first-person viewpoint), sensors mounted on robots (the second-person viewpoint) and sensors embedded in the informationally structured environment (the third-person viewpoint). Each sensor has its advantage and disadvantage, while the proposed concept can compensate the disadvantages by combining the advantages of all sensors. The proposed concept can be used to understand a user's intention and context of the scene with high accuracy, thus it enables to provide proactive services by service robots. As one of applications of the proposed concept, we developed a HCI system combines the first-person sensing and the third-person one. We show the effectiveness of the proposed concepts through experiments.
