Natural human-robot interaction for elderly and disabled healthcare application

Abstract

Natural human-robot interaction plays an important role in effective nursing services system provided by service robots for the elderly and disabled people. This paper proposed a multimodal “human-robot integration” collaboration system, and set up a shared collaboration interface between human and service robot. Consequently, Users and service robots can naturally communicate and retrieve information from the collaborative interface with multimodality(e.g. head gesture, eye gaze) in an interactive dialogue approach. By this way, making the service robots fully understand human's intention, so they can collaborate and complete tasks well. Furthermore, some experiments were conducted, and the results suggest that it is effective to identify user's intention in light of the advantage of different modalities, the shared collaboration interface can provide more information both from human and robots to improve the naturalness of human-machine collaboration. The proposed methods can provide a new way for exploiting human-service robots cooperation.