回帰的意図理解をめざす共同注意ロボット (特集ロボット工学と哲学)

概要

論文の詳細を見る
Human beings can convey their intentions to other peoplenon-verbally, through looks and gestures. It is known thatduring development, infants acquire this ability beforethey learn to speak. We have focused on the phenomenonof “joint attention,” wherein infants try to look at objectsby following their parent’s gaze. This behavior begins as areflective one, but then progresses further into the nextstage—understanding and sharing other peoples’ intentions.We try to clarify joint attention by constructing asimple robot that visually interacts with human beings.In this paper, we suggest two important mechanisms forunderstanding and sharing intentions; an associationmechanism to produce an intentional gaze following, andan inference mechanism to recursively rectify the robot’sown intentions by understanding the interacting person’sintentions.
日本科学哲学会 = Philosophy of Science Society, Japanの論文