Learning From and About Others: Towards Using Imitation to Bootstrap the Social Understanding of Others by Robots

摘要: We want to build robots capable of rich social interactions with humans, including natural communication and cooperation. This work explores how imitation as a learning teaching process may be applied building socially intelligent robots, summarizes our progress toward robot imitate facial expressions from simple imitative games played human, using biologically inspired mechanisms. It is possible for the bootstrap this ability infer affective reaction human whom it interacts then use assessment guide its subsequent behavior. Our approach heavily influenced by ways infants learn communicate their caregivers come understand actions expressive behavior others in intentional motivational terms. Specifically, guided hypothesis that between infant caregiver, starting mimicry, are significant stepping-stone developing appropriate behavior, predicting others' actions, ultimately understanding people beings.