Learning for joint attention helped by functional development

摘要

Abstract Cognitive scientists and developmental psychologists have suggested that development in perceptual, motor and memory functions of human infants as well as adaptive evaluation by caregivers facilitate learning for cognitive tasks by infants. This article presents a robotic approach to understanding the mechanism of how learning for joint attention can be helped by such functional development. A robot learns visuomotor mapping needed to achieve joint attention based on evaluations from a caregiver. The caregiver adjusts the criterion for evaluating the robot's performance from easy to difficult as the performance improves. At the same time, the robot also gradually develops its visual function by sharpening input images. Experiments reveal that the adaptive evaluation by the caregiver accelerates the robot's learning and that the visual development in the robot improves the accuracy of joint attention tasks due to its well-structured visuomotor mapping. These results constructively explain what roles synchronized functional development in infants and caregivers play in task learning by infants. Keywords: JOINT ATTENTIONVISUAL DEVELOPMENTADAPTIVE EVALUATIONVISUOMOTOR LEARNING