Developmental Learning: A Case Study in Understanding “Object Permanence”

The concepts of muddy environment and muddy tasks set the ground for us to understand the essence of intelligence, both artificial and natural, which further motivates the need of Developmental Learning for machines. In this paper, a biologically inspired computational model is proposed to study one of the fundamental and controversial issues in cognitive science – “Object Permanence.” This model is implemented on a robot, which enables us to examine the robot’s behavior based on perceptual development through realtime experiences. Our experimental result shows consistency with prior researches on human infants, which not only sheds light on the highly controversial issue of object permanence, but also demonstrates how biologically inspired developmental models can potentially develop intelligent machines and verify computational modeling that has been established in cognitive science.