Developing Social Robots

Intellectual Merit: The goal of this proposal is to make progress on computational problems that elude the most sophisticated AI approaches but that infants solve seamlessly during their first year of life. To this end we will develop an integrated system (a child robot) whose sensors and actuators approximate the levels of complexity of human infants. The target is for this robot to learn and develop autonomously a key set of sensory-motor and communicative skills typical of 1 year old infants. The project will be grounded in developmental research with human infants, using motion capture and computer vision technology to characterize the statistics of early physical and social interaction. An important aspect of the proposal is the effort to integrate developmental processes from very different domains under a common framework. The proposed projects explore how principles from control theory can drive the robot to learn how to control its body, to learn about physical objects, and to learn how to interact with people.