Joint attention emerges through bootstrap learning

A human-like intelligent robot is expected to have the capability to develop its cognitive functions through experience without a priori knowledge or explicit teaching. In addition, the realization of this kind of robot can lead us to understand the developmental mechanisms of human beings. This paper proposes a bootstrap learning model by which a robot can acquire the ability of joint attention without a caregiver’s evaluation or a controlled environment based on the robot’s embedded mechanisms: visual attention and learning with self-evaluation. Through learning based on the proposed model, the robot finds a correlation in sensorimotor coordination when joint attention succeeds and consequently acquires the ability of joint attention by accumulating the appropriate correlation and losing the uncorrelated coordination as statistical outliers. The experimental results show the validity of the proposed model.