Infants become sensitive to the regular behavior of their caregivers by the end of 4 months old. In this paper, we propose a communication system for a robot to acquire early communication. The acquisition of the communication is proceeded by the interactions of the three components; the memory module, the reward prediction module and the internal state module. The emotional change triggers the transfer of the sensor data stored in the short-term memory to the long-term memory. Once the memory segments are formed, the sensor data are compared with them. When the coincidence of the starting signal of stored data with the sensor data is detected, the prediction of the reward begins. The responses of the simulated robot with the proposed system are examined with and without the memory module when the caregiver takes the regular and irregular peekaboo communication. The results partly explain the behaviors observed in infants.

This paper proposes a learning model which enables a baby robot to acquire the early communication in human development. The robot stores the time sequence of sensor information in its memory when the internal state rises up by the sudden sensor change such as big sound or face detection. The memory helps the robot to predict the response of the caregiver. The experimental result shows that the robot can acquire one of the early communications, peekaboo, by the proposed system.