In this paper,our aim is to realize natural communication between people and robots based on time information and perceived information.First,we explain the hardware specification of the robot partner used in this research.Second,we discuss the application of YUV model as well as steady-state genetic algorithms for detecting and extracting humans.Third,we explain the using of fuzzy spiking neural network for conversation learning system by voice recognition and perceptual information.Finally,we show the experimental results of the proposed method and discuss the future direction of this research.