We propose a model of evolutionary communication with voice signs and motion signs between two robots. In our model, a robot recognizes other's action through reflecting its self body dynamics by a Multiple Timescale Recurrent Neural Network (MTRNN). Then the robot interprets the action as a sign by its own hierarchical Neural Network (NN). Each of them modifies their interpretation of signs by re-training the NN to adapt the other's interpretation throughout interaction between them. As a result of the experiment, we found that the communication kept evolving through repeating miscommunication and re-adaptation alternately, and induced the emergence of diverse new signs that depend on the robots' body dynamics through the generalization capability of MTRNN.
