Development of compositional and contextual communication of robots by using the multiple timescales dynamic neural network

The current paper introduces neurorobotics experiment on acquisition of complex communicative skills with human via learning. A dynamic neural network model which is characterized by its multiple timescale dynamics characteristics was utilized as a neuronal model for controlling a humanoid robot. In the experimental task, the humanoid robot was trained to generate specific sequential movement patterns as responding to various sequences of imperative gesture patterns demonstrated by the human subjects by following predefined compositional semantic rules. The experimental results showed that (1) the MTRNN can learn to extract compositional semantic rules with generalization in the higher cognitive level, (2) the MTRNN can develop further higher-order cognition capability for controlling the internal contextual processes as situated to on-going task sequences without being provided with cues for explicitly indicating task segmentation points. The analysis on the dynamic characteristics developed in the MTRNN through learning indicated that the aforementioned cognitive mechanisms were achieved by developing adequate functional hierarchy by utilizing the constraint of the multiple timescale property and the topological connectivity imposed on the network configuration.