Interacting with NeuroCognitive Robots: A Dynamical Systems View

In this paper, we will explore possibilities of dynamic interactions between human and neurocognitive robots especially focusing on the psychological problems of joint attentions and turn-taking. Firstly, we will show that movement patterns of a joystick-type haptic device which are driven by a simple attractor-based memory dynamics of recurrent neural network (RNN) can introduce novel interactive experiences to human subjects based on their force and proprioceptional sensations. Secondly, we will show experiments of joint attention game between human and a humanoid robot based on imitation learning. In the experiments, an extended scheme of RNNs is utilized for constructing a mirror system by which recognition of other’s movements and generation of owns can be naturally synchronized in the realtime imitation. These experiments suggest that spontaneous shifts in joint attentions as well as turn taking have resulted from so-called the open-dynamic structures where stable and unstable manifold coexist in the coupling between the robots and human cognitive processes.