Creative Dance MTRNN-PB

Humanoid Robot OP2 uses taught dances to create own new dance patterns.

First, tutors teach OP2 13 different dances. Those dances were used to train a MTRNN with parametric bias (PB). By exploring OP2’s PB space, the newly created dance patterns can be play back.


Two humanoid robots learn to predict each other’s behavior by inferring its intention. This project has been just started…


A humanoid robot learns to acquire a set of primitive behaviors and their combinations. The robot experiment utilizes MTRNN model which is characterized by its composition of fast and slow dynamics parts.

Video Paper

iCub robot controlled by MTRNN

iCub robot is controlled by MTRNN. This was done by Martin Peniak at Univ. of Plymouth


sdr chaos 2

A humanoid robot spontaneously generates sequences of learned primitives. Chaos self-organized in the higher level of artificial brain (MTRNN model) generates pseudo stochastic sequences of moving an object among left, middle and right positions on a table.

Video Paper


Mental rehearsing and planning based on partially learned behavioral experiences. Visual stream image is generated for actually experienced ones as well as hallucinated ones.

Video Paper

Pathology of schizophrenia reconstructed in a humanoid robot

Robot picking up white cube

Pathology of schizophrenia (delusion of control) is reconstructed in a humanoid robot. The delusion of control is manifested under malfunction of top-down and bottom-up interactions in MTRNN.

Video Paper


A mobile robot with a hand learns to associate primitive sentences and corresponding behaviors with certain level of generalization. In the video, a robot, by recognizing a sentence “hit red”, generated the corresponding behavior. The robot was implemented with RNNPB model.

Video Paper