Nonparametric Motion Retargeting for Humanoid Robots on Shared Latent Space

Abstract

In this work, we present a semi-supervised learning method to transfer human motion data to humanoid robots with its emphasis on the feasibility of transferred robot motions. To this end, we propose a data-driven motion retargeting method named locally weighted latent learning (LWL 2 ) which possesses the benefits of both nonparametric regression and deep latent variable modeling. The method can leverage both paired and domain-specific datasets and can maintain robot motion feasibility owing to the nonparametric regression and graph-based heuristics it uses. The proposed method is evaluated using two different humanoid robots, the Robotis ThorMang and COMAN, in simulation environments with diverse motion capture datasets. Furthermore, the online puppeteering of a real humanoid robot is implemented.