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 (LWL2 ) 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.
Original language | English |
---|---|
Title of host publication | Robotics |
Subtitle of host publication | Science and Systems XVI |
Editors | Marc Toussaint, Antonio Bicchi, Tucker Hermans |
Publisher | MIT Press Journals |
ISBN (Print) | 9780992374761 |
DOIs | |
Publication status | Published - 2020 |
Externally published | Yes |
Event | 16th Robotics: Science and Systems, RSS 2020 - Virtual, Online Duration: 2020 Jul 12 → 2020 Jul 16 |
Publication series
Name | Robotics: Science and Systems |
---|---|
ISSN (Electronic) | 2330-765X |
Conference
Conference | 16th Robotics: Science and Systems, RSS 2020 |
---|---|
City | Virtual, Online |
Period | 20/7/12 → 20/7/16 |
Bibliographical note
Publisher Copyright:© 2020, MIT Press Journals. All rights reserved.
ASJC Scopus subject areas
- Artificial Intelligence
- Control and Systems Engineering
- Electrical and Electronic Engineering