Learning Whole-body Motor Skills for Humanoids

Chuanyu Yang, Kai Yuan, Wolfgang Merkt, Taku Komura, Sethu Vijayakumar, Zhibin Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

This paper presents a hierarchical learning framework that can learn a wide range of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained in a realistic physics simulator using the robot model in a setup designed to be able to easily transfer and deploy synthesized control policies to real world platforms. The advantage over traditional methods that integrate high-level planner and feedback control is that one single coherent policy network is generic for generating versatile, unprogrammed balancing and recovery motions against unknown perturbations at arbitrary locations (e.g., legs, torso). Furthermore, the proposed framework allows the policy to be learned with any state-of-the-art learning algorithm. By comparing the proposed approach with other methods in literature, we found the performance of learning is similar in terms of disturbance rejection with additional benefits of generating generic and versatile behaviors.
Original languageEnglish
Title of host publication2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)
Place of PublicationBeijing, China
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages8
Publication statusPublished - 24 Jan 2019
Event2018 IEEE-RAS 18th International Conference on Humanoid Robots - Beijing, China
Duration: 6 Nov 20189 Nov 2018

Publication series

ISSN (Electronic)2164-0580


Conference2018 IEEE-RAS 18th International Conference on Humanoid Robots
Abbreviated titleHumanoids 2018
Internet address


Dive into the research topics of 'Learning Whole-body Motor Skills for Humanoids'. Together they form a unique fingerprint.

Cite this