Cross-Domain Motion Transfer via Safety-Aware Shared Latent Space Modeling

Sungjoon Choi, Joohyung Kim

Research output: Contribution to journalArticle

Abstract

This letter presents a data-driven motion retargeting method with safety considerations. In particular, we focus on handling self-collisions while transferring poses between different domains. To this end, we first propose leveraged Wasserstein auto-encoders (LWAE) which leverage both positive and negative data where negative data consist of self-collided poses. Then, we extend this idea to multiple domains to have a shared latent space to perform motion retargeting. We also present an effective self-collision handling method based on solving inverse kinematics with augmented targets that is used to collect collision-free poses. The proposed method is extensively evaluated in a diverse set of motions from human subjects and an animation character where we show that incorporating negative data dramatically reduces self-collisions while preserving the quality of the original motion.

Original languageEnglish (US)
Article number8972567
Pages (from-to)2634-2641
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume5
Issue number2
DOIs
StatePublished - Apr 2020

Keywords

  • collision avoidance
  • Deep learning in robotics and automation
  • motion and path planning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Biomedical Engineering
  • Human-Computer Interaction
  • Mechanical Engineering
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Control and Optimization
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Cross-Domain Motion Transfer via Safety-Aware Shared Latent Space Modeling'. Together they form a unique fingerprint.

  • Cite this