all AI news
Universal Humanoid Motion Representations for Physics-Based Control
April 15, 2024, 4:45 a.m. | Zhengyi Luo, Jinkun Cao, Josh Merel, Alexander Winkler, Jing Huang, Kris Kitani, Weipeng Xu
cs.CV updates on arXiv.org arxiv.org
Abstract: We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. Due to the high dimensionality of humanoids and the inherent difficulties in reinforcement learning, prior methods have focused on learning skill embeddings for a narrow range of movement styles (e.g. locomotion, game characters) from specialized motion datasets. This limited scope hampers their applicability in complex tasks. We close this gap by significantly increasing the coverage of our …
abstract arxiv control cs.cv cs.gr cs.ro dimensionality embeddings humanoid humanoids narrow physics prior reinforcement reinforcement learning representation skills type universal
More from arxiv.org / cs.CV updates on arXiv.org
Compact 3D Scene Representation via Self-Organizing Gaussian Grids
2 days, 3 hours ago |
arxiv.org
Fingerprint Matching with Localized Deep Representation
2 days, 3 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne