news
Researchers Create Faster, Cheaper Way to Teach a Humanoid Robot to Walk Over Real-World Terrain
Primary tabs
Machine learning Ph.D. student Feiyang Wu led development of a new kind of whole-body controller that allowed the humanoid robot to traverse all those varied surfaces. His method is computationally faster and cheaper than the leading approaches for training robotic controllers. And he was surprised how well it worked, even on surfaces that weren’t included in the training.
Summary
Machine learning Ph.D. student Feiyang Wu led development of a new kind of whole-body controller that allowed the humanoid robot to traverse all those varied surfaces. His method is computationally faster and cheaper than the leading approaches for training robotic controllers. And he was surprised how well it worked, even on surfaces that weren’t included in the training.
Groups
Status
- Workflow status: Published
- Created by: hashcraft6
- Created: 09/10/2026
- Modified By: hashcraft6
- Modified: 09/10/2026
Categories
Keywords
User Data