Pixel co-designed robot system learns general-purpose mobile manipulation
Original title: Pixel: A Co-Designed Full-Stack Robot System for Learning General-Purpose Mobile Manipulation
Pixel integrates hardware, teleoperation, whole-body control, and policy learning for dexterous mobile tasks.
Pixel combines low-cost wheeled humanoid hardware with compliant grippers, multiple teleoperation and robot-free human data-collection interfaces, a unified whole-body controller, and a common policy learning pipeline. A hierarchical learning stack enables language-conditioned visuomotor control and long-horizon task execution. Evaluations across hardware, data collection, and policy learning demonstrate behaviors requiring dexterity, active perception, navigation, and whole-body coordination.
- Supports human and robot demonstrations
- Enables language-conditioned control
- Demonstrates dexterity and navigation tasks
- Provides extensible foundation for robot learning
From the original article
1 min read at arxiv.orgGeneral-purpose mobile manipulation requires a combination of capable robot hardware, scalable demonstration collection, expressive whole-body control, and effective policy learning. Yet these components are often developed independently, creating mismatches that limit the capabilities of the complete system. We present Pixel, a co-designed full-stack system for learning general-purpose mobile manipulation.
By Tony Tao · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.