Research
Building the Most Diverse UMI Dataset in Robotics
How we scaled UMI collection to over one million unique tasks in eight weeks and optimized costs down to $10 per recorded hour.
Argus: An Open-Source Annotator for Robotics Data
Introducing Argus, an open source dataset-and-format-agnostic harness for the densest annotation of robot learning data.
We Looked at the Data
We audited popular open-source robotics datasets, found recurring quality problems, and are releasing a manifest of the results.
Introducing Reinforced Planning (RP-1)
The first fully learned planner to refine robot action plans from scratch: 2.4x higher success on hard tasks and 67x faster at scale.