Three active research lines, written as notes for a technical reader: the problem, the approach, and how far it is from a production environment.
Industrial robots need re-teaching for every new task. WIZARD uses one-shot imitation learning, developed with UC Berkeley, to adapt from a single demonstration with zero retraining.
A grasping policy trained entirely on randomly assembled shape primitives, which then transfers to real objects it has never seen — removing the in-domain data collection step.
Dexterous manipulation degrades when contact is uncertain and vision alone cannot resolve it. T-Rex closes the loop between touch and control. A 36-researcher multi-institutional collaboration — our contribution is documented in the author list, not claimed as sole authorship.
We use Google Analytics to understand how the site is used. Nothing is collected until you accept, and the site works the same without it. Your choice is remembered on this device for 30 days.