From 2,000 Labels to 200k Picks: Deploying Learned Visuomotor Policies at Righthand Robotics
How we replaced a rule-based picking heuristic with a learned visuomotor policy and scaled it to production.
Projects
StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects
We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more RGB images.
Deep Deformation Corrections in Human Skeletal Animation
We present a deformation correction technique called deep body deformation (DBD) to improve realism in skeletal animated human characters.
Guidance Waist Pack for the Visually Impaired
We designed a visual aid system, featuring path planning, navigation, and object detection to help the visually impaired in daily activities.
Towards 3D Human Shape Recovery Under Clothing
We present a learning-based scheme for robustly and accurately estimating clothing fitness as well as the human shape on clothed 3D human scans.