AutoRobot

Diffusion policy improved with movement prmitives for fast inference ball catching task

Finetune Vision-Language-Action Model (Pi0.5)

Pi0.5 with Spatial Module

Learning picking/localizing gauze and tracking surgical tool from human daily skills

Autonomous endoscopic camera manipulator scanning using a noisy demonstration set

Learning pseudo surgical skill training task (ring-and-rail task) using a noisy demonstration set.

Autonomous ultrasound scanning for breast seroma using imitation learning