You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This project implements a Generalist Robotics Policy (GRP) using a Vision Transformer (ViT) architecture. The model is designed to process multiple input types, including images, text goals, and goal images, to generate continuous action outputs for robotic control.