Add to Favourites
To login click here
A group from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has designed Feature Fields for Robotic Manipulation (F3RM), a system that blends 2D images with foundation model features into 3D scenes to help robots identify and grasp nearby items. F3RM offers robots the ability to interpret open-ended text prompts using natural language, helping the machines manipulate objects. This method could assist robots with picking items in large fulfillment centers with inevitable clutter and unpredictability, allowing them to match text descriptions to objects regardless of variations in packaging.
