Enable simulation to be used to train, validate, and adapt robot behaviors for the real world.
Enable robots to generalize and share task knowledge that has been taught to them by people.
Enable robots to continually learn, improve, and share skills from experience in the real world.
Enable robots to touch and sense throughout their body and learn by physically interacting with their environments.
Led by Russ Tedrake, the Large Behavior Models team includes world-class researchers focusing on machine learning, dynamics and simulation, human-robot interaction, and hardware and software for dexterous manipulation.
This video showcases the applicability of Diffusion Policy to complex, multi-step tasks.
This video illustrates autonomous recovery with Diffusion Policy on a transparent and deformable object.
This video demonstrates inexpensive and flexible robot teaching via Universal Manipulation Interfaces (UMI).
Drake is a C++ toolbox for analyzing the dynamics of our robots and building control systems for them.
Click the image below for more information.
Punyo is a design for a soft bubble gripper that allows for robust and perceptive manipulation.
Click the image below for more information.
