Reusing large datasets is crucial to scale vision-based robotic manipulators to everyday
scenarios due to the high cost of collecting robotic datasets. However, robotic platforms …

Large policies pretrained on diverse robot datasets have the potential to transform robotic
learning: instead of training new policies from scratch, such generalist robot policies may be …

The creation of large, diverse, high-quality robot manipulation datasets is an important
stepping stone on the path toward more capable and robust robotic manipulation policies …

Open-sourced, user-friendly tools form the bedrock of scientific advancement across
disciplines. The widespread adoption of data-driven learning has led to remarkable …

We present Universal Manipulation Interface (UMI)--a data collection and policy learning
framework that allows direct skill transfer from in-the-wild human demonstrations to …

Robotic manipulation can be formulated as inducing a sequence of spatial displacements:
where the space being moved can encompass an object, part of an object, or end effector. In …

We study how the choice of visual perspective affects learning and generalization in the
context of physical manipulation from raw sensor observations. Compared with the more …

The field of visual representation learning has seen explosive growth in the past years, but
its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual …

Manipulation tasks such as preparing a meal or assembling furniture remain highly
challenging for robotics and vision. Traditional task and motion planning (TAMP) methods …

One of the great promises of robot learning systems is that they will be able to learn from
their mistakes and continuously adapt to ever-changing environments, but most robot …