Building effective imitation learning methods that enable robots to learn from limited data
and still generalize across diverse real-world environments is a long-standing problem in …

If a robot masters folding a kitchen towel, we would expect it to master folding a large beach
towel. However, existing policy learning methods that rely on data augmentation still don't …

Shape assembly aims to reassemble parts (or fragments) into a complete object, which is a
common task in our daily life. Different from the semantic part assembly (eg, assembling a …

We present a framework for specifying tasks involving spatial relations between objects
using only 5-10 demonstrations and then executing such tasks given point cloud …

Abstract We introduce Equivariant Neural Field Expectation Maximization (EFEM), a simple,
effective, and robust geometric algorithm that can segment objects in 3D scenes without …

In this work, we present an approach to construct a video-based robot policy capable of
reliably executing diverse tasks across different robots and environments from few video …

Equivariance has gained strong interest as a desirable network property that inherently
ensures robust generalization. However, when dealing with complex systems such as …

Many complex robotic manipulation tasks can be decomposed as a sequence of pick and
place actions. Training a robotic agent to learn this sequence over many different starting …

While grasp detection is an important part of any robotic manipulation pipeline, reliable and
accurate grasp detection in $ SE (3) $ remains a research challenge. Many robotics …

Humans excel at transferring manipulation skills across diverse object shapes, poses, and
appearances due to their understanding of semantic correspondences between different …