We propose a sim-to-real framework for dexterous manipulation which can generalize to
new objects of the same category in the real world. The key of our framework is to train the …

We present RoboGen, a generative robotic agent that automatically learns diverse robotic
skills at scale via generative simulation. RoboGen leverages the latest advancements in …

Commercial depth sensors usually generate noisy and missing depths, especially on
specular and transparent objects, which poses critical issues to downstream depth or point …

We present Im2Flow2Act, a scalable learning framework that enables robots to acquire real-
world manipulation skills without the need of real-world robot training data. The key idea …

Reliable object grasping is a crucial capability for autonomous robots. However, many
existing grasping approaches focus on general clutter removal without explicitly modeling …

Learning-based stereo methods usually require a large scale dataset with depth, however
obtaining accurate depth in the real domain is difficult, but groundtruth depth is readily …

We propose a new dataset and a novel approach to learning hand-object interaction priors
for hand and articulated object pose estimation. We first collect a dataset using visual …

This paper focuses on the sim-to-real issue of RGB-D grasp detection and formulates it as a
domain adaptation problem. In this case, we present a global-to-local method to address …

Accurately manipulating articulated objects is a challenging yet important task for real robot
applications. In this paper, we present a novel framework called Sim2Real 2 to enable the …

Manipulating unseen articulated objects through visual feedback is a critical but challenging
task for real robots. Existing learning-based solutions mainly focus on visual affordance …