We address the challenge of generating 3D articulated objects in a controllable fashion.
Currently modeling articulated 3D objects is either achieved through laborious manual …

Rapid progress in high-level task planning and code generation for open-world robot
manipulation has been witnessed in Embodied AI. However, previous studies put much …

Robotic behavior synthesis, the problem of understanding multimodal inputs and generating
precise physical control for robots, is an important part of Embodied AI. Despite successes in …

Robotic manipulation in everyday scenarios, especially in unstructured environments,
requires skills in pose-aware object manipulation (POM), which adapts robots' grasping and …

Previous studies on robotic manipulation are based on a limited understanding of the
underlying 3D motion constraints and affordances. To address these challenges, we …

Manipulating articulated objects with robotic arms is challenging due to the complex
kinematic structure, which requires precise part segmentation for efficient manipulation. In …

Robotic grasping is a fundamental aspect of robot functionality, defining how robots interact
with objects. Despite substantial progress, its generalizability to counter-intuitive or long …

Articulated objects are commonly found in daily life. It is essential that robots can exhibit
robust perception and manipulation skills for articulated objects in real-world robotic …

Convolution is a fundamental operation in the 3D backbone. However, under certain
conditions, the feature extraction ability of traditional convolution methods may be …

Providing functionality through articulation and interaction with objects is a key objective in
3D generation. We introduce MIDGArD (Modular Interpretable Diffusion over Graphs for …