Enabling robotic manipulation that generalizes to out-of-distribution scenes is a crucial step
toward the open-world embodied intelligence. For human beings, this ability is rooted in the …

Learning 3D human-object interaction relation is pivotal to embodied AI and interaction
modeling. Most existing methods approach the goal by learning to predict isolated …

Affordance detection and pose estimation are of great importance in many robotic
applications. Their combination helps the robot gain an enhanced manipulation capability …

Learning from Demonstrations, the field that proposes to learn robot behavior models from
data, is gaining popularity with the emergence of deep generative models. Although the …

Computer vision tasks typically involve describing what is visible in an image (eg
classification detection segmentation and captioning). We study a visual common sense task …

Robotic manipulation with two-finger grippers is challenged by objects lacking distinct
graspable features. Traditional pre-grasping methods, which typically involve repositioning …

Humans perceive and interact with the world with the awareness of equivariance, facilitating
us in manipulating different objects in diverse poses. For robotic manipulation, such …

Embodied learning for object-centric robotic manipulation is a rapidly developing and
challenging area in embodied AI. It is crucial for advancing next-generation intelligent robots …

Training visual reinforcement learning agents in a high-dimensional open world presents
significant challenges. While various model-based methods have improved sample …

Effectively manipulating articulated objects in household scenarios is a crucial step toward
achieving general embodied artificial intelligence. Mainstream research in 3D vision has …