1

Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects
Composable Part-Based Manipulation
Paper Website
Human-In-The-Loop Task and Motion Planning for Imitation Learning
arXiv Website
Imitating Task and Motion Planning with Visuomotor Transformers
arXiv Website
Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions
M2T2: Multi-task Masked Transformer for Object-centric Pick-and-Place
Website
MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
arXiv Website
Path Signatures for Diversity in Probabilistic Trajectory Optimisation
arXiv
RVT: Robotic View Transformer for 3D Object Manipulation
Website
SCONE: A Food Scooping Robot Learning Framework with Active Perception
Paper