4 papers
Talk Through It: End User Directed Manipulation Learning
Carl Winge, Adam Imdieke, Bahaa Aldeeb +2
Training generalist robot agents is an immensely difficult feat due to the requirement to perform a huge range of tasks in many different environments. We propose selectively train…
SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics
Alireza Rezazadeh, Athreyi Badithela, Karthik Desingh +1
Learning multi-object dynamics from visual data using unsupervised techniques is challenging due to the need for robust, object representations that can be learned through robot in…
DNBP: Differentiable Nonparametric Belief Propagation
Anthony Opipari, Jana Pavlasek, Chao Chen +3
We present a differentiable approach to learn the probabilistic factors used for inference by a nonparametric belief propagation algorithm. Existing nonparametric belief propagatio…
Break and Make: Interactive Structural Understanding Using LEGO Bricks
Aaron Walsman, Muru Zhang, Klemen Kotar +3
Visual understanding of geometric structures with complex spatial relationships is a fundamental component of human intelligence. As children, we learn how to reason about structur…