Adversarial Object Rearrangement in Constrained Environments with Heterogeneous Graph Neural Networks
Xibai Lou,Houjian Yu,Ross Worobel,Yang Yang,Changhyun Choi,Xibai Lou,Houjian Yu,Ross Worobel,Yang Yang,Changhyun Choi
Adversarial object rearrangement in the real world (e.g., previously unseen or oversized items in kitchens and stores) could benefit from understanding task scenes, which inherently entail heterogeneous components such as current objects, goal objects, and environmental constraints. The semantic relationships among these components are distinct from each other and crucial for multi-skilled robots ...
