SDF-Based Graph Convolutional Q-Networks for Rearrangement of Multiple Objects
Hogun Kee,Minjae Kang,Dohyeong Kim,Jaegoo Choy,Songhwai Oh,Hogun Kee,Minjae Kang,Dohyeong Kim,Jaegoo Choy,Songhwai Oh
In this paper, we propose a signed distance field (SDF)-based deep Q-learning framework for multi-object re-arrangement. Our method learns to rearrange objects with non-prehensile manipulation, e.g., pushing, in unstructured environments. To reliably estimate Q-values in various scenes, we train the Q-network using an SDF-based scene graph as the state-goal representation. To this end, we introduc...
