Feb, 2022
IFOR: 机器人物体重新排列的迭代流量最小化
IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
Ankit Goyal, Arsalan Mousavian, Chris Paxton, Yu-Wei Chao, Brian Okorn...
TL;DRIFOR is an end-to-end method for accurately rearranging unknown objects in unstructured environments by applying an optical flow model based on RAFT and iterative minimization algorithm, which works well in cluttered scenes and real-world situations while being trained only on synthetic data.