| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Thu, 18 Dec 2025 15:06:54 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"6944188e-35a2"
expires: Sun, 28 Dec 2025 17:33:39 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 43F8:2D64E0:7CB4EB:8BF001:6951679B
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 17:23:39 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210091-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766942619.309247,VS0,VE212
vary: Accept-Encoding
x-fastly-request-id: 7b2d63e127ace0d1f6a7fe0e50beb519ac76f7b3
content-length: 3421
IFOR
IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
|
|
|
|
|
|
|
|
|
|
|
|
|
|
 |
TLDR
● Robotic system for vision based object rearragement system; Iteratively minimizes flow.
● Input is RGBD images of the current and target scene; No privilaged information used.
● Trained entirely in simulation; Zero-shot transfer to real world.
● Tested on objects not seen during training.
● Input is RGBD images of the current and target scene; No privilaged information used.
● Trained entirely in simulation; Zero-shot transfer to real world.
● Tested on objects not seen during training.
Paper
IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
Ankit Goyal, Arsalan Mousavian, Chris Paxton, Yu-Wei Chao, Brian Okorn, Jia Deng and Dieter Fox
@inproceedings{goyal2022ifor,
title={IFOR: Iterative Flow Minimization for Robotic Object Rearrangement},
author={Goyal, Ankit and Mousavian, Arsalan and Paxton, Chris and Chao, Yu-Wei and Okorn, Brian and Deng, Jia and Fox, Dieter},
booktitle={arXiv:2202.00732},
year={2022}
}Summary
Accurate object rearrangement from vision is a crucial problem for a wide variety of real-world robotics applications in unstructured environments. We propose IFOR, an end-to-end method for the challenging problem of object rearrangement for unknown objects given an RGBD image of the original and final scenes. First, we learn an optical flow model to estimate the relative transformation of the objects purely from synthetic data. This flow is then used in an iterative minimization algorithm to achieve accurate positioning of previously unseen objects. Crucially, we show that our method applies to cluttered scenes, and in the real world, while training only on synthetic data.
Method
IFOR takes as input RGB+D images of a current and a goal scene, and uses these to make predictions as to which objects should move and by which transformations, using RAFT to estimate optical flow. This is then sent to a robot planning and execution pipeline which is capable of grasping of unknown objects and motion planning in scenes with unknown geometry.
Real World Examples
|
|
 |
 |
 |
 |
 |
Synthetic Examples
 |
 |
 |
 |
 |
Comparison with Prior Work
 |
 |