Rearrangement Planning for General Part Assembly

Yulong Li, Andy Zeng, Shuran Song
Proceedings of The 7th Conference on Robot Learning, PMLR 229:127-143, 2023.

Abstract

Most successes in autonomous robotic assembly have been restricted to single target or category. We propose to investigate general part assembly, the task of creating novel target assemblies with unseen part shapes. As a fundamental step to a general part assembly system, we tackle the task of determining the precise poses of the parts in the target assembly, which we term “rearrangement planning". We present General Part Assembly Transformer (GPAT), a transformer-based model architecture that accurately predicts part poses by inferring how each part shape corresponds to the target shape. Our experiments on both 3D CAD models and real-world scans demonstrate GPAT’s generalization abilities to novel and diverse target and part shapes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-li23a, title = {Rearrangement Planning for General Part Assembly}, author = {Li, Yulong and Zeng, Andy and Song, Shuran}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {127--143}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/li23a/li23a.pdf}, url = {https://proceedings.mlr.press/v229/li23a.html}, abstract = {Most successes in autonomous robotic assembly have been restricted to single target or category. We propose to investigate general part assembly, the task of creating novel target assemblies with unseen part shapes. As a fundamental step to a general part assembly system, we tackle the task of determining the precise poses of the parts in the target assembly, which we term “rearrangement planning". We present General Part Assembly Transformer (GPAT), a transformer-based model architecture that accurately predicts part poses by inferring how each part shape corresponds to the target shape. Our experiments on both 3D CAD models and real-world scans demonstrate GPAT’s generalization abilities to novel and diverse target and part shapes.} }
Endnote
%0 Conference Paper %T Rearrangement Planning for General Part Assembly %A Yulong Li %A Andy Zeng %A Shuran Song %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-li23a %I PMLR %P 127--143 %U https://proceedings.mlr.press/v229/li23a.html %V 229 %X Most successes in autonomous robotic assembly have been restricted to single target or category. We propose to investigate general part assembly, the task of creating novel target assemblies with unseen part shapes. As a fundamental step to a general part assembly system, we tackle the task of determining the precise poses of the parts in the target assembly, which we term “rearrangement planning". We present General Part Assembly Transformer (GPAT), a transformer-based model architecture that accurately predicts part poses by inferring how each part shape corresponds to the target shape. Our experiments on both 3D CAD models and real-world scans demonstrate GPAT’s generalization abilities to novel and diverse target and part shapes.
APA
Li, Y., Zeng, A. & Song, S.. (2023). Rearrangement Planning for General Part Assembly. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:127-143 Available from https://proceedings.mlr.press/v229/li23a.html.

Related Material