JA-TN: Pick-and-Place Towel Shaping from Crumpled States based on TransporterNet with Joint-Probability Action Inference

Halid Abdulrahim Kadi, Kasim Terzić
Proceedings of The 8th Conference on Robot Learning, PMLR 270:3107-3123, 2025.

Abstract

Towel manipulation is a crucial step towards more general cloth manipulation. However, folding a towel from an arbitrarily crumpled state and recovering from a failed folding step remain critical challenges in robotics. We propose joint-probability action inference JA-TN, as a way to improve TransporterNet’s operational efficiency; to our knowledge, this is the first single data-driven policy to achieve various types of folding from most crumpled states. We present three benchmark domains with a set of shaping tasks and the corresponding oracle policies to facilitate the further development of the field. We also present a simulation-to-reality transfer procedure for vision-based deep learning controllers by processing and augmenting RGB and/or depth images. We also demonstrate JA-TN’s ability to integrate with a real camera and a UR3e robot arm, showcasing the method’s applicability to real-world tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-kadi25a, title = {JA-TN: Pick-and-Place Towel Shaping from Crumpled States based on TransporterNet with Joint-Probability Action Inference}, author = {Kadi, Halid Abdulrahim and Terzi\'c, Kasim}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {3107--3123}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/kadi25a/kadi25a.pdf}, url = {https://proceedings.mlr.press/v270/kadi25a.html}, abstract = {Towel manipulation is a crucial step towards more general cloth manipulation. However, folding a towel from an arbitrarily crumpled state and recovering from a failed folding step remain critical challenges in robotics. We propose joint-probability action inference JA-TN, as a way to improve TransporterNet’s operational efficiency; to our knowledge, this is the first single data-driven policy to achieve various types of folding from most crumpled states. We present three benchmark domains with a set of shaping tasks and the corresponding oracle policies to facilitate the further development of the field. We also present a simulation-to-reality transfer procedure for vision-based deep learning controllers by processing and augmenting RGB and/or depth images. We also demonstrate JA-TN’s ability to integrate with a real camera and a UR3e robot arm, showcasing the method’s applicability to real-world tasks.} }
Endnote
%0 Conference Paper %T JA-TN: Pick-and-Place Towel Shaping from Crumpled States based on TransporterNet with Joint-Probability Action Inference %A Halid Abdulrahim Kadi %A Kasim Terzić %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-kadi25a %I PMLR %P 3107--3123 %U https://proceedings.mlr.press/v270/kadi25a.html %V 270 %X Towel manipulation is a crucial step towards more general cloth manipulation. However, folding a towel from an arbitrarily crumpled state and recovering from a failed folding step remain critical challenges in robotics. We propose joint-probability action inference JA-TN, as a way to improve TransporterNet’s operational efficiency; to our knowledge, this is the first single data-driven policy to achieve various types of folding from most crumpled states. We present three benchmark domains with a set of shaping tasks and the corresponding oracle policies to facilitate the further development of the field. We also present a simulation-to-reality transfer procedure for vision-based deep learning controllers by processing and augmenting RGB and/or depth images. We also demonstrate JA-TN’s ability to integrate with a real camera and a UR3e robot arm, showcasing the method’s applicability to real-world tasks.
APA
Kadi, H.A. & Terzić, K.. (2025). JA-TN: Pick-and-Place Towel Shaping from Crumpled States based on TransporterNet with Joint-Probability Action Inference. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:3107-3123 Available from https://proceedings.mlr.press/v270/kadi25a.html.

Related Material