---
OA_place: publisher
OA_type: hybrid
PlanS_conform: '1'
_id: '11442'
abstract:
- lang: eng
text: "Enabling additive manufacturing to employ a wide range of novel, functional
materials can be a major boost to this technology. However, making such materials
printable requires painstaking trial-and-error by an expert operator,\r\nas they
typically tend to exhibit peculiar rheological or hysteresis properties. Even
in the case of successfully finding the process parameters, there is no guarantee
of print-to-print consistency due to material differences between batches. These
challenges make closed-loop feedback an attractive option where the process parameters
are adjusted on-the-fly. There are several challenges for designing an efficient
controller: the deposition parameters are complex and highly coupled, artifacts
occur after long time horizons, simulating the deposition is computationally costly,
and learning on hardware is intractable. In this work, we demonstrate the feasibility
of learning a closed-loop control policy for additive manufacturing using reinforcement
learning. We show that approximate, but efficient, numerical simulation is\r\nsufficient
as long as it allows learning the behavioral patterns of deposition that translate
to real-world experiences. In combination with reinforcement learning, our model
can be used to discover control policies that outperform\r\nbaseline controllers.
Furthermore, the recovered policies have a minimal sim-to-real gap. We showcase
this by applying our control policy in-vivo on a single-layer, direct ink writing
printer. "
acknowledgement: "This work is graciously supported by the following grant agencies:
FWF Lise Meitner (Grant M 3319), SNSF (Grant 200502), ERC Starting Grant (MATERIALIZABLE-715767),
NSF (Grant IIS-181507).\r\n"
article_number: '112'
article_processing_charge: No
article_type: original
arxiv: 1
author:
- first_name: Michael
full_name: Piovarci, Michael
id: 62E473F4-5C99-11EA-A40E-AF823DDC885E
last_name: Piovarci
orcid: 0000-0002-5062-4474
- first_name: Michael
full_name: Foshey, Michael
last_name: Foshey
- first_name: Jie
full_name: Xu, Jie
last_name: Xu
- first_name: Timothy
full_name: Erps, Timothy
last_name: Erps
- first_name: Vahid
full_name: Babaei, Vahid
last_name: Babaei
- first_name: Piotr
full_name: Didyk, Piotr
last_name: Didyk
- first_name: Szymon
full_name: Rusinkiewicz, Szymon
last_name: Rusinkiewicz
- first_name: Wojciech
full_name: Matusik, Wojciech
last_name: Matusik
- first_name: Bernd
full_name: Bickel, Bernd
id: 49876194-F248-11E8-B48F-1D18A9856A87
last_name: Bickel
orcid: 0000-0001-6511-9385
citation:
ama: Piovarci M, Foshey M, Xu J, et al. Closed-loop control of direct ink writing
via reinforcement learning. ACM Transactions on Graphics. 2022;41(4). doi:10.1145/3528223.3530144
apa: Piovarci, M., Foshey, M., Xu, J., Erps, T., Babaei, V., Didyk, P., … Bickel,
B. (2022). Closed-loop control of direct ink writing via reinforcement learning.
ACM Transactions on Graphics. Association for Computing Machinery. https://doi.org/10.1145/3528223.3530144
chicago: Piovarci, Michael, Michael Foshey, Jie Xu, Timothy Erps, Vahid Babaei,
Piotr Didyk, Szymon Rusinkiewicz, Wojciech Matusik, and Bernd Bickel. “Closed-Loop
Control of Direct Ink Writing via Reinforcement Learning.” ACM Transactions
on Graphics. Association for Computing Machinery, 2022. https://doi.org/10.1145/3528223.3530144.
ieee: M. Piovarci et al., “Closed-loop control of direct ink writing via
reinforcement learning,” ACM Transactions on Graphics, vol. 41, no. 4.
Association for Computing Machinery, 2022.
ista: Piovarci M, Foshey M, Xu J, Erps T, Babaei V, Didyk P, Rusinkiewicz S, Matusik
W, Bickel B. 2022. Closed-loop control of direct ink writing via reinforcement
learning. ACM Transactions on Graphics. 41(4), 112.
mla: Piovarci, Michael, et al. “Closed-Loop Control of Direct Ink Writing via Reinforcement
Learning.” ACM Transactions on Graphics, vol. 41, no. 4, 112, Association
for Computing Machinery, 2022, doi:10.1145/3528223.3530144.
short: M. Piovarci, M. Foshey, J. Xu, T. Erps, V. Babaei, P. Didyk, S. Rusinkiewicz,
W. Matusik, B. Bickel, ACM Transactions on Graphics 41 (2022).
corr_author: '1'
date_created: 2022-06-10T06:41:47Z
date_published: 2022-06-01T00:00:00Z
date_updated: 2025-09-10T09:36:45Z
day: '01'
ddc:
- '000'
department:
- _id: BeBi
doi: 10.1145/3528223.3530144
ec_funded: 1
external_id:
arxiv:
- '2201.11819'
isi:
- '000830989200091'
file:
- access_level: open_access
checksum: 27f6fe41c6ff84d50445cc9b0176d45b
content_type: application/pdf
creator: dernst
date_created: 2022-06-28T08:32:58Z
date_updated: 2022-06-28T08:32:58Z
file_id: '11467'
file_name: 2022_ACM_acceptedversion_Piovarci.pdf
file_size: 33994829
relation: main_file
success: 1
file_date_updated: 2022-06-28T08:32:58Z
has_accepted_license: '1'
intvolume: ' 41'
isi: 1
issue: '4'
language:
- iso: eng
license: https://creativecommons.org/licenses/by/4.0/
month: '06'
oa: 1
oa_version: Submitted Version
project:
- _id: eb901961-77a9-11ec-83b8-f5c883a62027
grant_number: M03319
name: Perception-Aware Appearance Fabrication
- _id: 24F9549A-B435-11E9-9278-68D0E5697425
call_identifier: H2020
grant_number: '715767'
name: 'MATERIALIZABLE: Intelligent fabrication-oriented Computational Design and
Modeling'
publication: ACM Transactions on Graphics
publication_identifier:
eissn:
- 1557-7368
issn:
- 0730-0301
publication_status: published
publisher: Association for Computing Machinery
quality_controlled: '1'
related_material:
link:
- description: News on ISTA website
relation: press_release
url: https://ista.ac.at/en/news/machine-learning-3d-printing-fluids/
scopus_import: '1'
status: public
title: Closed-loop control of direct ink writing via reinforcement learning
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: journal_article
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 41
year: '2022'
...