Autonomous robotic nanofabrication with reinforcement learning
Copyright © 2020 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY)..
The ability to handle single molecules as effectively as macroscopic building blocks would enable the construction of complex supramolecular structures inaccessible to self-assembly. The fundamental challenges obstructing this goal are the uncontrolled variability and poor observability of atomic-scale conformations. Here, we present a strategy to work around both obstacles and demonstrate autonomous robotic nanofabrication by manipulating single molecules. Our approach uses reinforcement learning (RL), which finds solution strategies even in the face of large uncertainty and sparse feedback. We demonstrate the potential of our RL approach by removing molecules autonomously with a scanning probe microscope from a supramolecular structure. Our RL agent reaches an excellent performance, enabling us to automate a task that previously had to be performed by a human. We anticipate that our work opens the way toward autonomous agents for the robotic construction of functional supramolecular structures with speed, precision, and perseverance beyond our current capabilities.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2020 |
---|---|
Erschienen: |
2020 |
Enthalten in: |
Zur Gesamtaufnahme - volume:6 |
---|---|
Enthalten in: |
Science advances - 6(2020), 36 vom: 11. Sept. |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Leinen, Philipp [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Revised 01.10.2020 published: Electronic-Print Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.1126/sciadv.abb6987 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM314897607 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM314897607 | ||
003 | DE-627 | ||
005 | 20231225153731.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2020 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1126/sciadv.abb6987 |2 doi | |
028 | 5 | 2 | |a pubmed24n1049.xml |
035 | |a (DE-627)NLM314897607 | ||
035 | |a (NLM)32917594 | ||
035 | |a (PII)eabb6987 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Leinen, Philipp |e verfasserin |4 aut | |
245 | 1 | 0 | |a Autonomous robotic nanofabrication with reinforcement learning |
264 | 1 | |c 2020 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 01.10.2020 | ||
500 | |a published: Electronic-Print | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Copyright © 2020 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY). | ||
520 | |a The ability to handle single molecules as effectively as macroscopic building blocks would enable the construction of complex supramolecular structures inaccessible to self-assembly. The fundamental challenges obstructing this goal are the uncontrolled variability and poor observability of atomic-scale conformations. Here, we present a strategy to work around both obstacles and demonstrate autonomous robotic nanofabrication by manipulating single molecules. Our approach uses reinforcement learning (RL), which finds solution strategies even in the face of large uncertainty and sparse feedback. We demonstrate the potential of our RL approach by removing molecules autonomously with a scanning probe microscope from a supramolecular structure. Our RL agent reaches an excellent performance, enabling us to automate a task that previously had to be performed by a human. We anticipate that our work opens the way toward autonomous agents for the robotic construction of functional supramolecular structures with speed, precision, and perseverance beyond our current capabilities | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Esders, Malte |e verfasserin |4 aut | |
700 | 1 | |a Schütt, Kristof T |e verfasserin |4 aut | |
700 | 1 | |a Wagner, Christian |e verfasserin |4 aut | |
700 | 1 | |a Müller, Klaus-Robert |e verfasserin |4 aut | |
700 | 1 | |a Tautz, F Stefan |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Science advances |d 2015 |g 6(2020), 36 vom: 11. Sept. |w (DE-627)NLM247717614 |x 2375-2548 |7 nnns |
773 | 1 | 8 | |g volume:6 |g year:2020 |g number:36 |g day:11 |g month:09 |
856 | 4 | 0 | |u http://dx.doi.org/10.1126/sciadv.abb6987 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 6 |j 2020 |e 36 |b 11 |c 09 |