Integrated AI Framework for Room-Temperature Atom Manipulation in Scanning Probe Microscopy
Source abstract
Abstract
We demonstrate an integrated artificial intelligence (AI) framework for autonomous atom manipulation of silver atoms on a Si(111)-(7 × 7) surface at room temperature. The framework combines four machine learning models that evaluate tip and surface conditions, detect Ag atoms, locate defect-free half-unit cells (HUCs), and evaluate manipulation conditions. This integration enables autonomous scanning tunneling microscopy operation with key functions including thermal drift correction, probe tip conditioning, and automated atom manipulation. The integrated AI framework demonstrated robust long-term operation, autonomously performing atom manipulation over 25 h. During this period, the system successfully executed both lateral transfer of Ag atoms between adjacent HUCs and vertical pickup operations without human intervention. While the manipulation success rate remains limited by tip stability challenges, the system demonstrates the feasibility of AI-driven autonomous operation at room temperature, providing a foundation for future high-throughput atomic-scale fabrication.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Surface and Thin Film Phenomena · Force Microscopy Techniques and Applications · Advanced Electron Microscopy Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Graduate School of Engineering Science, The University of Osaka, 1-3 Machikaneyama, Toyonaka, Osaka 560-8531, Japan
Funding
Japan Society for the Promotion of Science · JKA Foundation · Kyoto Technoscience Center
References (49)
Show source-provided references
1. 10.1103/PhysRevLett.49.5710.1103/PhysRevLett.49.57 ↗
2. Chen C. J. · 2008
3. 10.1103/PhysRevLett.56.93010.1103/PhysRevLett.56.930 ↗
4. Morita S. · 200210.1007/978-3-642-56019-4 ↗
5. 10.1038/344524a010.1038/344524a0 ↗
6. 10.1038/nmat129710.1038/nmat1297 ↗
7. 10.1038/nnano.2009.34710.1038/nnano.2009.347 ↗
8. 10.1103/PhysRevLett.85.277710.1103/PhysRevLett.85.2777 ↗
9. 10.1002/anie.20050222910.1002/anie.200502229 ↗
10. 10.1126/science.114436610.1126/science.1144366 ↗
11. 10.1126/science.107524210.1126/science.1075242 ↗
12. 10.1038/nnano.2012.2110.1038/nnano.2012.21 ↗
13. 10.1126/science.121431910.1126/science.1214319 ↗
14. 10.1126/science.120172510.1126/science.1201725 ↗
15. 10.1038/nphys408010.1038/nphys4080 ↗
16. 10.1038/nnano.2016.13110.1038/nnano.2016.131 ↗
17. 10.1103/PhysRevLett.79.69710.1103/PhysRevLett.79.697 ↗
18. 10.1126/science.116060110.1126/science.1160601 ↗
19. 10.1063/1.210811210.1063/1.2108112 ↗
20. 10.1063/1.273941010.1063/1.2739410 ↗
21. 10.1038/s41598-025-01578-y10.1038/s41598-025-01578-y ↗
22. 10.1038/s42005-020-0317-310.1038/s42005-020-0317-3 ↗
23. 10.1021/acsnano.1c0210410.1021/acsnano.1c02104 ↗
24. 10.1021/acsnano.4c1876010.1021/acsnano.4c18760 ↗
25. 10.1038/s42256-022-00555-810.1038/s42256-022-00555-8 ↗
26. 10.1557/s43577-022-00324-310.1557/s43577-022-00324-3 ↗
27. 10.1002/jemt.2438410.1002/jemt.24384 ↗
28. 10.1002/smtd.20240081310.1002/smtd.202400813 ↗
29. 10.1088/2632-2153/ab42ec10.1088/2632-2153/ab42ec ↗
30. 10.1021/acsnano.8b0220810.1021/acsnano.8b02208 ↗
31. 10.35848/1882-0786/acecd610.35848/1882-0786/acecd6 ↗
32. 10.1038/s42256-022-00460-010.1038/s42256-022-00460-0 ↗
33. 10.1021/acsnano.2c0530310.1021/acsnano.2c05303 ↗
34. 10.1038/s41524-025-01642-110.1038/s41524-025-01642-1 ↗
35. 10.1002/adma.20220134510.1002/adma.202201345 ↗
36. 10.1016/j.patter.2023.10070410.1016/j.patter.2023.100704 ↗
37. 10.1021/cs300570910.1021/cs3005709 ↗
38. 10.1038/s41467-022-35149-w10.1038/s41467-022-35149-w ↗
39. Drexler K. E. · 1986
40. 10.1063/1.509959010.1063/1.5099590 ↗
41. 10.1016/j.cpc.2021.10825810.1016/j.cpc.2021.108258 ↗
42. 10.1103/PhysRevLett.94.17610410.1103/PhysRevLett.94.176104 ↗
43. 10.1038/ncomms536010.1038/ncomms5360 ↗
44. 10.1063/5.021433010.1063/5.0214330 ↗
45. 10.1063/5.013933010.1063/5.0139330 ↗
46. 10.1103/PhysRevB.78.20530510.1103/PhysRevB.78.205305 ↗
47. 10.1002/advs.20220395710.1002/advs.202203957 ↗
48. 10.1038/3015610.1038/30156 ↗
49. Paszke, A. PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv (Computer Science.Machine Learning) , December 3, 2019, 1912.01703, ver. 1. https://arxiv.org/abs/1912.01703 (accessed 2025-11-04).