Artificial Intelligence Meets Micro/Nanorobotics
7 affiliations
- 1Future Energy and Innovation Laboratory Central European Institute of Technology Brno University of Technology Brno Czech Republic
- 2Department of Chemical Engineering Institute For Polymer Research Center For Bioengineering and Biotechnology Waterloo Institute for Nanotechnology University of Waterloo Waterloo Ontario Canada
- 3Faculty of Electrical Engineering and Computer Science VSB – Technical University of Ostrava Ostrava Czech Republic
- 4IT4Innovations VSB – Technical University of Ostrava Ostrava Czech Republic
- 5Regional Centre of Advanced Technologies and Materials Czech Advanced Technology and Research Institute (CATRIN) Palacký University Olomouc Olomouc Czech Republic
- 6Office of Research and Development Asia University Taichung Taiwan
- 7Department of Chemical and Biomolecular Engineering Yonsei University Seoul South Korea
Abstract
Microrobots and nanorobots are a developing technology, which evolved from simple “motoric” motion‐capable micro/nanomachines to physical machine intelligence capable of communicating with each other using chemical or physical signals. Meanwhile, artificial intelligence (AI) is rapidly integrating into our modern life. We explore here how AI can be implemented in micro‐ and nanorobotic systems. The advancement of AI enhances micro‐ and nanorobots’ performance but also drives a fundamental transition from externally actuated, task‐specific platforms toward autonomous, adaptive, and multifunctional systems capable of operating in highly complex environments for clinical and environmental applications. At the micro/nanoscale, propulsion, sensing, and control face several limitations, including limited onboard computation, which hinder deterministic navigation and task execution. Recent advances in machine learning, including deep learning, reinforcement learning, and physics‐informed models, now offer powerful solutions to overcome those limitations. This perspective highlights how the convergence of AI and micro‐ and nanorobot technologies is creating a promising hybrid discipline for translational applications in both clinical and environmental settings. AI‐assisted design accelerates the discovery of functional materials tailored to specific applications, optimizes geometric and surface properties for efficient propulsion, and enables generative fabrication of micro‐ and nanorobot architectures. Moreover, deep learning‐based ultrasound, optical depth estimation, and multimodal perception enable precise real‐time localization—an essential requirement for closed‐loop autonomythereby enhancing the imaging and tracking of micro‐ and nanorobots. Additionally, the use of digital twins offers a predictive model of real‐world experimentation supporting risk assessment and patient‐specific planning for biomedical applications. The advances in AI‐enhanced micro‐ and nanorobots will transform the targeted drug delivery, minimally invasive diagnostics, biosensing, environmental remediation, and pollutant capture by integrating real‐time perception and adaptive decision‐making into fully autonomous devices in complex clinical and environmental conditions.
Related
- Using artificial intelligence for clinical trial quality assurance in a multi-institutional neurovascular-sparing prostate radiotherapy trial
- Future of Artificial Intelligence for Science in Japan 2024 Community Report
- Advancing Nuclear Physics with Machine Learning and Artificial Intelligence
- Artificial intelligence and machine learning for magnetic nanoparticles and nanocarriers in cancer imaging, drug delivery, and magnetic control: a systematic review
- From proof of concept to practice: the next decade of artificial intelligence in metasurface photonics
BibTeX
@article{yurtsever2026artificial,
title = {{Artificial Intelligence Meets Micro/Nanorobotics}},
author = {Fatma M. Yurtsever and Minitha Cherukutty Ramakrishnan and Ian Kuula Ross and Ivan Zelinka and Hamed Shahsavan and Michal Otyepka and Martin Pumera},
journal = {Advanced Materials (Deerfield Beach, Fla.)},
year = {2026},
month = aug,
doi = {10.1002/adma.74721},
url = {https://doi.org/10.1002/adma.74721},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Artificial Intelligence Meets Micro/Nanorobotics
AU - Fatma M. Yurtsever
AU - Minitha Cherukutty Ramakrishnan
AU - Ian Kuula Ross
AU - Ivan Zelinka
AU - Hamed Shahsavan
AU - Michal Otyepka
AU - Martin Pumera
PY - 2026
DA - 2026/08/27
JO - Advanced Materials (Deerfield Beach, Fla.)
DO - 10.1002/adma.74721
UR - https://doi.org/10.1002/adma.74721
AB - Microrobots and nanorobots are a developing technology, which evolved from simple “motoric” motion‐capable micro/nanomachines to physical machine intelligence capable of communicating with each other using chemical or physical signals. Meanwhile, artificial intelligence (AI) is rapidly integrating into our modern life. We explore here how AI can be implemented in micro‐ and nanorobotic systems. The advancement of AI enhances micro‐ and nanorobots’ performance but also drives a fundamental transition from externally actuated, task‐specific platforms toward autonomous, adaptive, and multifunctional systems capable of operating in highly complex environments for clinical and environmental applications. At the micro/nanoscale, propulsion, sensing, and control face several limitations, including limited onboard computation, which hinder deterministic navigation and task execution. Recent advances in machine learning, including deep learning, reinforcement learning, and physics‐informed models, now offer powerful solutions to overcome those limitations. This perspective highlights how the convergence of AI and micro‐ and nanorobot technologies is creating a promising hybrid discipline for translational applications in both clinical and environmental settings. AI‐assisted design accelerates the discovery of functional materials tailored to specific applications, optimizes geometric and surface properties for efficient propulsion, and enables generative fabrication of micro‐ and nanorobot architectures. Moreover, deep learning‐based ultrasound, optical depth estimation, and multimodal perception enable precise real‐time localization—an essential requirement for closed‐loop autonomythereby enhancing the imaging and tracking of micro‐ and nanorobots. Additionally, the use of digital twins offers a predictive model of real‐world experimentation supporting risk assessment and patient‐specific planning for biomedical applications. The advances in AI‐enhanced micro‐ and nanorobots will transform the targeted drug delivery, minimally invasive diagnostics, biosensing, environmental remediation, and pollutant capture by integrating real‐time perception and adaptive decision‐making into fully autonomous devices in complex clinical and environmental conditions.
SN - 0935-9648
SN - 1521-4095
ER -