Skip to content
DraconiticResearch
Search Sources API
181,713 studies31 sourcesUpdated 57 min ago
Peer-reviewedCC BY-NC-NDNature communications

Learning for micro-scale mechano-flow co-manipulation.

  • Yujian An1,2
  • Jianxin Yang2
  • Bingze He1,2
  • Yao Guo3,4
  • Guang-Zhong Yang5,6
6 affiliations
  1. 1Shanghai Key Laboratory of Flexible Medical Robotics, Tongren Hospital, Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China.
  2. 2Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.
  3. 3Shanghai Key Laboratory of Flexible Medical Robotics, Tongren Hospital, Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China. [email protected].
  4. 4Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China. [email protected].
  5. 5Shanghai Key Laboratory of Flexible Medical Robotics, Tongren Hospital, Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China. [email protected].
  6. 6Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China. [email protected].
Read full textPDFDOICite

Abstract

Dexterous manipulation is a fundamental yet unresolved topic in robotics, particularly in the realm of micro-manipulation of flexible objects. The complex interplay among external forces, intrinsic material properties, and environmental factors that govern shape deformation presents significant challenges to learning and control. This paper introduces a mechano-flow co-manipulation scheme for flexible micro-objects. It achieves precise handling of floating micro-objects by dynamically adjusting the flow field at the air-liquid interface, enabling simultaneous control of both manipulation and focal planes. A real-time flow prediction framework is proposed based on a reversible neural network, termed FlowNet, achieving bidirectional prediction of input flow and resulting spatio-temporal flow distribution with high accuracy. Through experimental validation, including linear-drive characterization, open-loop trajectory following, and manipulation of different flexible objects, we demonstrate the system's versatility, precision, and stability. The proposed system offers a promising approach for micro-manipulation through mechano-flow interaction for flexible micro-objects.

Related

  1. Multi-mode hybrid micro-gripper for micro-manipulation and micro-assembly.
    Gianmauro Fontana, Nicola Iacono, Gabriele Papadia +1
    HardwareXPeer-reviewedCC BYFull textCondensed matterEurope PMC
  2. Ultra-large-scale compilation and manipulation of quantum circuits with Pandora
    Ioana Moflic, Alexandru Paler
    npj Quantum InformationPeer-reviewedCC BY 4.0Quantum physics & quantum informationCrossref
  3. Analysis of the rarefied flow at micro-step using a DeepONet surrogate model with a physics-guided zonal loss function
    Ehsan Roohi, Amirmehran Mahdavi
    Microfluidics and NanofluidicsPeer-reviewedLicence not statedFull text8 citedStatistical & nonlinear physicsOpenAlex
  4. First results on hydration time effect on Wharton's jelly mechanical behaviour from micro to macro scale
    Martina Isnardi, Emilien Schall, Alexis Da Rocha +5
    Multidisciplinary Biomechanics JournalPeer-reviewedCC BY 4.0Full textGeneral physicsHAL
  5. Flow-rate controls on trapped hydrogen redistribution in a heterogeneous sandstone: a synchrotron X-ray micro-CT study
    Catherine Spurin, Sojwal Manoorkar, Sharon Ellman +7
    arXivPreprintCC BY 4.0Full textGeophysics & seismologyFluid dynamicsarXiv

Cite

BibTeXRIS
BibTeX
@article{an2026learning,
  title = {{Learning for micro-scale mechano-flow co-manipulation.}},
  author = {Yujian An and Jianxin Yang and Bingze He and Yao Guo and Guang-Zhong Yang},
  journal = {Nature communications},
  year = {2026},
  month = sep,
  doi = {10.1038/s41467-026-77746-z},
  url = {https://europepmc.org/article/MED/42907462},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - Learning for micro-scale mechano-flow co-manipulation.
AU  - Yujian An
AU  - Jianxin Yang
AU  - Bingze He
AU  - Yao Guo
AU  - Guang-Zhong Yang
PY  - 2026
DA  - 2026/09/21
JO  - Nature communications
DO  - 10.1038/s41467-026-77746-z
UR  - https://europepmc.org/article/MED/42907462
AB  - Dexterous manipulation is a fundamental yet unresolved topic in robotics, particularly in the realm of micro-manipulation of flexible objects. The complex interplay among external forces, intrinsic material properties, and environmental factors that govern shape deformation presents significant challenges to learning and control. This paper introduces a mechano-flow co-manipulation scheme for flexible micro-objects. It achieves precise handling of floating micro-objects by dynamically adjusting the flow field at the air-liquid interface, enabling simultaneous control of both manipulation and focal planes. A real-time flow prediction framework is proposed based on a reversible neural network, termed FlowNet, achieving bidirectional prediction of input flow and resulting spatio-temporal flow distribution with high accuracy. Through experimental validation, including linear-drive characterization, open-loop trajectory following, and manipulation of different flexible objects, we demonstrate the system's versatility, precision, and stability. The proposed system offers a promising approach for micro-manipulation through mechano-flow interaction for flexible micro-objects.
SN  - 2041-1723
ER  -