Journal article · 2026 · Open access

Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber

Zhaofan He, Lele Wang, Haidi Geng, Zhengyang Lu, Tiantian He, Hongkun Zhong, Hailong Zhang, Runfeng Zhu, Qingxiang Zhao, Yuan Meng, Dan Li, Ping Yan and 2 more

Science Advances, 12(24), eaef6263 · Published 12 June 2026 · DOI 10.1126/sciadv.aef6263

Open full textCite this paper

In brief

“Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber” is a 2026 journal article by Zhaofan He and 13 co-authors, published in Science Advances. OpenAlex counts 6 citations as of 22 November 2026, which puts it in the top 3% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Science Advances.

Citations
6
Most cited in
2026 (6)
Field-weighted impact
6.70
References
50
Authors
14

Abstract

The evolution of soft robots into embodied intelligent systems relies fundamentally on precise proprioception. However, a universal solution for capturing continuous deformations during diverse interactions, particularly in spatially confined interventional scenarios, remains lacking. Here, we introduce a deep learning-enabled versatile shape perception method based on a single-ended multimode fiber (MMF). By leveraging the intrinsic integration advantages of optics, our minimalist reflective architecture physically eliminates the dependence on complex demodulation units and distal devices. Furthermore, treating chaotic optical speckle fields as data streams encoding high-dimensional shape information, reconfigurable neural decoders resolve a single physical channel into versatile perception modes tailored to heterogeneous tasks: discrete state confirmation on soft grippers (>99% accuracy), continuous shape tracking on bionic dexterous hands (~5-fold spatial resolution enhancement), and intuitive 3D morphological reconstruction of soft surgical robots (IoU>0.93). Overall, our work establishes a versatile framework for breaking hardware adaptability limits via computation, laying a solid foundation for closed-loop control in digital twins of soft robots.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

He, Z., Wang, L., Geng, H., Lu, Z., He, T., Zhong, H., Zhang, H., Zhu, R., Zhao, Q., Meng, Y., Li, D., Yan, P., Liu, Q., & Xiao, Q. (2026). Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber. Science Advances, 12(24), eaef6263. https://doi.org/10.1126/sciadv.aef6263

MLA 9

He, Zhaofan, et al. “Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber.” Science Advances, vol. 12, no. 24, 2026, p. eaef6263. https://doi.org/10.1126/sciadv.aef6263.

Chicago

He, Zhaofan, Lele Wang, Haidi Geng, Zhengyang Lu, Tiantian He, Hongkun Zhong, Hailong Zhang, et al. 2026. “Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber.” Science Advances 12 (24): eaef6263. https://doi.org/10.1126/sciadv.aef6263.

Harvard

He, Z. et al. (2026) ‘Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber’, Science Advances, 12(24), p. eaef6263. doi:10.1126/sciadv.aef6263.

IEEE

Z. He et al., “Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber,” Science Advances, vol. 12, no. 24, p. eaef6263, 2026, doi: 10.1126/sciadv.aef6263.

BibTeX

@article{he2026deep,
  title     = {{Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber}},
  author    = {He, Zhaofan and Wang, Lele and Geng, Haidi and Lu, Zhengyang and He, Tiantian and Zhong, Hongkun and Zhang, Hailong and Zhu, Runfeng and Zhao, Qingxiang and Meng, Yuan and Li, Dan and Yan, Ping and Liu, Qiang and Xiao, Qirong},
  journal   = {Science Advances},
  year      = {2026},
  volume    = {12},
  number    = {24},
  pages     = {eaef6263},
  doi       = {10.1126/sciadv.aef6263},
  url       = {https://doi.org/10.1126/sciadv.aef6263}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Engineering › Biomedical Engineering › Soft Robotics and Applications

  • soft robots
  • shape perception
  • multimode fiber
  • optical sensing
  • proprioception
  • optical speckle
  • soft gripper
  • 3D reconstruction

Work with this paper

Most-cited papers in Engineering

All highly cited Engineering papers

Questions about this paper

How do I cite this paper in APA style?

He, Z., Wang, L., Geng, H., Lu, Z., He, T., Zhong, H., Zhang, H., Zhu, R., Zhao, Q., Meng, Y., Li, D., Yan, P., Liu, Q., & Xiao, Q. (2026). Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber. Science Advances, 12(24), eaef6263. https://doi.org/10.1126/sciadv.aef6263

How many times has this paper been cited?

6 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Science Advances: sign in and open the full text from this page.

Who wrote this paper?

Zhaofan He, Lele Wang, Haidi Geng, Zhengyang Lu, Tiantian He, Hongkun Zhong, Hailong Zhang, Runfeng Zhu, Qingxiang Zhao, Yuan Meng, Dan Li, Ping Yan and 2 more.

What is the DOI of this paper?

10.1126/sciadv.aef6263, permanently at https://doi.org/10.1126/sciadv.aef6263. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.