EUVIMEDOpdag EUVIMED
Open access

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

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

Science Advances · 2026-06-12 · 12 (24)

DOI: 10.1126/sciadv.aef6263 ↗

At a glance

Journal article in Science Advances, published on 2026-06-12. Written by Zhaofan He and 13 co-authors. Institution: Department of Precision Instrument, Tsinghua University, Beijing 100084, China. Cited 2 times so far (Crossref); 53 references. The full text is freely available in PubMed Central. Funded by: National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

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.

Authors and institutions

  • Department of Precision Instrument, Tsinghua University, Beijing 100084, China.
  • State Key Laboratory of Precision Space-time Information Sensing Technology, Beijing 100084, China.
  • Weixian College, Tsinghua University, Beijing 100084, China.
  • West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu 610041, China.

ORCID profiles: Zhaofan He, Lele Wang, Tiantian He, Hailong Zhang, Runfeng Zhu, Qingxiang Zhao, Yuan Meng, Qiang Liu, Qirong Xiao

Funding

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation

Cite

APA

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). https://doi.org/10.1126/sciadv.aef6263

Vancouver

He Z, Wang L, Geng H, Lu Z, He T, Zhong H, et al. Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber. Science Advances. 2026;12(24). doi:10.1126/sciadv.aef6263

BibTeX
@article{He2026,
  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},
  title = {Deep learning–enabled versatile shape perception for soft robots via single-ended multimode fiber},
  journal = {Science Advances},
  year = {2026},
  volume = {12},
  number = {24},
  doi = {10.1126/sciadv.aef6263}
}
Start for free →