EUVIMEDOpdag EUVIMED
Open access

Super-resolution tactile sensor arrays with sparse units enabled by deep learning

Depeng Kong iD, Yuyao Lu iD, Shuyao Zhou iD, Mengke Wang, Gaoyang Pang iD, Baocheng Wang iD, Lipeng Chen, Xiaoyan Huang, Honghao Lyu iD, Kaichen Xu iD, Geng Yang iD

Science Advances · 2025-07-04 · 11 (27)

DOI: 10.1126/sciadv.adv2124 ↗

At a glance

Journal article in Science Advances, published on 2025-07-04. Written by Depeng Kong and 10 co-authors. Institution: State Key Laboratory of Fluid Power and Mechatronic Systems, School of Mechanical Engineering, Zhejiang University, Hangzhou 310030, China. Cited 106 times so far (Crossref); 58 references. The full text is freely available in PubMed Central.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

High-resolution tactile perception is essential for humanoid robots to perform contact-based interaction tasks. However, enhancing resolution is typically accompanied by increasing the density of sensing nodes, large numbers of interconnecting wires, and complex signal processing modules. This work presents super-resolution (SR) tactile sensor arrays with sparsely distributed taxels powered by a universal intelligent framework. Such smart sensor systems involve a general topological optimization strategy for taxel layout design and a deep learning model called self-attention–assisted tactile SR. Driven by the proposed model, they can dynamically distinguish high-density pressure stimuli by generating 2700 virtual taxels from only 23 physical taxels. An SR scale factor of more than 115 and an average localization error of 0.73 millimeters are achieved, approximating human fingertip accuracy and surpassing current state-of-the-art solutions. This framework enhances flexible sensors with SR capabilities in a facile and energy-efficient manner, illustrating the potential to equip robots with embodied tactile perceptions.

Authors and institutions

  • State Key Laboratory of Fluid Power and Mechatronic Systems, School of Mechanical Engineering, Zhejiang University, Hangzhou 310030, China.
  • School of Electrical and Computer Engineering, The University of Sydney, Sydney 2006, Australia.
  • Tencent Robotics X Laboratory, Tencent, Shenzhen 518057, China.
  • College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China.
  • Zhejiang Key Laboratory of Intelligent Robot for Operation and Maintenance, Hangzhou 310030, China.

ORCID profiles: Depeng Kong, Yuyao Lu, Shuyao Zhou, Gaoyang Pang, Baocheng Wang, Honghao Lyu, Kaichen Xu, Geng Yang

Cite

APA

Kong, D., Lu, Y., Zhou, S., Wang, M., Pang, G., Wang, B., Chen, L., Huang, X., Lyu, H., Xu, K., & Yang, G. (2025). Super-resolution tactile sensor arrays with sparse units enabled by deep learning. Science Advances, 11(27). https://doi.org/10.1126/sciadv.adv2124

Vancouver

Kong D, Lu Y, Zhou S, Wang M, Pang G, Wang B, et al. Super-resolution tactile sensor arrays with sparse units enabled by deep learning. Science Advances. 2025;11(27). doi:10.1126/sciadv.adv2124

BibTeX
@article{Kong2025,
  author = {Kong, Depeng and Lu, Yuyao and Zhou, Shuyao and Wang, Mengke and Pang, Gaoyang and Wang, Baocheng and Chen, Lipeng and Huang, Xiaoyan and Lyu, Honghao and Xu, Kaichen and Yang, Geng},
  title = {Super-resolution tactile sensor arrays with sparse units enabled by deep learning},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {27},
  doi = {10.1126/sciadv.adv2124}
}
Start for free →