EUVIMEDOpdag EUVIMED
Open access

Touching with torque enables human-level robotic dexterity

Ling Wang iD, Yu Sun iD, Laihao Yang iD, Yuxuan Sun, Qingkai Guo, Yixue Liu, Xuefeng Chen iD, Yajing Shen iD

Science Advances · 2026-03-06 · 12 (10)

DOI: 10.1126/sciadv.aec3263 ↗

At a glance

Journal article in Science Advances, published on 2026-03-06. Written by Ling Wang and 7 co-authors. Institution: School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China. Major MEDLINE topics: Robotics, Torque, Touch. Cited 1 times so far (Crossref); 43 references. The full text is freely available in PubMed Central. Funded by: National Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Hong Kong RGC General Research Fund.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Achieving human-like forceful manipulation remains a major challenge in robotics because of the lack of critical environmental interaction cues such as collisions, balance, and resistance. We present a torque-angle-pressure (TAP) tactile sensor leveraging magnetic flux density gradients to achieve bidirectional, ultrasensitive (~0.1°, ~0.4 newton-millimeter), and high-linearity ( R 2 = 0.99) sensing over a wide range (±241.6 newton-millimeter) through a single readout channel. The accurate torque sensing ability provides both force and distance information, bringing the environment into the interaction loop. A TAP-equipped robot can perform vision-free stable object placement and complete a balance beam stacking challenge in just 2.4 seconds with a success rate of 81.5%—both measured metrics surpassing human performance. It also supports adaptive daikon slicing with real-time posture and motion adjustments—capabilities rarely achievable in existing robotic systems. This work advances tactile sensing, enables forceful manipulation in unstructured environments, and represents a key step toward effective human-robot collaboration.

Subjects

MeSH terms (MEDLINE)

RoboticsTorqueTouchHumans

Authors and institutions

  • School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China.
  • HKUST Shenzhen Research Institute, Shenzhen 518057, China.
  • Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China.
  • Center for Smarting Manufacturing, The Hong Kong University of Science and Technology, Hong Kong SAR, China.

ORCID profiles: Ling Wang, Yu Sun, Laihao Yang, Xuefeng Chen, Yajing Shen

Funding

  • National Science Foundation of China
  • Guangdong Basic and Applied Basic Research Foundation
  • Hong Kong RGC General Research Fund

Cite

APA

Wang, L., Sun, Y., Yang, L., Sun, Y., Guo, Q., Liu, Y., Chen, X., & Shen, Y. (2026). Touching with torque enables human-level robotic dexterity. Science Advances, 12(10). https://doi.org/10.1126/sciadv.aec3263

Vancouver

Wang L, Sun Y, Yang L, Sun Y, Guo Q, Liu Y, et al. Touching with torque enables human-level robotic dexterity. Science Advances. 2026;12(10). doi:10.1126/sciadv.aec3263

BibTeX
@article{Wang2026,
  author = {Wang, Ling and Sun, Yu and Yang, Laihao and Sun, Yuxuan and Guo, Qingkai and Liu, Yixue and Chen, Xuefeng and Shen, Yajing},
  title = {Touching with torque enables human-level robotic dexterity},
  journal = {Science Advances},
  year = {2026},
  volume = {12},
  number = {10},
  doi = {10.1126/sciadv.aec3263}
}
Start for free →