Soft Magnetic Skin for Super-Resolution Tactile Sensing with Force Self-decoupling

Principal Investigator: Dr. Jia PAN (Department of Computer Science)

This project is showcased in the inaugural exhibition – Engineering for Better Living in Innovation Wing Two

Project information


Human skin can sense subtle changes of both normal and shear forces as well as perceive stimulus with finer resolution than the average spacing between mechanoreceptors. By contrast, existing tactile sensors for robotic applications are inferior, lacking both accurate force decoupling and proper spatial resolution. This project aims at developing skin-alike soft tactile sensors based on principles of magnetic fields.

Novelty of the Project

In this project, we demonstrate a soft tactile sensor with self-decoupling and super-resolution abilities by designing a sinusoidally magnetized flexible film (with the thickness ~0.5 millimeters), whose deformation can be detected by a Hall sensor according to the change of magnetic flux densities under external forces. The sensor can accurately measure the normal force and the shear force with a single unit and achieve a 60-fold super-resolved accuracy enhanced by deep learning. By mounting our sensor at the fingertip of a robotic gripper we show that our robots can accomplish challenging tasks like stably grasping fragile objects under external disturbance and threading a needle via teleoperation.

Benefit to the Community

This research provides new insight into tactile sensor design and could be beneficial to various applications in robotics field, such as adaptive grasping, dexterous manipulation, and human-robot interaction.

Compared with the traditional tactile sensors that are either mechanically decoupled (using multiple sensing units) or decoupled by data-fitting methods (using complicated models), our sensor is able to measure both the normal and shear forces in a decoupled way, which dramatically simplifies the sensor structure and the calibration process, and is thus more suitable to be used in  practical applications than other sensors that are either complex to fabricate and calibrate or not robust for practical usage.

About the Scholar

Dr Pan is current the Assistant Professor at the Department of Computer Science, HKU. His research interests are robotics and artificial intelligence.

Project poster
Project video
Project images
Achievement of the Project
  • Yan, Z. Hu, Y. Shen*, and J. Pan*. Surface Texture Recognition by Deep Learning—enhanced Tactile Sensing. Advanced Intelligent Systems, 2021
  • Yan, Z. Hu, Z. Yang, W. Yuan, C. Song, J. Pan*, and Y. Shen. A soft magnetic skin for self-decoupled and super-resolved tactile sensing. Science Robotics, 6(51), 2021
  • Yan and J. Pan*. Fast localization and segmentation of tissue abnormalities by autonomous robotic palpation. lEEERobotics andAutomat/on Letters, 6(2):1707 – 1714, 2021
  • US Patent: Jia Pan, Yajing Shen, Youcan Yan (2021). A soft tactile sensor by flexible magnetic film, USA patent, filed.
  • The team has established connections with the industries including Huawei 2021 Lab and Delta Electronics.
Enquiry / Feedback

Please feel free to give your enquiry / feedbacks to the research team by filling the form ( Thank you!