Abstract
Magnetic tactile sensors are widely used in tactile servo and robotic manipulations because of their compact size and high sensitivity. However, their spatial resolution is constrained by the number of Hall elements in a contact area, while their limited capacity to perceive 3D information hinders their broader applications. This paper introduces a grid multipole magnetization method for magnetic tactile sensors that achieves super-resolution and 3D pose perception without increasing the density of Hall elements. By magnetizing the soft contact surface with the proposed grid multipole magnetization method and equipping with different deep neural networks (DNNs), this newly fabricated magnetic-based tactile sensor offers improved 3D sensing capabilities at a sampling frequency of 380 Hz of all 5 Hall sensors within a compact size of 20 × 20mm and a thickness of 3.5 mm. It accurately perceives single-point contacts (contact force ranging from 0 to 2.5 N, with spatial and force resolutions of 0.1 mm and 0.05 N, respectively), as well as providing measurements for 2D rotation angles (−90° to 90°, resolution: 0.33°) and capturing 3D pose features (roll, pitch, yaw angle resolutions: 0.046°, 0.128°, and 0.096° over ranges from −5° to 5°). The effectiveness of this methodology is validated through experiments demonstrating a remarkable improvement in spatial super-resolution by a factor of 70, offering innovative solutions for robotic tactile sensors with numerous potential applications in dexterous manipulation.
Funding Information
  • Shenzhen Basic Research Program (JCYJ20220818102415033, GXWD20231130153844002)

This publication has 29 references indexed in Scilit: