Table of Contents
Fetching ...

A Magnetic-Actuated Vision-Based Whisker Array for Contact Perception and Grasping

Zhixian Hu, Juan Wachs, Yu She

TL;DR

This work addresses tactile sensing and manipulation of delicate objects by introducing a vision-based, magnetically actuated whisker array with eight circularly arranged whiskers. A camera-based tracking system provides high-resolution tactile feedback while independent electromagnet actuation enables precise retraction and extension of each whisker. Key contributions include a detailed mechanical design on an Ecoflex membrane, a robust whisker-tracking pipeline, and validation through object classification (99.17% accuracy) and grasping experiments (87% success with eight whiskers). The approach demonstrates strong potential for precise tactile perception and reliable manipulation in soft robotics and delicate-object applications.

Abstract

Tactile sensing and the manipulation of delicate objects are critical challenges in robotics. This study presents a vision-based magnetic-actuated whisker array sensor that integrates these functions. The sensor features eight whiskers arranged circularly, supported by an elastomer membrane and actuated by electromagnets and permanent magnets. A camera tracks whisker movements, enabling high-resolution tactile feedback. The sensor's performance was evaluated through object classification and grasping experiments. In the classification experiment, the sensor approached objects from four directions and accurately identified five distinct objects with a classification accuracy of 99.17% using a Multi-Layer Perceptron model. In the grasping experiment, the sensor tested configurations of eight, four, and two whiskers, achieving the highest success rate of 87% with eight whiskers. These results highlight the sensor's potential for precise tactile sensing and reliable manipulation.

A Magnetic-Actuated Vision-Based Whisker Array for Contact Perception and Grasping

TL;DR

This work addresses tactile sensing and manipulation of delicate objects by introducing a vision-based, magnetically actuated whisker array with eight circularly arranged whiskers. A camera-based tracking system provides high-resolution tactile feedback while independent electromagnet actuation enables precise retraction and extension of each whisker. Key contributions include a detailed mechanical design on an Ecoflex membrane, a robust whisker-tracking pipeline, and validation through object classification (99.17% accuracy) and grasping experiments (87% success with eight whiskers). The approach demonstrates strong potential for precise tactile perception and reliable manipulation in soft robotics and delicate-object applications.

Abstract

Tactile sensing and the manipulation of delicate objects are critical challenges in robotics. This study presents a vision-based magnetic-actuated whisker array sensor that integrates these functions. The sensor features eight whiskers arranged circularly, supported by an elastomer membrane and actuated by electromagnets and permanent magnets. A camera tracks whisker movements, enabling high-resolution tactile feedback. The sensor's performance was evaluated through object classification and grasping experiments. In the classification experiment, the sensor approached objects from four directions and accurately identified five distinct objects with a classification accuracy of 99.17% using a Multi-Layer Perceptron model. In the grasping experiment, the sensor tested configurations of eight, four, and two whiskers, achieving the highest success rate of 87% with eight whiskers. These results highlight the sensor's potential for precise tactile sensing and reliable manipulation.

Paper Structure

This paper contains 9 sections, 4 equations, 9 figures, 1 table.

Figures (9)

  • Figure 1: Overview of the vision-based magnetic-actuated sensor. (a) Neutral state. (b) Retraction state. (c) Extension state.
  • Figure 2: Mechanical design of the sensor. (a) Overview of the sensor's mechanical design. (b) Top view of the sensor. (c) Top cross-section view showing the arrangement of the electromagnets and permanent magnets.
  • Figure 3: Image processing pipeline of the whisker tracking system. (a) Raw image. (b) Mask showing the filtered red color region. (c) Eroded image to eliminate the effects of the wires. (d) Detection of contour centers. (e) Image with yellow dots indicating the detected tracker centers when no external forces are applied to the whiskers. (f) Zoomed-in view of the yellow rectangle from (e). (g) Image with yellow arrows showing the movement of the tracker centers when external forces are applied to the whiskers. (h) Zoomed-in view of the yellow rectangle from (g)
  • Figure 4: Deflection angles of a whisker at various electromagnet voltages. A zero angle represents the neutral state, positive values indicate retraction, and negative values indicate extension.
  • Figure 5: (a) Experiment setup of the object classification experiment. (b) The sensor contacts the object from four directions at varying distances. (c) The five tested objects: yuanbao, eraser, light bulb. plastic cherry, and plastic strawberry.
  • ...and 4 more figures