Towards vision-based robotic skins: a data-driven, multi-camera tactile sensor

Abstract

This paper describes the design of a multi-camera optical tactile sensor that provides information about the contact force distribution applied to its soft surface. This information is contained in the motion of spherical particles spread within the surface, which deforms when subject to force. The small embedded cameras capture images of the different particle patterns that are then mapped to the three-dimensional contact force distribution through a machine learning architecture. The design proposed in this paper exhibits a larger contact surface and a thinner structure than most of the existing camera-based tactile sensors, without the use of additional reflecting components such as mirrors. A modular implementation of the learning architecture is discussed that facilitates the scalability to larger surfaces such as robotic skins.

arXiv commentAccompanying video: https://youtu.be/lbavqAlKl98

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• Ground truth force distribution for learning-based tactile sensing: a finite element approach
• Transfer learning for vision-based tactile sensing
• Touch Sensors with Overlapping Signals: Concept Investigation on Planar Sensors with Resistive or Optical Transduction

Cited by in corpus (4)

• Visual-tactile Fusion for Transparent Object Grasping in Complex Backgrounds
• When Vision Meets Touch: A Contemporary Review for Visuotactile Sensors from the Signal Processing Perspective
• Viko: An Adaptive Gecko Gripper with Vision-based Tactile Sensor
• Development of Soft Tactile Sensor for Force Measurement and Position Detection