Towards vision-based robotic skins: a data-driven, multi-camera tactile sensor
This addresses the need for scalable, high-resolution tactile sensing in robotics, though it appears incremental as it builds on existing camera-based sensor designs.
The paper tackled the problem of measuring contact force distribution in robotic skins by designing a multi-camera optical tactile sensor that maps particle patterns to force distributions using machine learning, achieving a larger contact surface and thinner structure without mirrors.
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.