The purpose of the paper is to present a novel cross-modal sensor whose tactile is computed by the visual information. The proposed sensor can measure the forces of robotic grasping.
The proposed cross-modal tactile sensor consists of a transparent elastomer with markers, a camera, an LED circuit board and supporting structures. The model and performance of the elastomer are analyzed. Then marker recognition method is proposed to determine the movements of the marker on the surface, and the force calculation algorithm is presented to compute the three-dimension force.
Experimental results demonstrate that the proposed tactile sensor can accurately measure robotic grasping forces.
The proposed cross-modal tactile sensor determines the robotic grasping forces by the images of markers. It can give more information of the force than traditional tactile sensors. Meanwhile, the proposed algorithms for forces calculation determine the superior results.
