A Real‐Time Imaging Sensing System to Visualize Elastomer Surface Profile Evolution for Dynamic Tactile Recognition

• DOI: 10.1002/adfm.202416731
• Publication Date: 2024-12-06T10:23:53Z
• Authors: Zhibin Zou; Zilan Li; Yuanzhi Zhou; Guoyuan Zhou; Weiliang Xu; Muxing Huang; Wenfeng Wu; Huiming Zhang; Zhaohe Dai; Xinming Li
• Keywords: Tactile sensor

Abstract Elastomer‐based interfaces provide rich functionalities for tactile sensing, particularly in making tiny differences contact dynamics potentially detectable. However, the minimal motion‐induced changes elastomer's surface and their disappearance during time‐lapse limit state recognition within current scheme of motion recognition. In this work, a new real‐time mode subtle deformations is proposed, which uses an optical sensing system to visualize distinguish variations profile evolution encoded as images. Illustrating with sphere, sliding‐induced asymmetric elastomer deformation visualized “drag” The convolutional neural network (CNN) algorithm used analyze contour features interaction between sphere elastic medium. Motion achieved 80% accuracy when displacement only 8.3% diameter produced. addition, also offers potential dynamic information through single image, 82.7% velocity This framework soft media paves way novel motion‐based input commands human‐computer applications.