TactScribe: A Wearable Fingertip Sensor for Vibrotactile Data Collection via Natural Stroking

Vibrotactile information obtained through fingertip contact is expected to enable various applications. However, existing recording systems rely on specialized instruments and wired connections, making it difficult to collect tactile data through natural human behavior. In this study, we propose a wearable tactile recording system that combines a small, flexible sensor worn on the fingertip with a wireless transmission system for sensor data. Using the proposed system, we collected vibrotactile data from five types of materials and conducted material classification experiments with machine learning. The results achieved 83.2% overall accuracy, demonstrating that the recorded data contains sufficient tactile information for material classification and suggesting the system’s potential for diverse vibrotactile dataset construction.