Improving Soft Capacitive Tactile Sensors: Scalable Manufacturing, Reduced Crosstalk Design, and Machine Learning

Abstract

Soft and flexible capacitive tactile sensors are an important tool to; accurately measure tactile forces in wearable health monitors and enable soft grasping in robots. Precise force measurements in real-time pave the way for enhanced human-machine interaction, improved automation safety, and novel medical diagnostics approaches. In this work, a parallel plate soft capacitive sensor array was fabricated using low-cost and scalable additive manufacturing-based methods (screen printing and spin coating) with EMI shielding. Experimental setups were developed to evaluate the applied force on the soft, flexible sensor based on the ratio of mutual capacitance (RMC). The preciseness of the sensor array was tested with a normal force testing setup using Zwick Roell’s benchtop testing machine. Furthermore, a Robot was used to apply the normal force on each sensor ranging between 1–15 N, and its values were recorded using a force and torque sensor. IoT-based electronics were used to measure the RMC from five contact points simultaneously and a Python script saved data over time. The values of RMC were mapped to their corresponding force values using linear regression algorithms. This work demonstrates the suitability of the proposed sensor design for various application areas such as soft robotics and prosthetics for complex force measurements in human-machine interaction scenarios.