Gel Biter: food texture discriminator based on physical reservoir computing with multiple soft materials

Abstract The human oral structure contains organs with distinctly different physical properties, such as teeth, gums, and tongues. When food enters the cavity, we can recognize tactile sensation shape of object from multiple perspectives through texture teeth tongue. Therefore, it is possible to regard structures a group sensors based on these functions. In this study, developed soft-matter artificial mouth that accurately detect subtle differences in by creating combining structural using polymer materials properties mounting them end-effectors for robot arm. same piezoelectric film sensor was embedded inside each organ, making acquire sensations completely signal waveforms. We tested whether data obtained material could be used excellent recognition applying various machine learning methods. an actual experiment, learned waveform chewing sweets snacks, rice crackers, applied classify data, which led accuracy rate over 90%.