Semi-Supervised Gait Generation With Two Microfluidic Soft Sensors

Nowadays, the use of deep learning for the calibration of soft wearable sensors has addressed the typical drawbacks of the microfluidic soft sensors, such as hysteresis and nonlinearity. However, previous studies have not yet resolved some of the design constraints such as the sensors are needed to be attached to the joints and many sensors are needed to track the human motion. Moreover, the previous methods also demand an excessive amount of data for sensor calibration which make the system impractical. In this letter, we present a gait motion generating method using only two microfluidic sensors. We select appropriate sensor positions with consideration of the deformation patterns of the lower-limb skins and mutual interference with soft actuators. Moreover, a semi-supervised deep learning model is proposed to reduce the size of calibration data. We evaluated the performance of the proposed model with various walking speeds. From the experiment, the proposed method showed a higher performance with smaller calibration dataset comparing to the other methods that are based on the supervised deep learning.