Estimation of Hand Motion from Piezoelectric Soft Sensor Using Deep Recurrent Network

Abstract

Soft sensors are attracting significant attention in human–machine interaction due to their high flexibility and adaptability. However, estimating motion state from these sensors is difficult due to their nonlinearity and noise. In this paper, we propose a deep learning network for a smart glove system to predict the moving state of a piezoelectric soft sensor. We implemented the network using Long-Short Term Memory (LSTM) units and demonstrated its performance in a real-time system based on two experiments. The sensor’s moving state was estimated and the joint angles were calculated. Since we use moving state in the sensor offset calculation and the offset value is used to estimate the angle value, the accurate moving state estimation results in good performance for angle value estimation. The proposed network performed better than the conventional heuristic method in estimating the moving state. It was also confirmed that the calculated values successfully mimic the joint angles measured using a leap motion controller.

Piezoelectric Sensor with a Helical Structure on the Thread Core

“…Piezoelectric materials have been widely adapted to measure biometric signals from humans' daily activity of living. For example, biometric signals such as walking motion [44] and hand motion [45] are measured through piezoelectric materials. Unlike the previous studies, the proposed sensor is capable of measuring biometric signals such as joint angles of humans with better comfortability and repeatability without external pockets.…”

Thermal Feedback System From Robot Hand for Telepresence

“…The silicone glove is composed of the four TEDs, four resistance temperature detector (RTD) sensors, and three flexible piezoelectric sensors with a silicone (Ecoflex 00-30, Smooth-On, Inc.) substrate. The details of the fabrication method of the silicone glove and piezoelectric sensors have been provided in our previous paper [34]. The flexible TED (Flexible Thermoelectric Device, Tegway Co.Ltd.)…”

“…To this end, we propose a thermal feedback teleoperating system using a thermal display glove with flexible thermoelectric devices (TEDs). The TEDs can generate the specified heat by the Peltier effect, which is a thermoelectric conversion effect to heating or cooling by electrical interaction between two different conductors [34]- [36]. In our previous study [37], we had demonstrated a thermal feedback glove for VR.…”

Kirigami-inspired self-powered pressure sensor based on shape fixation treatment in IPMC material

“…A voltage can only be produced due to the IPMC deformation (bending or compression), giving it advanced passive output performance that is not possible in the conventional strain sensors, which can be mainly categorized as resistive, capacitive, and inductive. Self-powered mechanisms such as electromagnetic induction, triboelectric, and piezoelectric nanogenerators that convert mechanical energy into electrical energy have been explored as sensors [37][38][39][40][41][42]. However, unlike IPMC, these methods can only generate instant electrical output at the transient state (dynamic response).…”