Soft sensor suits as man-machine interface for wearable power amplifier

The authors have developed innovative soft sensor suits embedded with electromyogram (EMG) and a variety of sensors for measuring human muscle activities. The sensor suits serve as a man-machine interface for human power amplification. This paper focuses on the EMG part of the sensor suits to study the fundamental issue of torque estimation based on the sensor readings. An innovative auto-calibration system is developed in this study based on multi-regression analysis and neural networks, where an universal database, rather than individual database for each operator, is proposed and as a result, the calibration time is dramatically decreased. The calibration system can also compensate for sensor positioning errors. In the end, the sensor suits are applied as a man-machine interface for a soft power amplifier composed of artificial muscles. The artificial muscles are successfully controlled using the torque information estimated by the EMG sensor suits. The relation between torque estimation errors on sensor suits and maneuverability of power amplifier is experimentally verified.