Recognition of walking intention using multiple bio/kinesthetic sensors for lower limb exoskeletons

Abstract

In order to assist the lower limb disabled people to walk, walking-support exoskeletons with bio/kinesthetic sensors such as EMG (Electromyography), gyroscope, and FSR (Force Sensing Resistor) have been developed. It is important to implicitly recognize the walking intention and control the walking-support mechanism. The objective of this work is to examine the walking intention while a person is walking with Lofstrand crutches by analyzing multiple bio/kinesthetic sensor signals. We developed watch/glove and shoe-insoles sensor modules using FSR sensors to recognize the user's walking states as well as intention to walk. The FSR signals measuring force at the palm and Gyro sensor signals reflecting the pose of the upper limb were used as clues for recognizing walking intention. While seventeen normal subjects walked for five gate cycles based on the triped walking (i.e., placing crutches in forward and then moving one step) with crutches, the FSR and Gyro signals were acquired from their palms and area of vertebrae lumbales. The result showed that the combination of FSR and Gyro signals could recognize user's implicit intention to walk - start walking, keep walking, and stop walking.