Real-time recognition of human lower-limb locomotion based on exponential coordinates of relative rotations

This paper proposes a data-driven method using a parametric representation of relative rotations to classify human lower-limb locomotion, which is designed for wearable robots. Three Inertial measurement units (IMUs) are mounted on the subject's waist, left knee, and right knee, respectively. Features for classification comprise relative rotations, angular velocities, and waist acceleration. Those relative rotations are represented by the exponential coordinates. The rotation matrices are normalized by Karcher mean and then the Support Vector Machine (SVM) method is used to train the data. Experiments are conducted with a time-window size of less than 40 ms. Three SVM classifiers telling 3, 5 and 6 rough lower-limb locomotion types respectively are trained, and the average accuracies are all over 98%. With the combination of those rough SVM classifiers, an easy SVM-based ensembled-system is proposed to classify 16 fine locomotion types, achieving the average accuracy of 98.22%, and its latency is 18 ms when deployed to an onboard computer.