Intention Detection of Gait Adaptation in Natural Settings
This work addresses the need for efficient and safe intention detection in neurorehabilitation and assistive robotics, though it appears incremental by combining existing technologies in a new application.
The paper tackles the problem of detecting gait adaptation intentions in natural settings without specialized equipment, achieving successful detection of adaptation steps and efficient classification of speed adjustments using a single RGB camera and wireless EEG signals.
Gait adaptation is an important part of gait analysis and its neuronal origin and dynamics has been studied extensively. In neurorehabilitation, it is important as it perturbs neuronal dynamics and allows patients to restore some of their motor function. Exoskeletons and robotics of the lower limbs are increasingly used to facilitate rehabilitation as well as supporting daily function. Their efficiency and safety depends on how well can sense the human intention to move and adapt the gait accordingly. This paper presents a gait adaptation scheme in natural settings. It allows monitoring of subjects in more realistic environment without the requirement of specialized equipment such as treadmill and foot pressure sensors. We extract gait characteristics based on a single RBG camera whereas wireless EEG signals are monitored simultaneously. We demonstrate that the method can not only successfully detect adaptation steps but also detect efficiently whether the subject adjust their pace to higher or lower speed.