Synergetic gait prediction and compliant control of SEA-driven knee exoskeleton for gait rehabilitation.

ABSTRACT: In recent years, lower limb exoskeletons have achieved satisfactory clinical curative effects in rehabilitating stroke patients. Furthermore, generating individualized trajectories for each patient and avoiding secondary injury in rehabilitation training are important issues. This paper explores the utilization of series elastic actuator (SEA) to deliver compliant force and enhance impact resistance in human-robot interaction, and we present the design of novel knee exoskeleton driven by SEA. Subsequently, the novel gait trajectory prediction method and compliant control method are proposed. The attention-based CNN-LSTM model is established to generate personalized gait trajectories for affected limbs, in which the spatial-temporal attention mechanism is adopted to improve the prediction a

SUBMITTER: Liu H 

PROVIDER: S-EPMC10853324 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature