Embodied Augmented Reality for Lower Limb Rehabilitation

Abstract

Immersive platforms have emerged as valuable tools in rehabilitation, with potential to enhance patient engagement and recovery outcomes. Addressing the limitations of traditional Virtual Reality (VR) setups that restrict physical movement, this paper presents the system architecture of a novel, head-worn, Augmented Reality (AR) system for lower limb rehabilitation. The rehabilitation experience is enhanced by embodying avatars that replicate patients' movements. The system integrates varied avatar perspectives, such as mirror and follow modes, based on an avatar centered interface. The proposed system architecture supports seated and standing exercises, expanding the scope of rehabilitation beyond just gait. Computer vision-based 3D pose estimation captures patients' movement, mapped onto the avatar in real-time, accurately estimating the co-ordinates of 3D body landmarks. Wearable sensors evaluate patients' movements by utilizing deep learning to discern movement patterns. Feedback to patients is provided based on visual cues indicating limb areas for exercise adjustment so that exercise execution is improved. Embodiment has the potential to improve exercise understanding and assists patients' rehabilitation recovery.