Repositioning care - supporting patients' transition from a supine to a sitting position- critically improving the health and quality of life of individuals with limited mobility.

We propose a deep neural network (DNN)-based architecture utilizing proprioceptive and visual attention mechanisms, along with impedance control to regulate the robot’s movements.

This study presents a humanoid robot system that assists in patient repositioning from supine to lateral by combining close-range 3D posture recognition using fisheye and RGBD cameras with adaptive trajectory generation based on body dynamics, achieving successful lifts across various body types.

This study presents a humanoid robot system that assists in sock-dressing. Deep predictive learning architecture dictates force control to manage friction and snagging against the skin, while accurately considering the shape and position of both the garment and the human body.