Intelligent Assistive Exoskeleton with Vision Based Interface

This paper presents an intelligent assistive robotic system for people suffering from myopathy. In this context, we are developing a 4 DoF assistive exoskeletal orthosis for the upper limb. A special attention is made toward Human Machine Interaction (HMI). We propose the use of visual sensing as interface able to convert user head gesture and mouth expression into a suitable control command. In that way, a non-intrusive cameras control is particularly adapted to disabled people. Moreover, we propose to robustify the command with a visual context analysis component. In this paper, we will first describe the problematic and the designed mechanical system. Next, we will describe the two approaches developed for visual sensing interface: head control and mouth expression control. Finally, we introduce the context detection for scene understanding.