Ramps and stairs detection and modelling system for a lower limb powered orthosis
Computer Vision, Powered Orthosis, Stair Detection, Ramp Detection.
In recent years, many studies have been carried out on the topic of powered orthosis related to locomotion assistance. The main goal of these devices is to assist the elderly and physically challenged persons in daily activities, replacing or increasing the movement of body articulations. Although a significant progress has been achieved, many challenges still remain. A desirable feature for powered orthosis is the planning of autonomous movements, so that the movements are automatically adapted as the user walks. Therefore, it is indispensable the use of a computer vision system in order to provide information about the environment where the user is located, classifying the structures of the scene as walkable or not. In this sense, we propose a new strategy for ramps and stairs detection which are in accordance with technical standards and can be climbed for orthosis users. Initially, we perform plane segmentation from point cloud data using a hypothesis and verification methodology. Through the plane normal analysis, it is possible to establish ramps and stairs candidates. Finally, connectivity tests are performed and the plane dimensions are verified in order to decide whether the ramps and stairs are qualified to be used. Preliminary results were obtained applying the method in a simulation environment, where it was possible to detect and model ramps and stairs satisfactorily.