Vision-based assistive navigation for robotic wheelchair platforms

摘要

In this paper we present an approach towards providing advanced navigational capabilities to robotic wheelchair platforms. Contemporary methods that are employed in robotic wheelchairs are based on the information provided by range sensors and its appropriate exploitation by means of obstacle avoidance techniques. However, since range sensors cannot support a detailed environment representation, these methods fail to provide advanced navigational assistance, unless the environment is appropriately regulated (e.g. with the introduction of beacons). In order to avoid any modifications to the environment, we propose an alternative approach that employs computer vision techniques which facilitate space perception and navigation. Computer vision has not been introduced todate in rehabilitation robotics, since the former is not mature and reliable enough to meet the needs of this sensitive application. However, in the proposed approach, stable techniques are exploited that facilitate reliable, automatic navigation to any point in the visible environment. This greatly enhances the mobility of the elderly and disabled, without requiring them to exercise fine motor control. Preliminary results obtained from the implementation of this approach on a laboratory robotic platform indicate its usefulness and flexibility.