Abstract
Range imagery provided by time-of-flight (TOF) cameras has been shown to be useful to facilitate robot navigation in several applications. Visual navigation for autonomous pipeline inspection robots is a special case of such a task, where the cramped operating environment influences the range measurements in a detrimental way. Inherent in the imaging system are also several defects that will lead to a smearing of range measurements. This paper sketches an approach for using TOF cameras as a visual navigation aid in pipelines, and addresses the challenges concerning the inherent defects in the imaging system and the impact of the operating environment. New results on our previously proposed strategy for detecting and tracking possible landmarks and obstacles in pipelines are presented. We consider an explicit model for correcting lens distortions, and use this to explain why the cylindrical pipe is perceived as a cone. A simplified model, which implicitly handles the combined effects of the environment and the camera on the measured ranges by adjusting for the conical shape, is used to map the robot's environment into an along-axis-view relative to the pipe, which facilitates obstacle traversal. Experiments using a model pipeline and a prototype camera rig are presented.