Ceiling-Based Visual Positioning for an Indoor Mobile Robot With Monocular Vision

Abstract

A regular ceiling is common in many offices. The plentiful parallels and corner points on the ceiling can serve as features for visual positioning for an indoor mobile robot. Based on the natural features on the ceiling, a new visual positioning method is proposed. A camera is mounted on the top of the mobile robot and pointed to the ceiling. At the beginning of visual positioning, the initial orientation and position of the mobile robot in the world frame is estimated with a specified block on the ceiling via perspective-n-point-based positioning method. With the motions of the mobile robot, its global orientation is calculated from the main and secondary lines feature when the ceiling has parallels. In other cases, its global orientation is estimated with point features on the ceiling. Then, its position is recursively computed with the point features. The error analysis and experiments verify the effectiveness of the proposed method.