Stairs recognition using stereo vision-based algorithm in NAO robot

Abstract

In this paper we do staircase detection with a stereo vision based algorithm through NAO robot, using one of this cameras. Robot programming was implemented in Python language using ROS software. The detection algorithm is divided in two parts: line detection and depth perception. In line detection process we use Hough transform and vanishing point criteria for line segmentation. Respecting depth perception, we use a stereo vision approach, comparing two images obtained from the same camera in different positions. The robot movements were modeled and interpreted as a movement routine using the Choregraphe software. As a result, NAO can identify and climb a staircase in a controlled ambience.