Position estimation algorithm based on natural landmark and fish-eyes' lens for indoor mobile robot

摘要

Many generic position estimation algorithms are vulnerable to ambiguity introduced by no unique landmarks. Also, the available high-dimensional image data is not fully used when these techniques are extended to vision-based localization. In this paper, we consider the problem of mobile robot indoor position estimation using only visual information from a single camera which has a fisheye lens. The position estimation algorithm based on natural landmark identification and barrel distortion calibration. When mobile robot is indoor environment, usual behavior consists of memorizing some key points along the performed path to use these compared with references map.