Automatic calibration and visual servoing for a robot navigation system

The problem of automatic location of a mobile robot in an indoor environment is attacked. Automatic location may be used for calibration to locate the robot accurately before it starts to navigate, or it can be used in visual servoing as feedback to the controller that is maintaining the robot´s course. The problem is examined in a special case in which the ground plane is assumed to be horizontal and there are two locally parallel sidelines available. This assumption holds in many indoor environments, such as hallways, where the system´s success has been demonstrated. The algorithm uses geometric features such as vanishing points and line orientations. Both theoretical analysis and experimental results show that the algorithm works very robustly and accurately