Automatic position estimation of a mobile robot

Traditionally, the position of a moving robot is monitored in an environment by using a 3D model of the scene and a 2D view of the scene from the current position of the robot. The authors propose automating the model generation step by using a robust model acquisition algorithm which also provides an estimate of the error in the acquired model. They show that the acquired 3D model along with the error estimate is reliable enough for a position estimation algorithm. The main contribution is a coupling of an automatic 3D model acquisition algorithm with a position estimation algorithm, resulting in an automatic position estimation algorithm. The second important contribution is an analysis of current 3D model acquisition algorithms in order to select the best algorithms to be coupled to the position estimation algorithm. The automatic position estimation algorithm developed consists of a bootstrapping stage for model acquisition followed by a stage for the estimation of the robot position