Developing a computational solution of mobile robot self-localisation problem

This paper presents a computational solution for the mobile robot self-localization problem using a new adaptive data fusion structure. Input sensors are employed for feeding the fusion structure, and consequently more precise perception from a highly noisy environment can be obtained. This adaptation process relies on two main steps; firstly, to choose the sensors and secondly, employing a model adaptation process. Using this process, the more incorrect data are eliminated, the more accurate localization results are obtained. Also, implementing more accurate sensor models, the values of error obtained in the final iterations will be less. By implanting the proposed process, simulation results indicate that the proposed structure is very useful and effective, especially when compared to the conventional techniques of localization problems solutions which rely mainly on the information theory.