Probabilistic relational reasoning in semantic robot navigation

摘要

Abstract. We examine the use of semantic web resources in robot nav-igation; more specifically, in qualitative navigation where uncertain rea-soning plays a significant role. We propose a framework for robot naviga-tion that connects existing semantic web resources based on probabilis-tic description logics, with probabilistic relational learning and planning. We show the benefits of this framework in a real robot, presenting a case study on how semantic web resources can be used to face sensor and mapping uncertainty in a practical problem.