Sensor Planning for Mobile Robot Localization -A hierarchical approach using Bayesian network and particle filter-

In this paper we propose a hierarchical approach to solve sensor planning for global localization of a mobile robot. The higher layer uses a Bayesian network which represents the contextual relation between the geometrical features of local environment, the robot sensing actions and the global localization beliefs. In the higher layer, the system allows sensor planning by taking into account the trade-off between global localization belief and the sensing cost to generate an optimal sensing action sequence. Through the optimal sequence of sensing action, the lower layer uses particle filter to efficiently and precisely localize the mobile robot. The simulation experiments show effectiveness of the proposed approach