Optimal Strategies for Mobile Robots Based on the Cross-Entropy Algorithm

This paper deals with the problem of optimizing the navigation of an intelligent mobile with respect to the maximization of the performance of the localization algorithm used during execution. It is assumed that a known map composed of features describing natural landmarks in the environment is given. The vehicle is also equipped with a range and bearing sensor to interact with its environment. The measurements are associated with the map to estimate its position. The main goal is to design an optimal path which guarantees the control of a measure of the performance of the map-based localization filter. Thus, a functional of the approximate Posterior Cramer-Rao Bound is used. However, due to the functional properties, classical techniques such as Dynamic Programming is generally not usable. To face that, we investigate a learning approach based on the Cross-Entropy method to stress globally the optimization problem.