Monte Carlo Localization driven by BVP

In this paper, we combine the path planner based on boundary value problems (BVP) and Monte Carlo Localization (MCL) to solve the global localization problem in sparse environments. This problem is difficult since several regions of this kind of environment do not provide relevant information for the robot to recover its pose. We propose an intelligent mechanism to put particles only in relevant parts of environment and lead the robot along these regions using the numeric solution of a BVP. Simulation results are presented to illustrate the potential of the method.