Localization in 3D environments using differential, evolution

It is necessary to determine the robot´s pose to localize a mobile robot in a known environment. If there is no information about the initial location, we are talking about global localization. In our previous work we solved this problem in a two-dimensional environment with an algorithm known as Evolutive Localization Filter (ELF). Based on evolutionary computation concepts, the proposed algorithm searches stochastically along the state space for the robot´s best pose estimate. In this paper we have improved our method designing an algorithm with new features, called ELF-3D, that uses three-dimensional sensorial information. The resulting global localization module has been tested in a simulated indoor environment. The most important improvement obtained is the accuracy of the method, allowing to apply it in manipulation tasks.