Studying localization with landmarks

Localization with landmarks is a recurrent problem in robotics. In order to perceive the environment, robots are often equipped with some exteroceptive sensors (such as camera, laser range finder, etc). One way of using these sensors for localization is to detect some features in the environment and to use them as landmarks. In this paper, we present how we tackle the complete set up of a fast, reliable and efficient localization system. We start by giving methods to optimize the landmark placement in our environment. Then, we show how a specific SLAM algorithm can be efficiently associated with a robust data association method to make simultaneous matching, localization and mapping (SMLAM) in this environment. We also give a method to integrate the need for localization in a path planning algorithm, and we finish by presenting experimental results which show the relevance and the efficiency of our method. Keywords— Robot localization, landmarks, SLAM, data association, landmark placement, sensor oriented path planning