Multiple Model Kalman Filters: A Localization\ud Technique for RoboCup Soccer

摘要

In the Standard Platform League (SPL) there are substantial sensor limitations due to the rapid motion of the camera, the limited field of view of the camera, and the limited number of unique landmarks.\udThese limitations place high demands on the performance and robustness of localization algorithms. Most of the localization algorithms implemented in RoboCup fall broadly into the class of particle based filters or\udKalman type filters including Extended and Unscented variants. Particle\udFilters are explicitly multi-modal and therefore deal readily with ambiguous sensor data. In this paper, we discuss multiple-model Kalman filters\udthat also are explicitly multi-modal. Motivated by the RoboCup SPL,\udwe show how they can be used despite the highly multi-modal nature\udof sensed data and give a brief comparison with a particle filter based\udapproach to localization.