Abstract A method is proposed which combines odometry and visual information for robot self-localization in soccer field. The method makes effective use of these two kinds of information by considering their characteristics simultaneously. On the one hand,odometry is used to effectively deal with the ambiguity which is prone to appear in landmark based visual localization. And on the other hand,the disambiguated visual localization results are useful to dynamically correct the accumulative odometry errors which are caused by robot motion. Finally,experiments are conducted on the Webots simulation platform and the results show the effectiveness of the proposed method.
[1] Thurn S,Burgard W,Fox D. Probabilistic Robotics. Cambridge,USA: MIT Press,2005 [2] Laue T,Haas T J,Burchardt A,et al. Efficient and Reliable Sensor Models for Humanoid Soccer Robot Self-Localization // Proc of the 4th Workshop on Humanoid Soccer Robots in Conjunction with the IEEE-RAS International Conference on Humanoid Robots. Paris,France,2009: 22-29 [3] Simmons R,Koenig S. Probabilistic Robot Navigation in Partially Observable Environments // Proc of the 14th International Joint Conference on Artificial Intelligence. Montreal,Canada,1995: 1080-1087 [4] Iocchi L,Mastrantuono D,Nardi D. A Probabilistic Approach to Hough Localization // Proc of the IEEE International Conference on Robotics and Automation. Seoul,Korea,2001,IV: 4250-4255 [5] Quinlan M J,Middleton R H. Multiple Model Kalman Filters: A Localization Technique for RoboCup Soccer // Baltes J,Lagoudakis M G,Naruse T,et al,eds. RoboCup2009: Robot Soccer World Cup XIII. Berlin: Spinger-Verlag,2010: 276-287 [6] Leonard J,Durrant-Whyte H. Directed Sonar Sensing for Mobile Robot Navigation. Norwell,USA: Kluwer Academic Publishers,1992 [7] Fox D,Burgard W,Dellaert F,et al. Monte Carlo Localization: Efficient Position Estimation for Mobile Robots // Proc of the 16th National Conference on Artificial Intelligence. Orlando,USA,1999: 343-349 [8] Rfer T,Laue T,Thomas D. Particle-Filter-Based Self-Localization Using Landmarks and Directed Lines // Bredenfeld A,Jacoff A,Noda I,et al,eds. RoboCup 2005: Robot Soccer World Cup IX. Berlin: Springer-Verlag,2006: 608-615 [9] Heinemann P,Haase J,Zell A. A Combined Monte-Carlo Localization and Tracking Algorithm for RoboCup // Proc of the IEEE/RSJ International Conference of Intelligent Robots and Systems. Beijing,China,2006: 1535-1540 [10] Marques C F,Lima P U. A Localization Method for a Soccer Robot Using a Vision-Based Omni-Directional Sensor // Stone P,Balch T,Kraetzschmar G,eds. RoboCup 2000: Robot Soccer World Cup IV. Berlin: Springer-Verlag,2001: 96-107 [11] Pérez D H,Barberá H M. Robust and Efficient Field Features Detection for Localization // Lakemeyer G,Sklar E,Sorrenti D G,et al,eds. RoboCup 2006: Robot Soccer World Cup X. Berlin: Springer-Verlag,2007: 347-354 [12] Utz H,Neubeck A,Mayer G,et al. Improving Vision-Based Self-Localization // Kaminka G A,Lima P U,Rojas R,eds. RoboCup 2002: Robot Soccer World Cup VI. Berlin: Springer-Verlag,2003: 25-40 [13] Sturm J,Rossum P,Visser A. Panoramic Localization in the 4-Legged League // Lakemeyer G,Sklar E,Sorrenti D G,et al,eds. Robocup 2006: Robot Soccer World Cup X. Berlin: Springer-Verlag,2007: 387-394 [14] Jensfelt P,Kristensen S. Active Global Localization for a Mobile Robot Using Multiple Hypothesis Tracking. IEEE Trans on Robotics and Automation,2001,17(5): 748-760 [15] zkucur N E,Akin H L. Localization with Non-unique Landmark Observations // Ruiz-del-Solar J,Chown E,Plger P G,eds. RoboCup 2010: Robot Soccer World Cup XIV. Berlin: Springer-Verlag,2011: 72-81 [16] Buschka P,Saffiotti A,Wasik Z. Fuzzy Landmark-based Localization for a Legged Robot // Proc of the IEEE/RSJ International Conference of Intelligent Robots and Systems. Takamatsu,Japan,2000,II: 1205-1210 [17] Jüngel M. Self-Localization Based on a Short-Term Memory of Bearings and Odometry // Proc of the IEEE/RSJ International Conference of Intelligent Robots and Systems. San Diego,USA,2007: 2494-2499 [18] Forsyth D,Ponce J. Computer Vision: A Modern Approach. New Jersey,USA: Prentice Hall,2003 [19] Fischler M,Bolles R. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Communications of the ACM,1981,24(6): 381-395
2013, Vol. 26 
