Seyyar Robotlarda Kullanılan Stokastik Konum Belirleme Algoritmalarının Karşılaştırmalı Analizi

Yıl 2015, Cilt: 3 Sayı: 1, 21 - 34, 01.05.2015

U. Bayaliev U. Brimkulov R. Sultanov

Öz

The problem of mobile robot localization is the problem of finding robots position in its environment. Localization ability plays important role for mobile and autonomous robots because robot must know its position to reach the goal. There are several types of localization problem. The fundamental one is | Position tracking | . In this case the initial position of the robot is known and the problem is at correcting its position after moving some steps is | Position tracking | . Global localization is harder because in this problem the robots initial position is not known and the movement and sensing of the robot may be erroneous. In this case robot must use the movement and sensor information to generate some belief about its position and solve the problem using stochastic methods. This study analyzes and compares stochastic algorithms for solving robot localization problem. To achive this, visual applications for Markov, Kalman and Monte-Carlo algorithms are implemented and their validity in solving the robot localization problem is shown.

Anahtar Kelimeler

Mobile Robot, Localization, Markov, Kalman, Monte-Carlo, Algorithm, Stochastic methods

Seyyar Robotlarda Kullanılan Stokastik Konum Belirleme Algoritmalarının Karşılaştırmalı Analizi

Öz

Seyyar robotların konum belirleme problemi robotun ortamdaki kendi konumunu bulmaya yönelik çalışmasıdır. Konum belirleme kabiliyeti seyyar ve otonom robotlar için önemli rol oynar çünkü robot amacına ulaşmak için konumunu bilmesi gerekir. Konum belirleme probleminin birkaç türü vardır. En temel problem 'Konum takip etme'dir. Bu durumda robotun başlangıç konumu bilinmektedir ve bir kaç hareket sonrasında robotun konumunu doğrulamaya 'Konum takip etme' denir. Global konum belirleme ise daha zordur, çünkü bu problemde robotun başlangıçtaki konumu bilinmemektedir ve ayrıca robotun hareket ve sensörlerinde hata olabilir. Bu durumda robot sensör ve hareket bilgilerini kullanarak konumu hakkında farklı tahmin ve ınanç oluşturduktan sonra problemi stokastik yöntemler ile çözmesi gerekir. Bu çalışmada robotun konum belirleme problemini çözen stokastik algoritmalar incelenip birbiri ile karşılaştırılmaktadır. Bunu yapmak için Markov, Kalman ve Monte-Carlo algoritmalar için görsel uygulama yapılarak problemi çözmedeki geçerliliği gösterilmektedir

Anahtar Kelimeler

Seyyar Robot, Konum belirleme, Markov, Kalman, Monte-Carlo, Stokastik yöntemler

Kaynakça

• [1] J. Borenstein, B. Everett, and L. Feng. D. Wehe. "Mobile Robot Positioning Sensors and Techniques", Journal of Robotic Systems 14(4), 231–249 (1997)
• [2] Thrun S., “Probabilistic Algorithms in Robotics”, CMU-CS-00-126, (2000)
• [3] Thrun S., Burgard W., Fox D., “Active Mobile Robot Localization”, Robotics, 1346-1352, (1996)
• [4] Burgard W. et al., “Integrating Global Position Estimation and Position Tracking for Mobile Robots: The Dynamic Markov Localization Approach”, International Conference on Intelligent Robots and Systems, (1998)
• [5] Fox D., Burgard W., Thrun S., “Markov Localization for Mobile robots in Dynamic Environments”, JAIR, 391-421, (1999)
• [6] Thrun S., Burgard W., Fox D., “A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots”, Machine Learning and Autonomous Robots (joint issue), 31/5, 1–25 (1998)
• [7] Thrun S. et al. ”Probabilistic Algorithms and the Interactive Museum Tour-Guide Robot Minerva”, The International Journal of Robotics Research Vol. 19, No. 11, pp. 972-999, (2000)
• [8] Thrun S., “Particle Filters in Robotics”, Uncertainty in AI, (2002)
• [9] Thrun S., Fox D., Burgard W., Dellaert F., “Robust Monte Carlo Localization for Mobile Robots”, IAAI, (2001)
• [10] Fox D., Burgard W., Dellaert F., Thrun S., “Monte Carlo Localization: Efficient Position Estimation for Mobile Robots”, AAAI Proceeding. (1999)
• [11] Dellaert F., Fox D., Burgard W., Thrun S., “Monte Carlo Localization for Mobile Robots”, ICRA, (1999)
• [12] Kose H., Celik B., H. Levent Akın. “Comparison of Localization Methods for a Robot Soccer Team”, International Journal of Advanced Robotic Systems, Vol. 3, No. 4. (2006)
• [13] Temizer S., Çağrı M., “Mesafe ölçümü tabanlı güvenilir konum tespiti
• teknikleri ve kara ve hava araçlari için örnek uygulamalar”, Havacilik ve uzay teknolojileri dergisi
• cilt 6 sayi 2 pp.33-48, (2013)
• [14] Qasem H., Ament C., Reindl L., “A new Particle Filter for Localization of a Mobile Base Station Based on Microwave Backscatter”, Proceedings of the 3rd workshop on positioning, navigation and communication, (2006)
• [15] Gustafsson G. et al., “Particle Filters for Positioning, Navigation and Tracking.” IEEE Transactions on Signal Processing, (2002)
• [16] Roy N., Thrun S., “Coastal Navigation with Mobile Robots.” Robotics, 1043-1049, (1999)
• [17] Thrun S., “Bayesian Landmark Learning for Mobile Robot Localization”, Machine Learning, (1997)
• [18] Fox D., Burgard W., Thrun S., “Active Markov Localization for Mobile Robots”, Robotics and Autonomous systems, Volume 25, Issues 3–4, Pages 195–207, (1998)
• [19] Schulz D., Burgard W., “Probabilistic state estimation of dynamic objects with a moving mobile robot”, Robotics and Autonomous Systems 34, 107–115, (2001)
• [20] Kwok C., Fox D., Meila M., “Adaptive Real-time Particle Filters for Robot Localization”, ICRA. (2003)
• [21] Nourbakhsh R.,, Siegwart R., “Introduction to Autonomous Mobile Robots”, MIT Press, (2004)
• [22] Russell S., Norvig P., “Artificial Intelligence, A Modern Approach. Third Edition”, Prentice Hall, (2010)
• [23] Fox D., Thrun S., Burgard W.. “Probabilistic Robotics”, MIT Press, (2005)
• [24] H. Erickson L., Knuth J., Jason M. O’Kane, Steven M. LaValle. “Probabilistic localization with a blind robot”, (2008)
• [25] Friedrich H., Dederscheck D., Krajsek K., Mester R., “View-based Robot Localization Using Spherical Harmonics: Concept and First Experimental Results”, LNCS 4713, pp. 21-31, (2007)
• [26] Moreno L. et al. “A Genetic Algorithm for Mobile Robot Localization Using Ultrasonic Sensors”, JIRS, (2002)
• [27] Gutmann J.S., Fox D., “An Experimental Comparison of Localization Methods Continued”, (2003)
• [28] Andreasson H., Treptow A., Duckett T., “Localization for Mobile Robots using Panoramic Vision, Local Features and Particle Filter”, ICRA, (2005)
• [29] Agrawal M., Konolige K.. “Real-time Localization in Outdoor Environments using Stereo Vision and Inexpensive GPS”, ICPR, (2006)
• [30] Jensfeld P. et al. “Feature based condensation for mobile robots”, ICRA, 2000
• [31] Se S., Lowe D., Little J.. “Vision-based Mobile Robot Localization And Mapping using Scale-Invariant Features”, ICRA, (2001)
• [32] Kosecka J., Li F., “Vision Based Topological Markov Localization”, ICRA, (2004)
• [33] Ankışhan H., Efe M., “Eşzamanlı konum belirleme ve harita oluşturmaya Kalman filtre yaklaşımları”, Mühendislik dergisi, Cilt: 1, Sayı: 1, 13-20, (2010)
• [34] Burgard W., Fox D., Hennig D., Schmidt T., “Estimating the Absolute Position of a Mobile Robot Using Position Probability Grids”, Proc. of the Fourteenth National Conference on Artificial Intelligence, (1996)
• [35] Kwok C., Fox D., Meila M.. “Real-time Particle Filters”, Proceedings of IEEE, (2002)
• [36] Miura J., Yamamoto K., “Robust View Matching-Based Markov Localization in Outdoor Environments”, IROS, (2008)
• [37] Jason M. O’Kane, Steven M. LaValle. “Localization with Limited Sensing”, IEEE Transactions in Robotics, (2006)
• [38] Jason M. O’Kane. “Global Localization Using Odometry”, (2006)
• [39] Gutmann J.S., “Markov-Kalman Localization for Mobile Robots”, Digital Creatures Laboratory, Sony Corporation, (2002)
• [40] Moreno L., Garrido S., Blanco D., “Mobile Robot Global Localization using an Evolutionary MAP Filter.” J Glob Optim 37:381–403, (2007)
• [41] James J.et al., “Framework for Natural Landmark-based Robot Localization”, Ninth Conference on Computer and Robot Vision, (2012)
• [42] Fox D., Thrun S., Burgard W., "Particle filters for mobile robot localization", Sequential Monte Carlo Methods in Practice Statistics for Engineering and Information Science, pp 401-428, (2001)