Bulanık Mantık Tabanlı Bir Hibrit Yol Takip Yöntemi

Öz

Literatürde otonom kara araçları yol takibi problemini çözmek için farklı yöntemler önerilmiştir. Bu yöntemler geometrik tabanlı ve model tabanlı yöntemler olarak iki ana gruba ayrılabilir. Model tabanlı yöntemlerde aracın dinamik modeli kullanılırken, geometrik tabanlı yöntemlerde sadece araç ve yol arasındaki geometrik ilişkilerden yararlanılır. Yapılarının basit olması nedeniyle geometrik tabanlı yöntemler uygulamalarda sıklıkla kullanılmaktadır. Stanley ve Pure Pursuit yöntemleri en yaygın kullanılan geometrik tabanlı yöntemlerdir. Stanley yöntemi düz yolda daha iyi bir yol takip performansı gösterirken, dönüşlerde daha düşük bir performans sergilemektedir. Pure Pursuit yöntemi ise dönüşlerde daha iyi bir performans sergilerken, düz yolda daha düşük bir performans göstermektedir. Bu çalışmada Pure Pursuit ve Stanley yöntemlerinin üstün yanlarını bir arada kullanabilmek için bulanık mantık tabanlı bir hibrit kontrol yöntemi önerilmiştir. Bu yöntemde yolun geometrisine bağlı olarak Stanley ve Pure Pursuit yöntemleri ile elde edilen direksiyon açı değerleri ağırlıklandırılarak tek bir direksiyon açısı değeri hesaplanmaktadır. Ağırlıklandırma parametresi dinamik olup bir bulanık çıkarım mekanizması tarafından ileri bakma açısı değerlendirilerek ayarlanmaktadır. Önerilen yöntemin performansı farklı yol şartlarında test edilmiş ve elde edilen sonuçlar Stanley, Pure Pursuit yöntemleri ve mevcut bir hibrit yöntem ile karşılaştırılmıştır. Benzetim sonuçları önerilen yöntemin diğer klasik iki yönteme ve mevcut hibrit yönteme göre daha üstün bir yol takip performansı sergilediğini göstermiştir.

Anahtar Kelimeler

• Yol takibi
• otonom araçlar
• geometrik yol takibi
• hibrit kontrol
• bulanık mantık.

A Fuzzy Logic Based Hybrid Path Tracking Method

Abstract

Various methods have been proposed to solve the path tracking problem of autonomous ground vehicles in the literature. These methods can be divided into two main groups as geometric-based and model-based methods. While the dynamic model of the vehicle is used in model-based methods, only geometric relations between the vehicle and the path are used in geometric-based methods. Geometric-based methods are frequently used in applications due to their simple structures. Stanley and Pure Pursuit methods are the most widely used geometric-based methods. While the Stanley method shows a better tracking performance on a straight path, it shows a lower performance on turns. On the other hand, the Pure Pursuit method performs better performance on turns but shows a lower performance on the straight paths. In this study, a fuzzy logic-based hybrid control method is proposed to use the advantages of Pure Pursuit and Stanley methods together. In this method, the steering angle value is calculated by weighting the steering angle values obtained by Stanley and Pure Pursuit methods depending on the geometry of the path. The weighting parameter is dynamic and is adjusted by a fuzzy inference mechanism by evaluating the look-ahead angle. The performance of the proposed method is tested under different path conditions and the results obtained are compared with Stanley, Pure Pursuit methods, and an existing hybrid method. The simulation results show that the proposed method exhibits a superior path tracking performance compared to the other two conventional methods and the existing hybrid method.

Keywords

• Path tracking
• autonomous vehicles
• geometric path tracking
• hybrid control
• fuzzy logic.

References

1. Amer, Noor Hafizah, Hairi Zamzuri, Khisbullah Hudha, and Zulkiffli Abdul Kadir. 2017. “Modelling and Control Strategies in Path Tracking Control for Autonomous Ground Vehicles: A Review of State of the Art and Challenges.” Journal of Intelligent and Robotic Systems: Theory and Applications 86(2): 225–54.
2. Amidi, Omead, and Charles Thorpe. 1991. “Integrated Mobile Robot Control.” Fibers’ 91, Boston, MA 1388: 504–23. http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=954451.
3. Cibooglu, Mertcan, Umut Karapinar, and Mehmet Turan Soylemez. 2017. “Hybrid Controller Approach for an Autonomous Ground Vehicle Path Tracking Problem.” 2017 25th Mediterranean Conference on Control and Automation, MED 2017 8: 583–88.
4. Guo, Hongyan et al. 2019. “Model Predictive Path Following Control for Autonomous Cars Considering a Measurable Disturbance: Implementation, Testing, and Verification.” Mechanical Systems and Signal Processing 118: 41–60. https://doi.org/10.1016/j.ymssp.2018.08.028.
5. Hoffmann, Gabriel M., Claire J. Tomlin, Michael Montemerlo, and Sebastian Thrun. 2007. “Autonomous Automobile Trajectory Tracking for Off-Road Driving: Controller Design, Experimental Validation and Racing.” Proceedings of the American Control Conference: 2296–2301.
6. Jalali, Kiumars, Steve Lambert, and John McPhee. 2012. “Development of a Path-Following and a Speed Control Driver Model for an Electric Vehicle.” SAE International Journal of Passenger Cars - Electronic and Electrical Systems 5(1): 100–113.
7. Park, Myung Wook, Sang Woo Lee, and Woo Yong Han. 2014. “Development of Lateral Control System for Autonomous Vehicle Based on Adaptive Pure Pursuit Algorithm.” International Conference on Control, Automation and Systems (Iccas): 1443–47.
8. Park, Myungwook, Sangwoo Lee, and Wooyong Han. 2015. “Development of Steering Control System for Autonomous Vehicle Using Geometry-Based Path Tracking Algorithm.” ETRI Journal 37(3): 617–25.

9. Ping, Em Poh, and Sim Kok Swee. 2012. “Simulation and Experiment of Automatic Steering Control for Lane Keeping Manoeuvre.” ICIAS 2012 - 2012 4th International Conference on Intelligent and Advanced Systems: A Conference of World Engineering, Science and Technology Congress (ESTCON) - Conference Proceedings 1: 105–10.
10. R. Craig Coulter. 1992. “Implementation of the Pure Pursuit Path Trahcing Algorithm.” Camegie Mellon University.
11. Raffo, Guilherme V. et al. 2009. “A Predictive Controller for Autonomous Vehicle Path Tracking.” IEEE Transactions on Intelligent Transportation Systems 10(1): 92–102.
12. Snider, Jarrod M. 2009. “Automatic Steering Methods for Autonomous Automobile Path Tracking.” Work (February): 1–78. http://www.ri.cmu.edu/pub_files/2009/2/Automatic_Steering_Methods_for_Autonomous_Automobile_Path_Tracking.pdf.
13. Yu, Lingli et al. 2020. “Driverless Bus Path Tracking Based on Fuzzy Pure Pursuit Control with a Front Axle Reference.” Applied Sciences (Switzerland) 10(1).