Otonom Araçlarda Nesne Tespiti, Şerit Tespiti, Haritalama ve Konumlandırmaya Yönelik Sensör Füzyon Tekniklerinin Uygulanması

Öz

Trafik kazaları çoğunlukla sürücü hatalarından kaynaklanmaktadır. Bu nedenle, otonom araçların bu kazaları önleme potansiyeli sürücünün araç ile olan bağını kestiğinden dolayı çok yüksektir. Otonom araçlar, çevreyi gözlemlemek için çeşitli sensörler kullanırlar ve bu sensörler, çevreyi doğru bir şekilde algılamak ve olası hataları azaltmak için sensör füzyon algoritmalarından yararlanırlar. Kameralar, radarlar, LiDAR'lar, IMU'lar, GPS ve ultrasonik sensörler, otonom araçlarda en yaygın kullanılan sensör türleridir. Bu bildiride, sensör verilerinin ve bunların füzyonuyla birlikte çeşitli filtreleme teknikleri ile iyileştirilmesi hakkında detaylı bilgi verecektir. Bildiride, otonom araçlarda bu teknolojilerin nesne tespiti, konum belirleme ve haritalama gibi işlevlerde nasıl kullanıldığı ve bunların potansiyel uygulamaları veriler eşliğinde görselleştirilmiştir. Ayrıca, 3 cm hata sapma miktarına sahip bir sensörden elde edilen verilerdeki hataların filtrelenmesi sonucunda verilerin gerçek değere %98,33 oranda yakınsadığı bununla birlikte sensör füzyonu tekniği ile de bu gerçek değere yakınsayan verinin %99’dan daha yüksek olduğu, dolayısıyla daha da doğru değerler verdiği gözlemlenmiştir.

Anahtar Kelimeler

• Otonom Araçlar
• Otonom Sürüş
• Sensörler
• Kamera
• Radar
• LiDAR
• IMU
• GPS
• Ultrasonik Sensör
• Sensör Füzyonu

Kaynakça

1. [1] Singh S. “Critical reasons for crashes investigated in the national motor vehicle crash causation survey”. Technical Report, 2015.
2. [2] Tefft BC. “Acute Sleep Deprivation and Risk of Motor Vehicle Crash Involvement”. Technical Report, Washington, D.C., Foundation for Traffic Safety, 2016.
3. [3] Crayton TJ, Meier BM. “Autonomous vehicles: Developing a public health research agenda to frame the future of transportation policy”. Journal of Transport & Health, 6, 245–252, 2017.
4. [4] Waymo L. "On the road to fully self-driving". Waymo Safety Report, 1-43, 2017.
5. [5] Yurtsever E et al. “A survey of autonomous driving: Common practices and emerging technologies”. IEEE Access, 8, 58443-58469, 2020.
6. [6] Fridman L, “Human-Centered Autonomous Vehicle Systems: Principles of Effective Shared Autonomy”. arXiv:1810.01835, 2018.
7. [7] Yamazato T, Takai I, Okada H, Fujii T, Yendo T, Arai S, Andoh M, Harada T, Yasutomi K, Kagawa K, Kawahito S. “Image-Sensor-Based Visible Light Communication for Automotive Applications”. IEEE Communications Magazine vol. 52 no. 7, 88-97, 2014.
8. [8] Neves R, Matos AC. “Raspberry PI based stereo vision for small size ASVs”. IEEE OCEANS, San Diego, 1-6, 2013.

9. [9] Maqueda AI, Loquercio A, Gallego G, Garcica N, Scaramuzza D, “Event-based vision meets deep learning on steering predicton for self-driving cars”. IEEE Computer Vision and Pattern Recognition (CVPR), 5419-5427, 2018.
10. [10] Steinbaeck J, Steger C, Holweg G, Druml N, “Next Generation Radar Sensors in Automotive Sensor Fusion Systems”. 2017 IEEE Sensor Data Fusion: Trends, Solutions, Applications (SDF), 2017.
11. [11] Borodacz K, Cezary S, Stanisław P, "Review and selection of commercially available IMU for a short time inertial navigation". Aircraft Engineering and Aerospace Technology 94.1, 45-59, 2022.
12. [12] Zhmud V A, Kondratiev N O, Kuznetson K A, Trubin V G, Dimitrov L V, "Application of ultrasonic sensor for measuring distances in robotics." Journal of Physics: Conference Series, 1015, 3, 2018.
13. [13] Day, C et al. “Pedestrian recognition and obstacle avoidance for autonomous vehicles using raspberry Pi”. Intelligent Systems Conference (IntelliSys), 2, 51- 69, 2020.
14. [14] Kalms L et al. “Robust lane recognition for autonomous driving”. IEEE Conference on Design and Architectures for Signal and Image Processing (DASIP), 1-6, 2017.
15. [15] Swaminathan, V et al. “Autonomous driving system with road sign recognition using convolutional neural networks”. IEEE International Conference on Computational Intelligence in Data Science (ICCIDS), 1- 4, 2019.
16. [16] Hwang K, Jung IH, Lee JM. “Implementation of autonomous driving on RC-CAR with Raspberry PI and AI server”. Webology, 19, 4444-4458, 2022.
17. [17] Burleigh N, King J, Bräunl T. “Deep learning for autonomous driving”. IEEE Digital Image Computing: Techniques and Applications (DICTA), 1-8, 2019.
18. [18] Dewangan DK, Sahu SP. “Deep learning-based speed bump detection model for intelligent vehicle system using raspberry pi”. IEEE Sensors Journal, 21(3), 3570-3578, 2020.
19. [19] Ozkan Z et al. “Object detection and recognition of unmanned aerial vehicles using Raspberry Pi platform”. Fifth IEEE International symposium on multidisciplinary studies and innovative technologies (ISMSIT), 467-472, 2021.
20. [20] Kim J, Han DS, Senouci B. “Radar and vision sensor fusion for object detection in autonomous vehicle surroundings”. Tenth IEEE International conference on ubiquitous and future networks (ICUFN), 76-78, 2018.
21. [21] Nobis F et al. “A deep learning-based radar and camera sensor fusion architecture for object detection”. IEEE Sensor Data Fusion: Trends, Solutions, Applications (SDF), 1-7, 2019.
22. [22] Lichtsteiner P, Posch C, Delbruck T. “A 128×128 120 db 15µs latency asynchronous temporal contrast vision sensor”. IEEE Journal SolidState Circuits, 43(2), 566–576, 2008.
23. [23] Thakur R “Scanning LIDAR in Advanced Driver Assistance Systems and Beyond: Building a road map for next-generation LIDAR technology”. IEEE Consumer Electronics Magazine, 5(3), 48-54, 2016.
24. [24] Baras N et al. “Autonomous obstacle avoidance vehicle using LIDAR and an embedded system”. Eigth IEEE International Conference on Modern Circuits and Systems Technologies (MOCAST), 1-4. 2019.
25. [25] Kutila M et al. “Automotive LIDAR sensor development scenarios for harsh weather conditions”. IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). 265-270, 2016.
26. [26] Jeong SH, Choi CG, Oh JN et al. “Low cost design of parallel parking assist system based on an ultrasonic sensor”. Int. J. Automot. Technol., 11, 409–416, 2010.
27. [27] Paidi V et al. “Smart parking sensors, technologies and applications for open parking lots: a review”. IET Intelligent Transport Systems, 12(8) 735-741, 2018.
28. [28] Rossi A et al. “Real-time lane detection and motion planning in raspberry pi and arduino for an autonomous vehicle prototype”. arXiv:2009.09391, 2020.
29. [29] Thadeshwar H et al. “Artificial intelligence based selfdriving car”. Fourth IEEE International Conference on Computer, Communication and Signal Processing (ICCCSP), 1-5, 2020.
30. [30] Sainath V et al. “Deep learning for autonomous driving system”. Second IEEE International Conference on Electronics and Sustainable Communication Systems (ICESC), 1744-1749, 2021.
31. [31] Jain AK. “Working model of self-driving car using convolutional neural network, Raspberry Pi and Arduino”. Second IEEE International Conference on Electronics, Communication and Aerospace Technology (ICECA), 1630-1635, 2018.
32. [32] Kayaduman A et al. “Development and application of sensor network for autonomous vehicles”. IEEE International Conference on Artificial Intelligence and Data Processing (IDAP), 1-5, 2018.
33. [33] Hata A, Wolf D. “Road marking detection using LIDAR reflective intensity data and its application to vehicle localization”. 17th IEEE International Conference on Intelligent Transportation Systems (ITSC), 584-589, 2014.
34. [34] Kuutti S et al. “A survey of the state-of-the-art localization techniques and their potentials for autonomous vehicle applications”. IEEE Internet of Things Journal, 5(2), 829-846, 2018.
35. [35] Kocic J, Jovicic N, Drndarevic V, “Sensors and Sensor Fusion in Autonomous Vehicles”. Telecommunications forum (TELFOR), 20-21, 2018.
36. [36] Yang Q, Sun J. “Location system of autonomous vehicle based on data fusion”. IEEE International Conference on Vehicular Electronics and Safety, 314- 318, 2006.
37. [37] Zhang F et al. “A sensor fusion approach for localization with cumulative error elimination”. IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), 1-6, 2012.
38. [38] Suhr JK et al. “Sensor fusion-based low-cost vehicle localization system for complex urban environments”. IEEE Transactions on Intelligent Transportation Systems, 18(5), 1078-1086, 2016.
39. [39] Oh SI, Kang HB. “Fast occupancy grid filtering using grid cell clusters from LIDAR and stereo vision sensor data”. IEEE Sensors Journal, 16(19), 7258-7266, 2016.
40. [40] Alqaderi H, Schulz R, “Enhancement of LIDAR Data Association and Fusion Using Imaging Radar GridMaps for Advanced Automotive Environment Perception”. IEEE Sensor Data Fusion: Trends, Solutions, Applications (SDF), 1-6, 2018.
41. [41] Li Q, Li R, Ji K, Dai W, "Kalman filter and its application." 8th IEEE International Conference on Intelligent Networks and Intelligent Systems (ICINIS), 2015.
42. [42] Aeberhard M, Kaempchen N, “High-Level Sensor Data Fusion Architecture for Vehicle Surround Environment Perception”. Proc. 8th Int. Workshop Intell, 2011
43. [43] Jeong DY, Velasco-Hernandez G, Barry J, Walsh J, “Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review”. State-of-the-Art Sensors Technologies, 2021.