Araştırma Makalesi
Yıl 2019,
Cilt: 31 Sayı: 1, 177 - 185, 15.03.2019
Öz
Otonom
araçlar, çevre koşullarını algılayarak kararlar alan ve aldıkları kararlar
doğrultusunda hareket eden araçlardır. Günümüzde otonom araçlara olan ilgi
hızla artmaktadır. Gelişen sensör, Grafik İşleme Birimi teknolojisi ve yapay
öğrenme yöntemlerindeki yenilikler ile birlikte otonom araç teknolojisi de
gelişmektedir. Bu çalışmada, küçük bir yer aracı ile yapay öğrenme yöntemlerini
kullanan otonom bir araç tasarlanmıştır. Bu amaçla, yer aracı üzerine çeşitli
sensörler, kamera ve NVIDIA TX2 kartı yerleştirilmiştir. Otonom yer aracının
insan sürüşünden öğrenmesi için, Evrişimsel Sinir Ağları ve Uzun Kısa-Vade
Hafıza Ağları birlikte kullanan bir model önerilmiştir. Geliştirilen modelleri
kullanan otonom araç, tasarlanan parkur üzerinde test edilmiştir. Tüm
uygulamalar başarılı bir şekilde gerçekleştirilmiştir. Elde edilen sonuçlar
grafikler ve şekiller ile verilmiştir.
Anahtar Kelimeler
Otonom araçlar Grafik İşleme Birimi Evrişimsel Sinir Ağları Uzun Kısa-Vade Hafıza Ağları derin öğrenme
Kaynakça
- [1] Gomez V. Object detection for autonomous driving using deep learning. PhD Thesis, Universitat At Politecnica De Catalunya, Automatica Robotica I Visio, Barcelona, 2015. [2] Nikbay K. Otonom araçların güzergah takibi için bir uygulama. Yüksek Lisans Tezi, Okan Üniversitesi Fen Bilimleri Enstitüsü, İstanbul, 2015. [3] Wason R. Deep learning: Evolution and expansion. Cognitive System Research 2018; 52: 701-708. [4] Mobileye pedestrian collision warning system, https://www.mobileye.com/our-technology/ (Erişim: 28 Ağustos 2018) [5] Coelingh E, Eidehall A and Bengtsson M. Collision warning with full auto brake and pedestrian detection - a practical example of automatic emergency braking. In Proceedings of the 13th International IEEE Conference on Intelligent Transportation Systems (ITSC); 19-22 September 2010; Funchal, Portugal, pp. 155-160. [6] Autonomous driving, https://www.bmw.com/en/index.html/ (Erişim: 17 Ağustos 2018) [7] VW Emergency Assistance System, https://safecarnews.com/ (Erişim: 11 Temmuz 2018) [8] Active safety technology, https://www.toyota-global.com/innovation/safety_technology/toyota-safety-sense/ (Erişim: 3 Eylül 2018) [9] Deng L and Yu D. Deep Learning: methods and applications, Foundations and Trends in Signal Processing 2014; 7: 3-4. [10] Christian S, Toshev A and Erhan D. Deep neural networks for object detection. In Proceeding of the Advances in Neural Information Processing Systems; 5-10 December 2013; Lake Tahoe, USA; pp. 2553-2561. [11] Krizhevsky A, Sutskever I and Hinton GE. Imagenet classification with deep convolutional neural networks. In Proceedings of the Advances in Neural Information Processing Systems; 3-6 December 2012; Lake Tahoe, USA; pp. 1097-1105. [12] Deng J, Berg A, Satheesh S, Su H, Khosla A and Fei-Fei L (2012). http://www.image-net.org/challenges/LSVRC/2012/ [13] Berg A, Deng J and Fei-Fei L. Large scale visual recognition, International Journal of Computer Vision 2010; 115(3): 211-252. [14] Bojarski M, Del Testa D, Dworakowski D, Firner B, Flepp B, Goyal P and Zhang X. End to end learning for self-driving cars 2016; arXiv preprint arXiv:1604.07316. [15] Santana E and Hotz G. Learning a driving simulator 2016; arXiv preprint arXiv:1608.01230. [16] Eraqi HM, Moustafa MN and Honer J. End-to-end deep learning for steering autonomous vehicles considering temporal dependencies 2017; arXiv preprint arXiv:1710.03804. [17] Karslı M, Satılmış Y, Şara M, Tufan F, Eken S and Sayar A. End-to-end learning model design for steering autonomous vehicle. In Proceedings of the 26th Signal Processing and Communications Applications Conference (SIU); 2-5 May 2018. [18] Du X, Ang MH, Karaman S and Rus D. A general pipeline for 3d detection of vehicles 2018; arXiv:1803.00387 [cs.CV]. [19] Ma F, Cavalheiro GV and Karaman S. Self-supervised sparse-to-dense: self-supervised depth completion from lidar and monocular camera 2018; arXiv:1807.00275 [cs.CV]. [20] Amini A, Soleimany A, Karaman S and Rus D. Spatial uncertainty sampling for end-to-end control 2018; arXiv:1805.04829 [cs.AI]. [21] Shin R, Karaman S, Ander A, Boulet MT and Connor J. Project based, collaborative, algorithmic robotics for high school students: Programming self driving race cars at MIT. In Integrated STEM Education Conference (ISEC); 11 March 2017; New Jersey, USA; pp. 195-203. [22] Slash 4×4 Platinum Edition, https://traxxas.com/products/models/electric/6804Rslash4x4platinum/ (Erişim: 10 Ocak 2018) [23] Weinstein AJ and Moore KL. Pose estimation of Ackerman steering vehicles for outdoors autonomous navigation. In Proceedings of the IEEE International Conference on Industrial Technology; 14-17 March 2010; Vina del Mar, Chile; pp. 579-584. [24] Velineon 3500 Brushless Motor, https://traxxas.com/products/parts/motors/velineon3500motor/ (Erişim: 10 Ocak 2018) [25] FOCBOX motor controller, https://www.enertionboards.com/electric-skateboard-parts/FOCBOX-programmable-brushless-motor-controller/ (Erişim: 22 Şubat 2018) [26] Autonomous machines, https://www.nvidia.com/en-us/autonomous-machines/embedded-systems-dev-kits-modules/ (Erişim: 7 Temmuz 2018) [27] Zed stereo camera, https://www.stereolabs.com/ (Erişim: 19 Haziran 2018) [28] RPLidar A2M6, https://www.seeedstudio.com/RPLidar-A2M6-The-Thinest-LIDAR-p-2919.html (Erişim: 5 Haziran 2018) [29] LeCun Y, Bottou L, Bengio Y and Haffner P. Gradient-based learning applied to document recognition. In Proceedings of the IEEE 1998; 86(11): 2278-2323. [30] Uçar A ve Bingöl MS. Derin öğrenmenin Caffe kullanılarak grafik işleme kartlarında değerlendirilmesi. DÜMF Mühendislik dergisi 2018; 9(1): 39-49. [31] Jarrett K, Kavukcuoglu K, Ranzato M and LeCun Y. What is the best multi-stage architecture for object recognition. In Proceedings of the International Conference on Computer Vision (ICCV); 29 September-2 October 2009; Nevada, USA; pp. 2146-2153. [32] LeCun Y, Kavukcuoglu K and Farabet C. Convolutional networks and applications in vision. In Proceeding of the Circuits and Systems International Symposium; 30 May-2 June 2010; Grenoble, France; pp. 253-256. [33] Ucar A, Demir Y and Guzelis C. Object recognition and detection with deep learning for autonomous driving applications. SIMULATION 2017; 93(9): 759-769. [34] Hochreiter S and Schmidhuber J. Long short-term memory. Neural computation 1997; 9(8): 1735-1780. [35] Martin S, Schlüter R and Ney H. LSTM neural networks for language modeling. In Proceedings of Thirteenth annual conference of the international speech communication association; 9-13 September 2012; Portland, USA; pp. 194-197. [36] LSTM and its diagrams, https://medium.com/mlreview/understanding-lstm-and-its-diagrams-37e2f46f1714/ (Erişim: 15 Ağustos 2018) [37] Bingöl MS. Grafik işleme ünitesi (GPU) tabanlı öğrenme kullanarak otonom araçlar için algılama sisteminin geliştirilmesi. Yüksek Lisans Tezi, Fırat Üniversitesi Fen Bilimleri Enstitüsü, Elazığ, 2018.
Yıl 2019,
Cilt: 31 Sayı: 1, 177 - 185, 15.03.2019
Öz
Kaynakça
- [1] Gomez V. Object detection for autonomous driving using deep learning. PhD Thesis, Universitat At Politecnica De Catalunya, Automatica Robotica I Visio, Barcelona, 2015. [2] Nikbay K. Otonom araçların güzergah takibi için bir uygulama. Yüksek Lisans Tezi, Okan Üniversitesi Fen Bilimleri Enstitüsü, İstanbul, 2015. [3] Wason R. Deep learning: Evolution and expansion. Cognitive System Research 2018; 52: 701-708. [4] Mobileye pedestrian collision warning system, https://www.mobileye.com/our-technology/ (Erişim: 28 Ağustos 2018) [5] Coelingh E, Eidehall A and Bengtsson M. Collision warning with full auto brake and pedestrian detection - a practical example of automatic emergency braking. In Proceedings of the 13th International IEEE Conference on Intelligent Transportation Systems (ITSC); 19-22 September 2010; Funchal, Portugal, pp. 155-160. [6] Autonomous driving, https://www.bmw.com/en/index.html/ (Erişim: 17 Ağustos 2018) [7] VW Emergency Assistance System, https://safecarnews.com/ (Erişim: 11 Temmuz 2018) [8] Active safety technology, https://www.toyota-global.com/innovation/safety_technology/toyota-safety-sense/ (Erişim: 3 Eylül 2018) [9] Deng L and Yu D. Deep Learning: methods and applications, Foundations and Trends in Signal Processing 2014; 7: 3-4. [10] Christian S, Toshev A and Erhan D. Deep neural networks for object detection. In Proceeding of the Advances in Neural Information Processing Systems; 5-10 December 2013; Lake Tahoe, USA; pp. 2553-2561. [11] Krizhevsky A, Sutskever I and Hinton GE. Imagenet classification with deep convolutional neural networks. In Proceedings of the Advances in Neural Information Processing Systems; 3-6 December 2012; Lake Tahoe, USA; pp. 1097-1105. [12] Deng J, Berg A, Satheesh S, Su H, Khosla A and Fei-Fei L (2012). http://www.image-net.org/challenges/LSVRC/2012/ [13] Berg A, Deng J and Fei-Fei L. Large scale visual recognition, International Journal of Computer Vision 2010; 115(3): 211-252. [14] Bojarski M, Del Testa D, Dworakowski D, Firner B, Flepp B, Goyal P and Zhang X. End to end learning for self-driving cars 2016; arXiv preprint arXiv:1604.07316. [15] Santana E and Hotz G. Learning a driving simulator 2016; arXiv preprint arXiv:1608.01230. [16] Eraqi HM, Moustafa MN and Honer J. End-to-end deep learning for steering autonomous vehicles considering temporal dependencies 2017; arXiv preprint arXiv:1710.03804. [17] Karslı M, Satılmış Y, Şara M, Tufan F, Eken S and Sayar A. End-to-end learning model design for steering autonomous vehicle. In Proceedings of the 26th Signal Processing and Communications Applications Conference (SIU); 2-5 May 2018. [18] Du X, Ang MH, Karaman S and Rus D. A general pipeline for 3d detection of vehicles 2018; arXiv:1803.00387 [cs.CV]. [19] Ma F, Cavalheiro GV and Karaman S. Self-supervised sparse-to-dense: self-supervised depth completion from lidar and monocular camera 2018; arXiv:1807.00275 [cs.CV]. [20] Amini A, Soleimany A, Karaman S and Rus D. Spatial uncertainty sampling for end-to-end control 2018; arXiv:1805.04829 [cs.AI]. [21] Shin R, Karaman S, Ander A, Boulet MT and Connor J. Project based, collaborative, algorithmic robotics for high school students: Programming self driving race cars at MIT. In Integrated STEM Education Conference (ISEC); 11 March 2017; New Jersey, USA; pp. 195-203. [22] Slash 4×4 Platinum Edition, https://traxxas.com/products/models/electric/6804Rslash4x4platinum/ (Erişim: 10 Ocak 2018) [23] Weinstein AJ and Moore KL. Pose estimation of Ackerman steering vehicles for outdoors autonomous navigation. In Proceedings of the IEEE International Conference on Industrial Technology; 14-17 March 2010; Vina del Mar, Chile; pp. 579-584. [24] Velineon 3500 Brushless Motor, https://traxxas.com/products/parts/motors/velineon3500motor/ (Erişim: 10 Ocak 2018) [25] FOCBOX motor controller, https://www.enertionboards.com/electric-skateboard-parts/FOCBOX-programmable-brushless-motor-controller/ (Erişim: 22 Şubat 2018) [26] Autonomous machines, https://www.nvidia.com/en-us/autonomous-machines/embedded-systems-dev-kits-modules/ (Erişim: 7 Temmuz 2018) [27] Zed stereo camera, https://www.stereolabs.com/ (Erişim: 19 Haziran 2018) [28] RPLidar A2M6, https://www.seeedstudio.com/RPLidar-A2M6-The-Thinest-LIDAR-p-2919.html (Erişim: 5 Haziran 2018) [29] LeCun Y, Bottou L, Bengio Y and Haffner P. Gradient-based learning applied to document recognition. In Proceedings of the IEEE 1998; 86(11): 2278-2323. [30] Uçar A ve Bingöl MS. Derin öğrenmenin Caffe kullanılarak grafik işleme kartlarında değerlendirilmesi. DÜMF Mühendislik dergisi 2018; 9(1): 39-49. [31] Jarrett K, Kavukcuoglu K, Ranzato M and LeCun Y. What is the best multi-stage architecture for object recognition. In Proceedings of the International Conference on Computer Vision (ICCV); 29 September-2 October 2009; Nevada, USA; pp. 2146-2153. [32] LeCun Y, Kavukcuoglu K and Farabet C. Convolutional networks and applications in vision. In Proceeding of the Circuits and Systems International Symposium; 30 May-2 June 2010; Grenoble, France; pp. 253-256. [33] Ucar A, Demir Y and Guzelis C. Object recognition and detection with deep learning for autonomous driving applications. SIMULATION 2017; 93(9): 759-769. [34] Hochreiter S and Schmidhuber J. Long short-term memory. Neural computation 1997; 9(8): 1735-1780. [35] Martin S, Schlüter R and Ney H. LSTM neural networks for language modeling. In Proceedings of Thirteenth annual conference of the international speech communication association; 9-13 September 2012; Portland, USA; pp. 194-197. [36] LSTM and its diagrams, https://medium.com/mlreview/understanding-lstm-and-its-diagrams-37e2f46f1714/ (Erişim: 15 Ağustos 2018) [37] Bingöl MS. Grafik işleme ünitesi (GPU) tabanlı öğrenme kullanarak otonom araçlar için algılama sisteminin geliştirilmesi. Yüksek Lisans Tezi, Fırat Üniversitesi Fen Bilimleri Enstitüsü, Elazığ, 2018.
Toplam 1 adet kaynakça vardır.
Ayrıntılar
| Birincil Dil | Türkçe |
|---|---|
| Bölüm | MBD |
| Yazarlar | |
| Yayımlanma Tarihi | 15 Mart 2019 |
| Gönderilme Tarihi | 20 Eylül 2018 |
| Yayımlandığı Sayı | Yıl 2019 Cilt: 31 Sayı: 1 |
