Research Article
BibTex RIS Cite

Evrişimli Sinir Ağları Tabanlı Aktif SLAM ve Keşif

Year 2021, Issue: 22, 342 - 346, 31.01.2021
https://doi.org/10.31590/ejosat.862953

Abstract

Mobil robotlar, serbest hareket seçenekleri ile kara, hava ve su gibi ortamlarda belirli bir işlevi yerine getirmek için kullanılan ve farklı işleme kabiliyetleri için birçok sensörle donatılmış yüksek performanslı robotlardır. Günümüzde nesne algılama, izleme ve haritalama gibi birçok görevde kullanılmaktadır. Haritalama uygulamalarında kullanılan mobil robotlar genellikle kullanıcı girdileri tarafından yönlendirilir. Bununla birlikte, bazı durumlarda, bu yönlendirme, aktif Eşzamanlı Lokalizasyon ve Haritalama (SLAM) anahtar sözcüğü altında incelenen keşif algoritmaları aracılığıyla özerk olarak uygulanır. Bu algoritmalar genellikle Lazer Görüntüleme Algılama ve Değişim (LIDAR) sensörüne dayanır. Bu sensör hantal bir yapıya sahip olduğundan ve ızgara doluluk haritaları uzun bir hesaplama süresi gerektirdiğinden, yeni tür algoritmalar geliştirmek gerekir. Bu çalışmada, kullanıcı girdilerinden bağımsız olan ve otonom olarak hareket eden bir mobil robot ile bir ortamın haritasını oluşturabilen yeni bir Evrişimli Sinir Ağı (CNN) tabanlı algoritma öneriyoruz. İlk aşama için CNN modelinin robota nasıl rehberlik edeceğini öğrenmesi için çevre görüntüsü ve bu görüntülerle ilgili tekerlek açılarından oluşan veri seti kullanılarak CNN yapısı eğitilir. İkinci aşama için robot, birincisinden farklı bir ortamda daha önce eğitilmiş ağ üzerinden otonom olarak gezdirilir ve eş zamanlı olarak ortamın haritası alınır. Gerçek zamanlı uygulama üzerinden eğitim ve test süreçleri gerçekleştirilmiş ve geliştirilen yöntemin avantajları doğrulanmıştır.

References

  • Durrant-Whyte, H., & Bailey, T. (2006). Simultaneous localization and mapping: part I. IEEE robotics & automation magazine, 13(2), 99-110. Available: http://dx.doi.org/10.1109/MRA.2006.1638022
  • Maurović, I., Seder, M., Lenac, K., & Petrović, I. (2017). Path planning for active SLAM based on the D* algorithm with negative edge weights. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 48(8), 1321-1331. Available: http://dx.doi.org/10.1109/TSMC.2017.2668603
  • Zeng, Z., Xiao, H., & Zhang, X. (2016). Self CNN-based time-series stream forecasting. Electronics Letters, 52(22), 1857-1858. Available: http://dx.doi.org/10.1049/el.2016.2626
  • Fuentes-Pacheco, J., Ruiz-Ascencio, J., & Rendón-Mancha, J. M. (2015). Visual simultaneous localization and mapping: a survey. Artificial intelligence review, 43(1), 55-81.
  • Kohlbrecher, S., Von Stryk, O., Meyer, J., & Klingauf, U. (2011, November). A flexible and scalable slam system with full 3d motion estimation. In 2011 IEEE international symposium on safety, security, and rescue robotics (pp. 155-160). IEEE. Available: http://dx.doi.org/10.1109/SSRR.2011.6106777
  • Whaite, P., & Ferrie, F. P. (1997). Autonomous exploration: Driven by uncertainty. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(3), 193-205.
  • Fatih, Ö. (2019). Efficient deep feature selection for remote sensing image recognition with fused deep learning architectures. The Journal of Supercomputing, vol. 76, no. 11, pp. 8413–8431, 2020. DOI: 10.1007/s11227-019-03106-y.

Convolutional Neural Networks Based Active SLAM and Exploration

Year 2021, Issue: 22, 342 - 346, 31.01.2021
https://doi.org/10.31590/ejosat.862953

Abstract

Mobile robots are high-performance robots that are used to perform a specific function in environments such as land, air and water, with free movement options and are equipped with many sensors for different processing capabilities. Today, it is used in many tasks such as object detection, tracking and mapping. Mobile robots used in mapping implementations are usually guided by user inputs. However, in some cases, this guidance is autonomously implemented through exploration algorithms that are examined under the active Simultaneous Localization and Mapping (SLAM) keyword. These algorithms are usually based on Laser Imaging Detection and Ranging (LIDAR) sensor. Since this sensor has a bulky structure and occupancy grid maps require heavy computing time, it is needed to develop new kinds of algorithms. In this study, we propose a novel Convolutional Neural Network (CNN) based algorithm that can create a map of an environment with a mobile robot that is independent of user inputs and move autonomously. For the first stage, the CNN structure is trained using the data set consisting of the environment image and the wheel angles related to these images so that the CNN model learns how to guide the robot. For the second stage, the robot is navigated autonomously through the trained network in an environment which is different from the first one, and the map of the environment is acquired simultaneously. Training and testing processes have been realized on a real-time implementation and the advantages of the developed method have been verified.

References

  • Durrant-Whyte, H., & Bailey, T. (2006). Simultaneous localization and mapping: part I. IEEE robotics & automation magazine, 13(2), 99-110. Available: http://dx.doi.org/10.1109/MRA.2006.1638022
  • Maurović, I., Seder, M., Lenac, K., & Petrović, I. (2017). Path planning for active SLAM based on the D* algorithm with negative edge weights. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 48(8), 1321-1331. Available: http://dx.doi.org/10.1109/TSMC.2017.2668603
  • Zeng, Z., Xiao, H., & Zhang, X. (2016). Self CNN-based time-series stream forecasting. Electronics Letters, 52(22), 1857-1858. Available: http://dx.doi.org/10.1049/el.2016.2626
  • Fuentes-Pacheco, J., Ruiz-Ascencio, J., & Rendón-Mancha, J. M. (2015). Visual simultaneous localization and mapping: a survey. Artificial intelligence review, 43(1), 55-81.
  • Kohlbrecher, S., Von Stryk, O., Meyer, J., & Klingauf, U. (2011, November). A flexible and scalable slam system with full 3d motion estimation. In 2011 IEEE international symposium on safety, security, and rescue robotics (pp. 155-160). IEEE. Available: http://dx.doi.org/10.1109/SSRR.2011.6106777
  • Whaite, P., & Ferrie, F. P. (1997). Autonomous exploration: Driven by uncertainty. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(3), 193-205.
  • Fatih, Ö. (2019). Efficient deep feature selection for remote sensing image recognition with fused deep learning architectures. The Journal of Supercomputing, vol. 76, no. 11, pp. 8413–8431, 2020. DOI: 10.1007/s11227-019-03106-y.
There are 7 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Akif Durdu 0000-0002-5611-2322

Nevzat Bol 0000-0001-6700-7707

Erol Öztürk 0000-0003-2267-9221

Mehmet Duramaz 0000-0001-8965-9802

Mehmet Korkmaz 0000-0002-1462-8005

Berat Yıldız 0000-0002-5675-6750

Ahmet Kayabaşı 0000-0002-9756-8756

Publication Date January 31, 2021
Published in Issue Year 2021 Issue: 22

Cite

APA Durdu, A., Bol, N., Öztürk, E., Duramaz, M., et al. (2021). Convolutional Neural Networks Based Active SLAM and Exploration. Avrupa Bilim Ve Teknoloji Dergisi(22), 342-346. https://doi.org/10.31590/ejosat.862953