Hector SLAM Based Navigation with Integrated Object Detection

Abstract

Bu çalışmanın amacı iç mekanlarda Hector Eş Zamanlı Lokalizasyon ve Haritalama (EZLH) ve “Sadece Bir Defa Bak” (SBDB) kullanan özel yapım bir otonom robotun nesneleri algılamasını ve onları sınıflandırmasını sağlayan bir yaklaşım geliştirmektir. Yaklaşım, Robot İşletim Sistemi (RİS) ve bilgisayarla görme teknolojilerine dayanmaktadır. Mobil robotun hareketi, izlediği yolu ve iletişimi, RİS navigasyon paketiyle kontrol edilmektedir. Makale, yeni bir harita oluşturmak için uygulanan algoritmanın ayrıntılı bir açıklamasının yanı sıra, mobil robotun donanım ve yazılım yapılandırmasına ilişkin bilgileri de sunmaktadır. Nesne tanımlama süreci ve harita oluşturma, düşük bütçeli bir Lazer Görüntüleme Algılama ve Mesafe Ölçümü (LGAMÖ) sensörü ile enkodersiz direkt akım (DA) motorlar kullanılarak yapılmaktadır. Sonuçlar, önerilen tekniğin nesneleri sırasıyla x ve y kartezyen eksenlerinde % 97.8 ve % 94.86 doğrulukla tespit edebildiğini göstermektedir.

Keywords

• Otonom robot
• Hector Eş Zamanlı Lokalizasyon ve Haritalama (EZLH)
• Robot İşletim Sistemi (RİS)
• Sadece Bir Defa Bak (SBDB)

HECTOR SLAM BASED NAVIGATION WITH INTEGRATED OBJECT DETECTION

Abstract

The main aim of this study is to develop an approach that detects and classifies objects in indoor areas by applying Hector Simultaneous Localization and Mapping (SLAM) and "You Only Look Once" (YOLO) algorithms to an autonomous, custom-made mobile robot. The approach is based on the Robot Operating System (ROS) and computer vision. The mobile robot's motion, path, and communication are controlled by the ROS navigation package. This paper provides a detailed description of the approach implemented to create a new map with objects, as well as information about the hardware and software configuration of the mobile robot. The object identification process and map creation are performed using a low-budget Laser Imaging Detection and Ranging (LIDAR) sensor and non-encoder DC motors. The results show that the proposed technique can detect objects with an accuracy of 97.8% and 94.86% for the x and y cartesian axes, respectively.

Keywords

• Autonomous robot
• Hector SLAM
• ROS
• YOLO

References

1. Bisallah, H.I., Oguin, K.J. and Oguine, O.C. (2022), YOLO v3: Visual and Real-Time Object Detection Model for Smart Surveillance Systems(3s), doi: 10.48550/arXiv.2209.12447
2. Chghaf, M.R. (2022), Camera, lidar and multi-modal SLAM systems for autonomous ground vehicles: a survey, Journal of Intelligent & Robotic Systems, volume (105):2. doi: 10.1007/s10846-022-01582-8
3. Craig, J.J. (2014), Introduction to Robotics Mechanics and Control (3 ed.), Leeds: Pearson Education Limited
4. Fadhil A. and Hakim H. (2019) Indoor low cost assistive device using 2D SLAM based on LIDAR for visually impaired people, Iraqi Journal of Electrical and Electronic Engineering (15)2: pp 115-12, doi: 10.37917/IJEEE.15.2.12
5. Hess, W., Kohler, D., Rapp, H. and Andor, D. (2016), Real-Time loop closure in 2D LIDAR SLAM, 2016 IEEE International Conference on Robotics and Automation (ICRA), pp: 1271-1278., doi: 10.1109/ICRA.2016.7487258.
6. Hossain, A. and Chowdhury, R.H. (2024) "Implementation of Hector SLAM Algorithm for Mapping Indoor Environments with Obstacles," 2024 IEEE 3rd International Conference on.
7. https://jokane.net/agitr/agitr-letter.pdf, Date of Access: 06.06.2023, Topic: A Gentle Introduction to ROS
8. https://sceweb.sce.uhcl.edu/harman/CENG5437_MobileRobots/Webitems2020/ROS_ROBOTICS_BY_EXAMPLE_SECOND_EDITION.pdf, Date of Access: 07.06.2023, Topic: ROS Robotics By Example-Second Edition. Leeds: Packt.

9. Hyeong, R.K., Lee, S., Park, T. and Kim, C. (2015) RViz: a toolkit for real domain data visualization, Telecommunication Systems (60): 337-345, doi: 10.1007/s11235-015-0034-5
10. K. Kamarudin et al. (2015), Improving performance of 2D SLAM methods by complementing Kinect with laser scanner, 2015 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS), Langkawi, 278-283, doi: 10.1109/IRIS.2015.7451625.
11. Kashi, M.S, Sriram, T.B. and Mohan, R. (2019), An Approach to labelled indoor mapping using SLAM and object detection. 2019 IEEE Region 10 Symposium (TENSYMP), 321-325. doi: 10.1109/TENSYMP46218.2019.8971298
12. Kohlbrecher, S., Meyer, J., Stryk O. von and U. Klingauf (2011), A flexible and scalable SLAM system with full 3D motion estimation, Proc. IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR), 155-160, doi: 10.1109/SSRR.2011.6106777.
13. M. Filipenko and I. Afanasyev (2018). Comparison of Various SLAM Systems for Mobile Robot in an Indoor Environment. In 2018 International Conference on Intelligent Systems (IS), pp. 400-407. doi: 10.1109/IS.2018.8710464.
14. Marder-Eppstein, E. et al. (2010), The office marathon: robust navigation in an indoor office environment, International Conference on Robotics and Automation, 300-307, doi: 10.1109/ROBOT.2010.5509725
15. Robotics, Automation, Artificial-Intelligence and Internet-of-Things (RAAICON), Dhaka, Bangladesh, 2024, pp. 218-223, doi: 10.1109/RAAICON64172.2024.10928605 https://dspace.mit.edu/bitstream/handle/1721.1/119149/16-412j-spring2005/contents/projects/1aslam_blas_repo.pdf, Date of Access: 07.06.2023, Topic: Blas MR and Riisgaard S (2005) SLAM for Dummies: A Tutorial Approach to Simultaneous Localization and Mapping.
16. Sapmaz, S. (2022), Eş zamanlı konum belirleme ve haritalama için bilgisayarlı görü ve sensör tabanlı otonom gezgin robot [A computer vision and sensor based autonomous mobile robot for simultenaous localization and mapping], M. Sc. Thesis, Ege University, TR.