Derin Öğrenme Yöntemleriyle Kapalı Alan Temizlik Robotunun Hareket Planlamasının Optimizasyonu

Öz

Günümüzde teknolojinin gelişmesiyle birlikte mobil robotlar da hayatımıza giriş yapmıştır. Mobil robotların kullanım alanlarından biri olan temizlik robotları, insan yaşamını kolaylaştıran araçlardan biri haline gelmiştir. Temizlik robotlarının en temel özelliği bulundukları ortamı insanların yerine temizlemeleridir. Bu çalışmada, otonom bir şekilde bulunduğu ortamın zemin temizleme işlemlerini gerçekleştirebilen bir robot süpürge tasarım ve gerçekleştirimi yapılmıştır. Geliştirilen robot süpürge, karşısına bir nesne çıkması durumunda yol planlamasını düzenleme özelliğine sahiptir. Yol planlamasını düzenleyebilmesi için derin öğrenme yöntemi kullanılmıştır. Derin öğrenme sayesinde, eğitim aşamasında öğretilen cisimlerden herhangi birisinin önüne çıkması durumunda oluşturulan algoritmaya göre yol planlamasını düzenleyebilmektedir. Bu sayede robot süpürge cisimlere takılmadan gezinme işlemine devam edebilmektedir.

Anahtar Kelimeler

• Derin öğrenme
• yol planlaması
• otonom
• mobil robotlar.

Optimization of Motion Planning of Indoor Cleaning Robot with Deep Learning Methods

Öz

Today, with the advancement of technology, mobile robots have entered our lives. Cleaning robots, one of the areas of use of mobile robots, have become one of the tools that make human life easier. The most basic feature of cleaning robots is that they clean their environment on behalf of humans. In this study, we designed and implemented a robot vacuum cleaner that can autonomously clean the floors of its environment. The developed robot vacuum cleaner can adjust its path plan when it encounters an object. Deep learning method was used to adjust the path planning. Thanks to deep learning, it can adjust its path plan according to the algorithm created when it encounters any of the objects taught during the training phase. This allows the robot vacuum cleaner to move without getting stuck on objects.

Anahtar Kelimeler

• Deep learning
• path planning
• autonomous
• mobile robots.

Kaynakça

1. Boztaş G, Aydoğmuş Ö. Implementation of pure pursuit algorithm for nonholonomic mobile robot using robot operating system. BAJECE, 2021; 9(4), 337-341.
2. https://www.mathworks.com/discovery/path-planning.html (Erişim tarihi: 07.07.2025)
3. Sohan M, Sai Ram T, Rami Reddy CV. A review on yolov8 and its advancements. In International Conference on Data Intelligence and Cognitive Informatics, 2024; Singapore: Springer. pp. 529-545.
4. Eren A, Doğan H. Design and implementation of a cost effective vacuum cleaner robot. TUJE, 2022; 6(2), 166-177.
5. Ramalingam B, Le AV, Lin Z, Weng Z, Mohan RE, Pookkuttath S. Optimal selective floor cleaning using deep learning algorithms and reconfigurable robot hTetro. Sci Rep, 2022; 12(1), 15938.
6. Nabi SA, Vardhan MK. NavRobotVac: A Navigational Robotic Vacuum Cleaner Using Raspberry Pi and Python. In Smart Computing Techniques and Applications: Proceedings of the Fourth International Conference on Smart Computing and Informatics, 2021 July; Singapore: Springer Singapore. Volume 2, pp. 159-167.
7. Prayash H. S. H., Shaharear M. R., Islam M. F., Islam S., Hossain N., Datta S. Designing and optimization of an autonomous vacuum floor cleaning robot. In 2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON), 29 November – 01 December 2019; Dhaka, Bangladesh: IEEE. pp. 25-30.
8. Adithya PS, Tejas R, Varun VS, Prashanth BN. Design and development of automatic cleaning and mopping robot. In IOP conference series: Materials science and engineering, 2019 November; IOP Publishing

9. Asafa TB, Afonja TM, Olaniyan EA, Alade HO. Development of a vacuum cleaner robot. Alex Eng J 2018; 57(4), 2911-2920.
10. Kukde M, Nagpurkar S, Dhakulkar A, Amdare A. Automatic & manual vacuum cleaning robot. IRJET, 2018; 5(02), 2196-2198.
11. Patel DC, Patil HS. Design and development of low cost artificial intelligence vacuum cleaner. IJRTER, 2017; 3(11), 59-67.
12. Rashid H, Mahmood A, Shekha S, Reza ST, Rasheduzzaman M. Design and development of a DTMF controlled room cleaner robot with two path-following method. In 2016 19th International Conference on Computer and Information Technology (ICCIT), 18–20 December 2016; Dhaka, Bangladesh: IEEE. pp. 484-489.
13. Domnitcheva S. Smart Vacuum Cleaner–An Autonomous Location-Aware Cleaning Device. In Proceedings of the 6th International Conference on Ubiquitous Computing, (2004 September); Tokyo, Japan. pp. 844-856.
14. https://www.ydlidar.com/product/ydlidar-x2 (Erişim tarihi: 07.07.2025)
15. https://en.wikipedia.org/wiki/Occupancy_grid_mapping (Erişim tarihi: 10.08.2025)
16. https://en.wikipedia.org/wiki/Bresenham's_line_algorithm (Erişim tarihi: 07.07.2025)
17. Gabriely Y, Rimon E. Spiral-STC: An on-line coverage algorithm of grid environments by a mobile robot. In Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No. 02CH37292), 11-15 May 2002; Washington, DC, USA: IEEE. Vol. 1, pp. 954-960.
18. Top A. Controlling the Mobile Robot with the Pure Pursuit Algorithm to Tracking the Reference Path Sent from the Android Device. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 2024; 15(1), 119-129.
19. Samuel M, Hussein M, Mohamad MB. A review of some pure-pursuit based path tracking techniques for control of autonomous vehicle. Int J Comput Appl, 2016; 135(1), 35-38.
20. https://docs.ultralytics.com/tr/models/yolov8/ (Erişim tarihi: 07.07.2025)
21. https://docs.ultralytics.com/tr/guides/yolo-performance-metrics/#how-to-calculate-metrics-for-yolo11-model (Erişim tarihi: 07.07.2025)