Annotatsiya
Ushbu maqolada sanoat robot manipulyatorlari uchun chuqur o‘qitish algoritmlariga asoslangan tasvirli boshqaruv tizimi taklif etilgan. Tizim ikki bosqichli neyron tarmoq arxitekturasidan iborat bo‘lib, obyektlarni real vaqt rejimida aniqlash uchun YOLOv8 modeli va ushlash pozasini baholash uchun GG-CNN modeli qo‘llanilgan. Taklif etilgan tizim PyBullet simulyatorida 6 erkinlik darajali UR5 robot manipulyatori bilan integratsiyalashtirildi va 5000 ta eksperiment orqali sinovdan o‘tkazildi. Olingan natijalar obyektlarni aniqlashda 94,2% mAP@0,5 va ushlash muvaffaqiyat darajasi 87,3% ga erishilganini ko‘rsatdi. Tizimning umumiy inference vaqti 42 ms ni tashkil etadi, bu real vaqt rejimida ishlash uchun yetarli. Sim-to-real transfer muammosini hal qilish maqsadida domain randomization usuli qo‘llanildi va u real sharoitdagi samaradorlikni 39,2% dan 84,5% gacha oshirishga imkon berdi.
Adabiyotlar:
1. Siciliano B., Khatib O. Springer Handbook of Robotics. – Berlin: Springer-Verlag, 2016. – 2227 p.
2. LeCun Y., Bengio Y., Hinton G. Deep learning // Nature. – 2015. – Vol. 521, № 7553. – P. 436–444.
3. Krizhevsky A., Sutskever I., Hinton G.E. ImageNet classification with deep convolutional neural networks // Communications of the ACM. – 2017. – Vol. 60, № 6. – P. 84–90.
4. Mahler J., Liang J., Niyaz S. et al. Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics // Proceedings of Robotics: Science and Systems. – Cambridge, MA, 2017. – P. 1–10.
5. Jocher G., Chaurasia A., Qiu J. YOLOv8 by Ultralytics. – 2023. URL: https://github.com/ultralytics/ultralytics (murojaat sanasi: 15.10.2025).
6. Morrison D., Corke P., Leitner J. Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach // Proceedings of Robotics: Science and Systems. – Pittsburgh, PA, 2018. – P. 1–10.
7. Kumra S., Joshi S., Sahin F. Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network // IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). – Las Vegas, NV, 2020. – P. 9626–9633.
8. Tobin J., Fong R., Ray A. et al. Domain randomization for transferring deep neural networks from simulation to the real world // IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). – Vancouver, BC, 2017. – P. 23–30.
9. Levine S., Pastor P., Krizhevsky A., Ibarz J., Quillen D. Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection // The International Journal of Robotics Research. – 2018. – Vol. 37, № 4–5. – P. 421–436.
10. Coumans E., Bai Y. PyBullet, a Python module for physics simulation for games, robotics and machine learning. – 2016–2024. URL: http://pybullet.org (murojaat sanasi: 20.10.2025).
11. Redmon J., Divvala S., Girshick R., Farhadi A. You Only Look Once: Unified, Real-Time Object Detection // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). – Las Vegas, NV, 2016. – P. 779–788.
12. Vaswani A., Shazeer N., Parmar N. et al. Attention is all you need // Advances in Neural Information Processing Systems. – 2017. – Vol. 30. – P. 5998–6008.