Proceedings of TUSUR University / Archive / Issue of Journal № 1, t. 29, 2026 / Control of a six-axis robotic manipulator using automatic 3D localization of target objects based on stereoscopic vision

Control of a six-axis robotic manipulator using automatic 3D localization of target objects based on stereoscopic vision

DOI: 10.21293/1818-0442-2026-29-1-135-143

Download article in PDF format

JATS xml

Abstract: Relevance. Accurate three-dimensional object localization is a critical requirement for robotic visual servoing systems that perform autonomous object grasping and manipulation. Purpose of the study. The study aims to develop and experimentally evaluate an integrated autonomous object grasping system based on stereo vision and a robotic manipulator. Methods. The proposed system employs a ZED 2 stereo camera, the YOLOv8 object detection model, a six-axis robotic manipulator, and the ROS 2 operating system. Object detection and two-dimensional coordinate estimation were performed using RGB images, followed by fusion with depth map data to obtain three-dimensional coordinates and their transformation into the robot base coordinate system. Novelty. An integrated visual servoing approach for robotic manipulation is proposed, providing sub-centimeter 3D localization accuracy using a consumer-grade stereoscopic sensor. Results. Experimental evaluation demonstrated a localization root mean square error (RMSE) of 2.95 mm in the XY plane. Autonomous grasping experiments achieved a success rate exceeding 97%. Practical significance. The developed system can be applied in industrial automation tasks, autonomous object grasping, and robotic visual servoing systems requiring high-precision spatial localization.

Keywords: stereo vision, 3d object localization, vision-guided robotics, depth accuracy, ros 2, robotic manipulation

For citation:
Kapustin V. V., Saira, Tislenko A. A. Control of a six-axis robotic manipulator using automatic 3D localization of target objects based on stereoscopic vision. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2026, vol. 29, no. 1, pp. 135–143. DOI: 10.21293/1818-0442-2026-29-1-135-143

Authors and copyright holders:

Kapustin V. V. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
Saira , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
Tislenko A. A. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)

1. He Y., Chen S. Advances in sensing and processing methods for three-dimensional robot vision. International Journal of Advanced Robotic Systems, 2018, vol. 15, no. 2, pp. 1–19.
2. Soori M., Dastres R., Arezoo B., Jough F.K. Intelligent robotic systems in Industry 4.0: A review. Journal of Advanced Manufacturing Science and Technology, 2024, vol. 4, no. 3, pp. 1–20.
3. Rayhan A. Artificial intelligence in robotics: From automation to autonomous systems. IEEE Transactions on Robotics, 2023, vol. 39, no. 7, pp. 2241–2253.
4. Panasiuk J. Controlling an Industrial Robot Using Stereo 3D-Vision Systems with AI Elements. Sensors, 2025, vol. 25, no. 20, pp. 1–32.
5. Li Z., Li S., Luo X. An overview of calibration technology of industrial robots. IEEE/CAA Journal of Automatica Sinica, 2021, vol. 8, no. 1, pp. 23–36.
6. Huang H., Liu J., Liu S., Jin P., Wu T., Zhang T. Error analysis of a stereo-vision-based tube measurement system. Measurement, 2020, vol. 157, pp. 1–17.
7. Zhao H., Ma W., Ji P., Zhang G., Shi B., Zhang Z., Yin W., Yang S. Modeling the measurement accuracy for binocular stereo vision system. Optics Express, 2025, vol. 33, no. 9, pp. 19051–19066.
8. Belhaoua A., Kohler S., Hirsch E. Error evaluation in a stereovision-based 3D reconstruction system. EURASIP Journal on Image and Video Processing, 2010, vol. 2010, no. 1, pp. 1–12.
9. Bier A., Luchowski L. Error analysis of stereo calibration and reconstruction. International Conference on Computer Vision/Computer Graphics Collaboration Techniques and Applications, Berlin, Springer, 2009, pp. 230–241.
10. Kronauer T., Pohlmann J., Matthé M., Smejkal T., Fettweis G. Latency analysis of ROS 2 multi-node systems. arXiv e-prints, 2021, art. no. arXiv:2101.02074.
11. Open Robotics. ROS 2 documentation. Available at: https://docs.ros.org/en/rolling/index.html (accessed: 3 November 2025).
12. Zhang G., Li C., Zhang X., Liu G., Liu Y., Zhao J., Xu S. An adaptable robotic system for assembling irregular earphone parts on factory automation. IEEE International Conference on Robotics and Biomimetics (ROBIO), IEEE, 2019, pp. 52–58.
13. Tassa Y., Erez T., Todorov E. Synthesis and stabilization of complex behaviors through online trajectory optimization. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, 2012, pp. 4906–4913.
14. Stereolabs. ZED 2 camera documentation. Available at: https://www.stereolabs.com/docs/ (accessed: 15 December 2025).
15. Valverde M., Moutinho A., Zacchi J.V. A survey of deep learning-based 3D object detection methods for autonomous driving across different sensor modalities. Sensors, 2025, vol. 25, no. 17, pp. 1–40.
16. Zhang G., Yang S., Hu P., Deng H. Advances and prospects of vision-based 3D shape measurement methods. Machines, 2022, vol. 10, no. 2, pp. 1–24.
17. Zhou L., Wu G., Zuo Y., Chen X., Hu H. A comprehensive review of vision-based 3D-reconstruction methods. Sensors, 2024, vol. 24, no. 7, pp. 1–36.
18. 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, USA, IEEE, 2016, pp. 779–788.