Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction

thesis Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction published yes Yusuf Aykin author 84542 Hans Sachs author 64589 Nikolai Gerzen author 76704 HansSachs editor 64589 DEP1055 department This paper presents a robotic system developed to enhance automation in construction workflows through advanced AI and computer vision technologies. The system integrates a robotic arm with a 3D point cloud camera and state- of-the-art 2D pre-trained Deep Learning models, such as GroundingDINO and SegmentAnything, to detect and seg- ment construction elements in 3D dynamic, unstructured environments. By processing point cloud data from the cam- era and aligning it with real-world coordinates, the system achieves precise object localization, enabling tasks such as element handling and assembly. Designed to address chal- lenges like clutter, occlusion, and variability in construction sites, this system bridges the gap between controlled labora- tory conditions and real-world applications. Experimental evaluations highlight its potential to improve efficiency and adaptability in construction tasks. https://www.th-owl.de/elsa/download/14036/14039/ISARC_Robotic_Vision_Yusuf_Aykin.pdf application/pdf no International Association for Automation and Robotics in Construction (IAARC)2025 eng Computer VisionArchitectureBuilding ConstructionRobotics in Construction Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC) 2413-584410.22260/isarc2025/0026 Aykin Y, Sachs H and Gerzen N (2025) Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction, Sachs H (ed.). International Association for Automation and Robotics in Construction (IAARC). Aykin Y, Sachs H, Gerzen N. Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction. Sachs H, editor. Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC). International Association for Automation and Robotics in Construction (IAARC); 2025. Y. Aykin, H. Sachs, N. Gerzen, Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction, International Association for Automation and Robotics in Construction (IAARC), 2025. Y. Aykin, H. Sachs, N. Gerzen, Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction, International Association for Automation and Robotics in Construction (IAARC), 2025. Aykin, Yusuf, Hans Sachs, and Nikolai Gerzen. Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction. Edited by Hans Sachs. Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC). International Association for Automation and Robotics in Construction (IAARC), 2025. <a href="https://doi.org/10.22260/isarc2025/0026">https://doi.org/10.22260/isarc2025/0026</a>. Aykin, Y., Sachs, H., & Gerzen, N. (2025). Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction. In H. Sachs (Ed.), Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC). International Association for Automation and Robotics in Construction (IAARC). <a href="https://doi.org/10.22260/isarc2025/0026">https://doi.org/10.22260/isarc2025/0026</a> Aykin, Yusuf/Sachs, Hans/Gerzen, Nikolai: Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction, hg. von Sachs, Hans, o. O. 2025. Y. Aykin, H. Sachs, and N. Gerzen, Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction. International Association for Automation and Robotics in Construction (IAARC), 2025. doi: <a href="https://doi.org/10.22260/isarc2025/0026">10.22260/isarc2025/0026</a>.

Aykin, Yusuf, Hans Sachs und Nikolai Gerzen. 2025. Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction. Hg. von Hans Sachs. Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC). International Association for Automation and Robotics in Construction (IAARC). doi:<a href="https://doi.org/10.22260/isarc2025/0026">10.22260/isarc2025/0026</a>, .

Aykin, Yusuf, et al. “Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction.” Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC), edited by Hans Sachs, International Association for Automation and Robotics in Construction (IAARC), 2025, <a href="https://doi.org/10.22260/isarc2025/0026">https://doi.org/10.22260/isarc2025/0026</a>.

Aykin, Yusuf ; Sachs, Hans ; Gerzen, Nikolai ; Sachs, H. (Hrsg.): Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction : International Association for Automation and Robotics in Construction (IAARC), 2025

Aykin Y, Sachs H, Gerzen N. Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction. (Sachs H, ed.). International Association for Automation and Robotics in Construction (IAARC); 2025. doi:<a href="https://doi.org/10.22260/isarc2025/0026">10.22260/isarc2025/0026</a> 140362026-09-17T14:27:18Z2026-09-17T14:43:42Z