@misc{14036,
  abstract     = {{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 segment construction elements in 3D dynamic, unstructured environments. By processing point cloud data from the camera and aligning it with real-world coordinates, the system achieves precise object localization, enabling tasks such as
element handling and assembly. Designed to address challenges like clutter, occlusion, and variability in construction
sites, this system bridges the gap between controlled laboratory conditions and real-world applications. Experimental
evaluations highlight its potential to improve efficiency and adaptability in construction tasks.}},
  author       = {{Aykin, Yusuf and Sachs, Hans and Gerzen, Nikolai}},
  booktitle    = {{Proceedings of the 42th International Symposium on Automation and Robotics in Construction : Montreal, Canada, July 28-31, 2025}},
  editor       = {{Zhang, Jiansong and Chen, Qian and Lee, Gaang and Gonzalez, Vicente A. and Kamat, Vineet}},
  issn         = {{2413-5844}},
  keywords     = {{Computer Vision, Architecture, Building Construction, Robotics in Construction}},
  location     = {{Montreal, Canada}},
  publisher    = {{International Association for Automation and Robotics in Construction (IAARC)}},
  title        = {{{Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction}}},
  doi          = {{10.22260/isarc2025/0026}},
  year         = {{2025}},
}