MultiCamAssembly DataPackage: Experimental Crane Assembly Runs and YOLO Vision Training Data

Read full text
Authors: Nils Opgenorth, Jack Otto, Achim Menges
Cited by: 0

Abstract

This DataPackage contains experimental field data produced with the MultiCamAssembly: Multi-Scalar Robotic Vision System Software Framework. It includes JSON log files and multi-view video recordings from five full-scale crane-based timber assembly runs using the distributed assembly robots (“cambots”). The package also provides the YOLO training data and trained models used on the assembly robots, including labeled images of prefabricated timber elements, training configurations, trained model weights, exported inference models, and Python scripts for evaluation.

Fields of Study & Subjects

Robot Manipulation and Learning BIM and Construction Integration Advanced Neural Network Applications

Publication details

Journal / source
Universitätsbibliothek Stuttgart
Publication date
19 January 2026
Document type
Dataset