Autonomous Safety Barrier Inspection in Construction: An Approach Using Unmanned Aerial Vehicles and SafeBIM

TY - GEN

T1 - Autonomous Safety Barrier Inspection in Construction: An Approach Using Unmanned Aerial Vehicles and SafeBIM

AU - Johansen, Karsten W.

AU - Pimentel de Figueiredo, Rui

AU - Golovina, Olga

AU - Teizer, Jochen

PY - 2021/11

Y1 - 2021/11

N2 - Construction sites are dynamic, and the environment is changing fast, which means the collective safety equipment, such as fall protection barriers, should also be changed to keep it compliant with the construction codes. However, any safety equipment can become non-compliant for several reasons, e.g., temporal removal in combination with incorrect or omitted re-installation or changes in the building process. Thus, there is a demand for frequent inspection of the equipment, which is time- and labor-intensive as this is currently done through manual examination by safety experts. In this work, we utilize an unmanned aerial vehicle (UAV) to detect the presence, absence, and defects of safety equipment in construction work-site environments. Furthermore, the UAV continuously inspects and provides safety object location information that human collaborators can use to improve safety within the environment. We utilize an 3D occupancy grid representation to map the environment and compact point pair feature representations for efficient and robust object recognition and pose estimation. To assess the applicability and accuracy of our methods for model-based pose estimation of Building Information Model (BIM) structures, we created a realistic, simulated construction environment. Our experiment demonstrates the applicability and precision of drone-aided localization and inspection of safety equipment in the construction industries.

AB - Construction sites are dynamic, and the environment is changing fast, which means the collective safety equipment, such as fall protection barriers, should also be changed to keep it compliant with the construction codes. However, any safety equipment can become non-compliant for several reasons, e.g., temporal removal in combination with incorrect or omitted re-installation or changes in the building process. Thus, there is a demand for frequent inspection of the equipment, which is time- and labor-intensive as this is currently done through manual examination by safety experts. In this work, we utilize an unmanned aerial vehicle (UAV) to detect the presence, absence, and defects of safety equipment in construction work-site environments. Furthermore, the UAV continuously inspects and provides safety object location information that human collaborators can use to improve safety within the environment. We utilize an 3D occupancy grid representation to map the environment and compact point pair feature representations for efficient and robust object recognition and pose estimation. To assess the applicability and accuracy of our methods for model-based pose estimation of Building Information Model (BIM) structures, we created a realistic, simulated construction environment. Our experiment demonstrates the applicability and precision of drone-aided localization and inspection of safety equipment in the construction industries.

KW - Automation

KW - augmented Reality (AR)

KW - human robot collaboration (HRI)

KW - inspection

KW - object detection and pose estimation

KW - point clouds

KW - safety

KW - unmanned aerial systems

UR - http://www.scopus.com/inward/record.url?scp=85127584368&partnerID=8YFLogxK

U2 - 10.22260/ISARC2021/0085

DO - 10.22260/ISARC2021/0085

M3 - Article in proceedings

SN - 978-952-69524-1-3

SP - 629

EP - 636

BT - Proceedings of the 38th International Symposium on Automation and Robotics in Construction, ISARC 2021

A2 - Feng, Chen

A2 - Linner, Thomas

A2 - Brilakis, Ioannis

T2 - 38th International Symposium on Automation and Robotics in Construction

Y2 - 2 November 2021 through 4 November 2021

ER -