ArticlePDF Available

Amalgamation of smart AIoT based construction site monitoring with robotics: viAct's extended horizon

Authors:

Abstract and Figures

The paper presents research insights on amalgamation AIoT and Robotic technology for construction site monitoring. For this purpose the paper studies the special case of viAct's smart cloud controlled robotic system with embedded camera that enables real time capturing of images, detecting various safety non-compliances by workers for maintaining a safe construction ecosystem. Furthermore, the automatic wheel base carries LiDar that can detect the objects in the form of point clouds generating a as-is model which is compared with the as-planned BIM model. This helps in regular day to day progress tracking of the real time scenario helping contractors and owners to have human prejudice free inspection of their construction sites. viAct's smart robotic system working in a collaborative robot background, is thus a value addition to the viAct's existing monitoring solution based on AIoT, making the entire monitoring more accurate, optimal and error free.
Content may be subject to copyright.
International Journal of Research in Engineering and Science (IJRES)
ISSN (Online): 2320-9364, ISSN (Print): 2320-9356
www.ijres.org Volume 09 Issue 10 ǁ 2021 ǁ PP. 24-27
www.ijres.org 24 | Page
Amalgamation of smart AIoT based construction site
monitoring with robotics: viAct's extended horizon
Gary Ng1, Hugo Cheuk2, Surendra Singh3, Baby Sharma4*
118 Wai Yip St, Kwun Tong, Hong Kong
*4 Corresponding Author: Baby Sharma (baby.sharma@viact.ai)
Abstract
The paper presents research insights on amalgamation AIoT and Robotic technology for construction site
monitoring. For this purpose the paper studies the special case of viAct’s smart cloud controlled robotic system
with embedded camera that enables real time capturing of images, detecting various safety non-compliances by
workers for maintaining a safe construction ecosystem. Furthermore, the automatic wheel base carries LiDar
that can detect the objects in the form of point clouds generating a as-is model which is compared with the as-
planned BIM model. This helps in regular day to day progress tracking of the real time scenario helping
contractors and owners to have human prejudice free inspection of their construction sites. viAct’s smart
robotic system working in a collaborative robot background, is thus a value addition to the viAct’s existing
monitoring solution based on AIoT, making the entire monitoring more accurate, optimal and error free.
Keywords: AIoT, viAct, Robotics, LiDar, Construction monitoring, BIM, Productivity monitoring, Collaborative
Robot Background
---------------------------------------------------------------------------------------------------------------------------------------
Date of Submission: 17-10-2021 Date of acceptance: 01-11-2021
---------------------------------------------------------------------------------------------------------------------------------------
I. Introduction
The construction industry is growing its horizon with monitoring automation and robotics technologies.
The working knowledge of electronics, mechanical and computer software has been used to operate robotic
systems in construction job-sites in a collaborative robot background (Feng et al.,2015). This helps in improving
the construction job-site for improving safety and productivity related concerns thereby improving quality of the
construction workplace (Nguyen & Choi, 2018). The earlier research depicts there is very low inclusion of
automation in the construction industry. This has been often linked to critical and dynamic working conditions
leading to slow adaptation of technological innovations in the construction job-sites. To fulfill this gap, the last
decade has witnessed boom in research on construction automation integrating robotics for various purposes
including designing, planning, monitoring safety and estimating productivity of construction project (Kim et al.,
2013; Klein et al., 2012). Thereby it could be stated that the construction ecosystem is transforming from
traditional construction to “Construction + Technology”, formally called “ConTechecosystem. Robots are
emerging as a crucial part of this automatic ConTech ecosystem. Robots used for construction monitoring are
electronically controlled systems using hydraulics making them suitable for working in large scale dynamic
construction projects in a collaborative robot background. Automation in construction monitoring is redefined
with machines and advanced technology with emerging of ConTech startups.
This chapter puts forward new a revolution in construction automations with amalgamation AI and
robotics for fine tune accuracy in monitoring of construction project taking in consideration special case of
viAct, Asia’s leading ConTech startup. viAct is a startup from Hong Kong that provides “Scenario-based
Vision Intelligence” solutions exclusively for construction industry all across Asia & Europe by successfully
deploying around 30 sites. viAct’s smart AI modules has been successfully providing extremely granular
insights on safety prepositions, productivity forethoughts and environmental compliances in jobsites by not only
tracking objects but by transforming vision to practical actions. Thus, the case study presented in this paper
fulfills all the requisites for stating viAct as one of its own kind in proving holistic scenario based solution
providers leveraging the power of AIoT and robotics. The chapter depicts the principal, working and
applications of an autonomous wheel based robotic system controlled via. cloud that carries camera, LiDar and a
digital display to automatically collect data using the existing (as-planned) BIM model by navigating through
the dynamic construction site, collecting and processing data by detecting various workforce related safety non-
compliances, daily productivity checks and therefore producing real time reports. In the former case, any safety
negligence is instantly alerted to the concerned authority. However in the later case, detecting the progress a
progress (as-built) model is generated which can be compared to the as-planned model in order to generate an
error free progress report with minimum human interference and prejudice.
Amalgamation of smart AIoT based construction site monitoring with robotics: ..
www.ijres.org 25 | Page
II. AI & Robotics in construction monitoring: viAct’s special case
2.1 Principle & Working
Robotic system used by viAct is designed taking in consideration the locomotive aspect. It is designed
to carry camera, Lidar and a digital display. As construction job-site is a dynamic environment, the robots used
for construction job-site monitoring is designed with outdoor all-terrain wheels. The wheel based locomotive
robot is effective systems as it can efficiently move through rough and dynamic terrains of construction job-site
detecting various complex scenarios in the construction site. The robotic system is precise than onsite mounted
job-site cameras in scenarios which are difficult to be captured by the later ones. Thus the robotic system is
more approachable than conventional construction monitoring methods, providing a holistic watch on every
nook and corner of the job-site. Thus, terrain locomotion system with wheels is used in viAct for achieving
optimum navigation with high levels of control and precision, without hampering freedom of movement in the
site as well as allowing reduction of human prejudice and biasness. This in-turn is indicative of a collaborative
robot environment for efficient monitoring. Apart from this actuators, are used to facilitate a fully autonomous
behavior in the wheel based robots. As the robotic systems need to interact with the environment in terms of
removing obstacles, opening doors or accessing elevators. An actuator produces motion via conversion of
energy and signals passing into the system. Thus, for making a robotic system efficient to work along with
human in a collaborative robot background, actuators are used for a fully autonomous behavior.
Furthermore, as the robot needs to collect colored visual information, structural geometry data of the
building, surface reflectance information, therefore various sensors like 3D Laser scanner. Thus, 3D Laser
Scanner is another important functional component of the robotic technology. In terms of technical aspect, the
3D laser scanning uses a laser beam for capturing features of objects in multiple directions within and around a
structure (Patil et al., 2017; Shrestha & Jeong, 2017). The captured data points are aggregated into a “point
cloud” and assigned X, Y, and Z coordinates which are then digitally saved. These cloud points are then used for
describing the spatial relationships between objects, providing a full characteristic depiction of the receiving
entities (Bueno et al., 2018). Its principal is based on measuring reflected pulses from the object’s surface by
sensors when a high speed rotating laser beam is subjected to objects (Ibrahim et al., 2019). The relative location
of the object to the scanner and the resolution angle is used to measure the resolution or the distance (mm)
between aforementioned points (Reboli et al., 2017). Apart from this, shape of the objects can also be
determined the point cloud data. Thus, 3D laser scanning is used for speedy collection of spatial data for
improving resolution of detection and minimizing unwanted data noise. Once the point cloud has been created in
a 3D spatial form, the data is exported for constructing complex geometric BIM models.
Another key aspect of viAct’s autonomous wheel based localization system is that it uses BIM model
of the building in conjunction with LiDARs for mapping precise and real-time position of the robot. BIM which
is a design document consisting of digital files or data (Bosche et al., 2015; Lagüela et al., 2013). It uses various
tools and technologies to generate digital representation of physical and functional characteristics of places
containing close relationships with each other in terms of space, size, quantity, and material of each structure. In
order to support progress measurements, project management, and project control; BIM’s information is
exchanged and associated online together through the software. Thus, by amalgamation of various building and
construction related information such as plans, financial budgets, and construction progress, it helps in creating
a virtual reality model of the building for optimal monitoring of the construction site by the robotic system for
an enhanced operational management. Thus, applying 3D laser scanning technology with a BIM model, an exact
volume schedule can be approved at each point of various construction phases or stages in order to accurately
determine the quantity of work done.
Amalgamation of smart AIoT based construction site monitoring with robotics: ..
www.ijres.org 26 | Page
Figure 1: BIM-3D laser scanning process
2.2 Application of viAct’s robotic system
viAct’s wheel based robotic system is an add-on to the existing application of viAct’s smart monitoring system
(Fig 2).
Figure 2: Application of viAct’s robotic system
Amalgamation of smart AIoT based construction site monitoring with robotics: ..
www.ijres.org 27 | Page
1.2.1 Worker PPE Detection
Workers working in viAct’s collaborative robot environment are safer than traditional construction
sites. In addition to providing holistic monitoring through existing cameras, viAct’s robotic system is a new
companion in the construction job-site that can help in detecting and monitoring PPE compliances in job-site.
The robotic system is fed with the scenario based intelligence of viAct which is controlled and operated through
viAct’s smart cloud in order to provide holistic, error-free monitoring of helmets, masks, PPE kits etc. In case of
any non-compliance detection, instant alert is sent to site managers and remote authorities for instant actions.
1.2.2 360° Photo Capturing
A large part of project monitoring involves documentation. Manual documentation involves capturing
pictures of the jobsite for the purpose of record keeping. However when a project site is too large and dynamic,
accuracy of manual documentation through manual capturing is an error prone task. In this respect, viAct’s
smart robotic system has been designed to automatically capture 360° pictures of the jobsite. These pictures
don’t just help in record keeping but also helps owners to keep a track of their ongoing projects with real time
images captured by the robotic system and stored in the cloud.
1.2.3 Progress Tracking through BIM
BIM along with 3D laser scanning is another advanced feature of the robotics system viAct. The 3D
laser scanner installed in the robotic system helps to capture cloud data points. This helps in comparing every
day progress of the construction site with the as-planned BIM model. Such accurate progress tracking helps
contractors to keep a strict watch on progress. At the same time as the progress reports are updated on viAct’s
cloud system real time progress reports can also been accessed by the property owners for having a transparent
workflow between contractors and workers.
III. Conclusion
The paper presents research insights on amalgamation AIoT and Robotic technology for construction
site monitoring. For this purpose the paper studies the special case of viAct’s smart cloud controlled robotic
system with embedded camera that enables real time capture of images, detecting various safety non-
compliances by workers for maintaining a safe construction ecosystem. Furthermore, the automatic wheel base
carries LiDar that can detect the object in the form of point clouds generating a as-is model which is compared
with the as-planned BIM model. This helps in regular day to day progress tracking of the real time scenario
helping contractors and owners to have human prejudice free inspection of the construction site. viAct’s smart
robotic system working in a collaborative robot background, is thus a value addition to the existing monitoring
solution based on AIoT, making the entire monitoring further accurate, optimal and error free.
References
[1]. Ibrahim, A. Sabet, and M. Golparvar-Fard, “BIM-driven mission planning and navigation for automatic indoor construction
progress detection using robotic ground platform,” Proc. 2019 Eur. Conf. Comput. Constr., vol. 1, pp. 182–189, 2019.
[2]. K. Patil, P. Holi, S. K. Lee, and Y. H. Chai, “An adaptive approach for the reconstruction and modeling of as-built 3D pipelines
from point clouds,” Autom. Constr., 2017.
[3]. Feng, Y. Xiao, A. Willette, W. McGee, and V. R. Kamat, “Vision guided autonomous robotic assembly and as-built scanning on
unstructured construction sites,” Autom. Constr., 2015
[4]. H. P. Nguyen and Y. Choi, “Comparison of point cloud data and 3D CAD data for on-site dimensional inspection of industrial plant
piping systems,” Autom. Constr., 2018.
[5]. Kim, C. Kim, and H. Son, “Automated construction progress measurement using a 4D building information model and 3D data,”
Autom. Constr., 2013.
[6]. Rebolj, Z. Pučko, N. Č. Babič, M. Bizjak, and D. Mongus, “Point cloud quality requirements for Scan-vs-BIM based automated
construction progress monitoring,” Autom. Constr., 2017.
[7]. Bosché, M. Ahmed, Y. Turkan, C. T. Haas, and R. Haas, “The value of integrating Scan-toBIM and Scan-vs-BIM techniques for
construction monitoring using laser scanning and BIM: The case of cylindrical MEP components,” Autom. Constr., 2015.
[8]. K. J. Shrestha and H. D. Jeong, “Computational algorithm to automate as-built schedule development using digital daily work
reports,” Autom. Constr., 2017.
[9]. L. Klein, N. Li, and B. Becerik-Gerber, “Imagedbased verification of as-built documentation of operational buildings,” Autom.
Constr., 2012.
[10]. M. Bueno, F. Bosché, H. González-Jorge, J. Martínez-Sánchez, and P. Arias, “4-Plane congruent sets for automatic registration of
as-is 3D point clouds with 3D BIM models,” Autom. Constr., 2018.
[11]. S. Lagüela, L. Díaz-Vilariño, J. Martínez, and J. Armesto, “Automatic thermographic and RGB texture of as -built BIM for energy
rehabilitation purposes,” Autom. Constr., 2013.
ResearchGate has not been able to resolve any citations for this publication.
Article
Inspection is vital in industrial plant construction and management. However, traditional inspection methods that rely on human involvement and paper documentation are becoming untenable as modern industrial plants are becoming larger and more complex than legacy facilities. Hence, an efficient and robust method is required to support the inspection of modern industrial plants. In this paper, an improved technique relying on terrestrial laser scanning (TLS) for data acquisition and normal-based region growing and efficient random sample consensus (RANSAC) for point cloud data processing is proposed for the on-site dimensional inspection of the piping systems of an industrial plant. Consequently, the as-built condition of the plant is assessed via a distance-based deviation analysis and a comparison of geometric parameters between the as-designed and as-built models. The method is validated using a dataset acquired from a compartment of a ship has verified the robustness and reliability of the proposed approach.
Article
Construction quality and progress control are demanding, yet critical construction activities. Building Information Models and as-built scanned data can be used in Scan-vs-BIM processes to effectively and comprehensively support these activities. This however requires accurate registration of scanned point clouds with 3D (BIM) models. Automating such registration remains a challenge in the context of the built environment, because as-built can be incomplete and/or contain data from non-model objects, and construction buildings and other structures often present symmetries and self-similarities that are very challenging to registration. In this paper, we present a novel automatic coarse registration method that is an adaptation of the ‘4 Points Congruent Set’ algorithm to the use of planes; we call it the ‘4-Plane Congruent Set’ (4-PlCS) algorithm. The approach is further integrated in a software system that delivers not one but a ranked list of the most likely transformations, so to allow the user to quickly select the correct transformation, if need be. Two variants of the method are also considered, in particular one in the case when the vertical axis is known a priori; we call that method the 4.5-PlCS method. The proposed algorithm is tested using five different datasets, including three simulated and two real-life ones. The results show the effectiveness of the proposed method, where the correct transformation always ranks very high (in our experiments, first or second), and is extremely close to the ground-truth transformation. Experimental comparison of the proposed approach with a standard, more intuitive approach based on finding 3-plane congruent sets shows the discriminatory power of 4-plane bases over 3-plane bases, albeit at no clear benefits in terms of computational time. The experimental results for the 4.5-PlCS method show that it delivers a non-negligible reduction in computational time (approx. 20%), but at no additional benefit in terms of effectiveness in finding the correct transformation.
Article
As-built schedules prepared during and after construction are valuable tools for State Highway Agencies (SHAs) to monitor construction progress, evaluate contractor's schedule performance, and defend against any potential disputes. However, previous studies indicate that current as-built schedule development methods are manual and rely on information scattered in various field diaries and meeting minutes. SHAs have started to collect field activity data in digital databases that can be used to automatically generate as-built schedules if proper computational algorithms are developed. This study develops computational algorithms and a prototype system to automatically generate and visualize project level and activity level as-built schedules during and after construction. The algorithm is validated using a real highway project data. The study is expected to significantly aid SHAs in making better use of field data, facilitate as-built schedule development, monitor construction progress with higher granularity, and utilize as-built schedule for productivity analysis.
Article
Automated extraction of 3D geometric shapes such as planes, spheres, cylinders, cones, and tori in laser-scanned point clouds is a challenging problem and a tedious process, especially when using cluttered data. This paper describes a modification of the existing Hough transform for the automatic detection of cylinder parameters in point clouds. Careful analysis reveals that the existing method still has excessive space and time complexity or yields imprecise outcomes. The approach described here modifies the orientation estimation with an area-based adaptive method that utilizes a small accumulator to detect significant peaks in the Hough space in the presence of single or multiple cylinders in the point cloud data. After orientation estimation, the position and radius are estimated using an orthonormal coordinate system with a circle fitting algorithm. These modifications are tested with extensive sets of real point cloud data, and experimental results show that the presented approach minimizes the space and time complexity. After detection, the relationship between cylinders is reconstructed to form a continuous axis network by tracking cylinder parameters obtained from earlier steps. Using the axis network of cylinders obtained from point clouds, models of entire pipelines that include straight pipes, elbow joints, and T-junctions are determinately defined, and output data is reconstructed in Smart Plant 3D (SP3D). The presented results show that the proposed approach indeed improves the computational complexity by reducing the space and time, and yields methods that can be employed in the automation of 3D pipeline model reconstruction.
Article
Unlike robotics in the manufacturing industry, on-site construction robotics has to consider and address two unique challenges: 1) the rugged, evolving, and unstructured environment of typical work sites; and 2) the reversed spatial relationship between the product and the manipulator, i.e., the manipulator has to travel to and localize itself at the work face, rather than a partially complete product arriving at an anchored manipulator. The presented research designed and implemented algorithms that address these challenges and enable autonomous robotic assembly of freeform modular structures on construction sites. Building on the authors' previous work in computer-vision-based pose estimation, the designed algorithms enable a mobile robotic manipulator to: 1) autonomously identify and grasp prismatic building components (e.g., bricks, blocks) that are typically non-unique and arbitrarily stored on-site; and 2) assemble these components into pre-designed modular structures. The algorithms use a single camera and a visual marker-based metrology to rapidly establish local reference frames and to detect staged building components. Based on the design of the structure being assembled, the algorithms automatically determine the assembly sequence. Furthermore, if a 3D camera is mounted on the manipulator, 3D point clouds can be readily captured and registered into a same reference frame through our marker-based metrology and the manipulator's internal encoders, either after construction to facilitate as-built Building Information Model (BIM) generation, or during construction to document details of the progress. Implemented using a 7-axis KUKA KR100 robotic manipulator, the presented robotic system has successfully assembled various structures and created as-built 3D point cloud models autonomously, demonstrating the designed algorithms' effectiveness in autonomous on-site construction robotics applications.
Article
Rehabilitation of the existing building stock is a key measure for reaching the proposed reduction in energy consumption and CO2 emissions in all countries. Building Information Models stand as an optimal solution for works management and decision-making assessment, due to their capacity to coordinate all the information needed for the diagnosis of the building and the planning of the rehabilitation works. If these models are generated from laser scanning point clouds automatically textured with thermographic and RGB images, their capacities are exponentially increased, since also their visualization and not only the consultation of their data increases the information available from the building. Since laser scanning, infrared thermography and photography are techniques that acquire information of the object as-is, the resulting BIM includes information on the real condition of the building in the moment of inspection, consequently helping to a more efficient planning of the rehabilitation works, enabling the repair of the most severe faults. This paper proposes a methodology for the automatic generation of textured as-built models, starting with data acquisition and continuing with geometric and thermographic data processing.
Article
As-built models and drawings are essential documents used during the operations and maintenance (OM) of buildings for a variety of purposes including the management of facility spaces, equipment, and energy systems. These documents undergo continuous verification and updating procedures both immediately after construction during the initial handover process to reflect construction changes and during occupancy stage for the changes that occur throughout the building's lifespan. Current as-built verification and updating procedures involve largely time consuming on-site surveys, where measurements are taken and recorded manually. In an attempt to streamline this process, the paper investigates the advantages and limitations of using photogrammetric image processing to document and verify actual as-built conditions. A test bed of both the interior and exterior of a university building is used to compare the dimensions generated by automated image processing to dimensions gathered through the manual survey process currently employed by facilities management and strategies for improved accuracy are investigated. Both manual and image-based dimensions are then used to verify dimensions of an existing as-built Building Information Model (BIM). Finally, the potential of the image-based spatial data is assessed for accurately generating 3D models. 2011 Elsevier B.V. All Rights Reserved.
BIM-driven mission planning and navigation for automatic indoor construction progress detection using robotic ground platform
  • A Ibrahim
  • M Sabet
  • Golparvar-Fard
Ibrahim, A. Sabet, and M. Golparvar-Fard, "BIM-driven mission planning and navigation for automatic indoor construction progress detection using robotic ground platform," Proc. 2019 Eur. Conf. Comput. Constr., vol. 1, pp. 182-189, 2019.
Automated construction progress measurement using a 4D building information model and 3D data
  • C Kim
  • H Kim
  • Son
Kim, C. Kim, and H. Son, "Automated construction progress measurement using a 4D building information model and 3D data," Autom. Constr., 2013.