Key tools


COGITO Tool   Visualization Description

Work Order Definition and Monitoring tool (WODM)

The WODM is the tool used for defining work order templates, generating work orders and executing/monitoring the defined workflow. The definition of work order templates and generation of work orders are conducted using the tool’s UI, but a workflow can also be imported from a BPMN file. Work orders execution can be monitored through communication using the WOEA tool.

Work Order Execution Assistance tool (WOEA)


The Work Order Execution Assistance tool (WOEA) is an app for smart glasses supporting work order execution and reporting. The worker is guided via smart glasses through the work order, which enables immediate reporting of the results of the work. WOEA can work online or offline and provides hands-free operation support. The app also enables Remote Assistance through video call with remote annotations.

Digital Twin Platform (DTP)

The Digital Twin Platform (DTP) is the core of the entire toolchain. It supports both the necessary information management as well as the semantic (and pragmatic) alignment among the COGITO services and data pre-processing systems, while enabling interoperability with existing and emerging standards and data formats covering numerous domains.

Process Modelling and Simulation tool (PMS)

The Process Modelling and Simulation tool allows to define and simulate both the construction business process model as well as the operative workflow model.

This allows the user to identify process steps that are critical for the successful implementation of the project exposing optimization opportunities to minimize time and/or cost.

The combination with real-world data is supported by data mining algorithms and statistical methods and allows the calibration of the simulation model to the actual process occurring on the construction site.

Digital Twin visualisation with AR (DigiTAR)

DigiTAR is a software package for commercial AR head-mounted displays (HMDs) to help visualise and interact in situ with the output of the QC tools (location, type and severity of geometric and visual defects) and Safety tools (location and type of safety hazards and expected mitigation measures).

GeometricQC Tool (gQC)

The GeometricQC tool controls automatically the geometric quality of the executed works against the specified geometric dimensions and tolerances given as-built 3D data acquired onsite. The as-built 3D data is (dense laser scanned) point clouds acquired on site. The specified dimensions are obtained from the as-design BIM model (part of the DT) and the specified tolerances are obtained from ISO/CEN standards used by industry (and translated digitally to enable the automated process). The QC results are modelled and semantically linked to the BIM/DT model.


VisualQC (vQC)

The Visual QC tool automatically detects in colour images (visual spectrum) common visual defects of constructed/erected concrete components and their severity. The QC results are modelled and semantically linked to the BIM/DT model.

Digital (Visual) Command Centre (DCC)

The DCC renders the 3D BIM model, IoT data and other data and annotations generated by the QC, H&S and Workflow tools (available through the DT platform). The DCC will help the Project Manager to monitor through visualisation the progress, QC defects and H&S issues; The DCC is solution to visualise/navigate the DT data, but not edit it.

 Visual Data Pre-Processing Tool


The Visual Data Pre-processing component is in charge of performing pre-processing over visual and geometric inputs, delivering them in an enhanced form to related components (the Geometric and Visual QC tools) through DT Platform. First, as-built data is captured onsite from all available sources (AR goggles, multimodal UAV-mounted cameras, laser scanners). Then raw data is registered with structural and geometric details and different filters are afterwards implemented (contrast, brightness, cropping, rescaling etc.) to enhance the data quality. The new processed data is finally provided to the DT Platform for further exploitation by the relevant tools.

BlockChain & Smart Contracts

A technological innovation that is associated with the Blockchain Technology are the Smart Contracts (SCs). A SC is a piece of self-executing computer algorithm that automatically runs when predetermined conditions are met. They are typically used to automate, verify and enforce the execution of a contractual agreement such as an SLA without the involvement of an intermediary party. They are deployed and executed on a blockchain, and
their scope is to express in a tamper proof manner, the terms that are contained within a conventional contract. They are inseparable from the underlying Blockchain technology, that can be characterized as a base layer technology, and it is mainly concerned with issues such as distributed data storage, cryptographic security and reaching consensus between the nodes of the network.

BlockChain SLA Manager

The Blockchain SLA Manager has a local DB with already designed SLAs that include predefined rules and KPIs. WODM could fetch the SLAs through the SLA Manager in order to bind relevant stakeholders with the respective KPIs. Then WODM inform the SLA Manager with the results and SLA Managers saves the SLA with the respective Stakeholders on the local DB. BC can fetch the completed SLA with the assigned stakeholders and the respective configurations to initiate & instantiate the Smart Contract operation.


The SafeConAI tool identifies regions in the BIM model where (specific types of) hazards are, suggests and adds mitigation measures to the model. It uses as input a 4D BIM of as-planned construction project, consisting of n time steps, where each time step corresponds to stage of construction of the asset. Six types of hazards in four major categories are considered (slips, trips, fall from height, caught-in between, struck-bys, electrocutions), and one or two specific safety code entries are considered for each of these hazards (i.e. approximately 6-12 safety codes total).



The ProActiveSafety tool utilizes behavioural data of resources (equipment and personnel) on the construction site to avoid close-calls, accidents, and collateral damage. Location data from the Location Data Acquisition Tools is analysed to predict trajectories of resources and detect imminent close-calls and accidents by cross-checking those trajectories with potential hazards based on previous experiences/observations, rules, and the probability of hazards given the dynamic nature of the work environment.


Top 3 Construction Site Safety Tips for 2020 - Stonerise Construction

The VirtualSafety tool provides personalized construction safety education and training, focusing on the top 6 hazards: Slips/trips/falls from height, caught-in between, struck-by, and electrocution. The highly realistic VR provides easy-to-use, reliable safe learning environment and technology that assists advanced HSE decision making and provide personalized feedback in a safe learning environment

IoT Data Pre-processing Module

Office building design 3D model

The IoT Data Pre-processing Module enhances location tracking systems by unifying various technologies and techniques. Unlike commercial solutions tied to specific technologies, our middleware offers technology-agnostic fusion of RTLS methods, improving accuracy and avoiding vendor lock-in. With custom pre- and post-processing capabilities, it provides a unified API for seamless data ingestion, delivery, and monitoring.

COGITO - materialising the digitalisation benefits for the construction industry to unleash the untapped potential in productivity improvement and increased safety.



In accordance with the current EU Regulation on General Data Protection, in this Privacy Policy we inform you about:

  • Who is responsible for the processing of your data: Presentation and identification of the CONTROLLER
  • Acceptance of General Conditions and use of the website
  • What data we collect
  • How and where information is shared
  • Security of your data
  • Rights and access to information
  • Changes to the Privacy Policy
Read more
Copyright © COGITO 2021

This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 958310