| HARMONI – HAZARD ASSESSMENT AND RISK MANAGEMENT OF NATECH EMERGENCIES WITH CROSS-COLLABORATION OPPORTUNITIES | HARMONI addresses the growing complexity of NaTech disasters by developing a comprehensive platform to enhance prevention, monitoring, and response for critical infrastructures (CIs). The platform will integrate existing data and lessons learned into a unified Knowledge Graph (KG) and the information gathered will serve for the creation of a database of Standard Operating Procedures (SOPs). The tools that will be offered by HARMONI are A) PREVENTION: Digital Twins (DTs) for CIs, enabling the modeling of cascading effects and worst-case scenarios to inform prevention and mitigation strategies. B) MONITORING: HARMONI combines advanced remote sensing algorithms, UAV-SAR imaging, and on-site data collection, to deliver real-time monitoring and early warnings of vulnerabilities, while C) ACTION/RESPONSE: will be guaranteed by its Hybrid NaTech Decision Assessment (HNDA) that integrates Federated Learning, human expertise, and SSH insights to recommend actionable SOPs tailored to evolving disaster scenarios. This ensures a holistic decision-making process, aligning technical capabilities with social and ethical considerations. The project includes six use cases, showcasing its technologies in diverse NaTech scenarios, including a cross-border collaboration use case to validate interoperability and scalability with existing systems. By fostering cooperation with ESA FutureEO initiatives and EU frameworks, HARMONI supports knowledge sharing and alignment with international standards. Ultimately, HARMONI aims to strengthen resilience, reduce disaster impacts, and provide innovative, interoperable solutions to NaTech crises, supporting safer, more sustainable management practices across Europe. |
|
DMaaST – INNOVATIVE MODELLING AND ASSESSMENT CAPABILITIES THROUGHT MAAS FOR MANUFACTURING ECOSYSTEM RESILIENCY (https://dmaast.eu) |
DMaaST aims to enhance the manufacturing ecosystem's resiliency and capability of self-adaptation in response to external events. It is achieved through a Smart Manufacturing Platform comprising 4 layers: The data layer establishes a foundation for mapping manufacturing ecosystem information using ontologies and decentralized knowledge graph (DKG), ensuring a trusted cross-organization real-time data integration. Next, a layer with a two-level cognitive digital twin is created, with the low-level DT modelling two use cases' manufacturing services production line; and the high-level DT modelling the main stages of use-cases’ sectors value chains. The resulting DTs will use human expertise-knowledge, data-driven algorithms and physical modelling to provide a reliable and robust DT of the manufacturing ecosystem. The next layer employs the data and modelling layer's information to present a multi-objective distributed decision support system (MO-DDSS) algorithm combining multi-objective techniques and the latest trends in Federated Deep Learning. This makes DTs actionable models and provides the necessary information to make optimal production decisions. The fourth layer focuses on presenting the information in a user-friendly manner with timely scoreboards. Additionally, a dedicated module will assess the production's circularity and sustainability and considering products traceability through the EU-DPP. Therefore, the sustainability and remanufacturing opportunities of the production process will be improved. The project ensures scalability, providing information for replicating and trying new manufacturing processes thanks to the manufacturing services digital warehouse while assessing risks and opportunities for improvement. DMaaST innovations enable the manufacturing ecosystem to adopt the Manufacturing as a Service concept by smoothly evolving all the technologies from a TRL3 to a consolidated TRL6 in 2 use cases in key sectors, aeronautics and electronics. |
| StressLens: Integrated XR & AI System for Industrial Stress and Safety | StressLens project develops an AI-based system using EDA and eye-tracking data via XR headsets to monitor worker stress and deliver real-time safety alerts. It focuses on personalized stress detection, prevention of cognitive overload, and real-time feedback. It includes multimodal sensing, adaptive model training (e.g., CNN, SVM), and validation in XR-based industrial testbeds. Aiming for over 90% accuracy in stress prediction, it enhances safety and worker well-being. It provides strong EU added value by enabling safer, more efficient workplaces through scalable, ethical, and open-source AI. Aligned with ENFIELD goals, it advances human-centric, trustworthy, and adaptive AI via GDPR-compliant, individualized monitoring and dynamic alerts. |
| Manufacturing Intelligent Digital Interactive Assistant (MINDIA) | The proposed MINDIA (Manufacturing Intelligent Digital Assistant) experiment aims to develop and validate a digital assistant that improves efficiency and communication in the plastics manufacturing sector, focusing on Cromic Plastik’s production processes. Currently, operators rely on manual monitoring and routine checks, which leads to delayed responses, increased waste, and limited coordination between production and logistics. MINDIA will be developed as an OVOS skill, deployed through the WASABI Docker Compose stack, and distributed via the WASABI White Label Shop to ensure reuse by other SMEs. The assistant will integrate real-time process data, voice-based interaction, and augmented reality (AR) visualization to support daily operations. Operators will access it through the COALA App on mobile devices or AR glasses, receiving spoken feedback, visual step-by-step instructions, and document-based guidance through DocuBoT. Using this setup, MINDIA will help users interpret process deviations, identify possible causes of inefficiencies, and improve communication during changeovers and scrap management. Technologically, MINDIA connects machine and sensor data with structured operational knowledge and contextual guidance, turning scattered experience and documents into an accessible, intelligent interface. This integration supports faster decision-making, smoother coordination between production and logistics, and reduced material waste. |
|
Model-based engineering of Digital Twins for early verification and validation of Industrial Systems (MATISSE), Proposal number: 101140216-2, Call: HORIZON-KDT-JU-2023-2-RIA, 2024 – 2027. |
Thanks to the advances in information technology, modern industrial systems are becoming increasingly intelligent and autonomous; thus their requirements for, e.g., correctness, availability, traceability and reliability, are also increasing. Monitoring, analysis and diagnosis of such industrial systems became pivotal and fueled the development of virtualization and simulation solutions such as digital twins. https://matisse-kdt.eu |
|
Advanced Technologies Platform for Sustainable Cities, Proposal Number: 22AG040, Call:1004- Mükemmeliyet Merkezi Destek Programı, 19 December 2022 – 19 December 2025 |
Developing software quality assurance, verification and validation tools for Fleet Management System components and endpoints is critical for sustainable city technology. In this context, verification and validation workflows, methods and tools will be developed for the artificial intelligence algorithms to be developed within the scope of the project together with mutation-based tests or model-based formal verification approaches, and demonstrations will be carried out by performing tests and applications on the system. https://1004.tubitak.gov.tr/tr/node/95 |
|
Multiplayer Collaborative Robotics Maintenance Training Platform in Extended Reality (XR4MCR), Mixed reality ecosystem for teaching robotics in manufacturing (MASTER-XR) Open Call 1, 2024-2025 |
The XR4MCR project utilizes Extended Reality (XR) technology to develop a comprehensive, multi-user virtual training solution for industrial robot maintenance, which will be tested in a real use case environment that simulates actual industrial conditions. Addressing the TC-9 challenge, it features an intuitive interface that reduces setup time and costs, offers scalable and flexible options, and prepares trainees for real-world industrial tasks with its multi-user capabilities. Anticipated outcomes include enhanced educational effectiveness and reduced training costs, aligning with MASTER-XR's objectives to simplify module creation without coding, thereby making robotics knowledge accessible and practically applicable. https://www.master-xr.eu/oc-project/xr4mcr/ |
|
Excellence in Extended Reality for Human-Robot Collaboration (XR4HRC), Extended Reality for Learning in New Dimensions (XR2Learn) Open Call 1, 2024 |
The XR4HRC Project focuses on creating immersive XR education and training solutions tailored for individuals entering roles involving robotic quality control systems in industrial settings. Our goal is to offer a simulated factory environment enriched with realistic robotic presence and comprehensive training in occupational health and safety procedures. Additionally, we incorporate remote examination and evaluation methods to enhance the learning experience. By aligning with XR2Learn, XR4HRC is dedicated to equipping today’s learners with tomorrow’s technology, preparing them to excel as future professionals in their field. https://xr2learn.eu/meet-the-winners-of-the-xr2learn-open-call-1-xr4hrc-project/ |
| OPtimize Electric Vehicle Autonomy (OPEVA), Proposal number: 101097267, Call: HORIZON-KDT-JU-2021-2-RIA, 1 January 2023 – 31 December 2025. |
The OPEVA project will study all actors that will create a modern "mobility experience", taking into account sustainability and resource optimisation in the transition to fossil fuel-free vehicles. It targets outputs in six critical technology areas in the ecosystem and four areas for socio-economic compatibility in order to accelerate the deployment of electric vehicles (EVs). The first technology area (TD1) in the OPEVA project targets innovation in collecting information not only from the battery, but also from other on-board sensors, driver behaviour and the vehicle itself, in order to create a performance and consumption model tailored to the individual vehicle and its driver. The second technology area (TD2) aims to optimise the individual driving segment using off-vehicle data such as road condition, weather, charging station location and occupancy, etc. collected from back-end systems. The third technology area (TD3) will also address the challenges related to the communication between the vehicle and the infrastructure to collect data from back-end systems. It also targets innovation in the use of charging stations and related applications (TD4). It also aims to better understand what the battery and its constituent cells actually do during real-world use for an improved battery management system (TD5). Finally, TD6 also covers driver-oriented human factors to optimise the use of electric vehicles. On the other hand, the OPEVA methods will consider economic factors (NTD1), legal and ethical aspects (N-TD2), human development related to EVs (N-TD3) and societal and environmental factors (NTD4). Studies will be carried out within the scope of the project in order to increase the acceptance and awareness of these developments in the society. https://opeva.eu |
| Verification and Validation of Automated Systems' Safety and Security (Valu3s), Proposal number: 876852-2, Call: H2020-ECSEL-2019-2-RIA, 1 May 2020 – 1 May 2023. |
Manufacturers of automated systems and their components have been allocating an enormous amount of time and effort in R&D activities. This effort translates into an overhead on the V&V (verification and validation) process making it time-consuming and costly. The ECSEL JU project VALU3S aims to evaluate the state-of-the-art V&V methods and tools, and design a multi-domain framework to create a clear structure around the components and elements needed to conduct the V&V process. The main expected benefit of the framework is to reduce time and cost needed to verify and validate automated systems with respect to safety, cyber-security, and privacy requirements. This is done through identification and classification of evaluation methods, tools, environments and concepts for V&V of automated systems with respect to the mentioned requirements. To this end, VALU3S brings together a consortium with partners from 10 different countries, amounting to a mix of 25 industrial partners, 6 leading research institutes, and 10 universities to reach the project goal. |
|
Prognostics and Health Management Tool for ROS, funded by EU ROSin Project, 2018-2020 |
PHM tool is model-based user interface which the user creates his system using various mechanical and electrical equipment’s, but can also calculates the reliability, failure rate and probability of task completion (POTC) of the created system. In addition, the PHM Tool offers the user the ability to formulate his own components and add them to the system. PHM Tool can also work with a real robot. Data from the sensors on the real robot are published via ROS topics. By subscribing to these topics in the PHM Tool, the system’s failure rate, reliability and POTC values are calculated together with the data which is obtained from the sensors. https://github.com/ESOGU-SRLAB/phm_tools-release https://github.com/ESOGU-SRLAB/phm_tools https://www.rosin-project.eu/ftp/prognostics-and-health-management-tool-for-ros |
Projects
Last Updated At: 1/8/2026