FEDORA at the 8th Conference on Sustainable Mobility & Intelligent Transportation Systems

Assistant Professor Panayiotis Kolios from the University of Cyprus, a partner in the FEDORA project, participated in the 8th Conference on Sustainable Mobility & Intelligent Transportation Systems, held in Nicosia, Cyprus, on 29 and 30 October 2026.

During the conference, he presented FEDORA’s vision and objectives, explaining how the project aims to improve multimodal traffic management through better use of mobility data, advanced optimisation tools, and simulation technologies.

Particular attention was given to the Nicosia Pilot, one of FEDORA’s six demonstration sites across Europe. Led by the University of Cyprus, the pilot examines how Unmanned Aerial Vehicles (UAVs) could be integrated into urban transport networks. Its activities focus on identifying suitable locations for mobility hubs, connecting aerial and ground transport services, and using UAVs to monitor traffic conditions.

Through simulation and evaluation, the pilot will investigate whether these solutions can help reduce travel times and congestion while making urban transport networks more efficient and resilient.

The conference also gave FEDORA the opportunity to engage with public and private sector stakeholders working in sustainable mobility and intelligent transport.

Discussions with researchers, industry representatives, and transport professionals provided a chance to exchange experiences, explore potential collaborations, and introduce FEDORA’s work to a wider audience.

These exchanges helped bring greater attention to the project’s research and its potential applications in urban mobility, particularly the use of UAV technologies to support more coordinated and sustainable transport systems.

The FEDORA Blog #03 – Towards Fairer and Smarter Traffic Management: ETH Zurich’s Contributions to FEDORA

Who should get priority when our roads become congested?

Traditional traffic management focuses primarily on reducing delays and improving traffic flow. Yet not every journey has the same urgency, and treating all travellers equally does not necessarily lead to fair outcomes. Within the EU-funded FEDORA project, researchers at ETH Zurich are exploring how innovative incentive mechanisms and advanced simulation tools can make urban mobility more efficient, flexible and fair.

 

Rethinking Traffic Prioritisation and Incentives Through Artificial Currencies

One focus of ETH Zurich’s research is the development of new approaches to managing traffic demand and allocation of supply. Conventional congestion pricing can help regulate road use, but often faces public resistance due to fairness concerns. Could alternative approaches offer a better balance?

To investigate this question, ETH Zurich is exploring Karma mechanisms, which use non-monetary credits to coordinate how travellers share limited road capacity. By combining game theory with multi-agent reinforcement learning, researchers investigate how individual decisions and interactions can lead to more efficient and equitable outcomes.

Another promising concept is the Urban Priority Pass, which allows travellers with particularly urgent needs to receive priority at traffic signals. Using a Manhattan-inspired case study, ETH Zurich has investigated how such prioritisation can work and how markets could allocate priority according to different travellers’ needs. 

From Research Concepts to Open-Source Simulation

Developing innovative traffic management strategies is only the first step. How can we test them before introducing them into real cities?

To address this challenge, ETH Zurich has developed and released a first prototype of FEDORA’s modular simulation platform, publicly available on GitHub under the GNU General Public License.

The platform is designed to connect different traffic simulation environments with optimisation and control methods through reusable interfaces. Its initial prototype demonstrates the Priority Pass concept and includes a prototypic simulation demonstrator based on FEDORA’s Vienna pilot.

By making the framework modular and openly accessible, ETH Zurich aims to facilitate experimentation, reproducibility and collaboration across the FEDORA consortium and the wider research community.

 

Looking ahead

Together, these activities bring FEDORA closer to a future in which traffic management considers not only how efficiently vehicles move, but also how fairly limited transport resources are shared.

This entry is part of the FEDORA Blog series, where FEDORA partners share their insights from working in the project. This contribution has been provided by FEDORA partner ETH Zurich.

FEDORA Addresses Multimodal Traffic Governance at Tomorrow.Mobility World Congress 2026

On 4 November 2026, our FEDORA Project Coordinator, Dr. Roozbeh Mohammadi (ERTICO), moderated the session “When No One Is in Charge: Multimodal Traffic Governance” at the Tomorrow.Mobility World Congress in Barcelona.

 

The discussion addressed a challenge closely linked to FEDORA’s research: how transport authorities, operators and mobility providers can coordinate decisions when disruptions affect multiple transport networks, particularly when responsibilities are divided among different organisations.

The panel brought together three experts who examined the legal, operational and data-sharing aspects of multimodal transport governance.

Dr. Johanna (Yanna) Tzanidaki (AYA Consulting), member of FEDORA’s External Advisory Board (EAB), highlighted the limitations of existing legal frameworks. She explained that responsibilities are typically assigned to individual transport modes, while disruptions often affect entire networks. The growing use of artificial intelligence adds further complexity, particularly regarding accountability and decision-making authority.

Fellow panelists Dr. Aggelos Soteropoulos (AustriaTech) and Dimitris Tzanis (CERTH-HIT) contributed practical perspectives on multimodal transport governance. Dr. Soteropoulos shared examples from Austria, illustrating how cooperation between national, regional and municipal authorities supports coordinated responses to transport disruptions, while Dimitris Tzanis highlighted the need for formal agreements, clear responsibilities and sustainable funding models to enable effective data sharing beyond individual research projects.

The issues raised during the session reflect the challenges that FEDORA is working to address. As the project develops a federated ecosystem combining secure mobility data sharing, advanced optimisation services and simulation tools, it also examines how different transport stakeholders can cooperate and make coordinated decisions to put these solutions into practice.

This work is addressed through Task 2.4, Decision-Making Mental Model and Network Management Governance, which explores institutional responsibilities and decision-making processes to support more coordinated multimodal traffic management.

FEDORA’s six European pilots, supported by local Living Labs, provide different operational and institutional contexts for examining these challenges and identifying practical requirements.

FEDORA Presented at the 2026 ITS World Congress in Gangneung

The FEDORA project was featured at the 2026 ITS World Congress, held from 19 to 23 October in Gangneung, South Korea, as part of discussions on the future of AI-driven traffic management and cooperative transport systems.

Dr Johanna Tzanidaki, member of FEDORA’s External Advisory Board (EAB), presented the project during Special Interest Session SIS047, “Orchestrating Multi-modal Traffic in the CCAM Era through AI-Driven and Cooperative ITS”, organised and moderated by Dr Yiannis Karaseitanidis from the Institute of Communication and Computer Systems (ICCS).

The session explored how traffic management can move beyond separate, transport-specific systems towards integrated approaches that bring together automated and conventional vehicles, public transport, cycling, micromobility and shared mobility services.

In her presentation, “From managing traffic to conducting multi-modal mobility,” Dr Tzanidaki explained why managing different transport modes requires more than automation. Drawing on several European research projects, she examined how AI and data sharing can help transport stakeholders make informed decisions across complex mobility networks.

Based on Dr Tzanidaki’s presentation, FEDORA played a central role, with particular attention given to its approach to federating data, simulation and optimisation services.

Rather than bringing all mobility data into a single centralised system, FEDORA aims to enable transport authorities, operators and other stakeholders to collaborate while maintaining control over their own data. Through shared data catalogues, agreed access policies and governance arrangements, the project seeks to make information more accessible without compromising data sovereignty.

As Dr Tzanidaki explained, this approach addresses a practical challenge in multimodal traffic management, as organisations often need information from different sources but may be reluctant to share sensitive operational data. By establishing common governance rules, FEDORA aims to build trust between stakeholders and support more informed decisions.

The presentation also introduced FEDORA’s AI-supported decision making and simulation tools, including the Social Optimum Model for traffic signal optimisation in Vienna, agent-based simulation, event anticipation and vessel estimated time of arrival predictions. These solutions aim to help transport operators anticipate changing conditions, assess possible responses and improve the overall performance of mobility networks.

FEDORA’s approach is being tested and simulated across six pilot sites in Europe, covering different transport environments and mobility challenges, including traffic signals, logistics, transport demand, drones and inland waterways. These activities will help assess how the project’s solutions can be applied in different operational settings.

Same Place, Many Names: Resolving Data Ambiguity Across Languages

Teaching Data to Recognise “Gipuzkoa” and “Gipuzcoa” as the Same Place

This data-matching method was developed as part of FEDORA Deliverable D3.1 – Integrated Cross-Sectoral Data Space.

Anyone who has worked with real-world, multi-source data knows the problem: the same place, organisation or entity can appear under several different names. A Basque province might be spelled “Gipuzkoa” in one dataset and “Gipuzcoa” in another. A city might be abbreviated as “S. Cristóbal” in one source and written out fully as “San Cristóbal” in the next. And in genuinely multilingual regions, the same place might carry two entirely different names in two different languages — “Pamplona” in Spanish, “Iruña” in Basque — with no obvious textual overlap at all.

For a data space pulling in datasets from dozens of organisations and regions, this isn’t a cosmetic issue — it silently creates duplicate entries, breaks joins between datasets, and undermines analysis that depends on knowing two records actually refer to the same thing.

FEDORA’s solution combines three distinct matching techniques, each suited to a different kind of naming variation. The first, EditDistance, measures how many single-character changes — insertions, deletions or substitutions — it would take to turn one string into another, making it effective for catching typos and minor misspellings. The second, TF-IDF, breaks text into fragments and compares their statistical overlap, which makes it well suited to catching abbreviations. The third, and most sophisticated, uses text embeddings — numerical representations that capture the underlying meaning of a word rather than just its spelling — allowing the system to recognise that two completely different-looking strings, in two different languages, refer to the same concept.

Run together through the open-source PolyFuzz framework, these three models let the system automatically group name variants and flag likely duplicates for human review, rather than requiring every dataset to be manually reconciled by hand. In one worked example from the deliverable, the system correctly grouped “Hondarribia Gipuzkoa” with its misspelled variant “Hondarribia Gipuzcoa,” each match carrying a confidence score to support the final human check.

It’s a small step in a larger data-cleaning pipeline, but it’s foundational: before mobility data from six different European regions can be meaningfully compared, combined, or analysed together, it first has to agree on what to call the places it’s describing.

Learn more: The full methodology and worked examples are available in FEDORA Deliverable D3.1 – Integrated Cross-Sectoral Data Space, Section 5.1.1.

Filling the Gaps in Traffic Sensor Data

Reconstructing Missing Traffic Data with Tensor Mathematics

This tensor-based data imputation method was developed and tested as part of FEDORA Deliverable  D3.1 – Integrated Cross-Sectoral Data Space.

Traffic sensors fail. Induction loops drop out, communication links go down, and entire stretches of a city’s traffic network can go dark for hours, days, or longer. Yet the analytics, forecasting and traffic-management tools that cities rely on need continuous, complete data to work properly. The question FEDORA set out to answer is a practical one: when the data has holes in it, how do you reliably fill them back in?

The answer draws on a mathematical structure called a tensor — essentially a multi-dimensional generalisation of the tables and matrices most data tools use. Traffic data naturally has several dimensions at once: it varies by location, by day, and by time of day, and all of these dimensions are correlated — a traffic jam on one street tends to be linked to conditions nearby and to what happened at the same time yesterday. A technique known as low-rank tensor learning uses exactly this structure, treating the network’s spatial layout and its recurring temporal patterns as built-in clues that guide how missing values should be reconstructed.

Two specific methods were put to the test. One, called ST-LRTC, builds in the physical logic of how traffic actually flows through a network — respecting the continuity and daily rhythm of traffic and the way congestion propagates spatially between locations. The other, GLSKF, is tuned to capture both the big-picture, long-range patterns across the network and the short, sudden fluctuations — like a rush-hour spike — that a smoother model might miss.

Both were tested against real-world data: a month of vehicle-flow readings from 339 induction loops in a northern Spanish city, recorded every minute — over 44,000 data points per sensor location. The team then deliberately introduced six different patterns of missing data, from random single dropouts to entire sensors or entire days going silent, at severities ranging from a light 10% gap to a severe 90% blackout, and measured how accurately and how quickly each method could reconstruct the missing values.

The results give city operators and data teams something genuinely useful: an evidence-based comparison of how each method performs under different real-world failure scenarios, not just in theory. That matters because the type of data gap — a single faulty sensor versus a whole network outage — calls for different reconstruction strategies, and now there’s a documented basis for choosing between them.

It’s unglamorous, behind-the-scenes work, but it’s exactly the kind of engineering that keeps mobility data usable when the real world doesn’t cooperate — and it’s a foundation piece for any traffic-management or simulation tool built on top of incomplete, real-world sensor networks.

Learn more: The full methodology, algorithm details and results tables are available in FEDORA Deliverable  D3.1 – Integrated Cross-Sectoral Data Space, Section 5.3.2.1.

Towards Inclusive Real-Time Traffic Signal Control in Vienna

Modern urban traffic control systems can adjust signal timings in real time to keep traffic flowing efficiently. However, adaptive traffic signal control is still primarily designed to optimize conditions for motorized traffic, while the needs of pedestrians and cyclists are rarely considered explicitly. As a result, real-time detection of non-motorized traffic demand is often lacking. As cities pursue more sustainable, inclusive, and people-centered mobility solutions, this approach is becoming increasingly inadequate. 

The Vienna pilot within the FEDORA project represents an important step towards a more comprehensive and inclusive approach to traffic management. Led by ITS Vienna Region and implemented in collaboration with the Austrian Institute of Technology (AIT), the City of Vienna, and additional project partners, the pilot investigates how real-time information from all transport modes can be integrated into traffic signal control. 

A central challenge is the availability of reliable real-time data for vulnerable road users. To address this limitation, the pilot evaluates innovative camera-based sensing technologies capable of detecting and counting not only motor vehicles but also pedestrians and cyclists. By expanding the range of data available to traffic management systems, these sensors provide a significantly richer understanding of traffic conditions at intersections and along urban corridors. 

Image licensed under Creative Commons CC0 1.0 Universal (Public Domain Dedication).

 

Based on this enhanced situational awareness, FEDORA introduces a Social Optimum Model designed to support the allocation of green time across different transport modes. The model will be integrated into Vienna’s existing traffic signal control infrastructure and will enable signal plans to be adjusted in five-minute intervals. Rather than minimizing delays for a single transport mode, the Social Optimum Model aims to maximize overall societal benefit by considering the collective impacts of signal timing decisions across all road users. 

A central component of this approach is the definition of appropriate weighting factors for the various transport modes. Determining these weights is inherently complex, as priorities may vary according to location, time of day, traffic demand, or broader mobility policy objectives. The pilot therefore not only assesses the technical feasibility of real-time multimodal optimization but also explores how adaptive weighting strategies can reflect evolving urban mobility needs and policy goals. 

By combining advanced sensing technologies with innovative optimization methods, the Vienna pilot demonstrates how traffic management can evolve from vehicle-centered control to truly people-centered mobility management. Integrating the needs of pedestrians, cyclists and motorists into a single decision-making framework helps create a transport system that is not only more efficient, but also fairer, safer and better aligned with the goals of sustainable urban mobility.  

This entry is part of the FEDORA Blog series, where FEDORA partners share their insights from working in the project. This contribution has been provided by FEDORA partner ITS Vienna.

The FEDORA Data Space: A New Way to Share Mobility Data Without Giving Up Control

A Data Space, Not a Data Silo: How FEDORA Rethinks Mobility Data Sharing

The FEDORA Data Space was developed as part of FEDORA Deliverable D3.1 – Integrated Cross-Sectoral Data Space.

Sharing mobility data across organisations has traditionally meant one of two unsatisfying choices: pool everything into a single central repository and lose control over it, or keep everything locked in separate silos and lose the ability to collaborate. Neither works well for a sector like mobility, where traffic authorities, transport operators, research institutes and cities all hold pieces of the puzzle — but none of them wants to hand their data over to someone else’s server.

The FEDORA Data Space is built around a different idea: a “data space.” Rather than a central database, it’s an interoperable framework — common governance rules, shared standards, and a set of enabling services — that lets organisations exchange data directly with each other while each one keeps full control, or sovereignty, over its own data. Data physically stays with its owner until a trusted partner requests it and agrees to the owner’s usage terms; nothing is copied into a central pool by default.

Architecturally, FEDORA’s Data Space follows the International Data Spaces Reference Architecture Model (IDS-RAM), chosen for its mature, connector-based approach to secure exchange and its growing adoption across other European mobility data space initiatives. In practice, this means every participating organisation runs its own “Dataspace Connector” — a piece of software that handles publishing data offers, negotiating access, and transferring data securely and directly to another participant’s connector. No central authority ever sits in the middle of an actual data transfer.

 

Interaction of Data Space with other FEDORA Spaces. The Data Space provides input data for the Network Management Services Space and Simulation Space.
 

Around this core, FEDORA adds four components that work together: a Public Catalogue so anyone can discover what data exists without needing to know who holds it; a Smart Data Contracts Module, a blockchain-based ledger that records every data transaction in a tamper-proof, verifiable way; and a Mobility Data Harmonisation, Enrichment and Synthetisation Engine, which transforms raw, inconsistent datasets from different sources into a common, higher-quality format. Only the catalogue is centrally hosted — everything involving the actual movement of data is deliberately decentralised, once per participant.

The result is a system designed around seven concrete objectives: 

  • a public entry point for discovery, 
  • secure and encrypted data transfer, 
  • common data formats, 
  • interoperability with other data spaces, 
  • robust identity and access management, 
  • machine-readable contracts with full traceability, 
  • built-in data quality improvement.

The FEDORA Data Space is currently being rolled out across FEDORA’s project partners, ahead of a wider pilot phase across six European demonstration sites — from Vienna to Nicosia — each testing how the data space performs in real, operational conditions.

It’s infrastructure most people will never see directly — but it’s what will let a transport authority in one country responsibly share real, useful mobility data with a research team in another, without either side losing control of what they own

Breaking the Language Barrier in Mobility Data Catalogues

How the FEDORA Catalogue Learned to Read Every Language in Europe

The auto-translation pipeline described here was developed as part of FEDORA Deliverable D3.1 – Integrated Cross-Sectoral Data Space.

Open mobility data in Europe is scattered across hundreds of national and regional portals — and each one speaks its own language. A traffic dataset published by Austria’s data.gv.at portal might describe itself entirely in German; a French or Spanish regional portal will do the same in its own language. For anyone trying to search across all of them at once, that’s a problem: a catalogue that mixes languages becomes fragmented and hard to navigate, and keyword search quietly breaks down.

FEDORA’s answer is a purpose-built translation layer sitting inside its data catalogue, which is built on the open-source CKAN platform. Whenever a dataset is harvested or updated, a custom plugin automatically intercepts the incoming metadata — the title, description and tags — and routes it through a translation pipeline before it is indexed for search.

What makes the approach notable is how it translates. Rather than relying on a commercial cloud translation API, the plugin connects to a self-hosted instance of LibreTranslate, an open-source machine translation engine. Running it locally serves three purposes at once: it keeps sensitive metadata inside FEDORA’s own infrastructure, removes dependence on external services, and avoids hitting rate limits when harvesting large batches of datasets at once — a real risk when pulling in metadata from dozens of sources in a single run.

The translation itself is non-destructive. The English version is written into the catalogue’s main searchable fields, so every dataset becomes discoverable through a single, unified English-language search. But the original text isn’t discarded — it’s preserved alongside the translation, so a dataset originally published in Basque, German or Danish remains fully readable and searchable in its native language too. Users get both: one consistent search experience, and the original context intact underneath it.

The team has also been transparent about the pipeline’s limits. Based on observational checks, the underlying language-detection component performs at around 90% accuracy, with confidence dropping — and translations sometimes being skipped — for very short text strings. Built-in fallback logic ensures the system displays the original text rather than failing outright when something goes wrong, and edge cases are caught through manual review of the catalogue.

Looking ahead, the team is exploring the integration of a locally hosted large language model to strengthen the pipeline further — either to resolve the low-confidence detection cases or to replace the current translation engine altogether — all while keeping the same commitment to data sovereignty that shaped the original design.

It’s a small piece of infrastructure with an outsized effect: it’s what allows a researcher in Vienna, an engineer in Reggio Emilia, and a transport authority in Nicosia to search the same catalogue and actually find each other’s data.

Learn more: Read the full technical description in FEDORA Deliverable D3.1 – Integrated Cross-Sectoral Data Space, Section 4.3.

Inside the FEDORA Public Catalogue: One Front Door to Europe’s Mobility Data

One Search Box for Hundreds of Mobility Data Sources

The FEDORA Public Catalogue was developed as part of FEDORA Deliverable  D3.1 – Integrated Cross-Sectoral Data Space.

Europe’s mobility data landscape is vast and fragmented: government open-data portals, transport authorities, research institutes, private operators and geospatial agencies each publish datasets through their own systems, in their own formats, and often in their own language. For anyone trying to find relevant traffic, transit or logistics data, the practical starting point is usually a frustrating one — checking dozens of separate websites one by one.

The FEDORA Public Catalogue is designed to remove that friction. Built on CKAN, a widely used open-source data cataloguing platform, it acts as a single, publicly accessible entry point that lists what data is available across a wide range of external sources — without needing to centralise the data itself. Behind that simple front door is a genuinely substantial piece of integration engineering.

Datasets can be added manually, but the catalogue’s real strength is automated harvesting: a set of CKAN-based extensions that periodically pull in metadata from external portals, on a schedule ranging from continuous updates to monthly refreshes. To make that possible across such a fragmented landscape, the catalogue supports a whole family of metadata standards and protocols — from DCAT and DCAT-AP (including national variants used in Germany, Italy, Denmark, Spain, Norway, Sweden, Belgium and the Czech Republic) to the OGC standards used by geo-data portals, and APIs used by platforms like ArcGIS, Socrata and DKAN. Where a source doesn’t fit any of these standard patterns — as was the case with data.gv.at, Austria’s national open data portal — the team built a dedicated custom harvesting plugin to bridge the gap.

Managing dozens of these harvesting connections individually through a web interface doesn’t scale, so the team also built a command-line tool that lets administrators create, update or remove entire batches of harvesting sources from a single CSV file — turning what would be a slow, error-prone manual process into a single, auditable command.

Once data is in the catalogue, finding it is designed to be flexible: a simple keyword search for casual users, and an advanced Solr-powered search syntax for those who need it — supporting field-specific queries, wildcards, proximity matching, and fuzzy matching that tolerates typos and spelling variants. Results can be filtered by organisation, group, tag, format or licence, and individual datasets can include built-in visualisations — maps, charts, tables, or direct previews — depending on the type of data attached.

The catalogue is intentionally the visible tip of a larger system: behind the search box sits the harvesting infrastructure, the automatic translation pipeline, and the data quality tools that keep what’s listed trustworthy. Its job is deceptively simple — make it possible to type one query and find relevant mobility data, wherever in Europe it happens to live.

Learn more: The full technical description of the catalogue’s harvesting, search and visualisation capabilities is available in FEDORA Deliverable D3.1 – Integrated Cross-Sectoral Data Space, Chapter 4.