• BRRC - Connected & autonomous vehicles &road safety: infrastructure & otherelements

• HEU InCITIES (CSA) - Trailblazing Inclusive, Sustainable and Resilient Cities.

• PODS4RAIL - concept for Pods and Pod-Carriers on Railway.
  

• IMPROVA - Injury mitigation to promote vision-zero achievement

• SPINE - Smart Public Transport Initiatives for Climate -neutral cities in europe

• ADMIRAL - Advanced Multimodal Marketplace for Low Emission and Low Energy Transportation
  

• OptiMo - Optimising driver behaviour for safe, green and energy efficient mobility

• Utilizing Recycled Materials in Pavements for Increased Circularity and Climate Neutrality

• SENATOR - Smart Network Operator Platform enabling Shared, Integrated and more Sustainable Urban Freight Logistics

• CCAM - CulturalRoad, Cultural, regional and societal factors to overcome barriers to connected, cooperative and automated mobility deployment

• Developments in the field of innovative binders for asphalt mixtures

• Developments in the field of innovative binders for asphalt mixtures

• ERAPave - A Tool for Analysis and Design of Pavement Structures

• ERAPave - A Tool for Analysis and Design of Pavement Structures

• Academics4rail - Building a community of railway scientific researchers and academia for EU-Rail and enabling a network of PhDs (academia teaming with industry).

• Academics4rail, EU-Rail, PhD, academic, railway research

• PIoneer+ Co-creation of European universities with their local ecosystem

• PIoneer+ - Co-creation of European universities with their local ecosystem

• Utilizing Recycled Materials in Pavements for Increased Circularity and Climate Neutrality

• Evaluating the Impacts of Different Vehicle Configurations on Pavement Performance

• CapaCITIES (CSA) - Building Capacities for the Climate Neutral and Smart Cities Mission.

• ESEP4FREIGHT - European Shift Enabler Portal for Freight

• HERON - Improved Robotic Platform to perform Maintenance and Upgrading Roadworks

• MetaCCAZE - Flexible adapted MetaInnovations, use case, collaborative business and governance models to accelerate shared Zero Emission mobility for passengers and freight.

• INFRACOMS - Innovative & Future-proof Road Asset Condition Monitoring Systems

• Gaia-x - Mobility Data Spaces Landscape, block chain; data privacy
  

• SHOW - Shared Automation Operating Models for Worldwide Adoption
  

• RAILS - Recommendations and Roadmaps Towards Intelligent Railways"

DEVELOPING A NEW ​KIND OF MOBILITY ​SYSTEM.

Emissions-aware marketplace for ​multimodal logistics services

Data for Scope 3 emissions reporting

Selection of most emissions-efficient ​transportation provider

Developer Portal connecting IT ​developers and integrators

20 partners from 9 EU countries

4 pilots / Portugal-Spain, Slovenia-Croatia, Lithuania, Finland ​3 years / 01/05/2023-30/04/2026

7.3M€ EU Funding

Our three strategic goals

Goal 1: Promote talent development and circulation

• Objective 1: Foster a European approach to urban life and urban transition based on

cooperation, exchange and talent mobility in a spirit of equality, diversity and

inclusion.

• Objective 2: Offer tailored support for the development of leadership and human

capital to broaden mindsets and enhance skills to address societal transitions in

cities.

Goal 2: Foster challenge-based knowledge creation and transmission

• Objective 3: Stimulate, develop and share challenge-based learning approaches in

an interdisciplinary perspective tackling urban transition

• Objective 4: Facilitate and nourish society-oriented research and innovation that

tackle urban transitions.

• Objective 5: Co-create and disseminate solutions with urban, academic, economic,

social and political ecosystems to address common challenges.

Goal 3: Transform incentives and institutional models

• Objective 6: Build an efficient and sustainable governance and administration model

for the Alliance.

• Objective 7: Orchestrate and embed inter-institutional learning and collaboration to

enable the long-term alignment of strategies and institutional pathways.

• Objective 8: Share results and experiences to promote SDG11 and inspire the

renewal of the European higher education and research landscape.

European AgricultureData Space

European Cultural

Heritage Data Space

European Energy Data

Space

European Finance Data

Space

European Green Deal

Data Space

European Health Data

Space

European Language Data

Space

European Manufacturing

Data Space

European Media Data

Space

European Public

Administration Data Space

European Research and

Innovation Data Space

European Skills Data

Space

European TourismData

Space

Data collections of ​European bodies ​(e.g. RINF)

National Mobility ​Data Spaces ​(e.g. NAP)

SectorData ​Spaces

(e.g. IATA)

Data Spaces following the Gaia-X principles

Base-X

…

other ​Data ​Spaces

Base-X

…

Roadmaps for AI Integration in the Rail Sector: the RAILS project and beyond

123,45,6,732211811

L. De Donato, R. Tang, N. Bešinović

, F. Flammini

, R.M.P. Goverde, Z. Lin, R. Liu, S. Marrone, E. Napoletano, R. Nardone, S. Santini, V. Vittorini

1. University of Naples Federico II, Naples, Italy | 2. University of Leeds, Leeds, UK | 3. Delft University of Technology, Delft, Netherlands 4. Technical University of Dresden, Dresden, Germany | 5. University of Applied Sciences and Arts of Southern Switzerland, Lugano, Switzerland ​6. MälardalenUniversity, Eskilstuna, Sweden | 7. Linnaeus University, Växjö, Sweden | 8. University of Naples “Parthenope”, Naples, Italy

Introduction

The overall objective of the RAILS research project has been to ​investigate the potential and limitations of emerging artificial

intelligence and machine learning paradigms in the rail sector, in order ​tocontribute to roadmaps for future research in next generation ​signallingsystems, operational intelligence, and network management. ​RAILS has produced knowledge, groundbreaking research and ​experimental proof-of-concepts for the adoption of AI in rail automation, ​predictive maintenance and defect detection, traffic planning and ​capacity optimization. To that aim, RAILS has combined AI paradigms ​with the Internet of Things (IoT) and big data analytics. The results of ​RAILS are expected to stimulate innovation and research to improve

reliability, safety, security, and performance in intelligent railways, also

considering emerging threats, safety and certification issues that must

be addressed in the context of trustworthy and explainable AI.

WP1: State-of-the-Art of AI in the Railway Transport

DISCOVER

WP6: Project Management

WP3

AI for Predictive ​Maintenance ​and Defect ​Detection

WP2

AI for Rail ​Safety and ​Automation

WP4

AI for Traffic ​Planning and ​Management

ASSESS

WP5: Dissemination and Future Roadmaps

LEARN

Project partners

The RAILS Roadmapping Process

This project has received funding from the Shift2Rail Joint Undertaking ​under the European Union’s Horizon 2020 research and innovation ​programme under grant agreement n. 881782 Rails. The JU receives ​support from the European Union’s Horizon 2020 research and innovation ​program and the Shift2Rail JU members other than the Union.

The information and views set out in this document are those of the

author(s) and do not necessarily reflect the official opinion of Shift2Rail

Joint Undertaking. The JU does not guarantee the accuracy of the data

included in this document. Neither the JU nor any person acting on the

JU’s behalf may be held responsible for the use which may be made of the

information contained therein.

FrancescoFlammini

H2020 Project HERON

Improved Robotic Platform to perform Maintenance and Upgrading Roadworks

G. Andreoli(UGE), F. Schmidt (UGE), I. Katsamenis(ICCS), N. Bakalos(ICCS), Helen Oleynikova(ETHZ), Miquel ​Cantero(ROB), Carlos Martín-PortuguésMontoliu(ACCI), Yannis Handanos(OLO), Elena Avatangelou(INAC), ​Nikolaos Frangakis(IKH), Christos Polykretis(STWS), DimitriosBilionis(RISA), MarusaBenkic(CORTE), Dimitris ​Tsarpalis (RG)

Project HERON: scientific and technical content

Transpolis and RUPs testing

Transpolis (France) is an 80-hectare testing facility established by a consortium of 5 entities, ​including Gustave Eiffel University, officially opened in 2019 (fig. 3). Primarly, it serves as a ​controlled environment for testing autonomous vehicles, thanks to several kilometers of roadways ​(notably 12 km in the “city area”) and all reinforced concrete buildings. The facility is equipped ​with various types of Vehicle-to-Everthing (V2X) and Vehicle-to-Infrastructure (V2I) ​communication capabilities, alongside camera surveillance.

In terms of telecommunications, Transpolis features over 320 km of optical fiber, providing access ​to an Ethernet network accros most areas of the facility. An open LoRa network spans the whole ​proving ground, enabling the installation and use of a wide array of Internet of Things (IoT) ​sensors. Additionally, the site is covered by a 5G network coming from an antenna located ​centrally within the tracks. Energy needs are met by a private electrical distribution network, ​ensuring power supply throughout the facility, particularly in the “city area”.

Transpolisserves as the proving ground for various use cases, including:

• ​• ​•

Detection and repair of road markings;

Detection and repair of cracks in reinforced concrete;

Continuous V2I communication, between the vehicle and road side units.

Figure 3 : Aerial view of Transpolissite

In the frame of urban planning for the future city, the concept of Removable Urban Pavement (RUP) is studied, using ​hexagonal prefabricated concrete slabs. These removable slabs facilitate quick access to networks, enhance the ​longevity of road surface properties and are recyclable. Their prefabrication allows for the incorporation of additional ​integrated functions such as various textures, porous, noise-reducing or pollution-absorbing surface, as well as the ​integration of sensors, among others). Therefore, regular inspection of the RUPs for potential anomalies and timely ​repairs is ofutmost importance

Two structural working of these RUP are possible:

• The independent slabs with an easy installation and removal. Large and heavy (700kg) to ensure flapping with ​elastomer seal at theconnections.AsiteusingindependentRUPsis availableinSaint-Aubin/France.

• The interconnected slabs with aneasyinstallation and removal following a given path. Smaller and lightweighter ​(<300 kg) with sanded seal at the connections (fig. 4). Two sites equipped with interconnected slabs are available in ​Nantes/France : In city center a 12mx 7msite and at the pavement fatigue carrousel at the Nantes campus of Gustave ​Eiffel University (2m x 8m site) (fig. 5).

Traditionally, the RUP slabs are non-porous, allowing for installation or removal using suction methods. However, ​recent advancements have introduced porous slabs to enhance structural durability. In such instances, manual arms ​equippedwith clamps have beendevised for handlingtheseporousslabs.

Figure 4 : Installation of RUP test structure at Gustave Eiffel University

One of the current objectives is to enumerate from Deep Learning algorithms ​based on image captures:

• ​•

Hexagonal, half-edge and quarter slabs; ​Pavingstonessurroundingthestructure.

• ​• ​• ​•

Gaps between the slabs;

Differential settlements between the slabs; ​Spallingoftheslabs;

Rattling/flappingof theslabs.

Figure 5 : Aerial view of Nantes Gustave Eiffel University RUPs test structure with slabs identification ​(deep learning method) and subsurface characterization by Ground Penetrating Radar (GPR)

Use cases

Nowadays, the rapid and effective inspection, evaluation, maintenance and safe management of existing road infrastructures including highways and the overall road infrastructure network transport ​present a significant challenge for many operators and engineers.

The HERON system relies on enhanced intelligent control of a robotic vehicle (fig.

1), improved computer vision, Artificial Intelligence/Machine Learning methods,

along with appropriate sensors, decision-making algorithms, and Augmented Reality

(AR) components to carry out corrective and preventive maintenance tasks.

As a result, HERON enables a modular design of system operations, enhancing its

versatility and adaptability to various transportation infrastructures. This approach

helps in reducing fatal accidents, maintenance expenses, and traffic disruptions,

thereby enhancing network capacity and efficiency.

By using advanced data from various sources like Unmanned Ground Vehicle

(UGV) and Unmanned Aerial Vehicle (UAV) for surveillance, and established

methods from existing research and industry, the automated system can handle

emergency maintenance tasks when necessary. HERON is working on developing

and validating a new robotic platform designed for these tasks to be done safely,

quickly,reliably,andwithflexibility(fig.2).Figure 1 : From traditional tools to robotic sensors and actuators

The HERON system consists of:

• Autonomousgroundroboticvehiclecomplemented byautonomousdronesfor coordination;

• Diverse robotic equipment, including sensors and actuators (tools for cutting and filling, placing and ​compacting surface materials, installing modular components, laser scanners for 3D mapping) embedded on ​the main vehicle;

• Installation of a sensing interface both to the robotic platform and within the infastructure to enable ​enhanced monitoring (situational awareness) of structural, functional and road surface conditions, as well as ​markings;

• Controlsoftware linkingthesensinginterface with theroboticequipment for actuation;

• Augmented Reality (AR) visualization tools facilitating detailed observation of surface defects and ​marking during surveys by the robotic system;

• Implementation of Artificial Intelligence/AI-based toolkits serving a dual purpose: a) efficiently ​coordinating road maintenance/upgrading workflows, and b) intelligently processing distributed data from ​vehicle and infrastructure sensors to ensure safe operations without disrupting routine activities or traffic ​flows;

•Integrationof all data intoan advancedvisualizationuser interface to support decision-making; ​•Communication modules enabling Vehicle-to-Infrastructure/Everything data exchange for predictive ​maintenance and enhanced user safety.

Figure 2 : HERON’s concept

Conclusion

HERON proposes an unified automated system along with an independent ground robotic vehicle designed for maintaining road infrastructures complemented by autonomous drones for ​coordination with exchange infrastructure data to enhance user safety. An extensive database is currently being constructed to enhance potential anomaly detection performance. Deep learning ​detectionalgorithms are alreadyshowingpromisingresults.

Bibliography

Katsamenis I. et al., Robotic Maintenance of Road Infrastructures: The HERON Project, Proceedings of the 15th Internationale Conference on Pervasive Technologies Related

toAssistive Environments(PETRA’22),pp-628-635,Corfu, Greece, 2022.

Andreoli G. et al., Subsurface characterization of Removable Urban Pavements (RUP) using Ground Penetrating Radar (GPR), 20th International Conference on Ground

PenetratingRadar (GPR 2024),Jun2024,Changchun,China(underreview).

Research Village Associations Stand presentations programme

Exhibition Booth #6 Main Hall