The shift to more sustainable mobility systems is one of the major priorities to accomplish the goals established by the European Green Deal to make Europe the first climate neutral continent by 2050. Railways plays a crucial role in this regard, but it is essential to enhance the current resilience and capacity of the network, in particular from lifeline structures, such as bridges. Within this regard, several open points affecting the current INF TSI and described in the ERA Technical Note are yet to be closed, namely those related to the Dynamic Train Categories previously specified in EN15228:2015 and the limits of validity of the static compatibility checks currently stipulated EN15228:2021, the accuracy of the current dynamic amplification factors and damping values for railway bridges proposed in EN1991 2 (2003) and the validity of the deck acceleration limits imposed by EN1990-Annex A2 (2005) in both new and existing bridges. InBridge4EU aims to answer these points through the formulation of an enhanced and harmonized method to assess the European dynamic interface between railway bridges and rolling stock. The outcomes of this project will provide solid background to the guidance being drafted within the CEN/TC250/SC1 special group DIBRST for dynamics of bridges. Finally, as a consequence, the economic outcomes of changing any of the aforementioned criteria/parameters/methodologies in the current European railway bridge landscape will be carefully assessed. All the research carried out in InBridge4EU will converge on recommendations to ERA and CEN for revising and updating the current version of the TSIs and Eurocodes. Advanced numerical modelling and dynamic analyses of both bridge and railway vehicles, together with the development of extensive databases of bridge and rolling stock data obtained from the different partners of the consortium, will contribute to the successful achievement of the project’s objectives.

GNSS is amongst the “game-changing” technologies for future digital and automated rail operations, acknowledged in a 2015 report from the European Union Agency for Railways (ERA) on the longer-term perspective for the evolution of the European Rail Traffic Management System (ERTMS) and the EU Parliament in its adopted report on railway safety and signalling from July 2021 also calls for a joint effort towards the introduction of GNSS in ERTMS. Three major railway operators in Europe – DBN, SBB and SNCF – endorse and support the efforts of the EU Parliament and propose a follow-up-project to the "Certifiable Localization Unit with GNSS in the railway environment” (CLUG) project to demonstrate the technological readiness of the CLUG Localisation On-Board (LOC-OB) System. In CLUG 2.0 (CLUG Demonstration of Readiness for Rail), the system architecture aims to complement the existing European Train Control System (ETCS) odometry system by using GNSS to enable absolute safe train positioning whilst also transforming the way of train localisation is done today by demonstrating a GNSS-based multi-sensor fusion architecture. To ensure that an enhanced on-board localization in ERTMS/ETCS using GNSS is interoperable, the technological readiness of the LOC-OB System shall be demonstrated in CLUG 2.0. To achieve its objectives, the consortium continues the work started in the first CLUG project, by improving the design of the safe functional architecture and validating it against the requirements defined by the operators. Ultimately, all thanks to an improved LOC-OB System for ERTMS, benefits such as increasing the line capacity, reducing headways between trains, reducing expenditure for rail infrastructure rollout can help reduce emissions, and accelerate the adoption of sustainable and smart mobility solutions that revolve around rail. LOC-OB can make rail transport more attractive, enhance the competitiveness of rail for citizens and businesses.

According to the ERAccording to the ERA 2015 Report on ERTMS Longer Term Perspective, GNSS could prove a game changer for the European railway network by enabling a significant reduction of trackside equipment and by improving localisation performance. The conclusions of the STARS project have confirmed this potential. However, fusion with other sensors will be necessary to mitigate the known impact of local effects on GNSS performance. Capitalising on the achievements of EC and GSA funded projects, collaborating railway companies, i.e. SBB, DB and SNCF, would like to propose the project CLUG. This project will perform a mission analysis/needs identification and a preliminary feasibility study of an on-board localisation unit with the following characteristics: > failsafe on-board multi-sensor localisation unit consisting of a navigation core (IMU, tachometer, etc.) brought in reference using GNSS, track map and a minimal number of reference points; > on-board continuous localisation system that provides location, speed and other dynamics of the train; > operational and interoperable across the entire European rail network; > compatible with the current ERTMS TSI or with its future evolutions. To achieve its objectives,the CLUG's management and the design and development of the localization unit will follow agile processes taking into account former projects results – especially STARS – as well as observations resulting from new test campaigns. The CLUG consortium comprises railway companies (SNCF, DB Netz and SBB), railway signaling industries (CAF and Siemens), navigation specialists (Airbus Defense & Space, Naventik, FDC), a research institute (ENAC) and a certification expert (Navcert). Ultimately, this project is the key enabling technology for the future-proof development of train digitalisation and automation to respond to the increased mobility needs of all European citizen and goods by leveraging the train, a green safe and efficient means of transport.

The main ERSAT EAV objective is to verify the suitability of EGNSS (including EGNOS and Galileo early services) for safety railway application, in particular in regional lines scenario, for which a safe localization of the trains, based on satellite technologies, will be defined and developed, leading the way for the harmonization with the European ERTMS standard, by implementing the solution on a pilot line as reference. The objectives will be achieved, in a first phase by measuring and evaluating the gaps to be filled, in terms of technological criticalities and in relation to railway requirements, performing measurements under real operating conditions, building models and analysis with the help of the simulation, and finally defining and developing a system solution, implementing, testing and validating it on a pilot line, as reference for the future standardisation and certification processes. The ERSAT EAV proposal is relevant to the work programme for the exploitation of the space infrastructure, in particular prioritising the EGNSS uptake for the rail sector, fostering the competition and the innovation of the European space and rail industry and research community, and enhancing in parallel the strong coordination and synergy with the specific sector of European Railways and the main actors involved, building-up a system centered to the ERTMS platform and able to bring to the ERTMS the “competitivity-dividend” of the satellite promises, linked with the enormous opportunity of the local and regional lines in Europe that represent about 50% of the total railways length. The EGNSS-ERTMS based train control/protection system is especially beneficial in terms of operating costs compared to other solutions for upgrading the local/regional infrastructure, considering the forecasted average Benefit/Cost ratios of 2.2 at the European level and a remarkable increase of safety.

The scope of AI4REALNET covers the perspective of AI-based solutions addressing critical systems (electricity, railway, and air traffic management) modelled by networks that can be simulated, and are traditionally operated by humans, and where AI systems complement and augment human abilities. It has two main strategic goals: 1) to develop the next generation of decision-making methods powered by supervised and reinforcement learning, which aim at trustworthiness in AI-assisted human control with augmented cognition, hybrid human-AI co-learning and autonomous AI, with the resilience, safety, and security of critical infrastructures as core requirements, and 2) to boost the development and validation of novel AI algorithms, by the consortium and AI community, through existing open-source digital environments capable of emulating realistic scenarios of physical systems operation and human decision-making. The core elements are: a) AI algorithms mainly composed by supervised and reinforcement learning, unifying the benefits of existing heuristics, physical modelling of these complex systems and learning methods, as well as, a set of complementary techniques to enhance transparency, safety, explainability and human acceptance; b) human-in-the-loop decision making for co-learning between AI and humans, considering integration of model uncertainty, human cognitive load and trust; c) autonomous AI systems relying on human supervision, embedded with human domain knowledge and safety rules. The AI4REALNET framework will be validated in 6 uses cases driven by industry requirements, across 3 network infrastructures with common properties. The use cases are focused on critical challenges and tasks of network operators, considering strategic long-term goals, such as decarbonisation, digitalisation, and resilience to disturbances, and are formulated in a unified sequential decision problem where many AI and non-AI algorithms can be applied and benchmarked.