Real and synthetic scenarios generated for the development, training, virtual testing and validation of CCAM systems

Informazioni relative al progetto

SYNERGIES

ID dell’accordo di sovvenzione: 101146542

DOI

10.3030/101146542

Data della firma CE 27 Maggio 2024

Data di avvio 1 Giugno 2024

Data di completamento 31 Maggio 2027

Finanziato da

• Climate, Energy and Mobility

Costo totale

€ 18 833 167,05

Contributo UE

€ 18 636 667,60

Coordinato da

IDIADA AUTOMOTIVE TECHNOLOGY SA
Spain

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (12)

D8.1 Evaluation Framework methodology

Evaluation framework to assess the platform’s performance. The deliverable refers to T8.1

D1.5 Initial Exploitation Plan

Initial strategy for utilizing project results, exploring potential avenues for application to maximize project impact. The deliverable refers to T1.3.

D3.3 Data Generation Report

Report on the process and results of generating project data from vehicles, roadside infrastructure sensors and drones (T3.3), from advanced simulation tools (T3.4) and synthetic data based on Generative AI methods (T3.5).

D1.1 Project Management Plan

Overall procedures to be used by the consortium during the whole project execution for successful project execution. It provides a roadmap for the project team to follow and helps to ensure that the project is completed on time, within budget, and to the required quality standards. The deliverable refers to T1.1.

D2.2 Storylines definition and technical and interoperability requirements

User storylines definition and technical requirements for each of the storylines including the necessary components, subsystems and data flows. Interoperability requirements to establish data consistency and interoperability throughout the project. Data traceability, data trustworthiness and cybersecurity requirements. The deliverable refers to T2.2, T2.3 and T2.4.

D2.1 Stakeholder high-level requirements

Key needs and requirements gathered from main stakeholders and expected objectives of SYNERGIES platform, performance requirements and conditions of use. The deliverable refers to T2.1.

D4.1 Data formats, fusion, data compression and Semantic Framework

Design and implementation of extended data formats and ontologies, in alignment with the specifications of WP2, to support and streamline the creation of diverse data processing tools. Creation an integrated framework that seamlessly accommodates diverse data sources and fosters efficient inter-domain communication. The deliverable refers to T4.1 and T4.2.

D9.1 Preliminary report on stakeholders’ engagement

Reports on the engagement with stakeholders until M18 including (but not necessarily be limited) the management of an online cooperation platform, extending the one developed in the SUNRISE project, and the organisation of regular in-person and online workshop in alignment with the needs of the Work Package during the development stages of the projects. The deliverable refers to T9.1.

D10.1 Dissemination and communication plan

Outlines the plan for disseminating project results and communication strategies including the definition of audience and stakeholders (together with WP9); definition of strategy per targeted audience; communication plan with KPIs; identification of communication supportive tools and communication channels analysis. The deliverable refers to T10.1.

D5.1 Scenario Methodology Framework

Methodology for the harmonized toolchain for scenario identification, extraction, enrichment, and generation. The deliverable refers to T5.1.

D3.2 Assessment of available data from external sources

Analysis of the state-of-the-art in terms of available data and current scenario coverage from open data sources, other national and EU projects as well as looking on existing accident databases. The deliverable refers to T3.2.

D3.1 Methodology for Data Quality Assessment

Methodology to analyse quality and relevance of available and collected data and synthetically generated data for scenario generation. The deliverable refers to T3.1.

Data Management Plan (2)

D1.3 Mid-term Data Management Plan

Updated version at M18 of the guidelines and general plan describing how data has been managed in the project in order to guarantee the project objectives while complying with regulations and policies. The deliverable refers to T1.2.

D1.2 Initial Data Management Plan

Guidelines and general plan describing how data will be managed in the project in order to guarantee the project objectives while complying with regulations and policies. The deliverable refers to T1.2.

Demonstrators, pilots, prototypes (2)

D7.3 SYNERGIES platform release v2

Second release of SYNERGIES Platform. The deliverable refers to T7.1, T7.2 and T7.4.

D7.2 SYNERGIES platform release v1

First release of SYNERGIES Platform. The deliverable refers to T7.1, T7.2 and T7.4.

Websites, patent fillings, videos etc. (1)

D10.2 Project website

Describes the development and content of the project website. The deliverable refers to T10.1.

Pubblicazioni

Peer reviewed articles (1)

International Journal on Software Tools for Technology Transfer

Autori: Becker, Jan Steffen; Neurohr, Christian
Pubblicato in: International Journal on Software Tools for Technology Transfer, 2025, ISSN 1433-2779
Editore: Springer Verlag
DOI: 10.1007/S10009-025-00827-9

Conference proceedings (3)

Trustworthy Multimodal Generative AI for ADAS Development

Autori: Son Tong, Balakrishnan Ayyanar, Shiye Fang, Kohei Noma, Satoshi Sekine, Theo Geluk, Reiji Takeuchi (Siemens Digital Industries Software)
Pubblicato in: 2025 Japanese Society of Automotive Engineers (JSAE) Annual Congress (Spring), Numero No. 30-25, 2025
Editore: Japanese Society of Automotive Engineers (JSAE)

Tools for the validation of ADAS functions in field operational tests

Autori: Perez, Marc; Villalba, Raul; Leiva, Gisella
Pubblicato in: 2025
Editore: FISITA World Mobility Conference 2025
DOI: 10.46720/WMC25-A-GNL-015

Incorporating A Priori Statistical Situational Knowledge into Model Predictive Control Algorithms

Autori: Legran, Philippe; Ruß, Fabian; Beckmann, Jobst Nikolaus Bertram; Tarlowski, Sven; Eckstein, Lutz
Pubblicato in: "Proceedings of the Driving Simulation Conferene : ""Recent trends in driving simulation technology, virtual experience and testing"" : DSC 2025 Europe : Haus der Wirtschaft, Stuttgart, Germany, September 24-26, 2025 / editors: Andras Kemeny ; Jean-Rémy Charadonnet ; Florent Colombel<br/>Driving Simulation Conference Europe, DSC 2025, Stuttgart, Germany, 2025-09-24 - 2025-09-26", 2025
Editore: DSC 2025 Europe
DOI: 10.5281/ZENODO.19066444

Other (4)

Requirement Identification for Traffic Simulations in Driving Simulators

Autori: Tarlowski, Sven; Eckstein, Lutz
Pubblicato in: CoRR, 2025
Editore: arXiv
DOI: 10.18154/RWTH-2025-08750

Operationalization of Scenario-Based Safety Assessment of Automated Driving Systems

Autori: Op den Camp, Olaf; de Gelder, Erwin
Pubblicato in: 2025 IEEE International Automated Vehicle Validation Conference (IAVVC), 2025
Editore: IEEE
DOI: 10.48550/ARXIV.2507.22433

Comparing Normalizing Flows with Kernel Density Estimation in Estimating Risk of Automated Driving Systems

Autori: de Gelder, Erwin; Buermann, Maren; Op den Camp, Olaf
Pubblicato in: 2025 IEEE International Automated Vehicle Validation Conference (IAVVC), 2025, ISSN 1121-9624
Editore: IEEE
DOI: 10.48550/ARXIV.2507.22429

NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling

Autori: Bram Grooten; Farid Hasanov; Chenxiang Zhang; Qiao Xiao; Boqian Wu; Zahra Atashgahi; Ghada Sokar; Shiwei Liu 0003; Lu Yin 0006; Elena Mocanu; Mykola Pechenizkiy; Decebal Constantin Mocanu
Pubblicato in: CoRR, 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2505.17909