AI-based CCAM: Trustworthy, Explainable, and Accountable

Informations projet

AIthena

N° de convention de subvention: 101076754

DOI

10.3030/101076754

Projet clôturé

Date de signature de la CE 27 Juillet 2022

Date de début 1 Novembre 2022

Date de fin 31 Octobre 2025

Financé au titre de

• Climate, Energy and Mobility

Coût total

€ 5 999 547,50

Contribution de l’UE

€ 5 999 547,50

Coordonné par

FUNDACION CENTRO DE TECNOLOGIAS DE INTERACCION VISUAL Y COMUNICACIONES VICOMTECH
Spain

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Documents, reports (16)

Report on dissemination and standardisation activities

[T6.2-3] Report on the dissemination and standardisation activities carried out in tasks T6.2 and T6.3.

Methodology for explainable, trustworthy and human centric AI based system and function development

[T1.1-3] This deliverable will materialize the AITHENA methodology into a reference report to include definition of KPI related to trusted AI features (see GO-8).

Report on data sharing and integration with European data lakes, OpenData and OpenTool

[T6.4] Report on the plan and actions taken to integrate created data into data sharing initiatives at European level, including novel OpenData and OpenTool concepts.

Report on initial AI algorithm development

[T3.2-5] This report covers the initial AI algorithm developments including their initial feature validation according to the specified requirements and specifications.

Report on initial use case evaluation

[T5.2-4] This report covers the initial demonstrator validation and evaluation of the demonstrators against the specified requirements and specifications.

Privacy-preserving methods

[T2.3] This deliverable will report the designed privacy-preserving methods for application of GDPR-compliant ML.

Lessons learned, policy recommendations

[T6.5] Lessons learned, and derived policy recommendations for the exploitation of AI solutions in CCAM.

Life-cycle management framework for ML models

[T3.1] This report covers the designed AI-framework used for the development and life-cycle assessment of individual ML algorithms.

User group needs report and technical use case definition

[T1.4] This deliverable reports the action taken to identify user groups and gather from them requirements to detail the AITHENA use cases

Initial communication, dissemination and standardisation plan

T613 Initial strategy for AITHENA based on an initial market and stakeholder analysis

Report on final use case evaluation

[T5.2-4] This report covers the final demonstrator validation and evaluation of the demonstrators against the specified requirements and specifications. In addition, for each specific AI-driven approach in the use cases a dedicated AI lifecycle assessment is outlined.

Report on physical set-up, digital twin and hybrid testing approaches

[T4.2-4] This is the deliverable about activities T4.2-4, including report on physical set-up, digital twin and hybrid testing approaches.

Testing and evaluation methodology for AI-driven CCAM systems

[T5.1] This report outlines a joint testing and evaluation methodology for AI-driven CCAM systems to be applied in the corresponding use cases of task 5.2 to task 5.4.

Report on final AI algorithm development

[T3.2-5] This report covers the final AI algorithm developments including their final feature validation according to the specified requirements and specifications. In addition, all strength and weaknesses of the specific AI-driven approaches are outlined.

Updated communication, dissemination and standardisation plan

Update of the communication, dissemination and standardisation plan

ML DevOps-oriented data life-cycle governance and provenance framework

[T2.2] This deliverable will report RTD activities related to ML DevOps tools for data governance and provenance.

Publications

Conference proceedings (15)

A Multimodal Sensor Setup for In Situ Comparison of Driving Dynamics, Physiological Responses and Passenger Comfort in Autonomous Vehicles

Auteurs: Harald Devriendt, Mathieu Sarrazin, Thomas D'hondt, Konstantinos Gkentsidis, Karl Janssens
Publié dans: AHFE International, Intelligent Human Systems Integration (IHSI 2025): Integrating People and Intelligent Systems, Numéro 160, 2025
Éditeur: AHFE International
DOI: 10.54941/AHFE1005852

Identifying the influence of different environmental conditions on driving behavior using behavioral data

Auteurs: Guido Linden (geb. Küppers), Lutz Eckstein
Éditeur: Veröffentlicht auf dem Publikationsserver der RWTH Aachen University
DOI: 10.18154/RWTH-2025-06321

What Did I Learn? Operational Competence Assessment for AI-Based Trajectory Planners

Auteurs: Michiel Braat, Maren Buermann, Marijke van Weperen, Jan-Pieter Paardekooper
Éditeur: arXiv
DOI: 10.48550/ARXIV.2510.00619

Runtime Safety Assurance of Autonomous Vehicles

Auteurs: A. Forrai (Siemens Industry Software Netherlands B.V.), V. Neelgundmath, K.K. Unni, I. Barosan (Eindhoven University of Technology)
Publié dans: Proceedings: 2023 7th International Conference on System Reliability and Safety (ICSRS), 2023, ISSN 1272-4017
Éditeur: Zenodo
DOI: 10.5281/zenodo.12724017

Digital twin for synthetic data generation – application for automated driving systems

Auteurs: Hassan Hotait (HAN – University of Applied Sciences), Alexandru Forrai (Siemens Industry Software Netherlands B.V.)
Publié dans: Product solutions paper: 22nd Driving Simulation & Virtual Reality Conference, 2023, ISSN 1272-3883
Éditeur: Zenodo
DOI: 10.5281/zenodo.12723882

V2AIX: A Multi-Modal Real-World Dataset of ETSI ITS V2X Messages in Public Road Traffic

Auteurs: Guido Kueppers, Jean-Pierre Busch, and Lennart Reiher, Lutz Eckstein
Éditeur: arXiv
DOI: 10.48550/ARXIV.2403.10221

OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction

Auteurs: Severin Heidrich, Till Beemelmanns, Alexey Nekrasov, Bastian Leibe, Lutz Eckstein
Éditeur: arXiv
DOI: 10.48550/ARXIV.2503.10605

AITHENA: towards a trustworthy AI for CCAM development

Auteurs: Oihana Otaegui, Marcos Nieto, Sinziana Ioana Rasca, Jos den Ouden, Carles Ubach, Michael Stolz, Justyna Beckmann
Éditeur: Zenodo
DOI: 10.5281/ZENODO.16085152

Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR

Auteurs: Adwait Chandorkar, Hasan Tercan, Tobias Meisen
Éditeur: arXiv
DOI: 10.48550/ARXIV.2508.00744

Generative AI for Privacy Protection of Images in Autonomous Vehicles

Auteurs: Ruben Naranjo, Nerea Aranjuelo, Marcos Nieto, Oihana Otaegui, and Itsaso Rodriguez-Moreno
Éditeur: Zenodo
DOI: 10.5281/ZENODO.16087344

Simplifying Traffic Anomaly Detection with Video Foundation Models

Auteurs: Svetlana Orlova, Tommie Kerssies, Brunó B. Englert, Gijs Dubbelman
Éditeur: arXiv
DOI: 10.48550/ARXIV.2507.09338

Bridging trust, safety, efficiency and innovation: AI and explainable AI in road transport

Auteurs: Silvia Barbaro, Ted Zotos
Éditeur: Zenodo
DOI: 10.5281/ZENODO.17723684

An Evaluation of Time-triggered Scheduling in the Linux Kernel

Auteurs: Paraskevas Karachatzis, Jan Ruh, Silviu S. Craciunas (TTTech Computertechnik AG, Vienna, Austria)
Publié dans: RTNS '23: Proceedings of the 31st International Conference on Real-Time Networks and Systems, 2023, ISBN 9781450399838
Éditeur: ACM
DOI: 10.1145/3575757.3593660

MultiCorrupt: A Multi-Modal Robustness Dataset and Benchmark of LiDAR-Camera Fusion for 3D Object Detection

Auteurs: Till Beemelmanns, Quan Zhang, Christian Geller, Lutz Eckstein
Éditeur: arXiv
DOI: 10.48550/ARXIV.2402.11677

Explainable Multi-Camera 3D Object Detection with Transformer-Based Saliency Maps

Auteurs: Beemelmanns, Till; Zahr, Wassim; Eckstein, Lutz
Publié dans: Machine Learning for Autonomous Driving Workshop 2023 (NeurIPS), 2023, ISSN 2331-8422
Éditeur: ML4AD/arXiv
DOI: 10.48550/arxiv.2312.14606

Peer reviewed articles (8)

Trustworthiness Assurance Assessment for High-Risk AI-Based Systems

Auteurs: Georg Stettinger (Infineon Technologies AG); Patrick Weissensteiner (Virtual Vehicle Research GmbH); Siddartha Khastgir (International Manufacturing Centre, The University of Warwick)
Publié dans: IEEE Access, Numéro Volume: 12, 2024, ISSN 2169-3536
Éditeur: IEEE
DOI: 10.1109/ACCESS.2024.3364387

Toward Explainability in Urban Motion Prediction—Survey and Outlook

Auteurs: Ilma Okanovic, Michael Stolz, Bernhard Hillbrand
Publié dans: SAE International Journal of Connected and Automated Vehicles, Numéro 08, 2025, ISSN 2574-0741
Éditeur: SAE International
DOI: 10.4271/12-08-01-0009

Meta-YOLOv8: Meta-Learning-Enhanced YOLOv8 for Precise Traffic Light Color Detection in ADAS

Auteurs: Vasu Tammisetti, Georg Stettinger, Manuel Pegalajar Cuellar, Miguel Molina-Solana
Publié dans: Electronics, Numéro 14, 2025, ISSN 2079-9292
Éditeur: MDPI AG
DOI: 10.3390/ELECTRONICS14030468

LaANIL: ANIL with Look-Ahead Meta-Optimization and Data Parallelism

Auteurs: Vasu Tammisetti, Kay Bierzynski, Georg Stettinger, Diego P. Morales-Santos, Manuel Pegalajar Cuellar, Miguel Molina-Solana
Publié dans: Electronics, Numéro 13, 2025, ISSN 2079-9292
Éditeur: MDPI AG
DOI: 10.3390/ELECTRONICS13081585

Exploring the potential of standardized behaviour competencies in automated driving systems

Auteurs: Georg Stettinger, Patrick Weissensteiner, Nayel Fabian Salem, Marcus Nolte, Siddartha Khastgir
Publié dans: IFAC Journal of Systems and Control, Numéro 33, 2025, ISSN 2468-6018
Éditeur: Elsevier BV
DOI: 10.1016/J.IFACSC.2025.100320

A Methodology to Enhance Transparency for Trustworthy Artificial Intelligence for Cooperative, Connected, and Automated Mobility

Auteurs: Paola Natalia Cañas, Marcos Nieto, Oihana Otaegui, Igor Rodriguez
Publié dans: SAE International Journal of Connected and Automated Vehicles, Numéro 08, 2025, ISSN 2574-0741
Éditeur: SAE International
DOI: 10.4271/12-08-01-0010

WebLabel: OpenLABEL-compliant multi-sensor labelling

Auteurs: Itziar Urbieta, Andoni Mujika, Gonzalo Piérola, Eider Irigoyen, Marcos Nieto, Estibaliz Loyo, Naiara Aginako
Publié dans: Multimedia Tools and Applications, Numéro Volume 83, 2023, ISSN 2213-7793
Éditeur: Springer
DOI: 10.1007/s11042-023-16664-4

Explainable Safety Argumentation for the Deployment of Automated Vehicles

Auteurs: Patrick Weissensteiner, Georg Stettinger
Publié dans: Electronics, Numéro 13, 2025, ISSN 2079-9292
Éditeur: MDPI AG
DOI: 10.3390/ELECTRONICS13234606

Other (1)

Supporting automated driving systems development with synthetic data

Auteurs: Alexandru Forrai and Hamid Abdolhay
Éditeur: Zenodo
DOI: 10.5281/ZENODO.16993081