mUlti-Level Trustworthiness to IMprove the Adoption of hybrid arTificial intelligencE

Informations projet

ULTIMATE

N° de convention de subvention: 101070162

DOI

10.3030/101070162

Projet clôturé

Date de signature de la CE 12 Juin 2022

Date de début 1 Octobre 2022

Date de fin 30 Septembre 2025

Financé au titre de

• Digital, Industry and Space

Coût total

€ 3 529 112,50

Contribution de l’UE

€ 3 529 112,50

Coordonné par

THALES
France

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

Websites, patent fillings, videos etc. (1)

Project public website and social media

The ULTIMATE public website will provide information about the project, publications, news, and events.

Documents, reports (1)

Report on assessment of Hybrid-AI

Report summarising evaluation for hardware/software unsupervised testing (CBR), impact of AI component / system as a quantitative statistical approach (TEC) and component-based control verification (KTH). The report will include the results of the ethical impact assessment in the end-users’ governance context. The effect of the AI hybrid tools and solutions on wider society will also be considered.

Ethics Requirements (1)

OEI - Requirement No. 1

"The ""Hybrid AI for Robotic navigation and collaborative work"" demonstrator considers the detection and precise tracking of human workers. The ethics advisor should ensure that the rights of the workers are preserved concerning privacy and data protection and that they are truly free to accept or reject participation to the research experiment.A first report on this topic should be provided before the start of WP5 (meaning M12)."

Publications

Conference proceedings (5)

Real-world Application Facilitating Trustworthy Human-Robot Collaboration with Innovative Explainable Neuro-symbolic Reasoning

Auteurs: R. Kozik, S. Buś, G. Gawdzik, M. Pawlicki, A. Pawlicka and M. Choraś
Éditeur: IEEE

Towards Quality Measures for xAI algorithms: Explanation Stability

Auteurs: Marek Pawlicki
Publié dans: 2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA), 2023, ISBN 979-8-3503-4503-2
Éditeur: IEEE
DOI: 10.1109/DSAA60987.2023.10302535

Real-Time Anomaly Detection and Categorization for Satellite Reaction Wheels

Auteurs: Alejandro Penacho Riveiros, Yu Xing, Nicola Bastianello, Karl H. Johansson
Publié dans: 2024 European Control Conference (ECC), 2024
Éditeur: IEEE
DOI: 10.23919/ECC64448.2024.10591184

How Explainable Is Explainability? Towards Better Metrics for Explainable AI

Auteurs: Pawlicka, A., Pawlicki, M., Kozik, R., Kurek, W., Choraś M.
Publié dans: Research and Innovation Forum (RIIFORUM) 2023, 2024, ISBN 978-3-031-44721-1
Éditeur: Springer
DOI: 10.1007/978-3-031-44721-1_52

Formal Verification of Local Robustness of a Classification Algorithm for a Spatial Use Case

Auteurs: D. Longuet, A. Elouazzani, A. Penacho Riveiros, N. Bastianello
Publié dans: Proceedings Seventh International Workshop on Formal Methods for Autonomous Systems, ISSN 2075-2180
Éditeur: Electronic Proceedings in Theoretical Computer Science
DOI: 10.48550/ARXIV.2509.03948

Book chapters (3)

Supporting Human-Robot Collaboration and Safety with the Proposed Explainable Neuro-Symbolic Reasoning

Auteurs: Rafał Kozik, Aleksandra Pawlicka, Marek Pawlicki, Michał Choraś
Publié dans: Lecture Notes in Computer Science, Availability, Reliability and Security, 2025
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-032-00642-4_15

ULTIMATE Project Toolkit for Robotic AI-Based Data Analysis and Visualization

Auteurs: Rafał Kozik, Damian Puchalski, Aleksandra Pawlicka, Szymon Buś, Jakub Główka, Krishna Chandramouli, Marco Tiemann, Marek Pawlicki, Rafał Renk, Michał Choraś
Publié dans: Lecture Notes in Computer Science, Intelligent Information and Database Systems, 2024
Éditeur: Springer Nature Singapore
DOI: 10.1007/978-981-97-4985-0_4

Ensuring Trustworthiness of Hybrid AI-Based Robotics Systems

Auteurs: Eguia, Alexander; Quintano, Nuria; Marsh, Irina; Barreteau, Michel; Główka, Jakub; Sprońska, Agnieszka
Publié dans: 2024
Éditeur: Springer Nature
DOI: 10.1007/978-3-031-76428-8_27

Peer reviewed articles (2)

Neurocomputing

Auteurs: M. Pawlicki, A. Pawlicka, R. Kozik, M. Choraś
Publié dans: Neurocomputing, Numéro 950, 2024, ISSN 0925-2312
Éditeur: Elsevier
DOI: 10.1016/j.neucom.2024.127759

On the black-box explainability of object detection models for safe and trustworthy industrial applications

Auteurs: Alain Andres; Aitor Martinez-Seras; Ibai Laña; Javier Del Ser
Publié dans: Results in Engineering, 2024, ISSN 2590-1230
Éditeur: Elsevier
DOI: 10.48550/ARXIV.2411.00818