Towards Excellent Robotics and Artificial Intelligence at a Slovak university

Informations projet

TERAIS

N° de convention de subvention: 101079338

DOI

10.3030/101079338

Projet clôturé

Date de signature de la CE 14 Juillet 2022

Date de début 1 Octobre 2022

Date de fin 30 Septembre 2025

Financé au titre de

• Widening participation and spreading excellence

Coût total

€ 1 578 793,75

Contribution de l’UE

€ 1 499 890,00

Coordonné par

UNIVERZITA KOMENSKEHO V BRATISLAVE
Slovakia

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

Ethics Requirements (3)

OEI - Requirement No. 2

First report of the Ethics Advisor

OEI - Requirement No. 3

Second report of the Ethics Advisor

OEI - Requirement No. 1

The absence of a clear description of the methodology to be used in WP3 and the lack of clarity regarding human participation in research and of the data management requires the appointment of an Ethics Advisor.Artificial intelligenceWP3 will experiment Human Robot Interactions (HRI). Even though AI issues are identified in the Ethics table (Part A), WP3 description fails in considering properly the ethical issues leading to the use of these robots. There is no description of the methodology, therefore it is unclear how human participants will be involved in the research and how the ethical dimensions of their participation will be handled. Applicants have attached a statement regarding ethics in Annex1 of the project. However, it is unclear and unspecified how this statement will apply to the research and communication activities. This lack of methodological description on human participation raised specific ethical concerns that should be clarified.Personal dataEven though identified as an ethical issue, the data management of training, conference activities and research activities are not addressed. The data management plan is only stated in a vague manner and does not reflect the whole issues related to the management of personal data processing and technical safeguards that must be put in place to ensure that privacy and confidentiality will be ensured.The independent Ethics Advisor should be appointed at the beginning of the project. It should ensure that all the necessary authorisations and approvals are in place prior the commencement of the research to be conducted in WP3. The Advisor should report at M6 and M17.

Documents, reports (9)

Reports on achieving impact through dissemination and communication

Reports on achieving impact through dissemination and communication, to be delivered in M17 and M36.

Reports on joint research activities

Reports on joint research activities, to be delivered in M14 and M28.

Data management plan

Data management plan will be developed and constantly updated within the Management Work Package (WP6). Sensitive data will be marked by the level of confidentiality and also checked against any non-disclosure agreement. All produced data will be managed in line with the FAIR principles. The DMP will address the points below and will document the current status of reflection within the consortium about the data that will be produced and protected:Data set reference and name: Identifier for the data set to be produced;Data set description: origin, nature and scale and to whom it could be useful, and whether it underpins a scientific publication;Data sharing: Description of how data will be shared, including access procedures, embargo periods. In case a dataset cannot be shared, the reasons for this will be mentioned;Archiving and preservation (including storage and backup): Description of the procedures that will be put in place for long-term preservation of the data.

Detailed dissemination, exploitation and communication plan

The detailed plan will be prepared concerning all dissemination, exploitation and communication activities that have been proposed with the intention to maximize the impact of the TERAIS project on the key target groups - scientific community; prospective international students/research staff; prospective Slovak students/research staff; general public; business community; and funding actors. Overall communication will leverage comprehensive communication tools (above/below the line) to better correspond to the target group needs and the requirements of the communication objectives and key messages. Details are provided in Table 2.2a of the proposal.

Progress report (interim)

Progress reports (interim)

Detailed PM and QA Plan

Detailed Project Management and Quality Assurance Plan.

Reports on implementation of the Joint Research Strategy

Reports on implementation of the Joint Research Strategy, to be delivered in M16 and M28, It will contain steps and measures for joint involvement in EU project proposals, development of publications or presentations at scientific conferences from partners to the coordinating institution by organizing planned events.

Quality assurance reports

Quality assurance reports, to be delivered in M8, 13,18,25, 30

Reports on implementing the knowledge and skills transfer

Reports on implementing the knowledge and skills transfer, to be delivered in M12 and M28.

Publications

Conference proceedings (37)

Supersampling of Data from Structured-light Scanner with Deep Learning

Auteurs: Martin Melicherčík, Lukáš Gajdošech, Viktor Kocur, Martin Madaras
Publié dans: 2023 World Symposium on Digital Intelligence for Systems and Machines (DISA), 2023
Éditeur: IEEE
DOI: 10.48550/arXiv.2311.07432

Neural Field Conditioning Strategies for 2D Semantic Segmentation

Auteurs: Martin Gromniak, Sven Magg, Stefan Wermter
Publié dans: Artificial Neural Networks and Machine Learning – ICANN 2023, 2023
Éditeur: Springer Nature
DOI: 10.48550/arXiv.2304.14371

Clarifying the Half Full or Half Empty Question: Multimodal Container Classification

Auteurs: Josua Spisak, Matthias Kerzel, Stefan Wermter
Publié dans: Artificial Neural Networks and Machine Learning – ICANN 2023, 2023
Éditeur: Springer Nature
DOI: 10.48550/arXiv.2307.08471

Spike up Prime Interest in Science and Technology through Constructionist Games

Auteurs: Pavel Petrovič, Fedir Agarshev
Publié dans: 15th International Conference on Education and New Learning Technologies Proceedings, 2023
Éditeur: IATED
DOI: 10.48550/arXiv.2402.17243

Robust Self-Calibration of Focal Lengths from the Fundamental Matrix

Auteurs: Viktor Kocur, Daniel Kyselica, Zuzana Kukelova
Publié dans: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Numéro 25, 2024
Éditeur: IEEE
DOI: 10.48550/arXiv.2311.16304

Using Programmable Drone in Educational Projects and Competitions

Auteurs: Pavel Petrovič, Peter Verčimák
Publié dans: 15th International Conference on Education and New Learning Technologies Proceedings, 2023
Éditeur: IATED
DOI: 10.48550/arXiv.2402.17409

Sketch it for the Robot! How Child-Like Robots' Joint Attention Affects Humans' Drawing Strategies

Auteurs: Carlo Mazzola, Lorenzo Morocutti, Hillary Pedrizzi, Xenia Daniela Poslon, Andrej Lucny, Sarah Marie Wingert, Yukie Nagai, Francesco Rea, Alessandra Sciutti
Publié dans: 2024 IEEE International Conference on Development and Learning (ICDL), Numéro 4, 2024
Éditeur: IEEE
DOI: 10.5281/zenodo.11189963

Tuning-less Object Naming with a Foundation Model

Auteurs: Andrej Lucny, Pavel Petrovic
Publié dans: 2023 World Symposium on Digital Intelligence for Systems and Machines (DISA), 2023
Éditeur: IEEE
DOI: 10.48550/arXiv.2311.04924

Comparing Apples to Oranges: LLM-Powered Multimodal Intention Prediction in an Object Categorization Task

Auteurs: Hassan Ali, Philipp Allgeuer, Stefan Wermter
Publié dans: Lecture Notes in Computer Science, Social Robotics, 2025
Éditeur: Springer
DOI: 10.48550/ARXIV.2404.08424

Are Minimal Radial Distortion Solvers Necessary for Relative Pose Estimation?

Auteurs: Charalambos Tzamos, Viktor Kocur, Yaqing Ding, Torsten Sattler, Zuzana Kukelova
Publié dans: Lecture Notes in Computer Science, Computer Vision – ECCV 2024 Workshops, 2025
Éditeur: Springer
DOI: 10.48550/ARXIV.2410.05984

Appearance-based gaze estimation enhanced with synthetic images using deep neural networks

Auteurs: Dmytro Herashchenko, Igor Farkaš
Publié dans: 2023 IEEE Symposium Series on Computational Intelligence (SSCI), 2023
Éditeur: IEEE
DOI: 10.48550/arXiv.2311.14175

Learning Low-Level Causal Relations Using a Simulated Robotic Arm

Auteurs: Miroslav Cibula; Matthias Kerzel; Igor Farkaš
Publié dans: International Conference on Artificial Neural Networks ICANN 2024, 2024
Éditeur: Springer
DOI: 10.48550/ARXIV.2410.07751

When Robots Get Chatty: Grounding Multimodal Human-Robot Conversation and Collaboration

Auteurs: Philipp Allgeuer, Hassan Ali, Stefan Wermter
Publié dans: Lecture Notes in Computer Science, Artificial Neural Networks and Machine Learning – ICANN 2024, 2024
Éditeur: Springer
DOI: 10.48550/ARXIV.2407.00518

Robotic Imitation of Human Actions

Auteurs: Josua Spisak, Matthias Kerzel, Stefan Wermter
Publié dans: 2024 IEEE International Conference on Development and Learning (ICDL), 2024
Éditeur: IEEE
DOI: 10.48550/ARXIV.2401.08381

Merge, Explain, Iterate: A Combination of MHS and MXP in an ABox Abduction Solver

Auteurs: Martin Homola, Júlia Pukancová, Janka Boborová, Iveta Balintová
Publié dans: Logics in Artificial Intelligence. JELIA 2023, 2023
Éditeur: Springer
DOI: 10.5281/zenodo.10724508

RecViT: Enhancing Vision Transformer with Top-Down Information Flow

Auteurs: Štefan Pócoš; Iveta Bečková; Igor Farkaš
Publié dans: Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2024
Éditeur: scitepress
DOI: 10.5281/ZENODO.14766904

QuasiNet: A Neural Network with Trainable Product Layers

Auteurs: Kristína Malinovská, Slavomír Holenda, Ľudovít Malinovský
Publié dans: Artificial Neural Networks and Machine Learning – ICANN 2023, 2023
Éditeur: Springer Nature
DOI: 10.48550/arXiv.2401.06137

Processing and Segmentation of Human Teeth from 2D Images using Weakly Supervised Learning

Auteurs: Tomáš Kunzo, Viktor Kocur, Lukáš Gajdošech, Martin Madaras
Publié dans: 2023 World Symposium on Digital Intelligence for Systems and Machines (DISA), 2023
Éditeur: IEEE
DOI: 10.48550/arXiv.2311.07398

Novel Synthetic Data Tool for Data-Driven Cardboard Box Localization

Auteurs: Peter Kravár, Lukáš Gajdošech. Martin Madaras
Publié dans: Artificial Neural Networks and Machine Learning -- ICANN 2023, 2023
Éditeur: Springer Nature
DOI: 10.48550/arXiv.2305.05215

Real-time Addressee Estimation: Deployment of a Deep-Learning Model on the iCub Robot

Auteurs: Carlo Mazzola, Francesco Rea, Alessandra Sciutti
Publié dans: 2023 I-RIM Conference, 2023, ISBN 978-88-945805-4-9
Éditeur: I-RIM
DOI: 10.48550/arXiv.2311.05334

Controlling the Output of a Generative Model by Latent Feature Vector Shifting

Auteurs: Belanec, Róbert; Lacko, Peter; Malinovská, Kristína
Publié dans: 2023 World Symposium on Digital Intelligence for Systems and Machines (DISA), 2023
Éditeur: IEEE
DOI: 10.48550/arxiv.2311.08850

Open-Vocabulary Robotic Object Manipulation using Foundation Models

Auteurs: Griebenow, Stig; Özdemir, Ozan; Weber, Cornelius; Wermter, Stefan
Publié dans: ESANN 2025 proceesdings, 2025
Éditeur: i6doc
DOI: 10.5281/ZENODO.14774343

Three-view Focal Length Recovery From Homographies

Auteurs: Yaqing Ding, Viktor Kocur, Zuzana Berger Haladová, Qianliang Wu, Shen Cai, Jian Yang, Zuzana Kukelova
Publié dans: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Éditeur: IEEE
DOI: 10.48550/ARXIV.2501.07499

Replay to Remember: Continual Layer-Specific Fine-Tuning for German Speech Recognition

Auteurs: Theresa Pekarek Rosin, Stefan Wermter
Publié dans: Artificial Neural Networks and Machine Learning – ICANN 2023, 2023
Éditeur: Springer Nature
DOI: 10.1007/978-3-031-44195-0_40

Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation

Auteurs: Hassan Ali, Philipp Allgeuer, Carlo Mazzola, Giulia Belgiovine, Burak Can Kaplan, Lukáš Gajdošech, Stefan Wermter
Publié dans: 2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids), 2024
Éditeur: IEEE
DOI: 10.48550/ARXIV.2407.13505

Towards Bio-inspired Robotic Trajectory Planning via Self-supervised RNN

Auteurs: Miroslav Cibula, Kristína Malinovská, Matthias Kerzel
Publié dans: Lecture Notes in Computer Science, Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions, 2025
Éditeur: Springer
DOI: 10.48550/ARXIV.2507.02171

Safe Reinforcement Learning in a Simulated Robotic Arm

Auteurs: Luka Kovač, Igor Farkaš
Publié dans: Artificial Neural Networks and Machine Learning – ICANN 2023, 2023
Éditeur: Springer Nature
DOI: 10.48550/arXiv.2312.09468

Detection of Vascular Leukoencephalopathy in CT Images

Auteurs: Zuzana Cernekova; Viktor Sisik; Fatana Jafari
Publié dans: International Conference on Innovative Techniques and Applications of Artificial Intelligence, 2024
Éditeur: Springer
DOI: 10.48550/ARXIV.2501.09863

Practical solutions to the relative pose of three calibrated cameras

Auteurs: Charalambos Tzamos, Viktor Kocur, Yaqing Ding, Daniel Barath, Zuzana Berger Haladová, Torsten Sattler, Zuzana Kukelova
Publié dans: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Éditeur: IEEE
DOI: 10.48550/ARXIV.2303.16078

Robot at the Mirror: Learning to Imitate via Associating Self-supervised Models

Auteurs: Andrej Lúčny, Kristína Malinovská, Igor Farkaš
Publié dans: Artificial Neural Networks and Machine Learning – ICANN 2023, 2023
Éditeur: Springer Nature
DOI: 10.48550/arXiv.2311.13226

Evaluating the Significance of Outdoor Advertising from Driver’s Perspective Using Computer Vision

Auteurs: Zuzana Černeková, Zuzana Berger Haladová, Ján Špirka, Viktor Kocur
Publié dans: 2023 World Symposium on Digital Intelligence for Systems and Machines (DISA), 2023
Éditeur: IEEE
DOI: 10.48550/arXiv.2311.07390

Enhancement of 3D Camera Synthetic Training Data with Noise Models

Auteurs: Osvaldová, Katarína; Gajdošech, Lukáš; Kocur, Viktor; Madaras, Martin
Publié dans: Proceedings of the 27th Computer Vision Winter Workshop, 2024
Éditeur: Slovenian Pattern Recognition Society
DOI: 10.5281/zenodo.10694437

Executable Multi-Layered Software Models

Auteurs: Lukas Radosky, Ivan Polasek
Publié dans: Proceedings of the 1st International Workshop on Designing Software, 2024
Éditeur: ACM
DOI: 10.48550/ARXIV.2501.09863

CycleIK: Neuro-inspired Inverse Kinematics

Auteurs: Jan-Gerrit Habekost, Erik Strahl, Philipp Allgeuer, Matthias Kerzel, Stefan Wermter
Publié dans: Artificial Neural Networks and Machine Learning – ICANN 2023, 2023
Éditeur: Springer Nature
DOI: 10.48550/arXiv.2307.11554

To Whom are You Talking? A Deep Learning Model to Endow Social Robots with Addressee Estimation Skills

Auteurs: Carlo Mazzola, Marta Romeo, Francesco Rea, Alessandra Sciutti, Angelo Cangelosi
Publié dans: 2023 International Joint Conference on Neural Networks (IJCNN), 2023
Éditeur: IEEE
DOI: 10.48550/arXiv.2308.10757

A method for estimating roadway billboard salience

Auteurs: Zuzana Berger Haladova, Michal Zrubec, Zuzana Cernekova
Publié dans: ACM Symposium on Applied Perception 2024, 2024
Éditeur: ACM
DOI: 10.48550/ARXIV.2501.07342

Diffusing in Someone Else’s Shoes: Robotic Perspective-Taking with Diffusion

Auteurs: Josua Spisak, Matthias Kerzel, Stefan Wermter
Publié dans: 2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids), 2024
Éditeur: IEEE
DOI: 10.48550/ARXIV.2404.07735

Peer reviewed articles (4)

NICOL: A Neuro-inspired Collaborative Semi-humanoid Robot that Bridges Social Interaction and Reliable Manipulation

Auteurs: Matthias Kerzel, Philipp Allgeuer, Erik Strahl, Nicolas Frick, Jan-Gerrit Habekost, Manfred Eppe, Stefan Wermter
Publié dans: IEEE Access, Numéro 11, 2023, ISSN 2169-3536
Éditeur: IEEE
DOI: 10.48550/arXiv.2305.08528

Computer Vision and Image Understanding

Auteurs: Iveta Bečková; Štefan Pócoš; Giulia Belgiovine; Marco Matarese; Omar Eldardeer; Alessandra Sciutti; Carlo Mazzola
Publié dans: Computer Vision and Image Understanding, Numéro 253, 2025, ISSN 1077-3142
Éditeur: Academic Press
DOI: 10.48550/ARXIV.2407.03340

Collaborative software design and modeling in virtual reality

Auteurs: Martin Stancek, Ivan Polasek, Tibor Zalabai, Juraj Vincur, Rodi Jolak, Michel Chaudron
Publié dans: Information and Software Technology, Numéro 166, 2023, ISSN 0950-5849
Éditeur: Elsevier
DOI: 10.48550/arXiv.2311.17787

Snapture—a Novel Neural Architecture for Combined Static and Dynamic Hand Gesture Recognition

Auteurs: Hassan Ali, Doreen Jirak, Stefan Wermter
Publié dans: Cognitive Computation, Numéro 15, 2023, ISSN 1866-9964
Éditeur: Springer Link
DOI: 10.48550/arXiv.2205.15862

Book chapters (1)

Pointing-Guided Target Estimation via Transformer-Based Attention

Auteurs: Luca Müller, Hassan Ali, Philipp Allgeuer, Lukáš Gajdošech, Stefan Wermter
Publié dans: Lecture Notes in Computer Science, Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions, 2025
Éditeur: Springer Nature Switzerland
DOI: 10.48550/ARXIV.2509.05031