Projecten per jaar
Organisatieprofiel
Introductie / missie
The Mobile Perception Systems Lab researches methods in Artificial Intelligence that allow mobile autonomous systems to perceive their environment. Our long-term goal is to realize AI that can anticipate on future events in highly dynamic and complex environments. We always validate our AI methods 'in the loop', meaning in the context of challenging real-world applications, mainly from the industry domains of automotive, transportation, and logistics.
MPS is part of the Signal Processing Systems group and we work closely with the Embedded Systems group, the Dynamics and Control group, the Control Systems Technology group, and the TU/e-wide Strategic Area for Smart Mobility.
Highlighted phrase
Perception Through Anticipation
Organisatieprofiel
The MPS lab specializes in the following AI methods: deep learning, multi-modal computer vision, and simultaneous localization and mapping. These are key enabling technologies that allow mobile sensor platforms to perceive and interpret their environments from past and current sensory data, in essence estimating a dynamic digital world-model in real-time. In coming years, we aim to make a step in the direction of spatio-temporal reasoning engines that allow mobile sensor platforms to predict possible future events and thereby achieve anticipation capabilities. Currently, the lack of anticipation capabilities, is a key bottleneck in deploying mobile autonomous systems in complex and dynamic environments, such as self-driving cars in crowded inner cities. We firmly believe that in order to advance AI and its applications, both an inter-disciplinary approach and a strong cooperation with industry are required. Hence, we are involved in many cross-disciplinary European projects and initiatives, such as the International Connected and Automated Driving Institute (https://icadi.net), and we recently started the company AI In Motion to bring our technologies to the market (https://aiim.ai).
Vingerafdruk
Samenwerkingen en hoofdonderzoeksgebieden uit de afgelopen vijf jaar
Profielen
-
Gijs Dubbelman
- EAISI Foundational - Universitair Hoofddocent
- EAISI Mobility - Universitair Hoofddocent
- Electrical Engineering, Mobile Perception Systems Lab
Persoon: UHD : Universitair Hoofddocent
-
Daan de Geus
- Electrical Engineering, Mobile Perception Systems Lab
- Electrical Engineering, Video Coding & Architectures - Postdoc
Persoon: Prom. : Promovendus, PD : Postdoc
-
Jos H.V. den Ouden, MSc
- Electrical Engineering, Mobile Perception Systems Lab
- Electrical Engineering, Video Coding & Architectures - Projectmanager
Persoon: OBP : Ondersteunend en Beheerspersoneel
-
ROBUST AI: Explainable AI for Autonomous Vehicles
Zednik, C. (Project Manager), Ghezzi, M. (Projectmedewerker) & van Broeckhoven, B. (Projectmedewerker)
1/09/22 → 31/08/27
Project: Second tier
-
TOWR: Towards Open World Robotics
den Ouden, J. H. V. (Project communicatie medewerker), van de Molengraft, M. J. G. (Project Manager), de Vos, K. (Projectmedewerker), van Rhijn, G. (Projectmedewerker) & Steinbuch, M. (Projectmedewerker)
1/01/21 → 30/04/27
Project: Third tier
-
5G-MOBIX: 5G-MOBIX
Tafur Monroy, I. (Project Manager), Calabretta, N. (Projectmedewerker), Johannsen, U. (Projectmedewerker), Okonkwo, C. M. (Projectmedewerker), Heemstra de Groot, S. M. (Projectmedewerker), Dubbelman, G. (Projectmedewerker), Patterson, D. (Projectmedewerker), Rommel, S. (Projectmedewerker), Cimoli, B. (Projectmedewerker), den Ouden, J. H. V. (Projectmedewerker), Sanders, R. (Project communicatie medewerker), Meyer, E. (Projectmedewerker), Jancura, P. (Projectmedewerker) & Sahinel, D. (Projectmedewerker)
1/11/18 → 30/09/22
Project: Onderzoek direct
Onderzoeksoutput
-
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
Martin Garcia, G., Abou Zeid, K., Schmidt, C., de Geus, D., Hermans, A. & Leibe, B., 8 apr. 2025, 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025. Institute of Electrical and Electronics Engineers, blz. 753-762 10 blz. 10943344Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review
Open Access -
The BRAVO Semantic Segmentation Challenge Results in UNCV2024
Vu, T.-H. (Corresponderende auteur), Valle, E., Bursuc, A., Kerssies, T., de Geus, D., Dubbelman, G., Qian, L., Zhu, B., Chen, Y., Tang, M., Wang, J., Vojíř, T., Šochman, J., Matas, J., Smith, M., Ferrie, F., Basu, S., Sakaridis, C. & Van Gool, L., 12 mei 2025, Computer Vision – ECCV 2024 Workshops: Milan, Italy, September 29–October 4, 2024, Proceedings, Part XVII. Del Bue, A., Canton, C., Pont-Tuset, J. & Tommasi, T. (uitgave). Cham: Springer, blz. 290-306 17 blz. (Lecture Notes in Computer Science (LNCS); vol. 15639).Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review
Open Access -
Advances in Behavior Prediction Techniques for Intelligent Systems
Bighashdel, A., 20 mrt. 2024, Eindhoven: Eindhoven University of Technology. 216 blz.Onderzoeksoutput: Scriptie › Dissertatie 1 (Onderzoek TU/e / Promotie TU/e)
Open AccessBestand
Datasets
-
[Re] Object Detection Meets Knowledge Graphs - Supporting Datasets
Lemmens, J. L. A. (Ontwerper), Jancura, P. (Bijdrager), Dubbelman, G. (Bijdrager) & Elforai, H. (Ontwerper), Zenodo, 7 okt. 2021
DOI: 10.5281/zenodo.7385730, https://zenodo.org/record/7385730
Dataset
-
[Re] Object Detection Meets Knowledge Graphs - Supporting Datasets
Lemmens, J. (Ontwerper), Jancura, P. (Ontwerper), Dubbelman, G. (Ontwerper) & Elforai, H. (Ontwerper), Zenodo, 7 okt. 2021
Dataset
Prijzen
-
Best Paper Award
Sanberg, W. P. (Ontvanger), 17 jan. 2019
Prijs: Anders › Werk, activiteit of publicatie gerelateerde prijzen (lifetime, best paper, poster etc.) › Wetenschappelijk
-
Festival of Disruption
den Ouden, J. H. V. (Organisator)
13 okt. 2022Activiteit: Types deelname aan of organisatie van een evenement › Workshop, seminar, cursus of expositie › Professioneel
-
Webinar 5G-MOBIX Netherlands Trial Site's results and lessons learnt on 5G for CAM
den Ouden, J. H. V. (Bijdrager)
23 jun. 2022Activiteit: Types deelname aan of organisatie van een evenement › Workshop, seminar, cursus of expositie › Wetenschappelijk
-
Towards averaging out GNSS bias using visual SLAM
Das, A. (Spreker)
20 sep. 2020Activiteit: Types gesprekken of presentaties › Aangemelde presentatie › Wetenschappelijk
Knipsels
-
Advances in Perception for Automated Mobile Systems
de With, P. H. N. & Dubbelman, G.
26/01/23
1 item van Media-aandacht
Pers / media: Vakinhoudelijk commentaar
-
Use case: Remote driving with interconnected 5G networks
11/03/21
1 Mediabijdrage
Pers / media: Onderzoek
-
Testrit op TU Eindhoven: Plankgas naar de toekomst in auto die zelfstandig rijdt (Dutch only)
den Ouden, J., Roomi Zadeh, A., Dubbelman, G. & Dolatabadi Farahani, M.
17/09/18
1 item van Media-aandacht
Pers / media: PR activiteiten
Scripties/Masterproeven
-
3D Object Detection From LiDAR data using Distance Depended Feature Extraction
Engels, G. (Auteur), Dubbelman, G. (Afstudeerdocent 1), 30 okt. 2019Scriptie/Masterproef: Master
Bestand -
A hierarchical approach to Part-aware Panoptic Segmentation
Verboeket, B. L. E. (Auteur), Dubbelman, G. (Afstudeerdocent 1), 27 sep. 2022Scriptie/Masterproef: Master
Bestand -
Deep learning for opponent action prediction in robot soccer middle size league
van 't Klooster, M. E. (Auteur), Dubbelman, G. (Afstudeerdocent 1) & Nijmeijer, H. (Afstudeerdocent 2), 22 mei 2018Scriptie/Masterproef: Master
Bestand