The Cognitive Systems group at Reutlingen University develops trustworthy, human-centered AI systems that combine machine learning, computer vision, multimodal sensing, and cognitive modeling. Our research focuses on robust perception, uncertainty-aware decision-making, and adaptive human–machine interaction, supported by immersive experimental environments and real-world sensor platforms.
We translate methodological advances in interactive learning and multimodal system modeling into impactful applications — from autonomous mobility and inclusive assistive technologies to movement science, life sciences, and environmental monitoring.
Our mission is to design intelligent systems that are not only technically advanced, but also reliable, transparent, and beneficial to society.
The Cognitive Systems group develops trustworthy, human-centered AI systems with a strong methodological foundation:
Trustworthy AI & Uncertainty Quantification
Robust perception and decision-making under ambiguity, including AI-based sensor degradation estimation and safety-aware validation.Human-Centered AI & Cognitive Modeling
Computational modeling of perception and behavior, human-in-the-loop systems, and ethically responsible AI design.Human–Machine Interaction (HMI)
Adaptive, multimodal interfaces and real-time user-state estimation, validated in immersive and sensor-rich environments.Interactive & Continual Learning
Learning from human feedback, data-efficient adaptation, and cross-domain transfer learning.Multimodal Perception & Sensor Fusion
Vision-based tracking, movement and behavior analysis, and real-time fusion of heterogeneous sensor systems.
These methods are supported by advanced experimental infrastructures enabling realistic yet controlled system validation.
The methodological expertise translates into several high-impact domains:
Autonomous Systems & Mobility
Autonomous driving, perception assistance systems, adaptive HMIs, and inclusive mobility solutions.Inclusive & Assistive Technologies
AI for accessibility, human-aware automation, and participation-enhancing systems.Movement Science & Health
Multimodal motion capture for sports, rehabilitation, ergonomics, and diagnostic support.Life Sciences & Environmental Monitoring
AI-based biological data analysis, intelligent monitoring systems, and biodiversity observation.
The group’s core strength lies in methodological excellence with strong transferability, enabling impactful applications across mobility, health, inclusion, and environmental sustainability.
Labs & Research Center
Cognitive Systems Group has two laboratories and one research center, each dedicated to its own specialized research area.
Motion Capture Lab
AIDA Reality Lab
Applied Artificial Intelligence
Motion Capture Lab
Detaillierte Aufnahme und Simulation menschlicher Bewegungen. Durch Cognitive Computing Ansätze werden neue assistive Technologien ermöglicht. Das Labor erlaubt einzelne Personen, aber auch ganze Menschengruppen in Bewegung zu digitalisieren. Bewegungen werden intelligent verarbeitet. 3D-Scanner-Technologie unterstützt dabei die weitere Simulation bzw. Animation von Körpern und deren Bewegungen. Visuelle Sensorik erlernt mit Verfahren der künstlichen Intelligenz die automatische Deutung komplexer Szenen.
Anwendungsbeispiele/ Forschungsgebiete:
- Hochautomatisiertes Fahren, auch im städtischen Bereich
- klinische Anwendungen
- Neurorobotik
- Mensch-Roboter-Interaktion
- Mensch-Maschine-Schnittstellen
- allgemeine Bewegungsanalyse- und Synthese
- unterstützt durch Methoden im Bereich Computer-Vision und maschinelles Lernen
- menschlicher Wahrnehmung und grafischer Simulation
AIDA: Interactive AI Data Incubation Center - reality lab
AIDA ist ein KI-Leuchtturmprojekt im Rahmen von RegionWIN 2030 und betreibt den Aufbau einer einzigartigen Infrastruktur eines KI-Dateninkubators für die realitätsnahe Entwicklung von Sensorik, insbesondere für urbanes autonomes Fahren im Fußgängerumfeld.
Our Projects
We develop research projects that advance intelligent systems, human–machine interaction, and real‑world applications of AI. Explore a selection of our current and finished projects below.
Cooperations
Our research is built on strong collaborations with leading industry partners, academic institutions, and public organizations. These partnerships enable us to combine expertise, accelerate innovation, and translate scientific advances into real‑world impact.
Team Members
Wissenschaftlicher Mitarbeiter, Doktorand
Publications
Bramlage L, Curio C, "HIC SVNT DRACONES: Probing the Manifold Boundary for Post-Hoc Uncertainty Estimation", 21st International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU’2026), June 15, 2026 - June 19, 2026, Rome, Italy, Accepted.
Nair V, Rehmann M, de la Rosa S, Sachse M, Curio C, "Hidden in Plain Sight: How Motion Camouflage Impairs Driver Hazard Perception", International IEEE Intelligent Vehicles Symposium (IV). 2026, Accepted.
Bramlage L, Curio C, "IO-CUE: Post-Hoc Uncertainty Quantification as Behavioral Probing for Robust Dense Regression", International IEEE Intelligent Vehicles Symposium (IV). 2026. Accepted. (preprint)
Bramlage L., Curio C. "Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networks", arXiv.2506.00918 (preprint)
Maier F., Leute R., Paulokat M., Rosenhahn E.-O., Brunner M., Rehmann, M., Curio C., "Effect of external HMIs on pedestrian safety and traffic flow — A motion capture study", In Proceedings of the 16th International Symposium on Automotive Lighting (ISAL). Hrsg.: Khanh T., Quoc (2025), Darmstadt (22.09.2025-24.09.2025), doi: 10.26083/tuprints-00030845
Rehmann M., Brunner M., Curio C., "OODM-DS: Out-Of-Distribution Mitigation based on Dynamic Sampling for human pose dataset creation", IEEE 28th International Conference on Intelligent Transportation Systems (ITSC 2025) (ITSC 2025), November 18-21, 2025 in Gold Coast, Australia.
Rehmann M., Brunner M., Bramlage L., Curio C., "LOODM: Live Out-Of-Distribution Mitigation during human pose dataset production", 2025 IEEE Intelligent Vehicles Symposium (IV), Cluj-Napoca, Romania, 2025, pp. 1585-1592, doi: 10.1109/IV64158.2025.11097686.
Rehmann M., Brunner M., Curio C., "Towards relevant human-vehicle interaction data for perceptive machine learning", 2025 IEEE Intelligent Vehicles Symposium (IV), Cluj-Napoca, Romania, 2025, pp. 1313-1320, doi: 10.1109/IV64158.2025.11097661
Bramlage L., Karg M., Curio C., "Plausible Uncertainties for Human Pose Regression", 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, Jan., 2024. pp. 15087-15096, doi: 10.1109/ICCV51070.2023.01389.
Frey K., Brunner M., Curio C., Kemkemer R., "Curvature Perception of Mesenchymal Cells on Mesoscale Topographies", Adv. Healthcare Mater, Dec., 2024, doi: https://doi.org/10.1002/adhm.202402865.
Schiweck L., Saleh A., Curio C., "Towards Wearable Multi-Modal Human Activity Recognition with Deep Fusion Networks" at Twelfth International Workshop on Assistive Computer Vision and Robotics (ACVR), IEEE 18th European Conference on Computer Vision (ECCV), Milano, Sept. 29- Oct. 4, 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15634. Springer, Cham. doi. 10.1007/978-3-031-92591-7_17
Vinu Vijayakumaran Nair, Markus Rehmann, Stephan de la Rosa, Cristobal Curio., "Investigating Drivers' Awareness of Pedestrians Using Virtual Reality towards Modeling the Impact of External Factors", 35th IEEE Intelligent Vehicles Symposium (IV), Jeju Island, Korea, Republic of, 2024, pp. 3001-3008, doi: 10.1109/IV55156.2024.10588734.
Burgermeister D., "Data simulation in deep learning-based human recognition", Dissertation, 2023, doi: 10.15496/publikation-81046.
Gulde T., "Two-Dimensional Pose Estimation of Industrial Robotic Arms in Highly Dynamic Collaborative Environments", Dissertation, 2023, doi: 10.15496/publikation-84948.
Essich M., Rehmann M., Curio C., "Auxiliary Task-Guided CycleGAN for Black-Box Model Domain Adaptation", 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, Hawaii, 2023.
Uhlmann Y. , Brunner M., Bramlage L., Scheible J., and Curio C., "Procedural- and Reinforcement-Learning-Based Automation Methods for Analog Integrated Circuit Sizing in the Electrical Design Space", Electronics, vol. 12, no. 2, p. 302, Jan. 2023, doi: 10.3390/electronics12020302
Uhlmann Y., Essich M., Bramlage L., Scheible J., Curio C., "Deep Reinforcement Learning for Analog Circuit Sizing with an Electrical Design Space and Sparse Rewards", Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD (MLCAD), Snowbird / Utah, September 2022, pp. 21-26, doi: https://doi.org/10.1145/3551901.3556474.
Burgermeister D., Curio C., "PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation.", 2022 IEEE 33th International Symposium for Intelligent Vehicles (IV), Aachen, 2022, pp. 441-448, doi: 10.1109/IV51971.2022.9827202.
Nam Bach T., Junger, D., Curio, C., Burgert, O., "Towards Human Action Recognition during Surgeries using De-identified Video Data: De-identification Prototype for Visual Sensitive Information in the OR", Current Directions in Biomedical Engineering, vol. 8, no. 1, 2022, pp. 109-112, doi: 10.1515/cdbme-2022-0028.
Triess L., Curio C., Bukhari S. (Editors), "Second Workshop on Autonomy@Scale", Workshop at the IEEE International Conference on Intelligent Vehicles 2022, Aachen / Germany, June 2022. (https://www.ki-deltalearning.de/iv2022-2nd-ws-autonomyatscale)
Praetorius, A. S., Krautmacher, L., Tullius, G. & Curio, C. (2021), "User-Avatar Relationships in Various Contexts", In: Schneegass, S., Pfleging, B. & Kern, D. (Hrsg.), Mensch und Computer 2021 - Tagungsband, New York: ACM, pp. 295-300), doi: 10.1145/3473856.3474007.
Bramlage L., Cortese A. (2021) "Generalized attention-weighted reinforcement learning", Neural Networks, vol. 145, pp. 10-21, doi: https://doi.org/10.1016/j.neunet.2021.09.023.
Curio C., Bukhari S., Hafner F., Helm D., Kalb T., Rottmann M., Schneider G., Wiederer J. (Editors), Workshop at IEEE International Conference on Computer Vision, "Embedded and Real-World Computer Vision in Autonomous Driving", ERCVAD 2021, Oct. 27 2021.
Uhlmann Y., Essich M., Schweikardt M., Scheible J., Curio C. (2021) "Machine Learning Based Procedural Circuit Sizing and DC Operating Point Prediction", 17th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD), Jul. 19-22 2021. [accepted]
Sefati M., Curio C. (Editors), Workshop at the IEEE International Conference on Intelligent Vehicles, "Autonomy at Scale", Nagoya/ Japan, June 2021.
Ludl D., Gulde T., Curio C. (2020) Enhancing data-driven algorithms for human pose estimation and action recognition through simulation, in IEEE Transactions on Intelligent Transportation Systems.
[ DOI ]
Ludl D., Gulde T., Curio C. (2019) Simple yet efficient real-time pose-based action recognition, 22nd IEEE International Conference on Intelligent Transportation Systems (ITSC), 2019, pp. 581–588, doi: 10.1109/ITSC.2019.8917128.
Grützmacher S., Kemkemer R., Curio C. (2019) Using Deep Correlation Features to define the Meta Style of Cell Images for Classification. Journal of Current Directions in Biomedical Engineering, Band 5, Heft 1, Seiten 227–230, ISSN (Online) 2364-5504
[ DOI ]
Essich M., Ludl D., Gulde T., Curio C. (2019) Learning to Translate Between Real World and Simulated 3D Sensors While Transferring Task Models, In Proceedings of the 7th International Conference on 3D Vision (3DV), Sept. 16-19.
Gulde T., Ludl D., Andrejtschik J., Thalji S., Curio C. (2019) RoPose-Real: Real World Dataset Acquisition for Data-Driven Industrial Robot Arm Pose Estimation, IEEE International Conference on Robotics and Automation ICRA 2019, May 20-24, Montreal, pp 1-8, in Press.
Ludl D., Gulde T., Thalji S., Curio C. (2018) Using simulation to improve human pose estimation for corner cases, 21st IEEE International Conference on Intelligent Transportation Systems (ITSC), November 4-7, pp. 3575-3582.
Baulig G., Gulde T., Curio C (2019) Adapting Egocentric Visual Hand Pose Estimation Towards a Robot-Controlled Exoskeleton, In the Proceedings of the 4th Workshop on Observing and Understanding Hands in Action, IEEE European Conference on Computer Vision, Munich, Germany, September 8-14, Part VI.
[DOI]
Grützmacher S., Kemkemer R., Thies C., Curio C. (2018). Detecting Lamellipodia in Epithelial Cell Clusters Using a Fully Convolutional Neural Network for Phase Contrast Microscopy Images. Journal of Current Directions in Biomedical Engineering, 4(1), pp. 449-452. Retrieved 6 Feb. 2019.
[ DOI ]
Hanisch S., Burgert O., Curio C., Fröhlich F.A. (2018) Segmentierung und Tracking von minimal-invasiven robotergeführten Instrumenten, Deutsche Gesellschaft für Computer- und Roboterassistierte Chriurgie e.V. (CURAC), September, pp 1-8, in Press.
Gulde T., Ludl D., Curio C. (2018) RoPose: CNN-based 2D Pose Estimation of Industrial Robots. 14th IEEE Conference on Automation Science and Engineering (CASE). 463-470.
de la Rosa S, Fademrecht L, Bülthoff HH, Giese Martin A, Curio C (2018) Two ways to facial expression recognition? Motor and visual information have different effects on facial expression recognition, Journal of Psychological Science.
[ DOI ]
Chiovetto E, Curio C, Endres D, Giese M (2018) Perceptual integration of kinematic components in the recognition of emotional facial expressions, Journal of Vision; 18(4): p. 1-19. ISSN: 1534-7362.
[ DOI ]
Schuster F, Zhang W, Keller CG, Haueis M, Curio C (2017) Joint Graph Optimization Towards Crowd Based Mapping, IEEE ITSC2017
Cristóbal Curio (2017) Towards human movement understanding in highly automated environments Keynote at DFG-SPP Summer School ‘Cooperative interacting automobiles’ Schwäbisch Gmünd, 9. September 2017
Workshop on Machine Vision and Interfaces in Data Fusion Platforms for Automated Driving, IEEE IV2017 Schilling M*, Curio C (2016) Edt (* Hella).
[ PDF ]
Schuster F*, Keller CG*, Rapp M, Haueis M*, Curio C (2016) Landmark based Radar SLAM Using Graph Optimization IEEE ITSC2016.
Breidt M, Bülthoff Heinrich H, Curio C (2016) Accurate 3D head pose estimation under real-world driving conditions: A pilot study, IEEE ITSC2016.
Gulde T, Kärcher S*, Curio C (2016) Vision-based SLAM navigation for vibro-tactile human-centered indoor guidance ECCV2016 | (* University of Osnabrück, feelspace GmbH).
[ DOI ]
Schuster F*, Wörner M*, Keller CG*, Haueis M*, Curio C. (2016) Robust Localization based on Radar Signal Clustering IEEE IV2016 | (* Daimler AG R&D).
Ludl D, Randler D, Browatzki B, Curio C (2016) Towards purposeful intention prediction of pedestrians IEEE IV2016 - Workshop Talk
Workshop on holistic interfaces for environmental fusion models IEEE IV2016 | Schilling M*, Curio C (2016) Edts. (* Hella).
Curio C, Stiller C (2015) Interaction of Automated Vehicles with other Traffic Participants. Edts of Workshop at the 18th IEEE International Conference on Intelligent Transportation Systems, September 15-18, 2015
Borchers S, Martin D, Mieskes S, Rieger S, Curio C, Fäßler V (2015) Towards Audio-Based Distraction Estimation in the Car, In Proceedings of the Seventh International Conference on Advanced Cognitive Technologies and Applications (Cognitive 2015). IARIA, ISBN: 978-1-61208-390-2, pp. 187-190.
de la Rosa S, Choudery R, Curio C, Ullman S, Assif L und Bülthoff HH (2014) Visual categorization of social interactions. Visual Cognition, Vol. 22, Iss. 9-10, 2014.
de la Rosa S, Streuber S, Giese MA, Bülthoff HH und Curio C (2014) Putting Actions in Context: Visual Action Adaptation Aftereffects Are Modulated by Social Contexts, PLoS ONE 9(1) 1-10.
Engel D und Curio C (2013) Detectability Prediction for Increased Scene Awareness. IEEE Intelligent Transportation Systems Magazine, 5(4) 146-157.
Breidt M, Bülthoff HH und Curio C (2013) Accurate and marker-less head tracking using depth sensors. In: Theory and Practice of Computer Graphics 2013, 11th Conference on Theory and Practice of Computer Graphics (TP.CG.2013), Eurographics Association, Aire-la-Ville, Switzerland, 41-48.
Herdtweck C und Curio C (2013) Monocular Car Viewpoint Estimation with Circular Regression Forests. IEEE Intelligent Vehicles Symposium (IV 2013), IEEE, Piscataway, NJ, USA, 403-410.
Engel D, Herdtweck C, Browatzki B und Curio C (2011) Image Retrieval with Semantic Sketches, In: Human-Computer Interaction: INTERACT 2011, 13th IFIP TC13 Conference on Human-Computer Interaction, Springer, Berlin, Germany, 412-425.
Curio C, Bülthoff HH, Giese MA und Poggio TA (2010) Dynamic Faces: Insights from Experiments and Computation, 288, MIT Press, Cambridge, MA, USA. ISBN: 978-0-262-01453-3.
Curio C, Breidt M, Kleiner M, Bülthoff HH (2010). The Virtual Face Mirror Project: Revealing Dynamic Self-Perception in Humans. International Conference on Cognitive Systems. ETHZ
Engel D, Spinello L, Triebel R, Siegwart R, Bülthoff HH und Curio C (2009) Medial Features for Superpixel Segmentation. In Proceedings of the Eleventh IAPR Conference on Machine Vision Applications (MVA 2009). pp 248-252
Engel D, Curio C, Tcheang L, Mohler B, Bülthoff HH (2008) A psychophysically calibrated controller for navigating through large environments in a limited free-walking space. Proceeding VRST ‘08 Proceedings of the 2008 ACM symposium on Virtual reality software and technology, pp 157-164. ACM.
Curio C und Giese M (2005) Combining View-based and Model-based Tracking of Articulated Human Movements. IEEE Computer Society Workshop on Motion and Vision Computing (MOTION 2005), IEEE Computer Society, Los Alamitos, CA, USA, 261-268.
Bücher T, Curio C, Edelbrunner J, Igel C, Kastrup D, Leefken I, Lorenz G, Steinhage A und von Seelen W (2003) Image Processing and Behaviour Planning for Intelligent Vehicles. IEEE Transactions on Industrial Electronics, 90(1) 62-75.
von Seelen W, Curio C, Gayko J, Handmann U und Kalinke T (2000) Scene analysis and organization of behavior in driver assistance systems. IEEE International Conference on Image Processing (ICIP 2000), IEEE Operations Center, Piscataway, NJ, USA, 524-527.
Curio C, Edelbrunner J, Kalinke T, Tzomakas C und von Seelen W (2000) Walking Pedestrian Recognition. IEEE Transactions on Intelligent Transportation Systems, 1(3) 155-163.
