Noémie Jaquier is an Assistant Professor at KTH Royal Institute of Technology in Stockholm, Sweden. She leads the Geometric Robot Learning (GeoRob) Lab within the Division of Robotics, Perception, and Learning. Previously, she held postdoctoral positions at KIT (High Performance Humanoid Technologies Lab) and Stanford Robotics Lab, and completed her PhD at EPFL (2020) with a sabbatical at Bosch Center for AI. Education: PhD in Robotics, EPFL (2020) PhD Sabbatical: Bosch Center for AI Her research focuses on developing data-efficient robot learning and control algorithms using differential geometry and physics-based principles. Key interests include optimization under theoretical guarantees and applying geometric methods to enhance robotic autonomy. She teaches the Robotics Reading Group course (FDD3316) and maintains an active personal research webpage. Labs/Teams: Head of GeoRob Lab, collaborating with institutions like Stanford and KIT on humanoid robotics and AI-driven systems.
Truls Nyberg is an Industrial Postdoc at TRATON Group, affiliated with the Division of Robotics, Perception and Learning (RPL) at KTH Royal Institute of Technology. His research focuses on foundation models and vision-language models for decision-making and motion planning in autonomous vehicles, addressing critical challenges in occlusion handling and risk assessment. His academic background includes: PhD in Computer Science (Robotics, Perception and Learning) from KTH Royal Institute of Technology (2025), with thesis "Mind the Unknown: Risk- and occlusion-aware motion planning for autonomous vehicles" supervised by Jana Tumova and co-supervised by Patric Jensfelt MSc in Control and Information Systems from Linköping University BSc in Applied Physics and Electrical Engineering from Linköping University Nyberg's research centers on autonomous driving systems where occlusions create safety risks. He develops risk-aware motion planning algorithms using sequential reasoning about hidden objects, vehicle-to-everything (V2X) communication, and foundation models to enhance decision-making in complex traffic. His work bridges theoretical robotics with industrial applications, emphasizing real-world safety specifications and uncertainty handling in urban and highway scenarios. Analysis of his publications reveals a clear trajectory from fundamental risk-aware planning (2021) to advanced occlusion reasoning using V2X (2024). His research consistently targets safety-critical gaps in autonomous driving, with growing emphasis on cooperative perception and language-integrated vision models. Key trends include formal safety guarantees, real-time contingency planning, and leveraging hidden object predictions for proactive vehicle control. Nyberg was funded by the Wallenberg AI, Autonomous Systems and Software Program (WASP) during his doctoral studies. While no current student advising is documented, his industry-academia role at TRATON Group demonstrates strong collaboration between KTH and automotive manufacturing. His research directly addresses industrial challenges in commercial vehicle automation. As part of KTH's Robotics, Perception and Learning division, Nyberg contributes to Sweden's leading autonomous systems research environment. His work leverages state-of-the-art robotics labs and industry partnerships to translate academic innovation into practical solutions for next-generation autonomous vehicles.
Florian T. Pokorny is an Associate Professor in Machine Learning at the Division of Robotics, Perception and Learning (RPL), Department of Electrical Engineering and Computer Science (EECS), KTH Royal Institute of Technology. He coordinates research projects such as the Horizon Europe-funded SoftEnable and the WASP-funded Intelligent Cloud Robotics for Real-Time Manipulation at Scale . His research focuses on data-driven methods for robotic manipulation, including transfer learning, cloud robotics, and caging-based manipulation of rigid and deformable objects. Education: PhD in Mathematics, University of Edinburgh (supervisor: Michael Singer) MSc in Advanced Study in Mathematics (Part III), University of Cambridge BSc in Mathematics, University of Edinburgh Research Interests: His work emphasizes scalable robotic manipulation, leveraging deep learning and geometric/topological methods. Key areas include training data requirements, transfer learning, and cloud robotics paradigms for manipulation at scale. Recent projects explore energy margin analysis, caging-guided morphology optimization, and robust policy learning. Publications: His recent work spans topics like caging-based manipulation, federated learning, and cloud robotics infrastructure. Notable contributions include CageCoOpt (manipulation robustness), CloudGripper (open-source testbed), and RealCraft (zero-shot video editing). Awards & Grants: Funded by WASP, Horizon Europe, and the Knut and Alice Wallenberg Foundation. His group hosts the CloudGripper platform and collaborates on benchmarks like DLO@Scale. Advising & Labs: Supervises multiple PhD students and research engineers. Alumni include Robert Gieselmann (Amazon Robotics), Yiannis Karayiannidis (Chalmers University), and Anastasiia Varava (Postdoc at KTH). Active in organizing workshops like RoDGE (IROS 2025) and ICRA 2025 robotics learning events.
Miguel Serras Vasco is a postdoctoral researcher at KTH Royal Institute of Technology in Stockholm, Sweden, affiliated with the Robotics, Perception and Learning (RPL) division. He holds a PhD from Instituto Superior Técnico, University of Lisbon (2023), where his work earned the Best PhD Thesis in AI in Portugal award. His research focuses on multimodal perception, reinforcement learning, and aligning artificial agents with human perception. He previously worked as an RSS Pioneer and research intern at Sony AI. Education: PhD in Artificial Intelligence, Instituto Superior Técnico, University of Lisbon (2023) Research Interests: Vasco’s work bridges robotics, neuroscience, and AI, emphasizing embodied agents that co-exist with humans. He explores representation learning, human-aligned image models, and sample-efficient reinforcement learning. His recent projects include super-human autonomous racing agents and olfactory perception modeling with transformers. Key Contributions: Vasco co-developed the GT Sophy racing agent, achieved outstanding results in visual decoding from brain activity, and proposed methods like FLoRA for preference-based RL. His work on NeuralSolver advances algorithm extrapolation in reinforcement learning. Awards: Best PhD Thesis in AI in Portugal (APPIA, 2023) Outstanding Paper Award at RLC 2024 (for autonomous racing research) Grants/Advising: Vasco advises students on multimodal and reinforcement learning topics. He actively organizes conferences like the Reinforcement Learning and Video Games Workshop (RLVG) at RLC 2025 and collaborates with institutions like INESC-ID (Lisbon). Labs/Teams: Associated with the Collaborative Autonomous Systems unit at KTH and previously with the GAIPS Lab (INESC-ID, Lisbon).
Jonathan Styrud is a Researcher and Industrial Doctoral Student at the Division of Robotics, Perception, and Learning (RPL) at KTH Royal Institute of Technology, collaborating with ABB Robotics. His research focuses on developing control architectures for industrial robots using reinforcement learning techniques, particularly Behavior Trees, to automate assembly tasks in dynamic environments. His work is supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP-AI/MLX). He supervises master's theses, such as one exploring methods to avoid local minima in Genetic Programming of Behavior Trees. Notable contributions include investigating hybrid approaches between automated planning and machine learning to enhance robotic adaptability in unstructured settings. Research interests emphasize bridging the gap between simulation and real-world robot deployment, with a focus on transparency and modularity in control systems. His master's thesis proposal advocates for empirical evaluations of local minima mitigation techniques in robotic manipulation tasks, aiming to improve the efficiency of Genetic Programming. Academic supervision includes guiding projects on optimization algorithms for Behavior Trees, as detailed in his proposed master's thesis. Current affiliations include RPL at KTH and ABB Robotics, fostering industry-academia collaboration.
Anastasiia Varava is an affiliated faculty member and PhD student at KTH Royal Institute of Technology, working within the Division of Robotics, Perception and Learning. Her research focuses on computational geometry and topology applied to robotic manipulation, particularly caging theory and its practical implementations for handling rigid and deformable objects. She collaborates with advisors Florian Pokorny and Danica Kragic on theoretical and applied robotics challenges. Her work integrates robotics with interdisciplinary fields such as topology, machine learning, and computer vision. Key topics include path planning, deformable object manipulation, and geometric algorithms for motion verification. Recent contributions emphasize data-driven approaches for latent space modeling and visual action planning in robotics systems. Varava has authored or co-authored over 30 peer-reviewed articles and conference papers, covering topics from caging-based motion planning to molecular screening algorithms inspired by robotics. Her publications span journals like IEEE Transactions on Robotics and conferences such as IROS and ICRA, reflecting a strong focus on practical robotic systems with theoretical rigor. Her doctoral thesis, Path-Connectivity of the Free Space: Caging and Path Existence (2019), established foundational work on caging and path non-existence in robotics. Current projects involve advancing geometric evaluation techniques for data representations and exploring diffusion models for robotic skill learning.
Polina Kurtser is an Associate Professor at the Department of Computing Science, Umeå University. Her research focuses on machine learning, robotics, and sensor systems, particularly in agricultural and autonomous applications. She has held postdoctoral positions at AASS (Örebro University) and the Department of Radiation Sciences at Umeå University. PhD in Computer Vision and Agri-Robotics (Ben-Gurion University, 2019) Postdoctoral positions at AASS and Radiation Sciences, Umeå University Her work spans agricultural robotics, including sweet pepper harvesting, grape vine detection, and mechanical stress induction in plants. She also explores illumination-independent target detection, dynamic sensing strategies, and statistical models for fruit detectability. Recent publications highlight her contributions to color-to-thermal AI for building inspection, multi-camera vision for gesture recognition, and RGB-D datasets for agricultural perception. Her research integrates machine learning, sensor fusion, and autonomous navigation in challenging environments. She teaches deep learning, machine learning, robotics, and optimization. Her academic affiliations include collaborations in gastronomy (sensory evaluation of robot-cultivated basil) and medical robotics (e.g., ECG chaotic component detection via neural networks).
Magnus Haake is an Associate Professor in Cognitive Science at the Department of Philosophy, Lund University. He has been a researcher at the Department of Cognitive Science (LUCS) since 2012, following his doctoral studies and research at the Department of Design Sciences at Lund University from 2000-2011. Haake is affiliated with the Educational Technology Group (ETG) and participates in the Communication and Cognition Profile area as well as the LU Profile Area: Natural and Artificial Cognition. His educational background includes: Artistic and graphical education in Sweden and USA MSc in Engineering Physics from Lund University PhD in Design Sciences from Lund University Scholarship at University of California, San Diego (UCSD) Haake's research focuses on the intersection of cognitive science and educational technology, with particular emphasis on classroom-based learning environments. His work investigates how students, teachers, and learning materials interact within educational contexts, with special attention to the added value of educational technology. He explores how digital tools can support cognitive processes like attention and perseverance in diverse student populations, particularly in early childhood education settings. His approach integrates perspectives from cognitive science, social psychology, and interaction design to develop and evaluate educational interventions that are both scientifically grounded and practically applicable. His extensive publication record demonstrates a consistent focus on educational technology applications, particularly examining teachable agents, feedback mechanisms, and multimodal learning environments. The research shows progression from foundational work on virtual characters and pedagogical agents to more recent studies on attention scaffolding, information literacy, and the impact of educational interventions during the pandemic. A notable trend is the increasing focus on inclusive education approaches that combine adaptive instruction with universal design principles. Haake has received recognition through his involvement in significant research projects: TELEB: Technologically Enhanced Language learning and its Effect on the Brain (2021-2025) Learning, Context and Transfer: Exploring Constraints and Affordances in the Virtual and Digital Age (2019-2024) Virtuellt klassrum som forskningsplattform (2016-2021) Supporting Students' Productive Choices When Learning Gets Difficult (2015-2018) Påverkan av icke-verbala faktorer och omgivningsfaktorer på barns förståelse (2014-2019) He has supervised several doctoral students, including Jens Nirme in Cognitive Science, and served as assistant supervisor for E.-M. Ternblad's dissertation on "Learning, Context and Transfer." His supervisory approach emphasizes the integration of cognitive science principles with practical educational applications. Haake has also led multiple research projects examining how educational technology can support learning processes, particularly focusing on feedback mechanisms, attention management, and the role of multimodal communication in educational contexts. Haake is actively involved with the Educational Technology Group (ETG) at Lund University Cognitive Science (LUCS), which serves as a hub for interdisciplinary research connecting cognitive science with educational practice. His work often involves collaboration with researchers from psychology, linguistics, and educational sciences to develop and evaluate technology-enhanced learning environments. Recent projects have explored virtual classrooms as research platforms and the impact of non-verbal factors on children's comprehension.
Maurice Lamb is a researcher at the University of Skövde , affiliated with the Interaction Lab (ILAB) and the School of Informatics . His work bridges digital human modeling (DHM) , virtual reality , and human-robot interaction (HRI) with applications in automotive design and cognitive science . Research interests include: Automated design optimization using simulation-based multi-objective methods Collaborative tools for remote design reviews and CAD integration Cognitive implications of inverse kinematics solvers (FABRIK) in motor planning Impact of XR technologies on motor skill learning and human-agent coordination Methodological challenges in NARS (Negative Attitude toward Robots Scale) application Key projects include PLENUM (Vinnova-funded) and OKAVIM (AFA Insurance-funded), focusing on remote collaboration , ergonomics , and cognitive support in VR/XR . His publications span IEEE , Springer , and Elsevier journals, often co-authored with experts like Francisco Garcia Rivera, Erik Billing, and Dan Högberg.
Ingela Nyström is a Professor in Visualization at Uppsala University's Department of Information Technology. She serves as the node coordinator for InfraVis and as Director of Postgraduate Studies at the Department of Information Technology. Her interdisciplinary work bridges Uppsala University's three academic domains through collaborations with the Centre for Image Analysis (CBA), Centre for Women's Mental Health (WOMHER), Uppsala Centre for Digital Humanities (CDHU), and Medtech Science & Innovation (MTSI). Medical image analysis 3D visualization Haptics in surgery planning Interactive segmentation Digital geometry Biomedical engineering Her recent research focuses on rotation-equivariant neural networks for biomedical image classification, interactive segmentation tools for cranio-maxillofacial surgery planning, and precision evaluation of intraoral scanning technologies. Publications since 2023 demonstrate continued work on 3D imaging protocols for implant dentistry and surgical applications. 2024: Equivariant CNNs for rotation-invariant biomedical imaging 2023: In vivo precision studies of full-arch implant scans 2021: Virtual surgical planning with haptic assistance 2016-2017: Multimodal robotics perception and 3D segmentation tools 2014: Orbital morphology analysis in craniosynostoses 2005-2011: Foundational work in 3D skeletons and fuzzy object measurements
Erik Schaffernicht serves as a Senior Lecturer in the Department of Natural Sciences and Technology at Örebro University's School of Science and Technology. His research is primarily conducted through the Center for Applied Autonomous Sensor Systems (AASS) where he leads work in the Adaptive and Interpretable Learning Systems and Robot Navigation and Perception research groups. Dr. Schaffernicht's research spans multiple areas in robotics and artificial intelligence, with particular expertise in sensor systems, behavior trees, and gas distribution mapping. His work bridges theoretical computer science with practical applications in autonomous systems, environmental monitoring, and human-robot interaction. His research often involves developing novel algorithms for robot perception, control, and decision-making in complex environments. His recent publications demonstrate a strong focus on behavior trees for robot control, gas distribution mapping techniques, and applications of machine learning in robotics. The research shows increasing sophistication in using deep learning approaches for environmental sensing and robot navigation, with applications ranging from industrial safety to healthcare monitoring. Dr. Schaffernicht maintains an active research agenda with numerous publications in top robotics and AI venues, including IEEE Robotics and Automation Letters, Robotics and Autonomous Systems, and various IEEE conference proceedings. His work shows consistent collaboration with researchers across Europe, particularly with the AASS research center at Örebro University. His research projects include both ongoing work on automatic cognitive screening tests using eye-tracking technology and completed projects such as AIR (Action and Intention Recognition), RAISE (Robotic System for Air Quality Assessment), and SmokeBot (Mobile Robots for Disaster Site Inspection).
