Postdoctoral Fellowship (08) at Umea University, Sweden

This project proposes the implementation of a cognitive agent embodied in a humanoid robot Unitree G1 which will collaborate with a human partner to solve a spatial problem (e.g. 3D puzzle).

The tasks to be carried out are: (i) scene understanding: detection of objects and relations between objects, and use of these relations to infer new knowledge (i.e. reasoning); (ii) explore object affordances, learn the consequences of the actions carried out and enrich the knowledge base (i.e. learning by interaction); (iii) querying the knowledge base about what was useful in the past to predict actions that might be useful in the present, try them out and update its knowledge base (i.e. update learning). Also writing scientific papers and communicating our research advances in conferences.

Methods: programming a humanoid platform using ROS2 packages, solve SLAM, use imitation learning algorithms to learn pick-and-place actions, design HRI experiments with users, evaluate data, and share the code and benchmarks in open repositories.

The announced position is part of a translational and implementation research program aimed at bridging evidence from the Umeå HIT studies into scalable real-world practice in both digital and community settings.

Previous work within the Umeå HIT project has demonstrated that supramaximal high-intensity interval training (HIT), based on short, regulated cycling sprints is feasible, safe, and effective for older adults, with improvements in cardiorespiratory fitness (VO₂peak), leg strength, and working memory. Participants also expressed high motivation for this type of training with excellent adherence.

The aim of this postdoc project is to translate these findings into scalable, user-centered solutions that enable safe and effective implementation of HIT for older adults across contexts. The position includes planning, coordination, and execution of research within the project, including data collection, analysis, scientific reporting, and dissemination. Supervision of students may be included.

The postdoc will primarily work with:

• Co-creation and development of a digital HIT module
• Adaptation and implementation of exercise protocols for both home- and gym-based contexts
• Data collection, evaluation, and refinement of implementation strategies
• Analysis of quantitative and qualitative outcomes from pilot implementations

The research group currently consists of 3–5 members and collaborates closely with the Departments of Neurology, Pathology, and Radiology at Norrlands University Hospital (NUS), as well as Umeå University. The group includes a principal investigator, a PhD student, a research nurse, and several affiliated researchers and students. Our research spans the spectrum from epidemiological studies to analyses of cerebrospinal fluid, genetics, and protein biochemistry related to Parkinson’s disease and other alpha-synucleinopathies. A major focus is on genetic and lifestyle-related risk factors in individuals affected by these currently incurable disorders, to understand their causes and how they relate to synaptic dysfunction and impaired cell endocytosis. This research involves both clinical studies of patients and molecular biological analyses carried out locally in Umeå and through international collaborations, enabling robust findings across multiple datasets.

As a postdoctoral fellow, you are expected to independently conduct your own research project, including publications and engagement with the surrounding community. The research will be focused on educational work with a focus on one or more of the aesthetic subjects: Visual Arts, Music and Sloyd . You are expected to contribute to the development of the department’s research environment, for example by initiating collaborations with other researchers at the department, participating in and organizing seminars and other academic gatherings. You are also expected to attend other meetings and staff activities at the department, such as workplace meetings and staff days. Teaching at first-, second- and third-cycle levels (undergraduate, Master’s and doctoral levels) may occur up to a maximum of 20%, depending on the needs of the department.

The project will develop privacy-aware machine learning (ML) models. We are interested in data-driven models for complex data, including temporal data. We are interested in both data-driven models as well as models built from synthetic data. Within privacy, we are interested in different types of privacy measures and models (differential and integral privacy, k-anonymity), different scenarios (centralized and decentralized data; local and global privacy). For decentralized data, we consider federated learning. We are interested in privacy-preserving machine learning at a scale.

We are seeking a postdoctoral researcher to join project “Rapid Detect—Transboundary Action: Fast Species Detection using LAMP” at the Department of Ecology, Environment, and Geoscience, PI Associate Professor Anu Valtonen. This project is a collaboration among Umeå University, University of Eastern Finland, University of Oulu, and Natural Resources Institute Finland, funded by Interreg Aurora. The project seeks to apply LAMP (loop-mediated isothermal amplification), a molecular species identification/detection method, to a range of species that are invasive or endangered in Northern Fennoscandia. The successful candidate will be responsible for laboratory work in this project, further developing the method for practical application to contexts in ecology and conservation. Main tasks will include testing newly designed primer sets on samples derived from a range of tissues and substrates and extracting DNA from these diverse substrates as needed. An important goal of Rapid Detect is to engage relevant stakeholders, and the postdoctoral researcher will play an important role in streamlining the method for potential uptake by external parties, creating guidelines and eventually organizing a webinar and hands-on workshop. Where possible, samples will be sourced via partners, and the postdoctoral researcher will be partially responsible for obtaining samples from Sweden.