Master's thesis: Federated Self-Supervised Learning for Scalable Autonomous Driving på RISE Research Institutes of Sweden AB i Stockholm
RISE Research Institutes of Sweden AB · Stockholm
Master's thesis: Federated Self-Supervised Learning for Scalable Autonomous Driving
Background and project description
Autonomous vehicles generate massive amounts of multi-modal sensor data, including camera images, lidar point clouds, radar
...
Background and project description
Autonomous vehicles generate massive amounts of multi-modal sensor data, including camera images, lidar point clouds, radar
measurements, GPS information, and vehicle control signals. These heterogeneous data sources provide complementary information
that is essential for robust perception, localization, and decision-making. However, transferring such large volumes of data to
centralized servers is often impractical due to bandwidth limitations, storage costs, privacy concerns, and regulatory
constraints. Federated Learning (FL) offers a distributed and privacy-preserving framework that enables multiple vehicles, fleets,
or organizations to collaboratively train machine learning models without sharing their raw data. While FL has shown significant
promise for autonomous driving applications, its effectiveness is often limited by the availability of high-quality labeled data.
Deep learning-based perception modules require high-quality annotations, which are costly and complex to obtain. Self-supervised
learning (SSL) offers a solution by leveraging mostly unlabeled data with minimal labels. Early studies show that federated
self-supervised training can achieve performance comparable to centralized approaches, with potential improvements as larger
unlabeled datasets are used.
This thesis project aims to advance federated learning for autonomous vehicles by integrating self-supervised methods with robust
aggregation techniques to develop models that are efficient, generalizable, and capable of handling both common and rare driving
scenarios, while reducing reliance on manual annotation and avoiding the costs of central data storage.
The thesis is part of the research project DREAM – Distributed, Robust and Efficient AI for Autonomous Vehicles. The topic is
highly relevant for enabling scalable and efficient AI development in next-generation autonomous driving systems.
Main Tasks
* In this master thesis project, you will focus on:
A novel self-supervised learning approach to exploit all available data on the central server, even with limited labels
A hybrid federated learning scheme combining self-supervised and supervised techniques, adapted to local and global learning
rounds
Validation through extensive comparisons with fully supervised learning within the same federated scheme.
Demonstration of the efficacy of combining self-supervised and supervised learning on the Zenseact Open Dataset (ZoD) under
various federated scenarios.
Present findings to the project partners
Qualifications
We are looking for one or two highly motivated students with a good general background in machine learning and computer vision.
The following skills would be essential:
Deep learning
Computer vision
Python programming
Reading scientific papers
Handling complex systems
Federated learning (would be a bonus)
Conditions.
Location: RISE, Kista, Stockholm
Applications are reviewed on a rolling basis, apply as soon as possible, but no later than August 31st, 2026.
Starting date: As soon as possible, not later than September 1st, 2026.
Credits: 30 points
Compensation: 39990 SEK upon a successful completion of a high-quality thesis.
Supervisors:
Sima Sinaei (RISE)
Henrik Abrahamsson (RISE)
Welcome with your application!
Send in your application (CV, motivation letter, transcript of records) no later than August 31st.
For any questions, please contact:
Sima Sinaei, sima.sinaei@ri.se
Henrik Abrahamsson, henrik.abrahamsson@ri.se
Roll
Master's thesis: Federated Self-Supervised Learning for Scalable Autonomous Driving
Background
Autonomous vehicles rely on AI models trained on large-scale, multi-modal sensor data. As vehicle platforms evolve, changes in
sensors and hardware often require updating or retraining these models, which is costly and time-consuming. A key challenge is
therefore how to efficiently transfer knowledge between models operating under different configurations.
This thesis is part of the research project DREAM – Distributed, Robust and Efficient AI for Autonomous Vehicles. The topic is
highly relevant for enabling scalable and efficient AI development in next-generation autonomous driving systems.
Description
Sensor data and AI enable cars to detect objects, understand their environment and make decisions about how to respond. When
vehicles are updated and new models are developed, sensors and hardware often change, which in turn also affects the AI models
used. One approach would be to create a new AI model from scratch and collect new data each time the vehicle platform is updated.
A more efficient solution would be to transfer knowledge between models with varying architectures. In this Master’s thesis
project, we aim to investigate knowledge transfer between diverse models and hardware setups, ensuring that learning can continue
even when architectures change. The work will use the Zenseact Open Dataset and also explore knowledge transfer in a federated
learning context.
Main Tasks
In this master thesis project, you will focus on investigating knowledge transfer between diverse models and hardware setups in
autonomous vehicles. Specifically, you will:
* Explore how knowledge can be efficiently transferred between AI models with different architectures.
* Evaluate techniques for updating AI models when vehicle sensors or hardware change, without the need for full retraining or
collecting extensive new datasets.
* Analyze the effectiveness of the proposed approach through experiments using multi-modal sensor data, including vehicle control
signals, geographical positions, and lidar, radar, and camera measurements.
* Develop and experiment with a federated learning framework that incorporates knowledge transfer to maintain model performance
and adaptability in real-time, large-scale deployments.
Qualifications
We are looking for one or two highly motivated students with a good general background in machine learning and computer vision.
The following skills would be essential:
* Deep learning
* Federated learning (would be a bonus)
* Python programming
* Reading scientific papers
* Handling complex systems
Conditions
* Location: RISE, Kista, Stockholm
* Applications are reviewed on a rolling basis, apply as soon as possible, but no later than August 31st, 2026.
* Starting date: As soon as possible, not later than September 1st, 2026.
* Credits: 30 points
* Compensation: 39990 SEK upon a successful completion of a high-quality thesis.
Supervisors:
* Henrik Abrahamsson (RISE)
* Sima Sinaei (RISE)
Welcome with your application!
Send in your application (CV, motivation letter, transcript of records) no later than August 31st.
For any questions, please contact:
* Henrik Abrahamsson, henrik.abrahamsson@ri.se
* Sima Sinaei, sima.sinaei@ri.se
About the position
A three-year position as Postdoctoral Research Fellow in machine learning and artificial intelligence in epidemiology is available at the Department of Public Health and Interdisciplinary Health Science, Institute of Health and Society, Faculty of Medicine, University of Oslo.
The position is linked to the project LINDA-FAMILIA – Implementation of an Integrated Digital Health System for Infectious Diseases in Maternal and Child Health in East Africa, a Horizon Europe/Global Health EDCTP3 project.
The postdoctoral fellow will contribute to a work package on clinical research co-led by the University of Oslo and the Uganda National Institute of Public Health.
Up to 10% of the position will be devoted to career-promoting work, primarily teaching and supervision in machine learning and artificial intelligence for master students in epidemiology.
About the project:
LINDA-FAMILIA will do research within digital eRegistries for reproductive, maternal, newborn and child health services in four regions in East Africa: Addis Ababa Region, Ethiopia; Eastern Province, Rwanda; Kilimanjaro Region, Tanzania; and Lango sub-Region, Uganda.
The eRegistries are deployed to replace paper-based health information systems and support clinical care, disease surveillance and research through harmonized longitudinal individual-level data across the four countries. The systems include clinical decision support, referral coordination, targeted client communication, data management and interoperability.
The project will demonstrate the scientific value of these routinely collected real-world eRegistry data for multi-country clinical and epidemiological research on poverty-related infectious diseases in maternal, perinatal, neonatal and child health.
More about the position
The postdoctoral fellow will work at the interface of epidemiology, causal inference, prediction modelling, responsible AI, digital health and global maternal and child health.
The work will include development and application of machine learning and AI methods to large-scale, longitudinal, routinely collected eRegistry data. The successful candidate will collaborate with researchers, PhD candidates, postdoctoral fellows, public health institutions and Ministries of Health in Ethiopia, Rwanda, Tanzania and Uganda, as well as partners in Europe.
Some international travel for project meetings, workshops and collaboration with country teams should be expected.
A career plan shall be developed for the Postdoctoral Fellow, specifying the competencies the Postdoctoral Fellow should acquire. UiO is responsible for following up on the career plan and ensuring that the Postdoctoral Fellow has access to career guidance throughout the postdoctoral term.
Up to 10% of the position will be devoted to career-promoting work, primarily teaching and supervision in machine learning and artificial intelligence for master students in epidemiology.
The duration of appointment is 3 years.
Your areas of responsibility will be
The successful candidate will:
• Develop and apply machine learning and AI methods for epidemiological research using longitudinal eRegistry data.
• Contribute to comparative epidemiological studies across countries and data systems.
• Apply causal inference and targeted learning methods, including TMLE and Super Learner approaches where relevant.
• Contribute to the development and validation of risk prediction models for severe maternal, perinatal, neonatal and child outcomes related to poverty-related infectious diseases.
• Contribute to geospatial epidemiology analyses using GIS-linked eRegistry data.
• Develop reproducible R-based analysis pipelines, including support for DataSHIELD or other privacy-preserving/distributed analyses.
• Contribute to data harmonization, data quality assessment, missing data strategies, data anonymization and data sharing procedures.
• Contribute to protocols, statistical analysis plans and reporting for the registry-based cluster randomized trial of SMS and automated voice messaging reminders.
• Collaborate with and support researchers in the partner countries, including training and capacity-building activities.
• Publish results in peer-reviewed journals and present findings at international conferences and project meetings.
• Contribute to teaching and supervision in machine learning and AI for master students.
Qualifications
You must have:
• A degree equivalent to a Norwegian doctoral degree in epidemiology, biostatistics, statistics, machine learning, artificial intelligence, computer science, health data science, public health, medicine with strong quantitative methods, or a closely related field.
• The doctoral dissertation must be submitted for evaluation by the application deadline. Appointment is dependent on the public defense of the doctoral thesis being approved before the start of employment.
• Documented competence in statistical modelling, machine learning, artificial intelligence, causal inference, prediction modelling or related quantitative methods.
• Experience with analysis of large, complex health data, such as longitudinal data, registry data, electronic health records, cohort data or trial data.
• Strong programming skills in R, Python or equivalent scientific computing languages. Strong R skills are particularly relevant for this project.
• Excellent written and oral communication skills in English.
Desired qualifications:
Experience with one or more of the following will be considered an advantage:
• Maternal, perinatal, neonatal or child health epidemiology.
• Infectious disease epidemiology, poverty-related diseases or global health research in low- and middle-income countries.
• Digital health, DHIS2, eRegistries, electronic health records or routine health information systems.
• Targeted learning, TMLE, Super Learner, ensemble methods, causal machine learning or related methods.
• Geospatial epidemiology and GIS methods.
• DataSHIELD, federated learning or distributed multi-country data analysis.
• Registry-based trials, cluster randomized trials or pragmatic trials.
• Responsible AI, model validation, calibration, interpretability, bias assessment or fairness in health research.
• Teaching or supervision in epidemiology, machine learning, AI, biostatistics or health data science.
• Norwegian or another Scandinavian language is an advantage, but not a requirement.
Personal qualities
We are looking for a candidate who:
• Is motivated to develop an independent research profile in machine learning and AI for epidemiology.
• Can work independently and systematically.
• Has strong analytical and problem-solving skills.
• Enjoys interdisciplinary and international collaboration.
• Communicates well with researchers, clinicians, statisticians, software developers and public health partners.
• Contributes to a collegial and inclusive working environment.
Personal suitability will be emphasized.
We need different perspectives in our work
UiO is an open and internationally oriented comprehensive university that strives to be an inclusive and diverse workplace and academic environment. You can read more about UiO’s work on equality, inclusion, and diversity at uio.no.
We fulfill our mission most effectively when we draw upon our variety of experiences, backgrounds, and perspectives. We are looking for great colleagues—could you be the next one?
We will do our best to accommodate your needs. Relevant adjustments may include modifications to working hours, task adaptations, digital, technical, or physical adjustments, or other practical measures.
If you have an immigrant background, a disability, or CV gaps, we encourage you to indicate this in the job application portal. We always invite at least one qualified candidate from each group for an interview. In this context, disability is defined as an applicant who identifies as having a disability that requires workplace or employment-related accommodations. For more details about the requirements, please refer to the Employer portal (Norwegian).
The selections made in the job application portal are used for anonymized statistics that all state employers include in their annual reports.
More information about gender equality initiatives at UiO can be found here.
We hope you will apply for the position with us.
We offer
• A three-year postdoctoral position in an international and interdisciplinary research project.
• Opportunity to develop an independent research profile in machine learning, AI and epidemiology.
• Collaboration with research and public health partners in Norway, Ethiopia, Rwanda, Tanzania, Uganda and Europe.
• Access to a large international project working with real-world maternal and child health data.
• Career development support through the Faculty of Medicine’s postdoctoral program and an individual Career Development Plan.
• Committed colleagues in a good working environment.
• Good welfare schemes.
• Opportunity of up to 1.5 hours a week of exercise during working hours.
• A workplace with good development and career opportunities.
• Membership in the Statens Pensjonskasse, which is one of Norway's best pension schemes with beneficial mortgages and good insurance schemes.
• Salary in position as Postdoctoral Fellow, position code 1352 in salary range NOK from 610 000 to 720 000, depending on competence and experience. From the salary, 2 percent is deducted in statutory contributions to the State Pension Fund.
• Oslo’s family-friendly environment with rich opportunities for culture and outdoor activities.Exciting and meaningful tasks in an organization with an important societal mission, contributing to knowledge development, education, and enlightenment that promote sustainable, fair, and knowledge-based societal development.
Read more about the benefits of working in the public sector at Employer Portal.
Application
Your application should include:
• Application letter.
• CV.
• A complete list of publications.
• Project description.
• Transcripts and certificates.
• Contact information for 2-3 references.
Application with attachments must be submitted via our recruitment system Jobbnorge, click "Apply for the position".
When applying for the position, we ask you to retrieve your education results from Vitnemålsportalen.no. If your education results are not available through Vitnemålsportalen, we ask you to upload copies of your transcripts or grades. Please note that all documentation must be in English or a Scandinavian language.
General information
The best qualified candidates will invited for interviews.
Applicant lists can be published in accordance with Norwegian Freedom of Information Act § 25. When you apply for a position with us, your name will appear on the public applicant list. It is possible to request to be excluded from this list. You must justify why you want an exemption from publication and we will then decide whether we can grant your request. If we cannot, you will hear from us.
Please refer to Regulations for the Act on universities and colleges chapter 3 (Norwegian) and Guidelines concerning appointment to recruitment positions at UiO.
The University of Oslo has a transfer agreement with all employees that is intended to secure the rights to all research results etc.
Background
We are offering a Master’s thesis or possible internship within digital twins, eXtended reality, robotics, & autonomous systems in
the area of computer vision, 3D graphics plus AI-driven scene representation. We are focusing on the emerging field of 3D Gaussian
Splatting. It has gained attention as a powerful alternative to Neural Radiance Fields for high-quality, real-time rendering of
complex 3D environments. By representing scenes as collections of anisotropic Gaussian primitives, the method enables
photorealistic rendering with significantly improved efficiency and interactivity. Your work will be algorithm development,
implementation, experimentation, and scene evaluation using GPU-based frameworks.
Thesis Focus
* Real-time 3D scene reconstruction
* Dynamic Gaussian Splatting for moving objects and environments
* Compression and optimization of Gaussian representations
Work tasks
* State of the art survey, including code bases in this area
* Practical skills in Python/C++, CUDA, and deep learning frameworks
* A demonstration using a moving platform. 3D rendering that a camera mounted on the platform, presenting on a 3D display.
Desired background
We are looking for very motivated students with interests in:
* Computer vision / graphics
* Machine Learning
* Experience with PyTorch, OpenGL, CUDA, or 3D reconstruction, is very desirable.
Your background
Studying at a Swedish university, you should have a solid technical background + machine learning. Programming in at least 2
languages. Python+1 from Java, Rust, or C++.
Other information
You will be given an office at RISE, Kista expected there 2-3 days / week. Paid 1333 SEK per ECTS, tax deductible, paid on
satisfactory oral + written thesis defense. Start time Sept 2026.
Contact
Ian Marsh, Ph.D, Senior Researcher, ian.marsh@ri.se
Union representatives: For further information about labor unions, please contact the union representative, Ingemar Petermann,
SACO, +46 10 228 41 22 and Linda Ikatti, Unionen, +46 10 516 51 61.
Location: Kista, Tel: +46 70 772 1536
