Master's thesis; Scalable Federated Learning for Autonomous Driving with Self-Supervision
3 days ago
Background
Autonomous vehicles rely on vast amounts of multi-modal sensor data—including vehicle control signals, GPS, lidar, radar, and camera inputs—to perceive and navigate their environment. Sending all this data to central storage is often impractical due to high bandwidth and storage costs, and annotating it manually is nearly impossible because of the sheer volume. Federated learning (FL) provides a distributed, privacy-preserving alternative, allowing multiple entities to collaboratively train a shared model without exchanging local data.
Despite recent advances, FL faces challenges in large-scale, real-time vehicle deployments, particularly the need for 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 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.
Description
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 ZoD dataset ) under various federated scenarios.
- Present findings to the project partners
Key Responsibilities
- Design, implement, and optimize federated learning systems that efficiently scale across heterogeneous devices while maintaining privacy and compliance with data protection regulations.
- Collaborate with cross-functional teams to integrate machine learning models into distributed environments, ensuring high communication efficiency, fault tolerance, and robustness against model drift.
- Conduct research and development of novel algorithms for secure aggregation, differential privacy, and model compression to enhance scalability, convergence speed, and energy efficiency in federated networks.
Qualifications
We are looking 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)
Terms
- Industry supervisor:
- Sima Sinaei, PhD )
- Mina Alibeigi, PhD )
- Location: RISE, Kista, Stockholm
- Application deadline: November 15th, 2025
- Starting date: As soon as possible, not later than December 1st, 2025.
- Credits: 30 points
- Compensation: SEK upon a successful completion of a high-quality thesis.
Welcome with your application
-
Stockholm, Stockholm, Sweden RISE Research Institutes of Sweden AB Full time 400,000 - 800,000 per yearBackground The widespread adoption of autonomous vehicles (AVs) and advanced driver assistance systems has dramatically increased the volume of sensor data generated at the network edge. Leveraging this data for intelligent driving services requires machine learning models that are both accurate and privacy conscious. Federated Learning (FL) has emerged as a...
-
Stockholm, Stockholm, Sweden RISE Research Institutes of Sweden AB Full time 250,000 - 350,000 per yearBackground Autonomous vehicles rely on AI models and vast amounts of multi-modal sensor data—including vehicle control signals, GPS, lidar, radar, and camera inputs—to perceive and navigate their environment. When vehicles are updated and new models are developed, sensors and hardware often change, which in turn also affects the AI models used. One...
-
Master Thesis Program 2026
3 days ago
Stockholm, Stockholm, Sweden Einride Full time 450,000 - 600,000 per yearBorn autonomous. Born electric.Since 2016, our technology has connected global communities with the things they need – and all without the emissions. We're made up of experts in multiple fields and that's how we've developed a new way to move goods. This is technology purpose-built for the industry. This is safer, cleaner, and more reliable movement.We are...
-
Stockholm, Stockholm, Sweden RISE Research Institutes of Sweden AB Full time 40,000 - 60,000 per yearMaster's thesis; Machine learning (ML) models that can estimate the percentage of each fibre type contribution in a paper boardBackground The thesis forms part of the VINNOVA financed project "AI-Tomo: Accelerated materials characterisation by AI and X-ray tomography" ). The goal of AI-TOMO is to develop AI algorithms for fast, effective segmentation and...
-
Stockholm, Stockholm, Sweden Soundtrack Full time 60,000 - 80,000 per yearThe challengeWhat characterizes a musical work? In our music catalog of over 100 million tracks, a single musical work like "Bohemian Rhapsody" by Queen can exist in dozens of versions: the original studio recording, various remasters, a live performance, and even covers by other artists. Managing this complexity is a deep and fascinating challenge for...
-
Master Thesis
3 days ago
Stockholm, Stockholm, Sweden DEMA Full time 450,000 - 675,000 per yearDema helps leading brands make smarter marketing investment decisions through advanced analytics and modern Marketing Mix Modeling (MMM). Our platform combines statistical rigor with usability, enabling marketing teams to understand what truly drives performance and growth.We are now looking for a curious and motivatedMaster's studenteager to explore...
-
Master Thesis
1 day ago
Stockholm, Stockholm, Sweden ASSA ABLOY Full timeAre you a master's student in Computer Science looking for an innovative company to collaborate with on your master's thesis during the spring semester of 2026? Look no further. ASSA ABLOY is the global leader in access solutions and provides the latest technologies to give access to physical and virtual spaces for millions of people every day. Joining ASSA...
-
Master Thesis Intern Development
3 days ago
Stockholm, Stockholm, Sweden OSTTRA Full time 350,000 - 550,000 per yearAbout the Role:Master Thesis writerAbout OSTTRACandidates should note that OSTTRA is an independent firm, jointly owned by S&P Global and CME Group. As part of the joint venture, S&P Global provides recruitment services to OSTTRA - however, successful candidates will be interviewed and directly employed by OSTTRA, joining our global team of more than...
-
Master Thesis Proposal
3 days ago
Stockholm, Stockholm, Sweden Syntronic Full time 28,000 - 42,000 per yearDo you want to explore the frontier of autonomous systems?In this thesis, we invite one or two students to configure and deploy a simulated autonomous vehicle equipped with for example LiDAR, IMU and camera. The simulation-first approach enables freedom to test and evaluate different sensor fusion SLAM algorithms, with the possibility to later transfer the...
-
Master Thesis
1 day ago
Stockholm, Stockholm, Sweden ASSA ABLOY Group Full time 450,000 - 675,000 per yearAre you a master's student in Engineering or Economics looking for an innovative company to collaborate with on your master's thesis during the spring semester of 2026? Look no further.ASSA ABLOY is the global leader in access solutions and provides the latest technologies to give access to physical and virtual spaces for millions of people every day....
