Master's thesis; Efficient Knowledge Transfer in Heterogeneous Autonomous Driving Systems
2 days ago
Background
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 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 how knowledge distillation mechanisms can facilitate 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 distillation in a federated learning context.
Description
In this master thesis project, you will focus on investigating knowledge distillation as a method to support 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 distillation to maintain model performance and adaptability in real-time, large-scale deployments.
Key Responsibilities
- Design and Implement Knowledge Transfer Frameworks: Develop and optimize strategies for transferring knowledge between heterogeneous AI models in both simulations and real-world driving scenarios.
- Simulation, Evaluation, and Safety Oversight: Create and manage diverse simulation environments, monitor agent behavior, and ensure safe and efficient decision-making in autonomous systems.
- Collaboration, Integration, and Continuous Improvement: Work across AI architectures and vehicle platforms, coordinate among system components, mentor team members, and refine methods for performance and efficiency.
Qualifications
We are looking for 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
Terms
Industry supervisor:
Henrik Abrahamsson, PhD )
Sima Sinaei, PhD )
Division, department: Digital Systems division, Industrial Systems department
- Location: RISE, Kista, Stockholm
- Application deadline: November 30, 2025
- Start date: As soon as possible
- Credits: 30 points
- Compensation: SEK upon a successful completion of a high-quality thesis.
Welcome with your application
-
Kista, Stockholm, Sweden RISE Research Institutes of Sweden Full time 480,000 - 960,000 per yearBackgroundAutonomous 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...
-
Kista, Stockholm, Sweden RISE Research Institutes of Sweden Full time 400,000 - 600,000 per yearBackgroundThe 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...
-
Kista, Stockholm, Sweden RISE Research Institutes of Sweden Full time 450,000 - 700,000 per yearBackgroundAutonomous 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...
-
Kista, Stockholm, Sweden RISE Research Institutes of Sweden Full time 29,900 - 39,990 per yearIn the Internet of Things (IoT), a large number of connectable devices will be connected to the Internet, with many of them being heterogeneous or resource-constrained in terms of processing power, memory, accessibility, and energy budget. For these reasons, it is important that IoT networks can rely on efficient communication models together with strong...
-
Kista, Stockholm, Sweden RISE Research Institutes of Sweden Full time 400,000 - 600,000 per yearBackgroundAs monolithic AI models reach their limits in complex, dynamic environments, the future of robotic intelligence lies in creating teams of specialised agents that can collaborate to solve problems. This approach mirrors how human teams work, allowing for more robust, safe, and nuanced behaviours. This thesis project will explore this frontier by...
-
Kista, Stockholm, Sweden RISE Research Institutes of Sweden Full time 39,990 - 59,988 per yearBackgroundThe next generation of smart buildings requires systems that are not just automated, but intelligent and responsive to human behaviour. Automatic doors are a key component of modern infrastructure, yet they often lack the intelligence to differentiate between intent and incidental movement, leading to unnecessary openings that waste energy and can...
-
Kista, Stockholm, Sweden Huawei Sweden Full time 450,000 - 550,000 per yearLocation: Kista, StockholmPreferred starting date: Jan. 2026Extent: 1-2 student, 30hp.About The CompanyFounded in 1987, Huawei Technologies is one of the fastest growing telecommunications and network solutions providers in the world. At Huawei Technologies, we look for people who share our vision: to enrich life with communication. We are a leading supplier...
-
Kista, Stockholm, Sweden RISE Research Institutes of Sweden Full time 40,000 per yearWe have an open position for a master student to join us at the Connected Intelligence research unit, within the Computer Science department at RISE.BackgroundPrivate 5G networks are becoming essential for industries that need reliable, low-latency, and secure connectivity. Machine learning models are increasingly used in these networks to predict KPIs and...
-
Kista, Stockholm, Sweden RISE Research Institutes of Sweden Full time 40,000 - 60,000 per yearWe have an open position for a dedicated master student to join us at the Connected Intelligence research unit, within the Computer Science department at RISE.Background and purposeMachine learning (ML) has catalyzed the design and development of various intelligent systems over wide application domains. Many efforts have been made to deploy ML models on...
-
Kista, Stockholm, Sweden RISE Research Institutes of Sweden Full time 30,000 - 60,000 per yearBackgroundLarge audio-language models (LALMs) are moving from demos to production for assistants, meetings, and accessibility. Yet they remain vulnerable to adversarial audio that corrupts transcription, reasoning, and safety layers. Recent benchmarks show that seemingly benign edits, including content tweaks, emotional style shifts, and common acoustic...
