Skip to main content
Search
Menu

DREAM – Distributed, Robust and Efficient AI for Autonomous Vehicles

Project DREAM develops efficient solutions for real-time federated learning for autonomous vehicles. This enables the secure handling of large multimodal data sets and contributes to increased digitalization, road safety and more efficient AI systems for both the automotive industry and society.

This project addresses challenges with federated learning for large-scale real-time use in autonomous vehicles. Autonomous vehicle systems rely on large amounts of multimodal sensor data, where centralized processing is impractical due to privacy concerns and communication limitations. The project aims to make federated learning more efficient by using self-supervised learning to train models with mainly unannotated data. The project will further investigate knowledge distillation as a possible solution for transferring knowledge between different models with varying architectures when the platform changes. 

To streamline data exchange in federated learning, methods for compression and aggregation are studied. A large multimodal dataset will be collected using a fleet of vehicles equipped with sensors. This dataset will initially be shared within the project consortium but with the goal of eventually make the dataset public. 

The project contributes to advanced digitalization of Swedish industry. The work is important for the Swedish automotive industry, but the knowledge and expertise gained will be applicable in all domains related to federated learning, multimodal data and where there is a large number of nodes with limited embedded resources. The project is based on a strong collaboration between Zenseact, Scaleout, AI Sweden and RISE, and is expected to lead to more robust and efficient distributed AI systems.

Summary

Project name

DREAM

Status

Active

Region

Region Gotland, Region Stockholm, Region Uppsala

RISE role in project

Project management and research

Project start

Duration

24 months

Total budget

15.8 MSEK

Partner

RISE, Zenseact, Scaleout, AI Sweden

Funders

Vinnova

Coordinators

Project members

Sima Sinaei

Contact person

Sima Sinaei

Senior Researcher

+46 73 072 22 91

Read more about Sima

Contact Sima
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.

* Mandatory By submitting the form, RISE will process your personal data.

Henrik Abrahamsson

Contact person

Henrik Abrahamsson

Senior Researcher

+46 70 774 15 95

Read more about Henrik

Contact Henrik
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.

* Mandatory By submitting the form, RISE will process your personal data.