GreenAutoML4FAS - Automated Green-ML for Driver Assistance Systems

GreenAutoML4FAS - Automated Green-ML for Driver Assistance Systems

Led by:  Prof. Dr. Marius Lindauer
Team:  AutoML
Year:  2023
Funding:  BMUV
Duration:  2023 - 2026


What is the ecological challenge?

Nowadays, AI applications can be found in many devices used in daily life, which means that the average energy consumption of a person is constantly increasing. Due to the scarcity of resources, it is thus increasingly important to also develop AI applications in a resource-saving manner. However, in this context, a major challenge includes analyzing large amounts of data with security relevance. Due to its complexity, deep learning, frequently used for this purpose, usually requires high energy consumption and thus generates a large ecological footprint. In order to prevent this footprint from becoming too large, resource-efficient AI applications are absolutely necessary. As an example, in our project, we study driver assistance systems, which improve the safety, comfort, and economy of driving.

What contribution can AI make in concrete terms? 

The aim of the GreenAutoML4FAS project is to design a holistic system consisting of hardware, efficient coding and transmission of data and models, and dynamic and adaptive software in a resource-efficient manner. To this end, we will develop new resource-efficient AutoML systems that efficiently support developers in the entire AI development cycle. Exemplarily, the focus here is on driver assistance systems. Combining efficient algorithms, communication, and hardware in this area will lead to significant energy savings. Thus, the holistic concept developed in the project will also be transferred to other areas in which AI or deep learning is used as a machine learning method. 

What is the lighthouse character of the project?

Unlike many existing approaches, the project idea is based on a holistic approach to making AI applications resource-efficient. The knowledge- and application-oriented dissemination of the results is also worth mentioning: The developed concepts for efficient use of hardware, coding, as well as automated machine learning (AutoML) are documented and made available online. In particular, the further development of AutoML enables future AI projects to work resource-efficiently from the beginning, thus having the greatest possible long-term impact.


Funded by