Towards Safer and More Robust Automated Driving Systems

A collaboration with the University of Freiburg and Bosch Research aims to facilitate the development of safer, transparent, and more resilient systems overall.

Advancing the Next Generation of AI Algorithms for Safer and More Robust Automated Driving Systems
The AI-Drive team with a test vehicle from Bosch. Image Credit: Jürgen Gocke.

The primary focus centers on interlinked modules that are collectively optimized for automated driving. This partnership contributes to a larger initiative aimed at bolstering applied research in automated driving within Germany.

The cooperation project AI-Drive between the University of Freiburg and Bosch Research is our endeavor to develop the next generation of AI algorithms for automated driving to enable safer, more transparent, and more robust overall systems. To that end, the project is also an initiative to strengthen research on automated driving in Germany.

Dr. Abhinav Valada, Project Leader, Faculty of Engineering, University of Freiburg

The initiative is set to span three years, with Bosch allocating approximately 3.7 million euros for funding. Dr. Claudius Gläser is spearheading the project, overseeing the utilization of actual test vehicles provided by Bosch.

On the University of Freiburg’s front, ten doctoral students, under the guidance of Prof. Dr. Abhinav Valada, Prof. Dr. Frank Hutter, and Prof. Dr. Joschka Bödecker from the Faculty of Engineering and the ELLIS Unit Freiburg, are actively engaged in the research. This collaborative effort involves close coordination with researchers from Bosch Research.

The technological advancement in automated driving traditionally focuses on developing individual autonomy modules separately for perception, prediction, planning, and control. With the new generation of AI algorithms, we want to create a unified framework in which different modules are closely connected and jointly optimized.

Dr. Abhinav Valada, Project Leader, Faculty of Engineering, University of Freiburg

Valada added, “This will enable us to get even closer to human driving behavior, for example in terms of avoiding overly cautious or aggressive driving.”

One objective is to tightly integrate prediction and planning modules within the AI-Drive framework. In contrast to traditional deep learning models characterized by low transparency, AI-Drive adopts a transparent “white box” approach.

The system’s components are intentionally crafted to produce intermediate results that are interpretable by humans, fostering trust and streamlining certification processes.

The cooperation with the University of Freiburg is for us an important link to cutting-edge research in the field of automated driving and it allows us both to jointly advance the state of research and to incorporate it directly into future automation solutions.

Claudius Gläser, Bosch Research, University of Freiburg

The project aims to create cutting-edge techniques for neural architecture search, automating the design and optimization of network architectures. This initiative will contribute to enhancing the efficiency of the development and deployment cycle.

Overall, we hope that these developments will lead to a safer, more transparent, and more robust overall system for autonomous driving,” stated Professor Dr Frank Hutter.

The project also endeavors to contribute significantly to the scientific community. Technological and theoretical breakthroughs from this collaboration will be disseminated through publication in esteemed scientific journals and conferences.

Additionally, biannual symposiums will be arranged, providing a platform for doctoral students to showcase their work and evaluate the developed methods.

“AI-Drive” builds upon the extensive collaboration between the University of Freiburg and Bosch Research in the realm of machine learning. Notably, from 2018 to 2022, Hutter's Machine Learning Lab closely collaborated with Bosch Research to enhance joint research on AutoML.


Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.