AI Innovations for Safe Autonomous Driving
Representatives from Government and Industry discuss the opportunities for Germany as a location for the automotive industry

Generative AI will fundamentally change and accelerate the further development of autonomous driving. Used correctly, it can literally take previous technological advances to a new level: In line with the safety requirements of the German automotive industry, the use of generative AI makes it possible to develop safe, highly automated driving functions in every traffic context. The next steps towards fully automated (Level 4) and ultimately driverless autonomous driving (Level 5) are thus within reach.
High-level event at the Federal Ministry for Economic Affairs and Climate Action
How exactly this is to happen and why the time is ready for it was the subject of an economic policy discussion panel hosted by the Federal Ministry for Economic Affairs and Climate Action (BMWK) on Monday, October 7, 2024. Federal Minister Robert Habeck discussed the innovative power of Germany's leading industry in the promising areas of AI and autonomous driving with nine high-ranking people from the automotive industry.
The 60-minute debate with the industry's development board members - Mercedes-Benz CTO Markus Schäfer, Continental Automotive CTO Gilles Mabire, Bosch Mobility CTO Dr. Mathias Pillin, Valeo Germany CEO Holger Schwab, AVL EVP Jens Poggenburg and BIT TS Managing Director Cornelia Denk - the VDA Managing Director Dr. Marcus Bollig and the Chairman of the Board of Directors of Forschungszentrum Jülich Prof. Dr. Astrid Lambrecht focused on the opportunities for the German flagship industry, which is in the midst of the demanding transformation to electromobility and software-based
vehicles.
The occasion for the event was the lighthouse project nxtAIM – Generative Methods for Perception, Prediction and Planning, initiated by the VDA flagship Initiative for Autonomous and Connected Driving and funded by the BMWK. This project underlines Germany's leading position in the development and use of generative AI methods in the automotive context and at the same time represents a paradigm shift for the development of AI-based,
autonomous driving functions. The project was made possible by the preceding fundamental work in the four research projects of the KI family.
[The event was video-taped (German only):Autonomes Fahren und KI: Deutschlands Weg zur Mobilität der Zukunft - Youtube]
As the coordinator of the VDA flagship initiative, EICT played a key role in the conceptual and content-related preparation of the high-level event organised by the Federal Ministry for Economic Affairs and Climate Change. In addition, EICT was the hub for the VDA LI partner companie AVL, BOSCH, Continental, Mercedes-Benz, Valeo and VDA, which were actively involved in the event.
Generative AI and autonomous driving: nxtAIM research project breaks new ground
The ability of a vehicle to perceive its environment, predict how a traffic situation will
develop and then navigate safely is largely based on methods of machine learning and artificial intelligence. However, training autonomous driving functions requires not only large amounts of data, but above all driving data from traffic scenarios that are critical and safety-relevant. Until now, such data collection has been associated with high costs, time and personnel. The result today is narrowly defined operating environments (Operational Design Domain (ODD)) that are associated with limited vehicle speeds, weather
conditions and times of day.
The reason for this is the linear system architectures and discriminatory methods of machine learning used today. Necessary development progress, especially in scalability
(data, costs, computing capacities), transferability (expansion of operating environment (ODD)) and traceability (security and acceptance) are therefore only possible gradually. In the nxtAIM project, generative AI models form the basis of research. Linear system architectures can finally be supplemented by the feedback pathways in machine learning methods that have been missing so far. In this way, foundation models for driving data are built that take into account the high requirements for safe autonomous driving.
Provided that there is enough computing power, generative AI methods can be scaled and trained relatively easily on huge data sets without any special functional reference. They can be used in the field of perception, in the generation of sensor data, in the
behaviour prediction of road users and for route planning. In function development,
industry is no longer limited by the amount of data that is actually entered, but can synthetically generate almost unlimited new traffic and driving data. This opens up completely new possibilities for training, testing and validation of driving functions, especially in rare and critical traffic situations, and allows a gradual expansion of the previously limited ODD.
Three factors for project success
Under the leadership of Continental and Mercedes-Benz, the project consortium will show over the next three years that successful European AI development in the field of autonomous driving is possible. Generative AI methods have reached the maturity required for the automotive industry. If humans can no longer distinguish a generated image from
a real photo, then the quality of the generated data is high enough to train and test
perception systems. For the first time, the industrial partners involved in the project are making their driving data available - in compliance with the data protection framework conditions. With this data, which has been extensively collected in recent years, basic or foundation models can be developed that are suitable for the automotive sector. None of this would be possible without the great know-how of the participating project partners from industry and science. The cooperation with the Supercomputing Center at Forschungszentrum Jülich plays an important role in the project.
Citations
Robert Habeck, Federal Minister for Economic Affairs and Climate Action
"Germany already has a clear legal framework for autonomous driving. Now it's a matter of making highly automated and autonomous driving more widespread: step by step, always where it is already a good idea, such as in public transport, and always under the premise of high safety requirements. The use of artificial intelligence can spark a whole new dynamic here. Autonomous driving offers a wide range of economic opportunities for the German automotive and transport industries and for making mobility more sustainable in general. In order to further advance this highly relevant future topic with the safe use of artificial intelligence, we need a joint effort that focuses on the central core topics of the technologies. The AI models jointly developed in the nxtAIM research project on the basis of the data treasures provided by the individual manufacturers and suppliers are leading the way in this regard."
Marcus Bollig, Managing Director of the German Association of the Automotive Industry VDA:
"The nxtAIM project, funded by the BMWK, has transformed the national research ecosystem in autonomous and connected driving (AVF). Initiated and developed from the VDA Flagship Initiative for Autonomous and Connected Driving, the entire industry benefits from what the partners gathered in the initiative have worked on pre-competitive AVF research questions. The project is the result of first-class cooperation between science, business and politics."
Markus Schäfer, Member of the Board of Management of Mercedes-Benz Group AG, CTO for Development and Purchasing:
"In 2021, Mercedes-Benz was the first manufacturer in the world to receive approval for highly automated driving according to SAE Level 3 here in Germany. At the end of
September, we presented the fastest Level 3 automated driving system to date for private cars: our DRIVE PILOT up to 95 km/h. At the same time, we all know that global
competition is developing extremely dynamically. That is why we in Germany and Europe need an optimal interplay of research, cooperation and legal framework conditions so that we remain what we are: world leaders."
Gilles Mabire, CTO Continental Automotive Technologies:
"The mobility of the future needs new technologies and innovations, with new forms of cooperation. These include data and generative AI. Generative AI is the basic technology of the future. Together with partners from the industry and academia, we are working on Foundation models for the automotive sector that incorporate the world's knowledge of road traffic. Publicly funded research offers the opportunity to pool skills and knowledge for progress in AVF development."
Astrid Lambrecht, Chairwoman of the Board of Directors of Forschungszentrum Jülich:
"Large AI models, such as those necessary for autonomous driving, require top-of-the-line supercomputers on which they are trained. At Forschungszentrum Jülich, JUPITER, one of the most powerful AI computers in the world, is currently being developed. In this project, it is used jointly by science and industry. Close cooperation on this unique
machine is the key to innovations that keep Europe sovereign and competitive."
Mathias Pillin, CTO Bosch Mobility:
"Safety is fundamental to the breakthrough of autonomous driving. Ensuring this level of safety, especially with automated driving functions, is an enormous undertaking for the entire industry. This becomes even more critical with the integration of AI, as we need entirely new methods and safety assurance strategies in this area. A practical proof of safety can only be achieved through industry-wide collaboration."
Jens Poggenburg, Managing Director of AVL List:
"The great challenge with autonomous driving is that unpredictable and unforeseeable traffic events in real operation must be reliably solved in real time. This is especially true in highly complex mixed traffic. Integrated development along the entire value chain of the players involved in autonomous driving is an important prerequisite for success. The use of generative AI in conjunction with virtualization can significantly increase the speed of development here and reduce costs at the same time."
Holger Schwab, President of Valeo Germany:
"Research and development in the field of autonomous driving will remain essential in the future. We must continue to invest massively and continuously in order to maintain a strong market position internationally. Technology innovations such as generative AI, the willingness to cooperate pre-competitively and to define standards at an early stage
enable the German and European automotive industry to achieve the innovation boost that is and remains important in international competition with the USA and China."
Cornelia Denk, CEO BIT Technology Solutions GmbH:
"Certifiable AI and an extensive, relevant database have great value for the automotive industry as a whole. Innovative start-ups as well as specialized small and medium-sized technology companies are doing pioneering work for the entire industry and beyond.
However, politicians also need targeted funding programmes that are specifically tailored to the needs of smaller companies."
Photo: BMWK/Andreas Mertens