According to experts, the mobility of the future will be characterized by artificial intelligence (AI) and digitization. Autonomous driving will make traffic more efficient, safer and environmentally friendly, as well as more cost-effective. But for people to accept this new mobility, it must be extensively tested and demonstrated in real test environments.
As part of the new “BeIntelli” research project, an interdisciplinary team of scientists from the Technical University of Berlin (TU Berlin) and partners in the field want to develop and field-test the possibilities of AI for the mobility of the future based on platform economics. They also want to create a “showcase” that allows AI applications in mobility to be experienced. The consortium is led by Prof. Sahin Albayrak, head of the Distributed Artificial Intelligence Laboratory (DAI Lab) and the Department of Agent Technologies in Operational Applications and Telecommunications at the Berlin University of Technology.
Autonomous mobility from public transport to the logistics industry
The basis for the new research is the predecessor project DIGINET-PS. Here, the TU Berlin and its project partners set up, among other things, a digital urban test field for automated and connected driving on the Street of June 17th. “With BeIntelli, we are pursuing five core goals,” explains Sahin Albayrak: “The first is to create technological innovations for everyday life. We plan to research, develop and test new ideas and AI-based approaches as part of a holistic approach to mobility. These range from autonomous and connected driving to autonomous public transport, to automated logistics solutions for the final stretch. To this end, we are developing a software stack based on artificial intelligence, machine learning and distributed intelligence at TU Berlin, the AI Mobility Operating System.”
Extending the existing infrastructure to the Berlin Reichstag
To deploy the software and attain the second core objective, the existing digital test site on Street of June 17th will be extended toward Kurfürstendamm and the Berlin Reichstag. The corresponding sensor technology will be installed on the street, an edge infrastructure will be provided and a 5G communications infrastructure will be set up, the researchers explain. The third goal of the project is to test and validate autonomous vehicles on the test field. It is not just the road that is being digitized, however, as all vehicles will also be equipped with functions for autonomous driving.
To this end, three vehicles will be equipped with the necessary sensors and cameras to register their entire surroundings. The software developed at TU Berlin will act on the vehicles’ control technology to enable true autonomous driving. In addition to passenger cars, a delivery vehicle and a so-called explainer bus will also be equipped with this technology, says Dr. Jan Keiser, leader of a subproject and a colleague of Sahin Albayrak’s. “We can then use these vehicles to test their use in real operations and learn about real-world requirements.”
The explainer bus, a mobile real-life laboratory, informs the public
Step four will be to establish a platform economy for the new mobility. “The data from the smart infrastructure and vehicles, the AI models and services will be processed and made available in a way that favors the establishment of new business models and ecosystems. To this end, we will organize appropriate events and competitions,” explains Marc Augusto, subproject manager for the development of AI applications.
The researchers see the involvement of the public as a central focus of the project. This makes it crucial to publicly showcase autonomous mobility in a real-world environment, they say. “We want to not only inform the public but also encourage them to try out this new mobility. The benefits and background of AI-based mobility should be immediately apparent to all road users on the test route,” explains the project manager. The so-called explanatory bus, a mobile real-life laboratory, plays an important role in this. It will feature large displays that show the work of the sensors on the road and on the bus. Passengers will also be able to visualize the effect of the software on the control technology.
The bus could be used for public events, “but we also plan to use it as a regular means of transport on the test route at certain times,” explains Dr. Axel Hessler, subproject manager for the development of the AI platform.
Passersby will then be invited to use it freely. Trained staff on the bus will be available for explanations and discussions with the public. In parallel, the project will lay the foundation for the establishment of a Berlin center for experiential AI and digitization in mobility research.
Autonomous driving under supervision
All driving will, of course, take place under the supervision of trained safety personnel who can take control of the vehicles at any time. The demonstration of autonomous driving capabilities will also require special approvals for the test vehicles.
The project has a budget of around €17 million, with the German Federal Ministry of Transport and Digital Infrastructure (BMVI) funding it with around €13 million. The remainder of the project volume will be borne by the project partners: TU Berlin, GT-ARC, VMZ Berlin, ADAC BBR, IAV GmbH Ingenieurgesellschaft Auto und Verkehr, Bezirksamt Charlottenburg-Wilmersdorf von Berlin, Cheil Germany GmbH, DB Regio Bus Ost GmbH, Continental Automotive GmbH, TÜV NORD Mobilität GmbH & Co. KG, Berliner Verkehrsbetriebe, T-Systems International GmbH.