The technology company Continental is continuing the series of its PRORETA research projects together with the Technical University of Darmstadt, the University of Bremen and the Technical University of Ia?i (Romania).

PRORETA 5 is dedicated to one of the most demanding tasks for automated driving: recognizing complex traffic situations in city centers and how algorithms derive the right driving decisions from sensor data. By the end of 2022, algorithms based on artificial intelligence (AI) for the entire chain of effects of automated driving are to be developed and tested.

With an unregulated intersection, for example, it is a challenge to correctly interpret all objects relevant to the planned direction of travel, their direction of movement, intention and priority without human intervention. Artificial intelligence (AI) plays a key role in this. AI methods are to be tested where the implementation of classic approaches becomes too complex or reaches its limits. The big advantage of AI is that after a training phase, it is able to draw correct conclusions based on what it has learned, even in unknown situations. The motto 'urbAn drIving' reflects this element.

Division of tasks: more than the sum of the parts

The three-and-a-half year term PRORETA 5 project (2019-2022) examines the algorithms of cognition, behavior prediction and decision-making in a demonstration vehicle built and equipped by Continental. At the end of the project in September 2022, the aim is to assess the performance of the new AI-based automation at SAE (Society of Automotive Engineers) Level 4 using the most diverse city center scenarios and thus to show the potential for future use.

The algorithms based on artificial intelligence should be able to correctly recognize and interpret such complex traffic scenarios so that correct driving decisions can then be made. Part of this will be watching the human driver reduce and evaluate the complexity of the environment. The learnable algorithms of the PRORETA 5 project are to be trained according to similar principles in order to achieve a driving performance comparable to that of humans.

Research contribution from TU Darmstadt

The longstanding cooperation between Continental and the Department of Vehicle Technology at TU Darmstadt , headed by Professor Dr. Hermann Winner and theDepartment of Control Methods and Robotics under the direction of Professor Dr. Jurgen Adamy also forms an essential basis for PRORETA 5.

In order to be able to optimally and efficiently cover the individual processing steps along the chain of effects of automated driving with new solutions, the current PRORETA project was expanded to an inter-university and international level. The long-established cooperation between Continental and the TU Darmstadt, which has dedicated itself to individual sub-tasks of driver assistance and automation, forms the basis for the integration of further universities in the ongoing research cooperation.

The project coordinator on the university side, Professor Dr. Hermann Winner, Head of the Vehicle Technology Department (FZD) at TU Darmstadt, confirms the importance of interdisciplinary cooperation:

'

'The teamwork between Continental industry experts, doctoral students and students offers the opportunity to develop the latest future technology for the mobility of tomorrow, in a very realistic way in the vehicle. This cooperation is valuable for both sides. '

The team at TU Darmstadt focuses on the topics of systems and safety engineering, trajectory planning and control technology. The vehicle, which was initially trained in Bremen, will be handed over to the TU Darmstadt for further test drives during the course of the project.

In addition to the TU Darmstadt, the University of Bremen and Gheorghe Asachi Technical University Ia?i (Romania) are involved in PRORETA 5.

Continental AG / mho

PRORETA

TU Darmstadt has had a longstanding partnership with the technology company Continental. The joint PRORETA project is named after the upper boatswain on ancient Roman ships warning of shallows.

(C) 2020 Electronic News Publishing, source ENP Newswire