AUTOtech.agil

An open architecture for the mobility system of the future

The AUTOtech.agil project (Architektur und Technologien zur Orchestrierung automobiltechnischer Agilität) aims to create an open architecture for the mobility system of the future that can be implemented in both disruptive and established vehicle and mobility concepts.

Funded by the German Federal Ministry of Education and Research (BMBF), the project is formed by a consortium of leading German universities, SMEs, and companies in the field of automated and connected driving. The project is based on the previous project UNICARagil, in which a modular architecture for automated vehicles was researched and developed. In AUTOtech.agil, this architecture is to be extended beyond the vehicle boundaries and linked with validated concepts for roadside units, control rooms and the cloud. For this purpose, a modular kit of powerful and robust software modules is to be created that can be implemented both in the vehicle and in the supporting infrastructure. Based on the explicit communication of the capabilities of the individual modules in the form of a “quality vector”, a flexible distribution of intelligence in the system is possible. Thus, the use of intelligence outside the vehicle is also conceivable, so that other road users can benefit in addition to the automated vehicles.

AUTOtech.agil project
AUTOtech.agil project

The project will run for a period of three years up to September 2025. At FZD, four research associates are working on three different research topics in the areas of energy-efficient neuromorphic perception, function development of automated low-speed functions and modular (AI) assurance.

Responsible research associates: Melina Lutwitzi Lorenz Bayerlein Moritz Berghöfer Alexander Blödel Anton Kuznietsov Björn Klamann.

In the UNICARagil project, the safety system “Safe Halt” was developed, representing a functional fallback level of the automated driving function corresponding to SAE levels 4 and 5. Safe Halt uses redundant environmental perception sensors that are exclusively accessible to this function. In AUTOtech.agil, automated driving functions in the low-speed range (“automated low-speed functions”) are to be developed based on the safety system Safe Halt, using the described redundant perception sensors. The low-speed functions are thus intended to improve the cost-effectiveness of the redundant sensor technology as well as the energy efficiency of the automated vehicle. Exemplary use cases for automated low speed functions are automated valet parking or automated charging.

This topic is researched by Moritz Berghöfer.

Within the UNICARagil project, four highly automated vehicles were developed, which have sensor modules for environment perception. For the automated driving function, an environment representation model is created from the recorded sensor data using perception algorithms. For perception, the recorded data is processed on GPUs by artificial neural networks (ANN). This form of data processing is very energy intensive due to the amount of data and the type of processing.

In AUTOtech.agil, therefore, methods are now being researched to enable more energy-efficient perception through data processing on neuromorphic hardware. So called spiking neural networks (SNN) are used, which can be operated particularly efficiently on neuromorphic hardware.

This topic is researched by Lorenz Bayerlein.

Automated driving offers the opportunity to improve road safety. Nevertheless, proving a proof that possible incorrect behavior of automated vehicles does not pose an additional risk to road users is one of the key challenges in the introduction of such vehicles, as human drivers no longer act as a fallback level. Due to the complex environment in road traffic and the increasingly complex systems in the vehicle, established safeguarding methods result in efforts in the order of 10^9 kilometers. The approach of UNICARagil was to secure individual modules in isolation instead of the entire system, which both reduces the initial effort and prevents systems from having to be retested again and again after changes to modules. This approach will now be followed up by describing the capabilities of individual software and hardware modules in a “quality vector” and aggregating them into an overall function. In AUTOtech.agil, methods for modular validation are being developed, test cases defined and transferred to a homologation process.

This topic is researched by Alexander Blödel

In automated driving, artificial intelligence (AI) plays an important role, particularly in the area of perception. The main challenge of AI algorithms consists of the generalization quality. If the learning leads to a poor level of generalization, the AI algorithm faces problems with data that is not represented by the training data set. This may become difficult for the occurrence of so called “corner cases”, which describes infrequent and critical scenarios that can only be covered limitedly by the dataset. In the project “KI-Absicherung”, a safety argumentation for the AI-function of pedestrian detection was developed. In Autotech.agil, the assurance strategy is being expanded to further low speed functions. Furthermore, a uniform and system wide specification of the AI functions, including an aggregation between modules with AI- and non-AI-functions, is being made in order to develop a modular safety approval.

This topic is researched by Anton Kuznietsov