AVL and Partners Develop Highly Efficient Toolchain for Automated and Autonomous Driving Functions

To get automated and autonomous vehicles on the road quickly and safely, AVL is working with Microsoft, Hexagon, Synopsys, and Tracetronic on an integrated digital and automated toolchain. This facilitates highly efficient and precise simulation of driving functions and their testing in conjunction with various sensors, control elements, and driving environments. The aim is to increase the number of tests by a factor of 500 – while maintaining the same development time. 

Graz, Austria, March 2023: Testing automated and autonomous vehicles is currently a challenging task for the automotive industry. Complex driving functions have to withstand a wide variety of real driving scenarios and environmental conditions. Therefore, the interaction between sensors, control elements, and the vehicle environment is simulated and tested. In order to speed up the development of new functions and their integration, test procedures must be automated and optimally interlinked at every stage of development – from software in the loop to hardware in the loop and real-world road testing. To this end, AVL and its partners have launched the ADET Autonomous End-to-End-Testing initiative to develop a consistent, digital, and automated toolchain. This allows for the number of simulation runs to be increased by a factor of 500 – all while maintaining the same development time.
Straightforward, effective data exchange between test scenarios and teams
With digital, automated test workflows and innovative tools, the companies facilitate the effective creation and exchange of test scenarios. Manufacturer and supplier teams can access the results from anywhere and at any time. Any system malfunctions can be detected and eliminated early on in the development process. Thanks to the combined expertise of AVL, Microsoft, Hexagon, Synopsys, and Tracetronic, tests can be planned efficiently, and simulations can be implemented quickly on Microsoft Azure infrastructure. Evaluations and analyses of data and results are automated and exchanged seamlessly. Processes, tools, and test sequences are orchestrated centrally. This architecture will include services like Azure Kubernetes Service (AKS) for container orchestration, Azure Batch for auto-scaling, and Azure’s purpose-built HPC/AI compute instances. AI workloads including machine learning operations (MLOps) will be powered by Azure Machine Learning. 

Bernhard Mueller-Bessler, Head of Virtual Mobility, Hexagon: “ADET is intended to provide a boost for ADAS tests and in the future also AD tests. We can only be successful if everyone works together – in the right place, at the right time, and in the right constellation. That is why we decided to work as partners rather than individual players.”

Martin Böhm, Head of Autonomous Driving Software Solution, Tracetronic: “The efficiency and performance required to test and validate autonomous driving functions can only be achieved with perfectly coordinated processes and tools from the partners involved. By orchestrating testing in physical and virtual environments, we provide the foundation for distributed and highly scalable execution, enabling fast and precise feedback in the development process.”

Tom De Schutter, Vice President Engineering, Systems Design Group, Synopsys: “The effort and cost required to validate ADAS and automated driving systems are significant. Digital twins of the electronics for these applications address the need to efficiently run software and system tests at lower costs. By contributing to the ADET initiative with our virtual prototyping and testing solutions, Synopsys helps automotive companies to accelerate their software bring-up, software/hardware validation efforts, and to improve their time to market.”

Jens Poggenburg, Executive Vice President AVL: “This initiative offers AVL the opportunity to bring integrated tools for the development process of autonomous and software-oriented vehicles to the market and to make them available to customers in the form of Software-as-a-Service.”

Hermann Erlach, General Manager Microsoft Austria: “Data is the key to developing innovative technology, especially when it comes to automated and autonomous vehicles. The fivefold increase in simulation that runs without longer development times illustrates the transformative power of data. Together with AVL, we are accelerating the new age of mobility – driven by the power of artificial intelligence.”