Accelerating a safe autonomous future with AVL

The introduction of driver assistance functions (ADAS) and autonomous driving systems (AD) has become one of the strongest innovation drivers in the automotive industry. For vehicle manufacturers and suppliers safety, reduced operational costs and short development times are important requirements. Only by applying highly efficient development, simulation and testing methodologies, these requirements can be ensured. AVL’s competences cover all relevant aspects in developing and testing ADAS/AD systems - from systems design, controls and software development up to calibration, verification and validation. 

Though traffic accidents happen daily, fortunately it is rare for an individual driver to encounter an accident, but autonomous vehicles need to be prepared for all eventualities. They need to perform better than human drivers, they must gather robust experience in even the most infrequent adverse weather and light conditions, as well as countless traffic and road situations. It would take years to physically test an autonomous vehicle for the hundreds of millions of kilometers on public roads necessary before certification. Only through a combination of physical tests and simulations, manufacturers can validate their vehicles over such large distances under limitless conditions to ensure system robustness.

At the ADAS/AD competence center in Graz, Austria, AVL combines powerful simulation environments with cutting-edge evaluation and data analytics methods, allowing it to cover the hundreds of millions of test kilometers required to ensure safety. Thereby critical driving situations are identified, analyzed and evaluated in terms of functional safety as well perceived safety and comfort. AVL also developed a vehicle-in-the-loop test system, called AVL DRIVINGCUBE™ to ensure a reliable and efficient validation of ADAS/AD features integrated in a physical vehicle. The vehicle with physical or behavioral sensor models connects ADAS/AD functions under test with the simulated virtual environment and validate them under defined driving scenarios in this vehicle-in-the-loop testing environment.

A combination of physical and virtual testing is essential for the development and validation of autonomous vehicles

AVL’s tool chain strategy is based on an open and integrated tool environment. This approach allows the integration of different tools and content, an important aspect of the virtual and real validation of autonomous vehicles. Thereby AVL’s Model.CONNECT™ interlinks simulation models into a consistent virtual prototype, regardless of the tool they were created with. Simulation and hardware components can be easily integrated into a complete virtual/real Hardware-in-the-Loop and Software-in-the-Loop system. This facilitates continuous, model-based development in a wide range of powertrain and vehicle applications (e.g. vehicle dynamics, energy management, real driving emissions, driver assistance systems).

Throughout all phases of the physical and virtual testing, the highly automated evaluation tool AVL-DRIVE™ Autonomous is used to integrate objective measurable criteria regarding end consumer’s perception. The Human Centric Experience in autonomous vehicles is driving all AVL efforts in developing high quality ADAS calibrations up to Level 3. The evaluation technology AVL-DRIVE™ Autonomous allows a consistent comparability of results and thus unique target-oriented development.

AVL’s independence offers the freedom to optimize and tune our expertise, delivering the best solutions for any specific task. OEMs are supported by AVL from the early project phases like proof-of-concept of fully automated driving vehicles, throughout the individual development stages of assisted and automated driving features, right up to the finished product and, depending on the requirements, carry out smaller or larger work packages, including functions in series developments.

Visit our website to find out more about AVL’s ADAS/AD solutions.

Share this article