New method simplifies approval of automated driving systems


A new method developed by researchers at the Graz University of Technology could significantly improve and simplify the approval process for automated driving systems.

Driving simulator testing is used for many different reasons, especially since it can simulate any scenario almost immediately. These scenarios are unaffected by weather and weather conditions, and there is no risk to the safety of the vehicle, people or the environment.

Driving simulators are also much cheaper and require less organization compared to the real thing.

However, there are some questions surrounding the practice when it comes to automated driving.

Automated driving and driving simulators

Arno Eichberger is responsible for the research area “Automated driving and driving assistance systems” at the Institute for Automotive Engineering of the Graz University of Technology (TU Graz).

“In the field of highly automated driving, however, driving simulator studies are often questioned due to unrealism,” explains Eichberger. “In addition, until recently, there was no standardized test procedure that could be used to verify complex tasks such as the mutual interaction between man and the system (transfer procedures).”

The world’s first regulation for automated lane keeping systems (ALKS) was implemented in early 2021. According to Eichberger, the law addresses the issue of road approval.

“Until now, regulatory authorities did not know how to test and approve autonomous driving systems,” he said. “Automakers, in turn, did not know what requirements systems had to meet in order to be approved. “

The regulations have specified, on the basis of a bottling assistant, the approval criteria for highly automated systems up to a maximum speed of 60 km / h. Once the assistant is activated, he becomes responsible for the control. The driver can let go of the steering wheel, but he must take over in the event of a malfunction. The system must also recognize that the driver has this capability.

The new method

The new method developed by Eichberger and his team from Fraunhofer Austria, AVL and JOANNEUM RESEARCH was based on the regulation. It is able to safely, efficiently and realistically test the ability to take control in a driving simulator. The results can then be used for certification of ALKS systems.

The team had to go through various processes to prove the validity of the driving simulation using the test drive. There had to be a direct comparison between the driving simulation and the actual driving, which had to match as closely as possible.

The machine’s perception of the environment has proven difficult in this regard.

“If this is to work as it does in real life, the environments in the simulation have to match the real environment down to the centimeter,” Eichberger said.

The team achieved this precision using “ultra high definition maps” from JOANNEUM RESEARCH, which is a leading research institution in the world.

Patrick Luley is the head of the highly automated driving research laboratory at the DIGITAL Institute.

“We use a mobile mapping system to measure test environments,” Luley said. “Finally, a transparent 3D map with an extremely high level of detail is created from the measurement data. In addition to traffic infrastructure objects such as road signs, ground markings and guardrails, vegetation and buildings are also depicted on this map.

This automated UHD mapping process is much faster and cheaper than manual 3D modeling.

The last step is to transfer the high resolution 3D environment to the driving simulator.

According to Volker Settsgast of the Visual Computing business unit, “We prepare the data so that the 3D environment can be viewed at high speed. “

The validation is then checked by comparative races on the real route.

“With our method, it is possible for car manufacturers to easily compare and validate a certain sampling on the real track and in the driving simulator,” explains Eichberger. “This means that the test can finally be transferred from the real track to the driving simulator. “

The team is now working on implementing virtual approval testing over the next few months.


About Author

Comments are closed.