Efficiently Prove the Safety of AD Functions in Automated Endurance Tests 

Joint Showcase of dSPACE and AAI at Automotive Testing Expo

Paderborn/Novi, Michigan, October 24, 2023. At the Automotive Testing Expo (Novi, Michigan, October 24-26), dSPACE will be demonstrating in a joint showcase with AAI how to minimize residual risks when developing functions for autonomous driving and how to provide evidence of safe system behavior in known environments. To do this, dSPACE has combined AutoScenarios, an AI-based application from the AAI ReplicaR platform, with its Automotive Simulation Models (ASM) and AURELION, the software solution for sensor simulation and visualization.

The validation of functions for highly automated driving is elaborate and complex. In order to provide proof of safety in accordance with SOTIF (Safety of the Intended Functionality), several hundred thousand scenarios must be tested. With the joint showcase, dSPACE and AAI demonstrate how to maximize test coverage and thus safety proof, especially for unknown risks: Using an intuitive interface, AAI AutoScenarios provides the dSPACE simulations with huge amounts and variations of AI- and random-based realistic traffic situations with many road users, to which the test vehicle (SUT) needs to respond. "With this solution, we are demonstrating how driving functions can be tested and validated easily, quickly, and efficiently in automatically generated endurance tests," explains Dr. Hagen Haupt, Director Simulation Models & Scenarios at dSPACE.

Visitors to Automotive Testing Expo are invited to visit booth 3000 to learn more about this joint showcase.
 

About AAI

The vision of Automotive Artificial Intelligence (AAI) GmbH is to "create a replica of the world".
AAI, with its headquarters in Berlin, is dedicated to creating innovative software tools for validation of highly automated driving systems and vehicles in order to improve their reliability and performance.
The AAI ReplicaR platform provides a holistic synthetic world in simulation, combined with a consistent tool chain for virtual validation using closed and open loop testing as well as data-driven analysis.
Engineers developing highly automated driving are given the opportunity to achieve a comprehensive, reproducible, and structured test case coverage within a short period of time.
AAI ReplicaR’s highly scalable and traceable test methodology is not only beneficial for the development of highly automated driving, but also for the homologation of the respective technology.