The verification, validation and homologation of automated driving systems is highly dependent on the HD-Map availability for the ODD creation. Currently this is the bottleneck limiting the possibility of virtual verification and validation on available HD maps which are predominantly non-urban. Mapping areas conventionally is both costly and time consuming.To address this challenge, AVES Reality and AVL have joined forces. AVES offers an automated HD- Maps generation process and creates 3D environments from aerial images anywhere on the globe. Additionally, its parameter-based semantic environment reconstruction allows customization and variation to match ODD requirements. This enables early-stage assessment and evaluation of new areas for AD-Systems also in urban areas, long before detailed HD-Maps are created. AVL leverages these HD-Maps and 3D environments by integrating them in an AVL simulation toolchain and provides the customers with the possibility to run hundreds of thousands of scenarios per day frenabling V&V and SOTIF testing activities for automated driving. In summary, AVES Reality and AVL accelerate this process and enable the scaling of V&V and homologation of automated driving systems. The poster will introduce in the challenges and requirements of scenario-based testing using simulation for automated driving, the scope of the collaboration between AVL and AVES Reality and the solution approach we provide to enable and improve AD simulation.
Session:
Poster
|