Massively parallel virtual testing of safety-relevant driving systems
- /
- POC
- /
- Massively parallel virtual testing...
High-tech industry faces increasing complexity in autonomous systems, increasing validation costs. Virtual validation is crucial for affordable end-user prices. The VALICY framework uses HPC and AI to quickly scan dimensions for object classification errors in complex scenarios.
Start date: 01/11/2015
Duration in months: 18
Problem Description
Various branches of the high-technology industry are experiencing a strong increase in the complexity of their products. Mastering validation in complex environments, e.g. for autonomous cars, is one of the key challenges to advance technologies in realising affordable end-user prices.
Goals
New services
Challenges
Enormous amounts of test cases must be considered covering a huge testing and validation space.
Innovation results
The developed framework VALICY uses HPC and AI to quickly scan dimensions for object classification errors, allowing users to freely choose dimensions and parameter-spaces for test scenarios, such as a car arriving at a road intersection with multiple pedestrians and cars.
Business impact
The framework allows for early and rapid knowledge of the certification process over various variations. Benefits include parameter variation runs for 10-15 dimensions, thousands of validation runs within an hour, and validation within a budget of a few thousands €.