Abstract
Automated and connected driving up to autonomous vehicles is increasingly being used. But the distrust in their reliability is growing. The underlying algorithms are difficult to understand and thus intransparent. Traditional validations are complex, expensive and expensive. In addition, no transparent coverage for regression strategies for upgrades and updates is achieved. In this article Vector Consulting and the IAS of the University of Stuttgart show that classical methods have to be supplemented with cognitive test methods.
Users
Please
log in to take part in the discussion (add own reviews or comments).