Self-driving cars pose challenges to testing. The quantity and magnitude of sensor inputs create an enormous test vector space. Traditional manual testing methods are inadequate to cover this multi-dimensional vector space with test cases.
To address this challenge model-based techniques are applied to manage the testing complexity. Abstraction and automation increase the productivity of test engineering. Model-based test engineering allows generation of test cases, test data and predicted behavior. Sensor test generation, automated Navigation testing and turbulence induced testing are elements of a strategy to improve the efficiency of testing for self-driving cars.
A case study is provided as an example. Conclusions are then summarized.
The paper is found here.