In this paper, model-based testing strategies are described for the validation of an Adaptive Cruise Control (ACC) algorithm developed for a 2019 Chevrolet Blazer as part of the EcoCAR Mobility Challenge. A team of undergraduate and graduate students developed testing procedures to assess model fidelity, and to identify and resolve issues with the algorithm before deployment to a student-modified production vehicle. The algorithm validation is conducted via three progressive levels of validation environments: Model-In-the Loop (MIL), Hardware-In-the-Loop (HIL), and Driver-In-the-Loop (DIL). When the ACC algorithm is evaluated using system requirements in the testing sequence, the MIL environment performs the tests at least 87% faster than the HIL environment. The MIL environment can also utilize parallel computing, which leverages multi-core CPUs to conduct multiple simulations simultaneously. Although comparisons between MIL and HIL results revealed good agreements, slight differences in system dynamics highlights a need for future Vehicle-In-the-Loop (VIL) testing. By showing how the concepts can be applied to the validation of an autonomous feature in a vehicle with detailed test scenarios and evaluation metrics, the paper will serve as a good reference for the students and engineers interested in this field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.