Reference
O. J. Gietelink, B. De Schutter, and M.
Verhaegen, "Probabilistic approach for validation of advanced driver assistance
systems,"
Transportation Research Record, no. 1910, pp.
20-28, 2005.
Abstract
This paper presents a methodological approach for validation of advanced
driver assistance systems. The methodology relies on the use of randomized
algorithms that are more efficient than conventional validation using
simulations and field tests, especially with increasing complexity of the
system. The methodology consists of first specifying the perturbation space and
performance criteria. Then a minimum number of samples and a relevant sampling
space is selected. Next an iterative randomized simulation is executed,
followed by validation of the simulation model by hardware tests, in order to
increase the reliability of the estimated performance. The proof of concept is
illustrated with some examples of a case study involving an adaptive cruise
control system. The case study also points out some characteristic properties
of randomized algorithms regarding the necessary sample complexity, and the
sensitivity to model uncertainty. Solutions for these issues are proposed as
well as corresponding recommendations for future research.
Publisher page
Downloads
BibTeX
@article{GieDeS:05-005,
author = {Gietelink, Olaf J. and De Schutter, Bart and Verhaegen, Michel},
title = {Probabilistic Approach for Validation of Advanced Driver
Assistance Systems},
journal = {Transportation Research Record},
number = {1910},
pages = {20--28},
year = {2005}
}