Adaptive importance sampling for probabilistic validation of advanced driver assistance systems

Abstract

We present an approach for validation of advanced driver assistance systems, based on randomized algorithms. The new method consists of an iterative randomized simulation using adaptive importance sampling. The randomized algorithm is more efficient than conventional simulation techniques. The importance sampling pdf is estimated by a kernel density estimate, based on the results from the previous iteration. The concept is illustrated with a simple adaptive cruise control problem.

Original document

The different versions of the original document can be found in:

• http://resolver.tudelft.nl/uuid:a41e7437-fff8-4147-9c8e-e3a148619d6f

• http://www.dcsc.tudelft.nl/~bdeschutter/pub/rep/06_003.pdf

• http://www.dcsc.tudelft.nl/~bdeschutter/pub/rep/06_003.pdf,

https://repository.tudelft.nl/view/tno/uuid:a41e7437-fff8-4147-9c8e-e3a148619d6f,

http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.ieee-000001657344,

https://www.narcis.nl/publication/RecordID/oai%3Atudelft.nl%3Auuid%3Aa41e7437-fff8-4147-9c8e-e3a148619d6f,

https://academic.microsoft.com/#/detail/2099325143

• http://xplorestaging.ieee.org/ielx5/11005/34689/01657344.pdf?arnumber=1657344,

http://dx.doi.org/10.1109/acc.2006.1657344

• [ ]