2017
Conference article  Restricted

Challenges in certification of autonomous driving systems

Falcini F., Lami G.

Automotive Software  Deep Learning  Standards  Software Certification 

Autonomous Driving is the next frontier of the automotive industry. Advanced driver assistance systems (ADAS) are going to be pervasively used in modern automobiles. New ADAS are principally based on Artificial Intelligence (AI) technology, and in particular on deep learning. While the automotive community is aware of the important changes such a technology demands in terms of technical skills, development paradigms, and cultural approach, there is still a important lack to be filled in the availability of technical standards and, consequently, in terms of certification capability. The existing standards, in fact, are more or less explicitly referring to a traditional way of developing software and systems, so they not suitable at all to be applied to ADAS. In this paper the open issues in certification of AI technologies in automotive are addressed by providing an overview of the existing standards and the related applicability issues.

Source: IEEE International Symposium on Software Reliability Engineering Workshops, pp. 286–293, Toulouse, France, 23-26/10/2017


Metrics



Back to previous page
BibTeX entry
@inproceedings{oai:it.cnr:prodotti:380106,
	title = {Challenges in certification of autonomous driving systems},
	author = {Falcini F. and Lami G.},
	doi = {10.1109/issrew.2017.45},
	booktitle = {IEEE International Symposium on Software Reliability Engineering Workshops, pp. 286–293, Toulouse, France, 23-26/10/2017},
	year = {2017}
}