Publication

Future autonomous vehicles will rely on Deep machine learning algorithms (DML), whose correct behavior cannot be guaranteed by traditional software engineering approaches. This uncertainty is a big obstacle to ensure the quality of systems using DML, especially in automotive safety critical applications. The SMILE program has been proposed to address this challenge via developing method(s) that allow DML-based functions to be included into safety critical vehicular applications with quality control requirements from industrial standards. The SMILE program consists of several consecutive research projects:

• SMILE I project studied state-of-art within Verification and Validation for DML systems and mapping of the challenges faced by the automotive industry [1]. SMILE I concluded that we should focus on a Safety Cage Concept within the follow-up project(s).
• SMILE II project investigated the latest vehicle safety standards: (i) ISO 26262 [2] - functional safety, and lately complemented by (ii) PAS specification of ISO 21448 [3] - Safety of the Intended Function (SOTIF); implemented and tested a number of safety cage architectures in simulators [4], developed a framework for supervisor comparison [5]; and developed future research tool sets including generated datasets and an end-to-end vehicle controller. SMILE II observed that ISO 26262 alone cannot accommodate ML-based systems [6]–[8], the complement with the most recently published SOTIF (2019) will be more applicable. However, in its PAS edition, SOTIF only focused on what should be covered during systems engineering and leaves out how to achieve these goals in practice.

With the success and promising results from SMILE I/II, the SMILE III project further develops the safety cage concept into a reference system architecture and prototype(s), together with data management approaches, facilitating compliance with the evolving safety standards (including the insufficient prescriptive ISO/PAS 21448 edition).
The results from SMILE III will be of interest for automotive actors that plan to use DML to support autonomous functions in safety critical applications. These results will also provide valuable inputs for the development of related standards. The partners of project consortium are: RISE (lead partner), QRTECH, Semcon, Combitech, Infotiv, and ESI Nordics.