Statistical Test Coverage for Linux-Based Next-Generation Autonomous Safety-Related Systems

Abstract

Autonomous systems represent a significant leap forward in the ongoing technological evolution of dependable and safety-related systems, integrating features such as artificial intelligence, high-performance computing devices, General Purpose Operating Systems (GPOS) (e.g., GNU/Linux) and security requirements. Nonetheless, traditionally employed safety techniques and measures were not defined for safety-related systems with such features. Consequently, the need to research new methods and measures emerges in order to be able to achieve appropriate safety assurance. In this manuscript, we explore the limitations of traditional test coverage techniques, and we provide two complementary methods to pave the way towards the testing of Linux-based complex safety-related systems. The methods, which are based on statistical analyses, are presented and applied to a Linux-based Autonomous Emergency Braking (AEB) case study, specifically focusing on the kernel execution path test coverage.