Self-awareness has been used in many research fields in order to add autonomy to computing systems. In automotive systems, we face several system layers that must be enriched with self-awareness to build truly autonomous vehicles. This includes functional aspects like autonomous driving itself, its integration on the hardware/software platform, and among others dependability, real-time, and security aspects. However, self-awareness mechanisms of all layers must be considered in combination in order to build a coherent vehicle self-awareness that does not cause conflicting decisions or even catastrophic effects. In this paper, we summarize current approaches for establishing self-awareness on those layers and elaborate why self-awareness needs to be addressed as a cross-layer problem, which we illustrate by practical examples.

No abstract

No abstract

No abstract

Virtualization is a key technology to enable the use of multicore processors in automotive embedded systems. For sideby-side execution of mixed-criticality applications that access shared communication infrastructures, a secure and safe virtualization of I/O devices is required, which features a complete spatial and temporal isolation of individual virtual interfaces. We extended existing approaches of hardwarebased CAN virtualization to achieve a full isolation while maintaining the bounded latencies achieved in previous implementations. It is shown, that even a denial-of-service attack towards one virtual controller does not influence the behavior of other virtual controllers. In addition, the scheduling mechanism implemented to guarantee temporal isolation can be configured to provide differentiated service levels for real-time and best effort application domains.