Embedded software development has become one of the greatest challenges in the automotive domain, due to the rising complexity of vehicle systems. A method to handle the complexity of automotive software is Model Based Design (MBD). As MBD offers great advantages in early simulation and testing, it has become today's mainstream method for automotive software engineering. However, some aspects can be initially tested after the integration of software on real hardware components (usually by the supplier) and when all parts of a system (e.g. bus systems, sensors, actuators) are present. The consequence is that the requirement specification of the according system possibly contains gaps that can lead to software defects. New technologies like the AUTOSAR standard enable additional potentials for the validation of model based developed software. Due to the AUTOSAR software architecture it is possible for an OEM to realize an early "virtual" software integration with an acceptable effort and perform at next step a front loading of system tests. In this paper we present an approach that improves the quality of the requirement specification artifacts by using test front loading. In detail, we analyze the requirement engineering part of the software development process to identify aspects that can not be tested without having all system components. Afterwards, we classify these aspects and define an abstract test pattern that can be globally used for testing. Additionally, we illustrate our approach in a case study on an interior light system for the next MercedesBenz M-Class generation.

No abstract

No abstract