Adaptable Demonstrator Platform for the Simulation of Distributed Agent-Based Automotive Systems

摘要

Future autonomous vehicles will no longer have a driver as a fallback solution in case of critical failure scenarios. However, it is costly to add hardware redundancy to achieve a fail-operational behaviour. Here, graceful degradation can be used by repurposing the allocated resources of non-critical applications for safety-critical applications. The degradation problem can be solved as a part of an application mapping problem. As future automotive software will be highly customizable to meet customers' demands, the mapping problem has to be solved for each individual configuration and the architecture has to be adaptable to frequent software changes. Thus, the mapping problem has to be solved at run-time as part of the software platform. In this paper we present an adaptable demonstrator platform consisting of a distributed simulation environment to evaluate such approaches. The platform can be easily configured to evaluate different hardware architectures. We discuss the advantages and limitations of this platform and present an exemplary demonstrator configuration running an agent-based graceful degradation approach.