Adaptive Error and Sensor Management for Autonomous Vehicles: Model-Based Approach and Run-Time System

Abstract

Abstract. Over the past few years semi-autonomous driving functionality was introduced in the automotive market, and this trend continues towards fully autonomous cars. While in autonomous vehicles data from various types of sensors realize the new highly safety critical autonomous functionality, the already complex system architecture faces the challenge of designing highly reliable and safe autonomous driving system. Since sensors are prone to intermittent faults, using different sensors is better and more cost effective than duplicating the same sensor type because of diversity of reaction of different sensor typesto the same environmental condition. Specifying and validating sensors and providing technical means that enable usage of data from different sensors in case of failures is a challenging, time-consuming and error-prone task for engineers. Therefore, in this paper we present our model-based approach and a runtime system that improves the safety of autonomous driving systems by providing reusable framework managing different sensor setups in a vehicle in a case of a error. Moreover, the solution that we provide enables adaptive graceful degradation and reconfiguration by effective use of the system resources. At the end we explain in an example when and how the approach can be applied.

Challenges for the Self-Safety in Autonomous Vehicles

“…This type of reflective structure allows monitoring and changing its behavior for better adaptations at different levels of the architecture. The second trend represents the use of constructivist architectures managed by AI to tackle the limitations of current engineering practices by integrating heterogeneous processes at different scales of the system [22,23,27]. The third trend acknowledges the usage of knowledge bases separated from the execution processes, and allow bringing semantic and inference in the architecture, at conception or at run-time [18,26,29].…”

Safety framework and platform for functions of future automotive E/E systems

“…[3]. The information is used to check if the data from one type of sensor in case of failure can be replaced by the data from another type of sensor [4].…”

Run-Time Adaptive Error and State Management for Open Automotive Systems

“…Below we present the formal foundation of our approach as described in our work [4]. Definition 2 A System Function Architecture F a = (S f , S fc ) is composed by a finite set of System Functions S f and a set of System Function Clusters S fc .…”

“…A formal description of the degradation calculation algorithm, which calculates at run-time the actual system function degradation level for all active sf can be find in [4].…”