An Approach for Context-Sensitive Situational Risk Evaluation of Autonomous Systems

Abstract

Advances in automation technology and AI research, as well as the trend toward digitalization and networking, make modern automation systems complex, heterogeneous and dynamic, i.e., changes to the system and its environment are increasingly becoming the norm. Under such conditions, the classic safety process of certifying a snapshot at the end of the design phase becomes insufficient. To overcome this, we propose an approach that evaluates the safety of the actions of such systems at runtime. In doing so, the approach addresses three fundamental challenges of online safety assurance, namely, incorporating safety requirements into the online design process, coping with dynamic changes in the environment, and dealing with the uncertainties arising from dynamics and unpredictable environments and the adaptation of the system to them. The presented approach is applied to a specific scenario that shows promising results in simulation.