Towards supervisory risk control of autonomous ships

The objective of this paper is to outline a framework for online risk modelling for autonomous ships. There is a clear trend towards increased autonomy and intelligence in ships because it enables new functionality, as well as safer and more cost-efficient operations. Nevertheless, emerging risks are involved, related to lack of knowledge and operational experience with the autonomous systems, the dependency on complex software-based control systems, as well as a limited ability to verify the safe performance of such systems. The framework presented in the paper is the first step towards supervisory risk control, i.e., developing control systems for autonomous systems with risk management capabilities to improve the decision-making and intelligence of such systems. The framework consists of two main phases, (i) hazard identification and analysis through the systems theoretic process analysis (STPA), and (ii) generating risk models represented by Bayesian Belief Networks (BBN) based on the outcomes of the STPA. The application in the paper is aimed at autonomous ships, but the results of the paper have a general relevance for both manned and unmanned systems with different levels of autonomy, complexity, and major hazard potential.