Paper presented at AI and Data Science Conference
Prof Yiannis Papadopoulos from project partner University of Hull has presented a technical paper at the 3rd Annual International Conference on AI and Data Science, held in Athens Greece. The paper titled: Adaptive Decentralised Safety Monitors for Cooperative Intelligent Systems addresses the unprecedented safety challenges posed by cooperative intelligent systems such as cooperative robots and autonomous vehicles where system safety cannot be interpreted in a classical way as a set of safety goals related to the behaviour of one system and to which other systems contribute. The characteristics of these systems suggest that full assurance of safety at design time is impossible, therefore, part of the assurance must be moved during the operational phase.
The paper presents one of the cornerstone technologies and innovations of the SESAME project, which is a novel framework for dynamic safety assurance of cooperative intelligent systems that integrates design time models and runtime techniques to provide continuous assurance for the cooperative ensemble and its systems during operation. The approach uses a network of intelligent safety monitoring agents to deliver safety assurance within a cooperative system of systems. An agent for a system carries information about the safety assurance of the system in the form of dependability models called Executable Digital Dependability Identities (EDDI) and uses information shared by the agents of other cooperating systems in conjunction with information from the environment to provide dependability management at runtime, e.g. event monitoring, diagnostics, certification, risk prediction and action planning.