Week 9 - Dávid & Daša
Title: Conceptual Framework for Adaptive Safety in Autonomous Ecosystems
Abstract: The dynamic collaboration among hyper-connected Autonomous Systems promotes their evolution towards Autonomous Ecosystems. In order to maintain the safety of such structures, it is essential to ensure that there is a certain level of understanding of the present and future behavior of individual systems in these ecosystems. Adaptive Safety is a promising direction to control access to features between cooperating systems. However, it requires information about its collaborators within the environment. Digital Twins could be used to predict possible future behavior of a system. I would like to introduce a conceptual framework for Adaptive Safety that is being triggered based on the trust score computed from the predictive simulation of Digital Twins, which we suggest to use in Autonomous Ecosystems to load and safely execute third-party Smart Agents. By quantifying trust towards the agent and combining it with a decision tree, we leverage this as a deciding factor to conceal or expose certain features among collaborating systems.
Author: Daša Kušniráková
Title: Rethinking Certification for Higher Trust and Ethical Safeguarding of Autonomous Systems
Abstract: With the increasing complexity of software permeating critical domains such as autonomous driving, new challenges are emerging in the ways the engineering of these systems needs to be rethought. Autonomous driving is expected to continue gradually overtaking all critical driving functions, which is adding to the complexity of the certification of autonomous driving systems. However, the current certification procedures are not fully catching up with the dynamism and unpredictability of future autonomous systems, and thus may not necessarily guarantee compliance with all requirements imposed on these systems. In the presentation, I will present the results from the evaluation of current international standards used in the certification processes towards requirements derived from the requirements laid on dynamic software ecosystems and autonomous systems themselves, and outline a concept for incorporating the missing parts into the certification procedure.