Keynote speakers

The keynote speakers are shared for EUMAS 2018 and AT 2018.

EUMAS 2018 Keynote:

Photo of Prof Michael Fisher

Professor Michael Fisher, University of Liverpool

Trustworthy Autonomy

Truly autonomous systems, such as (future) robots or vehicles, will make their own decisions about what to do without necessarily consulting humans. How can we trust such systems if we do not know what, and crucially why, these systems will make their decisions? In this talk, I will describe how the use of agents at the cor of these systems can form  he basis for trustwortiness. Yet we need more: at least transparency and explainability, but ideally verifiability

Once we have autonomous systems based on a hybrid agent architecture that supports verifiability, then we can strongly analyse these systems and move towards not only trustworthiness, but ethical and responsible behaviour. I will provide some examples from our current and previous projects examining the deployment of hybrid agent architectures in both vehicles (road and air) and robots (domestic and industrial) and assessing safety, ethics, fault tolerance, etc.

This work, and the examples described, are derived from projects funded in the UK by EPSRC:

AT 2018 Keynote:

Elizabeth Sklar_1870-2.jpg

Professor Elizabeth Sklar,  Kings College London

Shared Decision Making in Human-Robot Teams

The future of robotics lies in developing safe and trustworthy methodologies for people and robots to collaborate. Whether operating in the office, classroom, home, hospital or disaster scenario, robots and humans need to be able to support each other in mixed-initiative interactions and take advantage of the unique capabilities of each species. Our research investigates ways in which robots can collect data from their environment, analyse the data, and then use that knowledge to make decisions in partnership with humans. This talk will focus on the use of computational argumentation and argumentation-based dialogue to facilitate shared decision making in human-robot teams. Experimental results obtained through studies with physical robots and human subjects will be highlighted.