(1) Towards Trusting Autonomous Systems AND (2) Debugging Agent Programs with ``Why?'' Questions

28^th February 2017, 13:00 Ashton Lecture Theater
Prof. Michael Winikoff
Department of Information Science
University of Otago
New Zealand

Abstract

[two shorter talks]

(1) Autonomous systems are rapidly transitioning from labs into our lives. A crucial question concerns trust: in what situations will we (appropriately) trust such systems? This talk proposes three necessary prerequisites for trust. The three prerequisites are defined, motivated, and related to each other. We then consider how to realise the prerequisites. This talk aims to articulate a research agenda, and although it provides suggestions for approaches to take and directions for future work, it contains more questions than answers.

(2) Debugging is hard, and debugging cognitive agent programs is particularly hard, since they involve concurrency, a dynamic environment, and a complex execution model that includes failure handling. Previous work by Ko & Myers has demonstrated that providing Alice and Java programmers with software that can answer ``why?'' and ``why not?'' questions can make a dramatic difference to debugging performance. This talk considers how to adapt this approach to cognitive agent programs, specifically AgentSpeak. It develops and formalises definitions for ``why?'' and ``why not?'' questions and associated answers, and illustrates their application using a scenario.