• January 14, 2016
  • 0

Cognitive Architectures for Social Human-Robot Interaction


HRI’16 2nd Workshop on Cognitive Architectures for Social Human-Robot Interaction

Full day workshop — Monday 7th March, 2016 (Christchurch, New Zealand)



** Submission deadline: Friday 22nd January, 2016
** Notification: Friday 29th January, 2016
** Final (accepted) submission: Friday 12th February, 2016
** Workshop: Monday 7th March, 2016 (full day workshop)

Cognitive Architectures are constructs (encompassing both theory and models) that seek to account for cognition (over multiple timescales) using a set of domain-general structures and mechanisms. Typically (but not always) inspired by human cognition, the emphasis is on deriving a set of principles of operation not constrained to a specific task or context. This therefore presents a holistic perspective: it forces the system designer to initially take a step back from diving into computational mechanisms and consider what sort of functionality needs to be present, and how this relates to other cognitive competencies. Thus the very process of applying such an approach to HRI may yield benefits, such as the integration of evidence from the human sciences in a principled manner, the facilitation of comparison of different systems (abstracting away from specific computational algorithms), and as a more principled manner to verify and refine the resultant autonomous systems.

For HRI, such an approach to building autonomous systems based on Cognitive Architecture – ‘cognitive integration’ – would emphasise first those aspects of behaviour that are common across domains, before applying these to specific interaction contexts for evaluation. Furthermore, given inspiration from human cognition, it can also inherently take into account the behaviour of the humans with which the system should interact, with the intricacies and sub-optimality that this entails.

To date, there have been relatively few efforts to apply such ideas to the context of HRI in a structured manner. The first workshop sought to bring attention to the topic by providing a forum to discuss the reasons and potential for the application of Cognitive Architectures to autonomous HRI systems. In this second workshop, we propose focusing more specifically on the application of Cognitive Architectures to *Social* HRI systems. The format of the workshop is oriented towards discussion shaped by participant contributions, and we expect vibrant interactivity to contribute to the cross-fertilization of ideas in this exciting area.

Contributions are encouraged from all who are interested in participation. A light-touch review process only will be applied to check for relevance – the emphasis of the workshop is on inclusion, discussion and dissemination. Prior to the workshop, the organizers will integrate these into a list of perspectives that will form the basis for the discussions. To facilitate this, we request that all submissions specifically answer the following questions:

(1) Why should you use cognitive architectures – how would they benefit your research as a theoretical framework, a tool and/or a methodology?
(2) Should cognitive architectures for social interaction be inspired by and/or limited by models of human cognition?
(3) What are the functional requirements for a cognitive architecture to support social interaction?
(4) How the requirements for social interaction would inform your choice of the fundamental computational structures of the architecture (e.g. symbolic, sub-symbolic, hybrid, …)?
(5) What is the primary outstanding challenge in developing and/or applying cognitive architectures to social HRI systems?
(6) Can you devise a social interaction scenario that current cognitive architectures would likely fail, and why would this be the case?

Please prepare a 2-4 page position paper including your research-informed answers to the above questions on cognitive architectures for specifically social human-robot interaction. The HRI template should be used for this submission (IEEE Conference Proceedings). A submission system will be opened closer to the submission deadline. All accepted position papers will be compiled into workshop proceedings, archived on arXiv. Even without a position paper, we would strongly encourage you to participate in the planned discussions.

In order to consolidate the outcomes of the workshop, we are planning a special issue (journal TBA), to which we will invite participants to submit extended versions of their workshop papers. To maintain continuity with the workshop, we will expect all submissions to answer the same questions listed above. Given this common ground between submissions, we envisage that this will additionally form a future reference  point for the application of Cognitive Architectures to social HRI research and applications.

** Paul Baxter (Plymouth University, U.K.), Greg Trafton (Naval Research Laboratory, USA),
and Séverin Lemaignan (Plymouth University, U.K.)
** Email: paul.baxter@plymouth.ac.uk