Socio-emotional Agency in Machines
Building Human-Agent Playful InteractionsRui Prada
Associate Professor
Instituto Superior Técnico Universidade de Lisboa
Coordinator
Specialisation in Games Game’s Lab Gamification
Consultant
Co-founder, President
Portuguese Society of
Science of Videogames
Author
Avid Gamer
Senior Researcher Founding Member
http://rageproject.eu/
Applied Games and Gamification
Experience and Game Design
Human-Agent Interaction
Socially Intelligent Agents
Imagineering Institute Visiting Researcher
Part I
People and Machines Together
Memorable Interactions
Unforgettable “Characters”
Socially Intelligent Act Socially
Understanding of Others
Social World Situation
Socio-emotional Emotions, social relations,
social identity
Instrumental Shared plans, coordination
People’s Perspective Accept Engage Trust
Coherence Expectations
Purpose Context
Human-like qualities “Personhood”
Believability “The illusion of life”
Believability requires a balance of several qualities
Research Goal Increase the behaviour
qualities and social intelligence of AI
characters
Group and relationship dynamics
Social influence and social power
Rui Prada, Ana Paiva: “Teaming Up Human with Synthetic Characters” in Artificial Intelligence, vol. 173 (1), pp. 80-103. 2009. Elsevier.
Gonçalo Pereira, Rui Prada, Pedro A. Santos: “Integrating social power into the decision-making of cognitive agents” in Artificial Intelligence. vol. 241, pp. 1-44, December 2016. Elsevier.
Reciprocity Balance
Heider Balance Theory
influence = power- resistance
Sources of power Reward Coercive
Legitimate Expert
ReferentFrench and Raven Sources of Power
Social Theatre (SIREN – FP7)
Social importance dynamics Cultural behaviour
Samuel Mascarenhas, João Dias, Rui Prada, Ana Paiva “A Dimensional Model for Cultural Behaviour in Virtual Agents” in Applied Artificial Intelligence, vol. 24 (6), pp. 552-574, July 2010. Taylor & Francis.
Samuel Mascarenhas, Nick Degens, Ana Paiva, Rui Prada, Gert Jan Hofstede, Adrie Beulens, Ruth Aylett: “Modeling culture in intelligent virtual agents: From theory to implementation” in Autonomous Agents and Multi-Agent Systems. pp. 1-32, 2015. Springer.
Claim and Confer Social Importance
Kemper Satus-power Interaction Dynamics
Cultural traits Individualism/collectivism
Power distance Uncertainty avoidance Masculinity/femininity
Long term/short term orientation Indulgence/restraint
Hofstede Model of Culture
Traveller (ECUTE – FP7)
Social practices Social identity and self-
esteemJoana Dimas, Phil Lopes, Rui Prada: “One for all, all for one: Agents with social identities” in proceedings of CogSci‘2013 - 35th Annual Meeting of the Cognitive Science Society, pp. 2195-2200, Berlin, Germany. August 2013. CSS.
Frank Dignum, Rui Prada, Gert Jan Hofstede: “From autistic to social agents” in proceedings of AAMAS’2014 - 13th International Conference on Autonomous Agents and Multiagent Systems, pp. 1161-1164, Paris, France. May 2014. IFAAMAS.
Frank Dignum, Virginia Dignum, Rui Prada, Catholijn M. Jonker: “A Conceptual Architecture for Social Deliberation in Multi-Agent Organizations: a position paper” in International Journal of Multiagent and Grid Systems. vol. 11 (3), pp. 147-166, 2015. IOS Press.
Identity personal, social (group
memberships)
Tajfel Social-identity Theory
salience = accessibility x fit
Tajfel Social-identity Theory
INVITE (UTAustin-PT)
Social robots Embodiment and non-verbal
communication
Iolanda Leite, André Pereira, Samuel Mascarenhas, Carlos Martinho, Rui Prada, Ana Paiva: “The influence of empathy in human-robot relations” in International Journal of Human Computer Studies, vol. 71 (3), pp. 250-260, January 2013. Elsevier.
André Tiago Pereira, Rui Prada, Ana Paiva: “Improving social presence in humanagent interaction” in proceedings of CHI’2014 - 32nd annual ACM conference on Human Factors in Computing Systems, pp. 1449-1458, Toronto, Canada. April 2014. ACM.
Emys Risk Player (LIREC – FP7)
Playing together a cooperative physics-based
puzzle platformer
Rui Prada, Phil Lopes, João Catarino, João Quitério, Francisco S. Melo: “The Geometry Friends Game AI Competition” in proceedings of CIG’2015 - IEEE Conference on Computational Intelligence and Games, pp. 431-438, Tainan, Taiwan. August 2015. IEEE.
Geometry Friends Game AI Competition
Part II
AI Characters in Applied Games
Games with Purpose
Games targeted at specific Learning
Treme-treme (2014)
MD for a Day (2014)
Festarola (2015)
JAMP (2016)
Two main reasons why applied (learning) games work
#1
Games enable practice, exploration and failure
#2
Games promote personal emotional experience
Image Source: https://c1.staticflickr.com/3/2200/2203264249_9fe46e5bbd_b.jpg
One can only learn about what a game play space
affords
8 Ball Pool, Miniclip
Learn about the rules of the game the force and angle of shots general tactics and strategy position play
Not about the execution details of the shot how to handle the cue the interaction with the opponent
Image sources http://a5.mzstatic.com/eu/r30/Purple1/v4/ba/fc/cc/bafccc5b-7644-7497-a633-d3effa944ed9/screen800x500.jpeg https://upload.wikimedia.org/wikipedia/commons/thumb/7/74/VR_Glasses.jpg/800px-VR_Glasses.jpg
Virtual Pool 4 Virtual Reality
Coverage and fidelity of the game interaction space
Learning Social Skills
The interaction space should support exploration and failure of social actions
AI characters increase the size of the social interaction
space (coverage)
AI characters need to be socially intelligent and
believable (fidelity)
http://rageproject.eu/
Realising an Applied Gaming Eco-system (H2020)
Create a platform to support diverse stakeholders in the
development, application and business of Applied Games
http://rageproject.eu/
Create a set of reusable game assets
Push the TRL of research outputs
http://rageproject.eu/
Emotional Appraisal + Embodiment
http://rageproject.eu/
Get Involved Try the Assets
http://rageproject.eu/rage-ecosystem/software-assets-inventory/
http://rageproject.eu/
Thank [email protected]
http://gaips.inesc-id.pt/rprada http://labjogos.tecnico.ulisboa.pt
http://spcvideojogos.org http://rageproject.eu