AIBACS: The Impact of Durative Variable state on the Design and Control of Action Selection

EPSRC Grant GR/S79299/01

January 2005-2008

---

Project Summary

1. We created psychologically-realistic artificial models of the onset, persistence and decay of emotion and drive response levels. We called this the Dynamic Emotion Representation (DER). These models are available as source code from our web page, and described in a number of publications so that they can be reimplemented for other systems. The basic representations a general-purpose framework for drives and emotions. We also provide XML scripts of events and emotions systems, and parameter settings which demonstrate the variety of behaviours and expressions generated by a face avatar. Behaviour varies appropriately depending on the avatar's prior emotional state and/or experiences.
2. We integrated a simplified version of the emotion and drive model into a current state-of-the-art dynamic-plan-based action-selection system, which is also available for download. We have demonstrated improved efficiency in meeting a variety of conflicting goals in a dynamic environment as a consequence of creating a simple network of durative state modules --- one regulating each goal. AI action selection is improved by providing these emotion-inspired pieces of decision-state memory, which are both more persistent than that found in even the best dynamic plans, but more responsive and contextually-appropriate than decisions based on ordinary memory (e.g. conventional knowledge bases or belief systems).
3. We produced a graphical system for humanoid Virtual Reality (VR) facial characters and personality expression which incorporates and depends on the full DER. We have conducted and published tests of the believability of the emotional models on ordinary human subjects. Although we began with a basic framework for the VR system, the work here went beyond our expected goals. In addition to incorporating the emotion/drive system into the humanoid and creating both GUI and XML scripting tools for controlling it (e.g. parameter setting, initiation and debugging), we also conducted novel graphics research for blending the facial expressions.
4. We have produced agent-based simulations of primate social interactions which tests the evolutionary efficacy of such representation systems. This is ongoing work, but has been presented at several primatology meetings as well as social simulation meetings. In addition, we have performed more basic research on the efficiency of this system, which has also been published and is being submitted further. We believe that new emotional states are required to regulate new evolutionary goals. For example, social emotions have evolved to regulate the social behavior of social species. Different drives/emotions help social agents avoid the dangers of both conflict and isolation. On the other hand, drives for sex and prestige encourage individuals to engage in individually-dangerous behavior that benefits their progeny and therefore their species or genes.
5. We have also put considerable effort into making the building of such complex models in agent-based simulations easier, both by creating a new research platform on top of an existing system (BOD / MASON) and by creating an IDE for dynamic plans. This work is downloaded regularly and has been used in applications as varied as computer game characters and military logistics simulations.

Associated Persons

• Principle Investigator
• Joanna Bryson
• Named Researcher
• Emmanuel Tanguy
• Research Officers
• Emmanuel Tanguy
• Jan Drugowitsch
• Tristan Caulfield
• Philipp Rohlfshagen
  
• Supported Students (PhD)
• Emmanuel Tanguy
• Hagen Lehmann
• Associated Project / Dissertation Students (not funded)
  
• Undergraduate
• Mary Estall, "Creating an Assistive Intelligent Environment using Behaviour Oriented Design (BOD)".
• MSc
  
• Paula Ellis, "Psychology on the Internet:  Emotional Facial Expressions in Virtual Agents,".
• Zhang Borui, "The Integration of EEFAS and Chatbots System."
• Ando Yasushi, "The Effect of Predation on the Evolution of Dominance Hierarchy in Primate Society,".
• Andrew Beggs "Aide Memoir Bot with Emotional Response (AMBER): A Desktop Prototype of a Behaviour-Based, Artificially Intelligent Care Device with a Virtual Reality Face,".
• Jiang Yifan, "Improving Speech Production for an Emotionally Expressive Facial Animation System."

Software

• The Dynamic Emotional Representation (DER) is a natural, real-time models of emotions for facial animation. This is distributed as a part of the Emotionally Expressive Facial Animation System (EE-FAS).
• Many software simulations (including some of Lehmann's social simulations and Rohlfshagen's flexible latching) were performed in BOD/MASON.  Drugowitsch & Caulfield contributed significantly to this infrastructure.
• Additional models built on other platforms can be found on the AmonI Software Page.
  

Publications

• Emmanuel A. R. Tanguy, Emotions: the Art of Communication Applied to Virtual Actors, PhD dissertation, Department of Computer Science, University of Bath.
  
• Joanna J. Bryson, Yasushi Ando and Hagen Lehmann ``Agent-based modelling as scientific method: a case study analysing primate social behaviour'', Philosophical Transactions of the Royal Society, B -- Biology, 362(1485):1685-1698, Sept 2007.
• Emmanuel Tanguy, Philip Willis and Joanna J. Bryson ``A Dynamic Emotion Representation Model Within a Facial Animation System'', The International Journal of Humanoid Robotics, 3(3):293-300, September 2006.
• Joanna J. Bryson (ed.), Adaptive Behavior 10(1), special issue on ``Mechanisms of Action Selection'', 2007. ``Mechanisms of Action Selection: Introduction to the Special Issue,'' pp. 5-8.
• Tony J. Prescott, Joanna J. Bryson, and Anil K. Seth (eds.), Philosophical Transactions of the Royal Society B 362(1485), special issue on ``Modelling Natural Action Selection'', Sept 2007. ``Introduction. Modelling Natural Action Selection'', pp 1521-1529.
• Joanna J. Bryson, Tony J. Prescott and Anil K. Seth (eds.), Modelling Natural Action Selection: Proceedings of an International Workshop, AISB, Sussex UK, 2005.
• Joanna J. Bryson, "The Impact of Durative State on Action Selection", AAAI Spring Symposium on Emotion, Personality and Social Behavior, pp? (6), AAAI, 2008.
  
• Emmanuel Tanguy, Philip Willis and Joanna J. Bryson, ``Emotions as Durative Dynamic State for Action Selection'', in The Twentieth International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, pp. 1537-1542, Morgan Kaufmann 2007.
• Cyril Brom, Jakub Gemrot, Michal Bída, Ondrej Burkert, Sam J. Partington and Joanna J. Bryson, ``POSH Tools for Game Agent Development by Students and Non-Programmers'', in The Nineth International Computer Games Conference: AI, Mobile, Educational and Serious Games, Dublin, Ireland, pp. 126-133, University of Wolverhampton 2006.
• Hagen Lehmann and Tino Schmidt, ``Modelling Intuition and Intentionality -- A Neuropsychological Perspective", in Proceedings of Computers and Philosophy -- An Intenational Conference, in press.
• Joanna J. Bryson, Tristan J. Caulfield and Jan Drugowitsch, ``Integrating Life-Like Action Selection into Cycle-Based Agent Simulation Environments'', in Proceedings of Agent 2005: Generative Social Processes, Models, and Mechanisms, Michael North, David L. Sallach and Charles Macal eds., pp. 67-81, Argonne National Laboratory 2006.
• Samuel J. Partington and Joanna J. Bryson, ``The Behavior Oriented Design of an Unreal Tournament Character'', The Fifth International Working Conference on Intelligent Virtual Agents, T. Panayiotopoulos, J. Gratch, R. Aylett, D. Ballin, P. Olivier and T. Rist, eds., pp. 466-477, Springer, 2005.
• Paula M. Ellis and Joanna J. Bryson, ``The Significance of Textures for Affective Interfaces'', The Fifth International Working Conference on Intelligent Virtual Agents, T. Panayiotopoulos, J. Gratch, R. Aylett, D. Ballin, P. Olivier and T. Rist, eds., pp. 394-404, Springer, 2005.
• Hagen Lehmann, JingJing Wang and Joanna J. Bryson, ``Tolerance and Sexual Attraction in Despotic Societies: A Replication and Analysis of Hemelrijk (2002)'', in Modelling Natural Action Selection: Proceedings of an International Workshop, J. J. Bryson, T. J. Prescott and A. K. Seth, eds., pp. 135-142, AISB, Sussex UK, 2005.

Links to PDF of these publications (unless linked above).

Other Dissemination

• Hagen Lehmann, talk: ``Environmental pressures influencing social order in macaques", Department of Computer Science, Charles University, Prague, 7 March 2008.
• Joanna J. Bryson, Panel participant, Humans and Humanoids -- Perspectives in Cognition ad Robotics, The Research Institute for Cognition and Robots -- CoR-University of Bielefeld, 9 October 2007.
• Hagen Lehmann and Joanna J. Bryson, ``The Socio-Ecological Model of Female Social Relationships in the Genus Macaca: An Agent Based Approach'', reviewed abstract and talk, presented at the biannual meeting of the European Federation for Primatology, 3 September 2007.
• Joanna J. Bryson, ``Emotions as Durative State for Action Selection'', invited panel presentation at AISB: Motivational and Emotional Roots of Cognition and Action, Hatfield, UK, April 2005.
• Joanna J. Bryson, talk: ``Conflict & Collaboration: Modelling Primate Social Behaviour'', Centre for Complexity Science, Imperial College London, 15 January 2008.
  
• Joanna J. Bryson, public lecture: "Can we build artificial intelligence -- and should we?", Bath Science Cafe, 14 January 2008.
  
• Joanna J. Bryson, Plenary: ``Cognition (and Robots)'', Humans and Humanoids -- Perspectives in Cognition ad Robotics, The Research Institute for Cognition and Robots -- CoR-Lab, University of Bielefeld, 9 October 2007.
• Joanna J. Bryson, Plenary: ``AI Architectures (or State Requirements for Human-like Action Selection)'' Network Meeting on Cognitive Architectures, The European Network for the Advancement of Artificial Cognitive Systems, Munich Airport, 29 June 2007.
• Joanna J. Bryson, talk: ``Action Selection for Human-Like Intelligence'', Center for Technology & Social Behavior, Northwestern University, 4 April 2007.
• Joanna J. Bryson, talk: ``Action Selection as Intelligent Systems Integration'', Google, Mountain View, CA, 15 August 2006.
• Joanna J. Bryson, talk: ``Conflicts & Collaboration: Modelling of the Evolution of Primate Social Behaviour'', Department of Psychology, University of Sheffield, 12 May 2006.
• Emannuel A. R. Tanguy, talk: "Emotions: The Art of Visual Communication for Virtual Actors", Department of Computer Science, University College London, 19 January 2006.
  
• Joanna J. Bryson, talk: ``Conflicts & Collaboration: Agent-Based Modelling of Primate Social Behaviour'', Artificial Intelligence Lab, Department of Informatics, University of Zurich, 15 November 2005.
• Joanna J. Bryson, talk: ``Conflict and Collaboration: Modeling Primate Social Behavior'', Northwestern Institute of Complex Systems (NICO), Northwestern University, 18 October 2005.
• Joanna J. Bryson, talk: ``Humanoid Faces for Assistive Ambient Intelligent Technology'', Bath Institute of Medical Engineering, Royal United Hospital, UK, 7 February 2005.