SciELO - Scientific Electronic Library Online

 
vol.11 número1SAR SIMULATION FOR CHIRAL WAVES IN HEAD MODELAVAILABILITY EVALUATION OF NETWORKS: AN APPROACH FOR N-TIER CLIENT SERVER ARCHITECTURE índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Revista Facultad de Ingeniería - Universidad de Tarapacá

versión On-line ISSN 0718-1337

Rev. Fac. Ing. - Univ. Tarapacá v.11 n.1 Arica jun. 2003

http://dx.doi.org/10.4067/S0718-13372003000100003 

  REVISTA FACULTAD DE INGENIERÍA, U.T.A. (CHILE), VOL. 111, 2003, pp. 11-24

DISEÑO DE UN MODELO DE PERCEPCIÓN PARA AGENTES VIRTUALES INTELIGENTES BASADO EN EL SISTEMA DE PERCEPCIÓN DE LOS SERES HUMANOS

Pilar Herrero1     Angélica de Antonio1

[1] Universidad Politécnica de Madrid, Facultad de Informática Campus de Montegancedo s/n, 28.660 Boadilla del Monte - Madrid, pherrero@fi.upm.es, angélica@fi.upm.es


RESUMEN

Una prioridad en Sistemas de Agentes Virtuales Inteligentes (AVIs) y Sistemas Multi-Agentes Virtuales Inteligentes (mAVIs), es introducir una percepción sensitiva similar a la que poseen los seres humanos que permita que los AVIs perciban, en tiempo real, el entorno que le rodea con una claridad de percepción similar a la que poseen los seres humanos. Algunos estudios dentro del área de investigación cognitiva introducen la percepción humana como el primer nivel de un modelo de "awareness" (consciencia). Basándonos en estos estudios, se ha desarrollado un modelo de percepción basado en uno de los más conocidos modelos de "awareness" desarrollados para trabajo colaborativo (CSCW). Este modelo es conocido como "Modelo Espacial de Interacción" (MEI) y gobierna "awareness" en Entornos Virtuales Colaborativos (EVC).

El modelo de percepción desarrollado extiende los conceptos fundamentales del MEI, introduciendo algunos factores propios de la percepción tanto visual como auditiva en humanos (como son la Agudeza Sensitiva o la Región de Transición Sensorial) y reinterpreta estos conceptos clave con el fin de introducirlos en el sistema perceptivo de un AVI. Una vez formalizado el modelo, se ha seleccionado una arquitectura de agentes para poder introducir, usar y validar este modelo. De entre todas las posibles arquitecturas, se ha seleccionado el Modelo de Triple Torre de Nilsson. La introducción de este modelo de percepción dentro de la arquitectura de agente seleccionada ha requerido la creación de un "motor de percepción" y un diseño semi-centralizado de percepción que permita manejar no sólo la percepción sensitiva del agente sino también algunos factores externos y adicionales tales como la atenuación.

Palabras claves: Entornos virtuales, agentes virtuales inteligentes, percepción, consciencia, Focus, Nimbus

 

ABSTRACT

A priority in Intelligent Virtual Agents Systems (IVAS) and multi- Intelligent Virtual Agents Systems (mIVAS) is to introduce human-like sensitive perception which allows an IVA to perceive its environment and surrounding objects in real-time with a human-like clarity of perception, gaining knowledge about its surroundings and experiencing any virtual simulated environment. Within the cognitive research area, there are some studies underwriting that human perception can be understood as a first level of an "awareness model". Following on from this research, we have developed a human-like perceptual model based on one of the most successful awareness models in Computer Supported Cooperative Work (CSCW), called the Spatial Model of Interaction (SMI), which manages awareness in Collaborative Virtual Environments (CVEs) through a set of key concepts.The perceptual model developed, extends the key concepts of the SMI by introducing some human-like factors typical of visual and hearing human perception - like Sense Acuity or Sense Transition Region - which are reinterpreted with the aim of introducing them as the key concepts of an IVA human-like perceptual model.


Having formalised the perceptual model, an appropriate agent architecture on which to use and test this perceptual model has been selected: a vertical layered architecture known as the Nilsson's Triple Tower Model. The introduction of this perceptual model into the agent perceptual block, has required the creation of a perceptual engine and the design of a semi-centralized approach to manage not just the sensitive agent perception, but also some other external and additional factors, such as attenuation.
brain tissue must have a few cells bearing protein molecules that happen to resonate at its rotation frequency.

Keywords: Virtual environments, intelligent virtual agents, perception, awareness, Focus, Nimbus




AGRADECIMIENTOS

El trabajo presentado en este artículo ha sido avalado y parcialmente financiado por la Universidad de Nottingham, habiéndose desarrollado una gran parte de este trabajo allí - en el centro de investigación "Communication Research Group (CRG)" de la Escuela de Informática y Tecnología de la Información de dicha universidad - bajo la dirección y continua supervisión de Steve Benford y Chris Greenhalgh.

Este trabajo ha sido parcialmente financiado por el Ministerio de Ciencia y Tecnología Español a través del proyecto TIC00-1346.

REFERENCIAS

[1] S. D. Benford and L. E. Fahlén; "A Spatial Model of Interaction in Large Virtual Environments". Proceedings of the Third European Conference on Computer Supported Cooperative Work (ECSCW'93). Milano. Italy. Kluwer Academic Publishers, pp. 109-124, 1993.        [ Links ]

[2] S. Benford et al.; "User Embodiment in Collaborative Virtual Environments. Proceedings of ACM Conference on Human Factors in Computing Systems", (CHI'95). Denver, Colorado, USA, pp. 242-249, 1995. http://www.acm.org/sigchi/ chi95/Electronic/documnts/papers/sdb_bdy.htm         [ Links ]

[3] B. Blumberg; Go with the Flow, "Synthetic Vision for Autonomous Animated Creatures. Proceedings of the First International Conference on Autonomous Agents", (Agents'97). Marina del Rey. California, pp. 538-539, 1997.        [ Links ]

[4] S. Card, T. Moran, A. Newell; The psychology of human-computer interaction. Hillsdale. NJ. Lawrence Erlbaum Associates. Inc, 1983.        [ Links ]

[5] S. Chopra-Khullar and N. Badler; Where to look? Automating attending behaviors of virtual human characters. Autonomous Agents and Multi-agent Systems 4(1/2), pp. 9-23, 2001.        [ Links ]

[6] S. Das, D. Grecu COGENT; "Cognitive agent to amplify human perception and cognition, Proceedings of the Fourth International Conference on Autonomous Agents. Barcelona. Spain, pp. 443-450, 2000.        [ Links ]

[7] P. Dourish and V. Bellotti; "Awareness and Coordination in Shared Workspaces",. Proceedings of the 4th ACM Conference on Computer-Supported Cooperative Work (CSCW). Toronto. Ontario. Canada, pp.107-114, 1992.        [ Links ]

[8] M. Endsley; "Design and evaluation for situation awareness enhancement", Proceedings of the Human Factors Society and 32nd Annual Meeting, Santa Monica. CA: Human Factors Society, 1, pp. 97-101, 1988.        [ Links ]

[9] M. Endsley; "Towards a theory of situation awareness", Technical report, Texas Technical University, Department of Industrial Engineering, 1993.        [ Links ]

[10] C. Greenhalgh; "Large Scale Collaborative Virtual Environments", Doctoral Thesis. University of Nottingham, 1997.        [ Links ]

[11] P. Herrero; "Awareness of interaction and of other participants", Technical Report. Amusement Esprit Project 25197, 1999.        [ Links ]

[12] P. Herrero; A. De Antonio, J. Segovia; "Is the Awareness of Avatars in a Virtual World Different from Human Awareness?", Workshop on the Future of Cves: Voltage in the Milky Night: The Future of CVE's. The Third International Conference on Collaborative Virtual Environments. ACM Collaborative Virtual Environments 2000. San Francisco. California. USA, 2000.        [ Links ]

[13] P. Herrero, A. De Antonio, S. Benford and C. Greenhalgh; "Increasing the Coherence between Human Beings and Virtual Agents",. Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems. Bologna. Italy, part 1, pp. 354-355, 2002.        [ Links ]

[14] P. Herrero, A. De Antonio; A Human Based Perception Model for Cooperative Intelligent Virtual Agents. Proceedings of the Tenth International Conference on Cooperative Information Systems (CoopIS 2002). Irvine. California. USA, pp. 195-212, 2002.        [ Links ]

[15] P. Herrero and A. De Antonio; "Introducing Human-like Hearing Perception in Intelligent Virtual Agents", To be published as full paper in proceedings of the Second International Joint Conference on Autonomous Agents and Multi-Agent Systems. Melbourne. Australia, 2003.        [ Links ]

[16] R. Hill; Soar: "An Architecture for Human Behavior Representation". Invited Panel Member and Presentation at the Workshop on Human Behavioral Representation, Conference on Modeling and Simulation. American Institute for Aeronautics and Astronautics (AIAA). Portland. Oregon, 1999.        [ Links ]

[17] R. Hill; "Modeling Perceptual Attention in Virtual Humans". Proceedings of the 8th Conference on Computer Generated Forces and Behavioral Representation, Orlando. Florida, 1999.        [ Links ]

[18] R. Hill, C. Han, M. Van Lent; "Perceptually Driven Cognitive Mapping of Urban Environments", Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems. Bologna. Italy, part 3, pp. 1389-1390, 2002.        [ Links ]

[19] R. Hill, Y.J. Kim and J. Gratch; "Anticipating Where to Look: Predicting the Movements of Mobile Agents in Complex Terrain", Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems. Bologna. Italy, part 2, pp. 821-827, 2002.        [ Links ]

[20] R. Hill, C. Han, M. Van Lent; "Applying Perceptually Driven Cognitive Mapping To Virtual Urban Environments; Conference on Innovative Applications of Artificial Intelligence (IAAI-2002). Edmonton. Canada, pp. 886-893, 2002.        [ Links ]

[21] N. Nilsson; "Teleo-Reactive Programs and the Triple-Tower Architecture", Electronic Transactions on Artificial Intelligence, Vol. 5 Section B, pp. 99-110, 2001.        [ Links ]

[22] H. Noser; "A Behavioral Animation System Based on L-systems and Synthetic Sensors for Actors", Ph.D. Thesis. École Polytechnique Fédérale De Lausanne. 1997.        [ Links ]

[23] J. Rickel, J. Gratch, R. Hill, S. Marsella and W. Swartout; "Steve Goes to Bosnia: Towards a New Generation of Virtual Humans for Interactive Experiences", Proceedings of AAAI Spring Symposium on Artificial Intelligence and Interactive Entertainment. Stanford University. California, pp. 67-71,2001.        [ Links ]

[24] T. Rodden; Populating the Application; "A Model of Awareness for Cooperative Applications", Proceedings of ACM 1996 Conference on Computer Supported Co-operative Work (CSCW'96). Boston. Massachusetts. USA. ACM Press, pp. 87-96, 1996.        [ Links ]

[25] D. Terzopoulos, X. Tu and R. Grzeszczuk; Artificial fishes: "Autonomous locomotion, perception, behavior, and learning in a simulated physical world", Journal of Artificial Life, 1, 4, pp. 327-351, 1994.        [ Links ]

[26] D. Terzopoulos, T. F. Rabie; "Animat Vision: Active Vision with Artificial Animals; Proceedings of the Fifth International Conference on Computer Vision (ICCV'95), Cambridge. MA. USA, pp. 801-808, 1995.        [ Links ]

[27] D. Terzopoulos and T. F. Rabie; Animat Vision: "Active Vision in Artificial Animals", Videre: Journal of Computer Vision Research, 1(1), pp. 2-19, 1997.        [ Links ]

[28] D. Terzopoulos; "Biological and Evolutionary Models give life to self-animating graphical characters with bodies, brains, behavior, perception, learning, and cognition", Artificial Life for Computer Graphics. Communications of the ACM, 42 (8), 1999. http://mrl.nyu.edu/~dt/papers/cacm99/cacm99.pdf         [ Links ]

[29] D. Thalmann; "A New Generation of Synthetic Actors: the Interactive Perceptive Actors", Proceedings of Pacific Graphics' 96. Taipeh. Taiwan, pp. 200-219, 1996.        [ Links ]

[30] D. Thalmann; "The Foundations to Build a Virtual Human Society", Proceedings of the 3rd International Workshop on Intelligent Virtual Agents (IVA'01). A. de Antonio, R. Aylett and D. Ballin (Eds.). Springer Lecture Notes in Artificial Intelligence, LNAI 2190. Madrid. Spain, pp. 1-14, 2001.        [ Links ]

[31] X. Tu and D. Terzopoulos; "Artificial Fishes: Physics, Locomotion, Perception, Behaviour", Proceedings of Computer Graphics, SIGGRAPH 94, pp 43-50, 1994.        [ Links ]

[32] W. K. Yeap and M. E. Jefferies; "Computing a representation of the local environment", Artificial Intelligence 107, pp. 265-301, 1999.        [ Links ]

[33] W. Zhang and R. Hill; "A Template-Based and Pattern-Driven Approach to Situation Awareness and Assessment in Virtual Humans", Proceedings of the Fourth International Conference on Autonomous Agents, Barcelona, Cataluña, Spain, ACM Press, pp. 116-123, 2000.        [ Links ]


Recibido el 08 de julio de 2003, aceptado 22 de septiembre de 2003.