Andr, E., Rist, T. and Mller, J. (1999). Employing AI Methods to Control the Behavior of Animated Interface Agents. Applied Artificial Intelligence 13:415-448.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....all scenarios. User Initiative Appreciates Introduction G rting Requests Respond Infoms Throats Understands Commands Figure 5: Grammar to ATN Mapping Emotional Models Our emotion models were built using several emotion and personality theories, including the Five Factor Model [2,42], Circumplex theory [34] and cognitive theory of emotions [33] The latter model underscores most of our work, providing a scheme for labeling common emotions based on how our virtual humans react to inputs, events, and objects [1] We also include an emotion reasoning architecture to describe ....

Andr6, E., Rist, T., & Milllet, J. (1999). Employing AI Methods to Control the Behavior of Animated Interface Agents. International Journal of Applied Artificial Intelligence, 13(4-5), 415-448.

....For example, Lester [15] generate deictic gestures and choose referring expressions as a function of the potential ambiguity and proximity of objects referred to. Rickel and Johnson [18] s pedagogical agent produces a deictic gesture at the beginning of explanations about objects. Andr et al. [1] generate pointing gestures as a sub action of the rhetorical action of labeling, in turn a sub action of elaborating. Cassell and Stone [3] generate either speech, gesture, or a combination of the two, as a function of the information structure status and surprise value of the discourse entity. ....

Andr, E., Rist, T., and Muller, J., Employing AI methods to control the behavior of animated interface agents, Applied Artficial Intelligence, vol. 13, pp. 415-448, 1999.

....example, Lester et al. 15] generate deictic gestures and choose referring expressions as a function of the potential ambiguity and proximity of objects referred to. Rickel and Johnson [19] s pedagogical agent produces a deictic gesture at the beginning of explanations about objects. Andr et al. [1] generate pointing gestures as a sub action of the rhetorical action of labeling, in turn a sub action of elaborating. Cassell and Stone [3] generate either speech, gesture, or a combination of the two, as a function of the information structure status and surprise value of the discourse entity. ....

Andre, E., Rist, T., & Muller, J., Employing AI methods to control the behavior of animated interface agents, Applied Artificial Intelligence, vol. 13, pp. 415-448, 1999.

....control. In this case, this architecture is more oriented to animal like simulation, where the dog Silas was one of the applications of the system. Some works have got closer to human like characters as the one presented in: Cosmos by Lester et al. [5] the PPP person explained by Elisabeth Andre [1], and Steve by Rickel and Johnson [9] However these characters have very different goals: they are pedagogical agents in charge of providing advice and explanations to the attendants. The work presented by Bates in his TOK architecture [2] is very interesting. The architecture is composed of ....

Elizabeth Andre. Employing ai methods to control the behavior of animated interface agents. Applied Artificial Intelligence, 13(45) :45--448, June-August 1999.

....of paths to contribute to the path by adding new pages to the path. Furuta and Shipman observed in classroom trials that WALDEN S PATHS was well received and that teachers would use WALDEN S PATHS in lieu of textbooks and slide shows [16] Andr, Rist, and Mller developed the WEBPERSONA [1]. Given a set of presentation goals, media objects, and temporal constraints, WEBPERSONA uses an intelligent planner to lay out a presentation on the Web. The author provides the goals to be accomplished during the presentation and WEBPERSONA automatically generates and lays out the ....

Andr, E., Rist, T., & Mller J. Employing AI methods to control the behavior of animated interface agents. Applied Artificial Intelligence, 13, 4 (Jun. 1999), 415448.

....engines aboard naval ships, including both individual tasks and team tasks. Steve is not limited to this domain; he can provide instruction in a new domain when given only the appropriate declarative domain knowledge. Despite the growing number of animated agents that converse with human users (Andr 1999; Johnson, Rickel, and Lester 2000; this book) Steve is unique in having domain independent capabilities to support task oriented dialogues situated in threedimensional virtual worlds. This chapter focuses on Steve s ability to integrate verbal and nonverbal communication to collaborate with ....

.... to explanation generation pioneered by McKeown (1985) In contrast, Andr and her colleagues employ a top down discourse planning approach to generating the communicative behavior of their animated agent, and they compile the resulting plans into finite state machines for efficient execution (Andr, Rist, and Mller 1999). The trade offs between these two approaches are well known (Moore 1995) Many of Steve s behavioral building blocks take several decision cycles to execute, and some (speech and locomotion) can take many decision cycles. During this period, Steve s perception and cognition modules remain ....

Andr, Rist, and Mller. 1999. Employing AI methods to control the behavior of animated interface agents. Applied Artificial Intelligence 13:415-448.

....the conversational skills of human users. Thus, for example, Lester s COSMO character ( 8] refers to the objects in his environment using pronouns, descriptions and or pointing gestures, according to a complex algorithm based on the linguistic theory of referential ambiguity. Andr and Rist ([1]) associate particular gestures to aspects of planning. They generate pointing gestures as a sub action of the rhetorical action of labelling, in turn a sub action of the action of elaborating. Similarly, Rickel and Johnson ( 11] have their pedagogical agent move to objects in the virtual world ....

André, E., T. Rist, & J. Mueller, "Employing AI Methods to Control the Behavior of Animated Interface Agents," Applied Artificial Intelligence, vol. 13, pp. 415-448, 1999.

....movable eyes, eyelids, eyebrows, and lips. Regardless of which body we use, our approach to animation is the same: the motor control module sends out messages to move and rotate graphical models of Steve s body parts. In contrast, some other researchers, such as Stone and Lester (1996) and Andre et al. 1998), create a library of animation sequences, and they dynamically string these together to control their agent s behavior. Our approach provides a finer granularity for behavior and allows Steve to interact with new virtual worlds without requiring the course author to build a domain specific ....

....library, but it results in high quality animation. Unlike Steve, Herman and Cosmo do not interact with a simulator, nor do they have any abilities to plan or replan procedural tasks. Several people have developed animated agents that can generate presentations. The PPP Persona (Andre Rist 1996; Andre, Rist, Mueller 1998) is an animated agent that combines speech and gestures to describe procedures for operating physical devices. The agent s body is controlled by flipping between different bitmap images of the agent in different poses. The agent cannot interact with a simulation, and it has no pedagogical ....

Andre, E.; Rist, T.; and Mueller, J. 1998. Employing AI methods to control the behavior of animated interface agents. Applied Artificial Intelligence. This issue.

.... in the student s field of view, Steve says Look over here and waits until the student is looking before proceeding with the demonstration) Steve s communicative suites are similar to the schemata approach to explanation generation pioneered by McKeown (McKeown 1985) In contrast, Andre et al. (Andre, Rist, Mueller 1998) employ a standard top down discourse planning approach to generating the communicative behavior of their animated agent, and they compile the resulting plans into finite state machines for efficient execution. The tradeoffs between these two approaches to discourse generation are well known ....

....at the level of individual words or syllables. This capability is needed to support many features of human conversation, such as the use of gestures, head nods, and eyebrow movements to highlight emphasized words. Like Steve, most current animated characters are incapable of such precise timing (Andre, Rist, Mueller 1998; Lester et al. 1998; Stone Lester 1996) One exception is the work of Cassell and her colleagues (Cassell et al. 1994) However, they achieve their synchronization through a multi pass algorithm that generates an animation file for two synthetic, conversational agents. Achieving a similar ....

Andre, E.; Rist, T.; and Mueller, J. 1998. Employing AI methods to control the behavior of animated interface agents. Applied Artificial Intelligence. Forthcoming.

No context found.

Andr, E., Rist, T. and Mller, J. (1999). Employing AI Methods to Control the Behavior of Animated Interface Agents. Applied Artificial Intelligence 13:415-448.

....as operators of a planning system. Starting from a complex presentation goal, e.g. to describe a technical device) the planner recursively performs a hierarchical goal decomposition until all subgoals have been expanded to elementary production, retrieval or presentation tasks (for details see [1]) The operators of the PPP system represent tactical knowledge about how to achieve presentation goals by means of a multimedia presentation including a character as an additional presentation device. Therefore, the operators are formulated from the point of view of a director who orchestrates ....

....but is a pure knowledge engineering task that manifests itself in writing plan operators for the components. In the sequel, we first introduce a rough classification of operators and then discuss some modi operandi in more detail. Building upon our earlier work on automated script generation [1], an operator represents a mapping rule that takes as input an abstract and usually complex communicative goal and either: a) maps it onto a set of less complex communicative goals (goal decomposition) or (b) specializes the goal by mapping it onto a more specific goal (goal specialization) or ....

[Article contains additional citation context not shown here]

Andr, E., Rist, T., and Mller. J. 1999. Employing AI methods to control the behavior of animated interface agents. Applied Artificial Intelligence 13:415--448.

....representations completely may be acceptable if these representations serve as decorations only. However, there are many examples of services which can hardly do without using graphical representations to encode information. For the purpose of illustration, we refer to DFKI s AiA Travel Agent [3] and to DFKI s Personal Picture Finder [4] Figure 1. Left: WWW interface of DFKI s Personal Picture Finder. For a given name the system searches the web for a picture of the person. Right: A typical collection of web pages (weather, hotel information and route descriptions) consulted by the AiA ....

Andr, E., Rist, T. and Mller, J. (1999). Employing AI Methods to Control the Behavior of Animated Interface Agents. Applied Artificial Intelligence 13:415-448.

....signal the beginning of lectures, meetings or talks. The portable domain will provide a real challenge to convey affective information in such an impoverished environment. Emotions and Personality The Persona system model extends the PPP animated presentation agent architecture developed at DFKI [2] with a number of new features most notably enhanced input and output modalities for affective communication, and an Affective Reasoning Engine for affective state recognition and generation. In line with recent research in affective computing [4] 16] and [22] we use two affective information ....

Andr, E., Rist, T. and Mller, J. (1999). Employing AI Methods to Control the Behavior of Animated Interface Agents. Applied Artificial Intelligence 13:415-448.

....the beginning of lectures, meetings or talks. The portable domain will provide a real challenge to convey affective information in such an impoverished environment. Emotions and Personality The Presence system model extends the PPP animated presentation agent architecture developed at DFKI [2] most notably with enhanced input and output modalities for affective communication, and an Affective Reasoning Engine for affective state recognition and modelling. In line with recent research in affective computing [21] we use two affective information processing channels (see Fig. 6) Our ....

Andr, E., Rist, T. and Mller, J. (1999). Employing AI Methods to Control the Behavior of Animated Interface Agents. Applied Artificial Intelligence 13:415-448.

....should do, the less there is a need to equip a character with a rich repertoire of reasonable self behaviors. In the AiA project (Adaptive Communication Assistant for Effective Infobahn Access) we developed a number of personalized information assistants that facilitate user access to the Web (Andr, Rist, and Mller 1999) by providing orientation assistance in a dynamically expanding navigation space. These assistants are characterized by their ability to retrieve relevant information, reorganize it, encode it in different media (such as text, graphics, and animation) and present it to the user as a multimedia ....

....hypothesis, however, was not supported by the data. We found numerical differences only in the expected direction: the proportion of recommendations actually followed by the subjects dropped off going from video based to cartoon style, audio, and text agents (for further details, see van Mulken, Andr, and Mller 1999). These findings suggest, among other things, that merely embodying an interface agent may not be enough: to come across as trustworthy, one may need to model the agent more deeply for instance, by giving it personality. We return to this issue later. in: J. Cassell, S. Prevost, J. Sullivan, ....

[Article contains additional citation context not shown here]

Andr, E., T. Rist, and J. Mller. 1999. Employing AI methods to control the behavior of animated interface agents. Applied Artificial Intelligence 13:415-- 448.

No context found.

Andr, E., Rist, T. and Mller, J. (1999). Employing AI Methods to Control the Behavior of Animated Interface Agents. Applied Artificial Intelligence 13:415-448.

....this chapter is to survey techniques for building IMMPSs, drawing upon lessons learned during the development of natural language generators. To 3 Application Sample Systems report generation MAGIC [23] PostGraphe [29] SAGE [43] RoCCo [6] technical documentation COMET [30] IDAS [60] PPP [10], Visual Repair [31] and WIP [5] route directions MOSES [48] mission planning and situation monitoring AIMI [51] CUBRICON [57] FLUIDS [36] project management EDWARD [17] IGING [26] business forms XTRA [3] configuration of computer networks MMI 2 [70] education and training PEA [54] ....

.... [57] FLUIDS [36] project management EDWARD [17] IGING [26] business forms XTRA [3] configuration of computer networks MMI 2 [70] education and training PEA [54] MAGPIE [34] Herman the Bug [66] COSMO [45] Steve [62] information kiosks ALFRESCO [65] ILEX [44] PEBA II [24] AiA [10] Figure 1: Applications for IMMP Systems faciliate the comparison of these systems, we will first present a generic reference model that reflects an implementation independent view of the authoring tasks to be performed by an IMMP system. After that, we will present techniques for automating and ....

E. Andre, T. Rist, and J. Muller. Employing AI Methods to Control the Behavior of Animated Interface Agents. Applied Artificial Intelligence Journal, 1998. to appear.

....conversation between human beings. Such a setting seems quite appropriate for a number of applications that draw on a distinguished agent user relationship. For example, an agent may serve as a personal guide or assistant in information spaces like the world wide web (as the AiA Persona [1]) or it can be a user s personal consultant or tutor (as Herman the Bug [13] and Steve [22] or it may come as a real estate sales person that tries to convince an individual customer (as the REA agent [5] However, there are also situations in which the emulation of a direct agent to user ....

....projects has discovered lifelike agents as a new means of computer based presentation. Noma and Badler [20] created a virtual human like weather reporter. Thalmann and Kalra [24] produced some animation sequences for a virtual character acting as a television presenter. The PPP and AiA Personas [1] developed at DFKI operate as desktop assistants or web chauffeurs. However, all these systems employ just one agent for presenting information. The Agneta Frida system [8] incorporates narratives into a web environment by placing two characters on the user s desktop. These characters watch the ....

[Article contains additional citation context not shown here]

Andr, E., Rist, T., and Mller, J. Employing AI Methods to Control the Behavior of Animated Interface Agents, Applied Artificial Intelligence 13:415-448, 1999.

....conversation between human beings. Such a setting seems quite appropriate for a number of applications that draw on a distinguished agent user relationship. For example, an agent may serve as a personal guide or assistant in information spaces like the world wide web (as the AiA Persona [1]) or it can be a user s personal consultant or tutor (as the Herman the Bug [13] and Steve [22] agents) or it may come as a real estate sales person that tries to convince an individual customer (as the REA agent [5] However, there are also situations in which the emulation of a direct ....

....projects has discovered lifelike agents as a new means of computer based presentation. Noma and Badler [20] created a virtual human like weather reporter. Thalmann and Kalra [24] produced some animation sequences for a virtual character acting as a television presenter. The PPP and AiA Personas [1] developed at DFKI operate as desktop assistants or web chauffeurs. However, all these systems employ just one agent for presenting information. The Agneta Frida system [8] incorporates narratives into a web environment by placing two characters on the user s desktop. These characters watch the ....

[Article contains additional citation context not shown here]

Andr, E., Rist, T., and Mller, J. Employing AI Methods to Control the Behavior of Animated Interface Agents, Applied Artificial Intelligence 13:415-448, 1999.

No context found.

Elisabeth Andre, Thomas Rist, and Jochen Muller. Employing AI methods to control the behavior of animated interface agents. Applied Artificial Intelligence, pages 415--448, 1999.

No context found.

Elisabeth Andre, Thomas Rist, and JochenMuller. Employing AI methods to control the behavior of animated interface agents. Applied Artificial Intelligence, 13:415--448, 1999.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC