J. Bates, B. Loyall, and S. Reilly. An architecture for action, emotion and social behaviour. Technical Report CMU-CS-92-144, School of Computer Science, Carnegie Mellon University, 1992.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....schemes were used, such as in in Weizenbaum s Eliza [200] program, where natural language rules were used to emulate a therapy session. Similarly, graphical virtual worlds and characters have been generated by rules, cognitive models, physical simulation, kinematics and dynamics [205] 176] 60] [11] [7] 184] 51] 36] These traditional approaches are currently being combined with statistical machine learning techniques [23] 210] 27] 1.1.2 Learning and Generative Models in Perception In machine perception, generative models and machine learning have become prominent tools in particular ....

J. Bates, B. Loyall, and S. Reilly. An architecture for action, emotion and social behaviour. Technical Report CMU-CS-92-144, School of Computer Science, Carnegie Mellon University, 1992.

....and Evaluation of Embodied Conversational Agents: A Proposed Taxonomy Katherine Isbister, Ph.D. 1904 23 rd Street San Francisco, CA 94107 ( 1 )415 722 1945 ki katherineinterface.com Patrick Doyle Stanford University Gates Computer Science Bldg. 2A Stanford, CA 94305 9020 ( 1) 650 723 6707 pdoyle cs.stanford.edu ABSTRACT This workshop call demonstrates that our field is eager to move ....

....and Evaluation of Embodied Conversational Agents: A Proposed Taxonomy Katherine Isbister, Ph.D. 1904 23 rd Street San Francisco, CA 94107 ( 1 )415 722 1945 ki katherineinterface.com Patrick Doyle Stanford University Gates Computer Science Bldg. 2A Stanford, CA 94305 9020 ( 1) 650 723 6707 pdoyle cs.stanford.edu ABSTRACT This workshop call demonstrates that our field is eager to move beyond first generation generalist ....

[Article contains additional citation context not shown here]

Bates, J., Loyall, A. B., and Reilly, W. S. An architecture for action, emotion, and social behavior. Technical Report CMU-CS-92-142, School of Computer Science, Carnegie Mellon University, Pittsburgh PA, 1992.

....behavior. These characters, also known as Synthetic actors (SA) or Believable Agents, act autonomously, exhibiting behavior which, from a human player s standpoint, is indistinguishable from the behavior of characters controlled by other human players. Several SA models have been proposed ([4], 5] 6] and [7] However, they do not fully meet the requirements of long term games whose duration usually exceeds a dozen hours. In long term games, such as strategy and adventure ones, it is necessary to guarantee both personality stability and reactive emotional responses, issues that can ....

....process. Following, we briefly review three SA related projects, which are the most relevant to the games we are currently developing (cf. Section 5.1) For each project, we sketch the mutual influence among personality traits, mood, attitudes and goals. 3. 2 The OZ Project The OZ project [4] aims at building synthetic actors that exhibit goal driven behavior in interactive environments. The model of emotions is based on the work of Orthony, Clore and Collins [15] The authors propose an architecture called TOK, where emotion is the main channel for expressing an actor s behavior ....

Bates, J., Loyall, A. & Reilly, W. S. An Architecture for Action, Emotion, and Social Behavior. Technical report CMU-CS-92-144, School of Computer Science, Carnegie Mellon University, Pittsburgh. (1992)

.... [10] A detailed account of terms used in the field of new or alternative AI can be found in [18] and [21] Detailed accounts of these interactions as well as general information on the emergence and architecture of believable agents developed within the Oz project can be found in [2] 3] [4], 16] and [18] These articles and a general presentation of the project are presented at the project web site (http: www.cs.cmu.edu project oz web papers.html) Details of Master Servant Scenarios, developed within The Virtual Theater Project, are described in [12] and presented at ....

....the emotional engine of the purely textual believable agent developed within the Oz project (cat Lyotard) human is defined as somebody whom the cat dislikes. In the course of interaction, Lyotard gets food from the human and is pet by the human, and the human becomes somebody liked by the cat. [4]. What has changed in this brief interaction is Lyotard s rudimentary cultural encyclopedia of the human . The fact that the notion of cultural encyclopedia includes the possibility of change is very important in the field of behavior based AI, because of the importance of the learning ....

[Article contains additional citation context not shown here]

J. Bates, A. B. Loyall, W. S. Reilly. An Architecture for Action, Emotion, and Social Behavior. Technical Report CMU-CS-92-144. School of Computer Science, Carnegie Mellon University, Pittsburgh, PA., 1992.

....characters to be animated realistically without pixel level control [19] These cognitive models often form a hierarchy with various levels of behavioural interpretation. A set of emotions built on cognitive ideas drives animated characters such as Lyotard, a synthetic cat implemented by Bates [4]. Bates architecture, Tok, and the emotion unit, Em, are based on the OCC (Ortney, Clore and Collins [45] cognitive structure of emotions. This yields a more tractable hierarchical approach to emotion synthesis and permits the high level development of behaviourally convincing characters. ....

J. Bates, B. Loyall, and S. Reilly. An architecture for action, emotion and social behaviour. Technical Report CMU-CS-92-144, School of Computer Science, Carnegie Mellon University, 1992.

....entities such as the story. The feasibility of the proposed architecture is illustrated by a prototype that is able of creating simple navigation scenes. Agents Agent technology has being applied in distributed AI [Bond and Gasser, 1988] in groupware [Baecker, 1993] in virtual environments [Bates et al., 1992] and in robotics [Brooks, 1990] Also agent oriented programming has been proposed as a post object paradigm [Shoham,1993] Agent theory is not mature yet and leads to several definitions of agents and their properties. A complete survey on agent theories, architectures and languages can be found ....

J. Bates, A. B. Loyall, W. S. Reilly, Integrating Reactivity, Goals, and Emotion in a Broad Agent, Technical Report CMU-CS-92-142, School of Computer Science, Carnegie-Mellon University, Pittsburgh, PA, 1992.

....process using emotion was developed by Inoue et al., using neural networks [11] Stimulated by the Japanese work, U.S. researchers have also begun working in the area of emotions and believable agents [1,14] Bates has been building a believable agent for his virtual world, the OZ project [2,3,21], using a model proposed by Ortony, Clore and Collins [18] Another model has been built by Velasquez [29] These two models provide a reasonable starting point for building computer simulations of emotions; however, they describe only basic emotions and their reactions, not their interactions. ....

J. Bates, A. Bryan Loyall and W. Scott Reilly. An Architecture for Action, Emotion, and Social Behavior. Technical Report CMU-CS-92-144, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, May 1992.

....entertainment, and training. For instance, in the education arena, intelligent tutoring systems need to interact with students in real time[32] In the arena of entertainment, recent work has focused on real time, dynamic interactivity among multiple agents within virtual reality environments[5, 12, 17]. Similarly, in the arena of training, there is a recent thrust on dynamic, real time interactive simulations[24, 26, 33] In these simulations, humans may interact with tens or hundreds of intelligent agents, as they participate in realistic traffic environments that simulate traffic jams and ....

J. Bates, A. B. Loyall, and W. S. Reilly. Integrating reactivity, goals and emotions in a broad agent. Technical Report CMU-CS-92-142, School of Computer Science, Carnegie Mellon University, May 1992.

....to achieve their goals. Many of these multi agent domains require the interaction to be dynamic and real time. For instance, in education, intelligent tutoring systems interact with students to provide real time feedback[12, 37] In entertainment, projects such as interactive fiction[3], virtual immersive environments[21] and virtual theatre[11] all involve real time and dynamic multi agent interaction (collaborative and competitive) Similarly, in training, a recent thrust on dynamic, real time simulations e.g. realistic traffic[7] air traffic control[25] and combat[27, ....

....or cricket, an orchestra, a discussion, a coauthored paper, a play, etc. It is only natural that this teamwork is (and will be) reflected in virtual and robotic agent worlds, e.g. robotic collaboration by observation[19] RoboCup robotic (and virtual) soccer[17] social agents[23] virtual theatre[3, 11], virtual battlefields[34, 27] If agents are to successfully inhabit such collaborative and competitive worlds, they must be proficient in understanding and tracking team activity. This paper has taken a step towards this goal and advanced the state of the art in agent tracking and plan ....

J. Bates, A. B. Loyall, and W. S. Reilly. Integrating reactivity, goals and emotions in a broad agent. Technical Report CMU-CS-92-142, School of Computer Science, Carnegie Mellon University, May 1992.

....on an earlier draft of this paper. 1 Introduction Many AI researchers are today striving to build agents for complex, dynamic multi agent domains, such as, virtual theatre[7] realistic virtual training environments (e.g. for emergency drill[17] or combat[22, 19] virtual interactive fiction[1], RoboCup robotic and virtual soccer[13] and robotic collaboration by observation[14] Most of this research has so far focused on enabling individual agents to cope with the complexities of these dynamic domains. One promising approach that has emerged is the use of hierarchical reactive plans. ....

....team operators were all explicitly excluded from consideration. The domain of focus there was tracking the behaviors of a team of enemy fighter jets. 7 Summary and Discussion In a variety of dynamic multi agent environments currently under development, achieving flexibility in teamwork is critical[7, 22, 1, 13]. Yet, given the uncertainity in such domains, preplanned coordination cannot sustain such flexible teamwork. To alleviate this problem, we have provided individual agents with an explicit representation of team goals and plans, and an underlying ex13 plicit model of team activity, which has ....

J. Bates, A. B. Loyall, and W. S. Reilly. Integrating reactivity, goals and emotions in a broad agent. Technical Report CMU-CS-92-142, School of Computer Science, Carnegie Mellon University, May 1992.

....the more the users will react as if in a human human interaction. Other researchers working on believable agents in interactive environments agree that such agents must have personalities and emotions, because people naturally attribute them to those agents, although they know they are not real [3, 9, 12]. People react to them as if they were human. The style of interaction is especially important, because personality and emotions can be expressed through that style. Such phenomena have been noticed on television and computer screens by the social scientists Reeves and Nass [15] They have shown ....

Bates, J., Loyall, A. B., and Reilly, W. S. An Architecture for Action, Emotion, and Social Behavior. Technical Report CMU-CS-92-144, School of Computer Science, Carnegie Mellon University, 1992.

....entertainment, and training. For instance, in the education arena, intelligent tutoring systems need to interact with students in real time[32] In the arena of entertainment, recent work has focused on real time, dynamic interactivity among multiple agents within virtual reality environments[5, 12, 17]. Similarly, in the arena of training, there is a recent thrust on dynamic, real time interactive simulations[24, 26, 33] In these simulations, humans may interact with tens or hundreds of intelligent agents, as they participate in realistic traffic environments that simulate traffic jams and ....

J. Bates, A. B. Loyall, and W. S. Reilly. Integrating reactivity, goals and emotions in a broad agent. Technical Report CMU-CS-92-142, School of Computer Science, Carnegie Mellon University, May 1992.

....process using emotion was developed by Inoue et al., using neural networks [11] Stimulated by the Japanese work, U.S. researchers have also begun working in the area of emotions and believable agents [1,14] Bates has been building a believable agent for his virtual world, the OZ project [2,3,21], using a model proposed by Ortony, Clore and Collins [18] Another model has been built by Velasquez [29] These two models provide a reasonable starting point for building computer simulations of emotions; however, they describe only basic emotions and their reactions, not their interactions. ....

J. Bates, A. Bryan Loyall and W. Scott Reilly. Integerating Reactivity, Goals and Emotion in a Broad Agent. Technical Report CMU-CS-92-142, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, May 1992.

....in a virtual historical setting[19] or virtual instructor in a training environment [1, 2] must interact with students in real time. Similarly, in the arena of entertainment, recent work has focused on real time, dynamic interactivity among multiple agents within virtual reality environments [6, 9]. Such real time interaction is also seen in robotic environments [11] In all these environments, agent tracking is a key capability required for intelligent interaction [38, 36, 40, 22, 4] It involves monitoring other agents observable actions and inferring their mental state their goals, ....

J. Bates, A. B. Loyall, and W. S. Reilly. Integrating reactivity, goals and emotions in a broad agent. Technical Report CMU-CS-92-142, School of Computer Science, Carnegie Mellon University, May 1992.

.... features and raw emotions goal successes, failures creation actions standards attitudes emotions goals behaviors Integrated Sense Model Sensory Routines sense language queries sense language queries Figure 1: Tok Architecture 2 Overview of Tok Tok contains a number of integrated components [4, 8, 9]. To explain these components, and particularly Em, we will look in abstract terms at how the entire architecture works (See Figure 1) 1 . The Tok agent is embedded in a physical world simulation and repeats a cycle of sense think act for the duration of the simulation. On a given cycle, the ....

.... decides it wants to respond, it sends a similar case frame representation to Glinda (not shown) which generates appropriate output based on both the case frame and pragmatic considerations such as the agent s emotional state [8] The integration of these modules is an interesting problem in itself [4], but not one that we will discuss here except for a brief description of the Em Hap integration in the behavioral features section below. 3 Models of Emotion Our emotion system is modeled on a scaled down version of the cognition based emotion model of Ortony, Collins, and Clore (OCC) 12] ....

[Article contains additional citation context not shown here]

Joseph Bates, A. Bryan Loyall, and W. Scott Reilly. Integrating reactivity, goals, and emotion in a broad agent. Technical Report CMU-CS-92-142, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, May 1992. To appear in Proceedings of the Fourteenth Annual Conference of the Cognitive Science Society, Bloomington, Indiana.

.... conference paper appearing in [25] 1 Introduction Many AI researchers are today striving to build agents for complex, dynamic multi agent domains, such as, virtual theatre[7] realistic virtual training environments (e.g. for emergency drill[18] or combat[28, 20] virtual interactive fiction[1], and robotic collaboration by observation[14] Most of this research has so far focused on enabling individual agents to cope with the complexities of these dynamic domains. One promising approach that has emerged is the use of hierarchical reactive plans. Reactive plans are qualified by ....

....operator hierarchy illustrated in Figure 5; and (ii) learning the general or common sense rules for teamwork that have been handcoded in this work. 8 Summary and Discussion In a variety of dynamic multi agent environments currently under development,achieving flexibility in teamwork is critical[7, 28, 1, 13]. Yet, given the uncertainty in such domains, preplanned coordination cannot sustain such flexible teamwork. To alleviate this problem, we have provided individual agents with an explicit representation of team goals and plans, and an underlying explicit model of team activity, which has already ....

J. Bates, A. B. Loyall, and W. S. Reilly. Integrating reactivity, goals and emotions in a broad agent. Technical Report CMU-CS-92-142, School of Computer Science, Carnegie Mellon University, May 1992.

No context found.

J. Bates, B. Loyall, and S. Reilly. An architecture for action, emotion and social behaviour. Technical Report CMU-CS-92-144, School of Computer Science, Carnegie Mellon University, 1992.

No context found.

Bates, J., Bryan Loyall, A., and Scott Reilly, W. (1992b). Integrating reactivity, goals, and emotion in a broad agent. Technical Report CMU--CS--92--142, School of Computer Science, Carnegie-Mellon University, Pittsburgh, PA.

No context found.

Bates, J., Bryan Loyall, A., and Scott Reilly, W. (1992a). An architecture for action, emotion, and social behaviour. Technical Report CMU--CS--92--144, School of Computer Science, Carnegie-Mellon University, Pittsburgh, PA.

No context found.

J. Bates, A. Bryan Loyall, and W. Scott Reilly. Integrating reactivity, goals, and emotion in a broad agent. Technical Report CMU--CS--92--142, School of Computer Science, Carnegie-Mellon University, Pittsburgh, PA, May 1992.

No context found.

Bates, J., Loyall, A.B. & Rielly, W.S. Integrating Reactivity, Goals, and Emotions in a Broad Agent. Technical Report CMU-CS-92-142, School of Computer Science, CarnegieMellon University, 1992.

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