Th e 9th lntemational Conference on Computer Supported Cooperative Work in Design Proceedings Agent-based Interaction Model fo r Collaborative Virtual Environments Xiaohong Mi, Jiaxin Chen Electron. I n $ Eng. Coll. Henan Univ. o f Sci. & Techno, He 'Nan Province, China cjx@mail. haust.edu.cn Abstract Interaction among users in the context of CoIIaborative firtual Environments (CVEr) afects the eflciency o f collaborative work In mosi o f the current CSCW application systems, users interaction is still bused on the traditional ways such as @ped chat and so on . In order to enrich the interaction among users, sumeone has proposed to a d d 3D avatars into the CVEs. Howevel; the poo r behavior usually shown by the avatars controlled by users makes it dtficult to achieve un acceptable level o f immersion or their users. This paper provides with a new point of view, prop osing an agent-based model for the study o f avatar'interaction in CVEs through the analysis o f dryerent interaction lavers among users, and presenting a semi-autonomous avatar uppronch. By attaching Q semi-autonomous intelligent virtual agent to the avatars, we can enhance the immersion and interact ion among users. Keywords: Collaborative Virtual Environments; Interaction; 3D Avatars; Intelligent Agent; Decision Mechanism 1 Introduction The concept of Computer Supported Cooperative Work (CSCW) has broken through the traditional application of computer, for it provides users with a WYSIWIS (What You See Is What I See) Collaborative Virtual Environments [l]. In addition, CVEs also allow users to collaborate in closely coupled and highly synchronized tasks, These tasks require very close or In of the current CSCW application systems, users' interaction is still based on the traditional ways such as typed chat an d so on. Thus, it is necessary to provide a means of interaction among users for better collaboration. In order to enrich the interaction among users, someone has proposed to add 3D avatars into the CVEs. Having avatars as user representations in CVEs stems from th e need of an identity that every user feels when he enters into the environment. It has several other functions: inform the user's presence to others, identify and differentiate users, visualize the users position and orientation, direction of interest, and enable communication among users [2]. However, th e poor behavior usually shown by the avatars controlEed by users makes it difficult to achieve an acceptable level of immersion for their users. The solution that we propose is to automate the static avatars, trying to make them interact in the same wa y as what users would do in real world. e advocate for the attachment of a semi-autonomous intelligent virtual agent to the avatars. By using AI techniques, we can build intelligent agents, and then the user can choose to take absolute control over the actions of his avatar, delegating the management of the rest to the agent. With more intelligence, avatars are able to perceive the environment and to make their own decisions, and thus can enhance the interacti on among users. Some previous works have also dealt in some way with the partial autonomy of avatars in an interactive environment. One of th e most interesting proposals is Th e CyberCafe, described by Rousseau and Hayes-Roth in [3]. They introduce the concept of synthetic actors. A synthetic actor may be autonomous or a user's avatar. An autonomous actor receives directions from the scenario an d other actors, and decides on its own behavior on th e virtual stage with respect to those directions [4]. An avatar i s largely directed by a user who selects actions to perform, although it also receives directions from th e scenario and from the other actors. In fact, the user chooses th e actions to be perform ed by the avatar, but the way to cany them out is chosen by the avatar. These actors are able to improvise their behavior in an interactive environment an d they own a repertoire of actions that are automatically planned to achieve each goal. Th e first problem of automating part of the behavior of an avatar is that if the user decides to delegate some functions on her personal agent, she will expect the behavior exhibited by the avatar to be similar to he r own behavior in t he same situation. She will also expect her avatar to behave in a consistent way. And, moreover, she wit1 expect a different behavior of her avatar towards the different avatars that populate the virtual world. In order to do so, the intelligent agent attached to our avatars must be able to manage several knowledge dimensions, such as user dimension and so on. And it also needs a decision mechanism that allows it to select the most appropriate action in very situation, 40 1
4
Embed
Agent-Based Interaction Model for Collaborative Virtual Environments
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
8/3/2019 Agent-Based Interaction Model for Collaborative Virtual Environments
CoIIaborative firtual Environments (CVEr) afects the
eflciency of collaborative work In mosi of the current
CSCW application systems, users interaction is stillbused on the traditional ways such as @ped chat and so
on . In order to enrich the interaction among users,
sumeone has propo sed to add 3D avatars into the CVEs.
Howevel; the poo r behavior usually shown by the avatarscontrolled by users makes it dtficult to achieve un
acceptable level of immersion or their users. This paper
provides with a new point of view, prop osing an
agent-based model fo r the study of avatar'interaction in
CVEs through the analysis of dryerent interaction laversamong users, and presenting a semi-autonomous avataruppronch. By attaching Q semi-autonomous intelligent
virtual agent to the avatars, we can enhance theimmersion and interaction among users.
Keywords: Collaborative Virtual Environments;Interaction; 3D Avatars; Intelligent Agent; DecisionMechanism
1 Introduction
The concept of Computer Supported CooperativeWork (CSCW) has broken through the traditionalapplication of computer, for it provides users with aWYSIWIS (What You See Is What I See) C ollaborativeVirtual Environments [l]. In addition, CVEs also allow
users to collaborate in closely coupled and highlysynchronized tasks, These tasks require very closecoordination between two or more users. But In most ofthe current CSCW application systems, users' interactionis still based on the traditional ways such as typed chat
and so on. Thus, it is necessary to provide a means ofinteraction amon g users for better collaboration. In order
to enrich the interaction among users, someone hasproposed to add 3D avatars into the CVEs. Havingavatars as user representations in CVEs stems from the
need of an identity that every user feels when he enters
into the environment. It has several other functions:inform the user's presence to others, identify anddifferentiate users, visualize the users position and
orientation, direction of interest, and enable
communication among users [2]. However, the poorbehavior usually shown by the avatars controlEed by
users makes it difficult to achieve an acceptable level ofimmersion for their users.
The solution that we propose is to automate thestatic avatars, trying to make them interact in the same
way as what users would do in real world. We advocatefor the attachment of a semi-autonomous intelligent
virtual agent to the avatars. By using AI techniques, wecan build intelligent agents, and then the user can choose
to take absolute control over the actions of his avatar,delegating the man agement of the rest to the agent. With
more intelligence, avatars are able to perceive theenvironment and to make their own decisions, and thus
can enhance the interaction among users.
Some previous works have also dealt in some way
with the partial autonomy of avatars in an interactiveenvironment. One of th e most interesting proposals is
The CyberCafe, described by Rousseau and Hayes-Rothin [3]. They introduce the concept of synthetic actors. Asynthetic actor may be autonom ous or a user's avatar. An
autonomous actor receives directions from the scenario
and other actors, and decides on its own behavior on the
virtual stage with respect to those directions [4]. Anavatar is largely directed by a user who selects actions toperform, although it also receives directions from th escenario and from the other actors. In fact, the user
chooses the actions to be perform ed by the avatar, but theway to cany them out is chosen by the avatar. Theseactors are able to improvise their behavior in aninteractive environment and they own a repertoire of
actions that are automatically planned to achieve each
goal.The first problem of automating part of the behavior
of an avatar is that if the user decides to delegate some
functions on her personal agent, she will expect the
behavior exhibited by the avatar to be similar to he r own
behavior in the same situation. She will also expect her
avatar to behave in a consistent way. And, moreover, shewit1 expect a different behavior of her avatar towards thedifferent avatars that populate the virtual world. In order
to do so, the intelligent agent attached to our avatars
must be able to manage several knowledge dimensions,such as user dimension and so on. And it also needs a
decision mechanism that allows it to select the mostappropriate action in very situation,
401
8/3/2019 Agent-Based Interaction Model for Collaborative Virtual Environments
The9th International Conference on Computer Supported Cooperative Work in Design Proceedings
This paper goes into a description of the different
interaction layers among users, and shows the limitationsof the current CVEs in each of these layers. Then we
describe the set of dimensions in the virtual agent’s
knowledge base that are needed to enhance users’
interaction. Afterwards, the application of theagent-based interaction model in a CV E is discussed and
some xperimental results are presented.
2 Interaction Layers
The design of CVEs enhances the collaboration ofusers, and the 3D avatar is an important factor. In amulti-user collaborative environment, if someone wants
to know others’ present work, he has to achieve it by
observing the actions of their avatars [ 5 ] . Considering the
actors of CVEs are not only the users but also theiravatars, we propose a four-interaction-layer as follows:user-user interaction, user-own avatar interaction,
user-other’s avatar interaction and avatar-avatarinteraction. It’s shown as Figure 1.
should be improved by adding more intelligent
capabilities to the avatars, thus increasing the user
immersion as well.
2.3. User-another’s avatar interaction
Entering most CVEs we can only find inexpressive
and static avatars, because they are merely used as asignal to indicate the presenc e and location of their users.
Once they have met, the communication turns to thetraditional user-user Iayer. If the avatar can provide some a
information about its owner, such as name, e-mail
address, vocation and so on, it can lead into a
reinforcement o f the interaction among users. This can
be accom pIished by building a user knowledge database.
2.4. Avatar-avatar interaction
In current CVEs, since avatars are not aware of
anything, they cannot interact intelligently with otheravatars without the intervention of their users. With more
intelligent avatars, which are able to perceive the
environment and to make their own decisions, this
interaction layer could be exploited to enhance user-user
interaction and to make avatars more useful for their
owners.
3 Architecture of an IntelligentAgent
Figure 1. Interaction layers among users
2.1. User-user interaction
This i s the kind of interaction in which users
communicate directly without the invention of their
avatars. Typed and voice chat is the most common tool
for this kind of interaction. People can discuss some
collaborating problems an d acquire others’ present work.However, it is neither natural nor fast.
2.2.User-own avatar interaction
The communication between a user and his ownavatar is one of the poorest exploited. Most of the currentCVEs consider the avatar just as a puppet that receives
commands and executes them without doing anyintelligent processing or learning, and they have no
awareness of the others [ 6 ] . The direction in layer 2
We should analyze, as a starting point, some of themost remarkable ideas of previous works. A goodapproximation to the architecture of an avatar is The
CyberCafe[3]. According to this architecture, a
participant has a mind and a body. We have adopted thearchitecture that is shown in Figure 2. Each avatar is
implemented as i t ~ l gent, i.e. something: ‘?hat can be
viewed as perceiving its environment through sensorsand acting upon that environment through effectors” 171,
which consists o f tw o main components: a physical bodyand an AI engine. The body is the 3D geometric
representation of the watar (together with its positionand speed), which provides the AI engine with allnecessary sensing and actuator services, whereas the AI
engine (mind) supplies all functionality necessary forworld representation, goal planning, sensing and acting,and emotions. This feature will allow us o cope with theunexplored interaction layers.
402
8/3/2019 Agent-Based Interaction Model for Collaborative Virtual Environments
Th e 9th nternational Conference on Computer Supported Coop erative Work in Design Proceedings
Figure 2. Architectureof an intelligent avatar
Within this architecture, ou r aim will be the
description o f the avatar’s mind. The mind will control
the actions to be performed by the avatar’s body in the
virtual world. .In order to build this mind we havedeveloped an intelligent agent that can be linked to the.
avatar.
In fact, an intelligent agent is a computer systemcapable of flexible autonomous action in some
environment. The main features of agent is showed as
follows:(1) Autonomy: Capable of acting independently,
exhibiting conbol over their internal state by flexible;(2) Social Ability: The ability to interact with other
agents (and possibly humans) via some kind ofagent-communication language, and perhaps cooperatewith others, and agents interact with environment
through sensors and effectors as shown in Figure 3;
Figure 3. Principle of agent
In order to perform the most appropriate actions invery situation, the agent must provide a set of decision
mechanism that depends on the following howledge
base [XI:
(1) User Dimension: First, th e agent must have
knowledge about its own user, in order to behave in thesame way she would do . It has to learn about her goals,
her concentration , her reactions, her personality, her likesand dislikes, etc.
(2 ) Introspective Dimension: O n the other hand, the
agent must manage some knowledge about itself (itsmind) and the avatar it is controlling (its body): external
appearance, personality, moods, past experiences,
location in the CVEs, etc.(3) Social Dimension: A third kind of knowledge to
be managed is to concern the rest of the avatars
inhabiting in the CVEs: their appearance, personalitytraits, mood, attitud es, past history of interaction, etc.
(4) Environment Dimension: Finally, the agent alsohas to manage some know ledge about the CVEs in which
itis
located: geometry, objects, exits, utility, etc.Among the interaction model we have advocated,sensors apperceive the information of environment with
it s own environment dimension, and then it will decide
on what to do and how to do it according to this
information and it s knowledge base; afterward, effectors
will perform the corresponding actions. Of course, this
needs an action database, too. Thus this model can
improve the interaction Iayers by delegating somefunctions on their personal agents. The structure of th e
intelligent agent we advocate is shown in Figure 4.
4 Algorithm for sensors an d effectors
The key elements of agent are it s sensors and
effectors. Every time an avatar performs an action, theagent attached to it first senses the environment via avision cone, if it gains awareness of other avatars in its
path, it will analyze this information, and then send it tothe decision mechanism; in the end, the effectors ‘select