Research of AI in animation

[Jonathan]

Archived from groups: comp.ai.games (More info?)

Hello. I am currently doing a research on artificial intelligence in 3D
animation for my final year project. The specific field of interest would be
in crowd control. The outcome of the project is the development of a demo
system showing the AI capabilities.

Question is what would be the best AI method to implement into crowd
behavior? I'm thinking of rule-based for now. Is it suitable?

Besides that, which open-source 3D engine would you recommend? Thanks.

 

[Guest]

Archived from groups: comp.ai.games (More info?)

Jonathan wrote:
> Hello. I am currently doing a research on artificial intelligence in 3D
> animation for my final year project. The specific field of interest would be
> in crowd control. The outcome of the project is the development of a demo
> system showing the AI capabilities.
>
> Question is what would be the best AI method to implement into crowd
> behavior? I'm thinking of rule-based for now. Is it suitable?
>
> Besides that, which open-source 3D engine would you recommend? Thanks.
>
>


There is a variety of work out there on modeling the behavior of crowds,
especially for military simulations. You might do a web search for
"modeling crowd behavior" and maybe also look for recent proceedings of
the BRIMS conference (used to be CGF).

A rule-based approach could work, but assuming you want "generic"
flowing types of crowds, reacting to different kinds of events, you
might actually be better off with some kind of dynamic mathematical
model, or a "flocking" type of system. You probably don't need much in
the way of knowledge-intensive decision making for this, but instead
want some more primitive types of reactive behavior.

 

[Jon]

Archived from groups: comp.ai.games (More info?)

Hey there, thanks a bunch. Googling "modelling crowd behavior" gave a ton of
papers to refer to. Just about what I need.

Now, I'm just wondering - What would be a suitable (not too technically
difficult) framework for my research. The basics of it are:
1. Crowd behavior in a battle environment
2. Some variables allowed to be changed of the agents for "individualism"
3. A 3D engine to show the behaviors

The rough idea I have in mind is:
Research on a suitable AI method. Define agents rules and behavior. Create
3d models and animate according to predetermined movements/behaviors.
Integrate models into 3D engine and program AI agents. Implementing AI
"engine" with 3D engine. Other aspects like pathfinding and rendering should
be taken care of by the 3D engine.

Did I miss out anything? Again, thanks!

"Randolph M. Jones" <rjones@colby.edu> wrote in message
news:42078FAD.6080203@colby.edu...
> Jonathan wrote:
>> Hello. I am currently doing a research on artificial intelligence in 3D
>> animation for my final year project. The specific field of interest would
>> be in crowd control. The outcome of the project is the development of a
>> demo system showing the AI capabilities.
>>
>> Question is what would be the best AI method to implement into crowd
>> behavior? I'm thinking of rule-based for now. Is it suitable?
>>
>> Besides that, which open-source 3D engine would you recommend? Thanks.
>
>
> There is a variety of work out there on modeling the behavior of crowds,
> especially for military simulations. You might do a web search for
> "modeling crowd behavior" and maybe also look for recent proceedings of
> the BRIMS conference (used to be CGF).
>
> A rule-based approach could work, but assuming you want "generic" flowing
> types of crowds, reacting to different kinds of events, you might actually
> be better off with some kind of dynamic mathematical model, or a
> "flocking" type of system. You probably don't need much in the way of
> knowledge-intensive decision making for this, but instead want some more
> primitive types of reactive behavior.
>
>

 

[Guest]

Archived from groups: comp.ai.games (More info?)

Jon wrote:
> Hey there, thanks a bunch. Googling "modelling crowd behavior" gave a ton of
> papers to refer to. Just about what I need.

Make sure you google "modeling" as well as "modelling", because we US
folks sometimes spell things in odd ways .

>
> Now, I'm just wondering - What would be a suitable (not too technically
> difficult) framework for my research. The basics of it are:
> 1. Crowd behavior in a battle environment
> 2. Some variables allowed to be changed of the agents for "individualism"
> 3. A 3D engine to show the behaviors

I haven't done crowd modeling specifically myself, but this looks about
right. I figure you want to start by examining exactly what the 3D
engine provides you in terms of control over each entity's movement, and
the sensory/terrain information you are able to query. This will give
you the basic input and output parameter space for the model. Then you
have to decide for yourself what types of "individualism" parameters you
want, but it will only make sense to use parameters that ultimately be
expressed in changes in behavior. And they will certainly depend on
whatever "flocking" (or whatever) model you ultimately decide to use.
If you are working in a battle environment, it might make sense to
implement cultural and emotional factors. Also, depending on what
you're looking for, you might want some representation of motivation
and/or goals. Why is each member of the crowd there in the first place?
That might have a lot to say about whether an individual will run
away, react angrily, etc.

>
> The rough idea I have in mind is:
> Research on a suitable AI method. Define agents rules and behavior. Create
> 3d models and animate according to predetermined movements/behaviors.
> Integrate models into 3D engine and program AI agents. Implementing AI
> "engine" with 3D engine. Other aspects like pathfinding and rendering should
> be taken care of by the 3D engine.
>
> Did I miss out anything? Again, thanks!

Sounds like a reasonable approach. As with any AI-oriented behavior,
I'd start with a specific (reasonably sized) scenario and set of
behaviors in mind, implement those (along with the basic interfaces,
etc.) and refine from there.

 

[Guest]

Archived from groups: comp.ai.games (More info?)

Jon wrote:
> Hey there, thanks a bunch. Googling "modelling crowd behavior" gave a ton of
> papers to refer to. Just about what I need.
>
> Now, I'm just wondering - What would be a suitable (not too technically
> difficult) framework for my research. The basics of it are:
> 1. Crowd behavior in a battle environment
> 2. Some variables allowed to be changed of the agents for "individualism"
> 3. A 3D engine to show the behaviors

If you want a flexible framework, advanced object collections,
data-model-view autogenerated GUI intefraces, advanced networking
interface and clustering thechnology, and don't care too much for the
missing eye candy of the GUI and the GL engine, and the fact that there
is no predefined terrain model (and, of course, no pathfinding), you
might want to look at Gled (http://www.gled.org/). The project is base
on the ROOT objective analysing C++ framework (http://root.cern.ch/).

Its author and his colaborators (including me) would be willing to
assist you since an advanced terrain model and pathfinding library is
planned.

> Other aspects like pathfinding and rendering should
> be taken care of by the 3D engine.

As I said, you would have to do this yoursef in this case...

Best regards,

-jan