Artificial Intelligence Depot
Visiting guest. Why not sign in?
News, knowledge and discussion for the AI enthusiast.
FEATURES COMMUNITY KNOWLEDGE SEARCH  
Get Creative: AI Article Writing Contest
Fancy the chance of getting developer focus, improving your research skills, sharing your artificial intelligence ideas, obtaining expert feedback, getting published online AND winning a prize?
Enter the AI Article Writing Contest!

Reply to Message

Not registered yet?

The AI Depot has a focused community of friendly users. Rather than let anyone abuse the site at the brink of promiscuity, we prefer to let only those with an active interest participate... this simply requires registering.

Why not sign up!

Joining the site's community is completely free. You can then post messages freely, and customise your personal profile at will. Specific privileges will also be granted to you, like being able to access printer-friendly articles without restrictions. So, why not register?

Username:
Password:
Subject:
Email me when someone replies.
Body:

Parent Message

Dumb and Dumber Architectural Design

Alex,

Maybe I didn't read the same article as you ;-) or perhaps I'm just a little jaded after 5 years in a Faculty of Architecture, but what I read in the article is a lot of what-if's and maybe's. The first half of the article gives a fairly good picture of the current use of computing in architectural practice -- computers are often used as replacements for drafting boards and little else. Some firms use computers for visualisation purposes and generate stunning images of their work, but the use of AI techniques in architectural practice is still in its infancy and this is despite 30 years of research in design computing!

The aim of design computing is to bring to architectural precisely the kinds of tools discussed in the article and although as a research programme it has been reasonably successful, little has been taken up by architects. Largely because many feel that they would be losing that creative something discussed in the article. However, that doesn't mean that there isn't exciting work being done in the academic world, in preparation for the architects to wake up to the possibilities of AI and that is how I got interested in the practical application of computational models of creativity.

Some of the most interesting work on simulating crowd flows includes the work by Space Syntax <http://www.spacesyntax.com/> that has had some success gaining acceptance by town planners and urban space designers. Other researchers have used multi-agent models of pedestrian flow, similar to Craig Reynolds models of flocking, to simulate emergency evacuations -- I have found the work of Dirk Helbing particularly interesting <http://www.helbing.org/>. I even implemented Helbing's "social force model" to provide a stimulating design problem for my "curious design agents". If you're interested to know more check out my paper "Designing for Interest and Novelty" on my home page <http://www.robsaunders.net/>.

-RoB-

47 posts.
Wednesday 23 January, 18:53
Reply
Should Have Said!

Hehe, ok!

How about this instead:

[...] they could be using a complex simulation [...]
[...] but it would definitely be cool for your house to self-adapt [...]

It's a shame, as the technology is available. If my memory serves me correctly, there was a Unreal mod that simulated a load of people in simple buildings for fire safety tests. I'll see if I can dig it up.

Craig Reynolds' stuff works great, but you have to admit people usually all have different behaviours (different parameters maybe), but also different high-level destinations. His work would need slightly adapting to blend all the behaviours in together: when do you queue at a doorway, and when try to get around it?

Anyway, that's remotely connected to some the bot navigation stuff I've been working on, so I'll see if I can do such a simulation!

935 posts.
Thursday 24 January, 06:27
Reply

Back to the Artificial Intelligence Depot.