Crowd-simulating software could improve building design
A new project that uses artificial intelligence to model how crowds move could help architects design better buildings.
Researchers from Bath and Bournemouth universities are working with engineering consultancy Buro Happold to create software that shows how a building’s design can enable or prevent large numbers of people moving easily through it.
The program will create a visual representation of a crowd, modelling it as a group of many individual ‘agents’ instead of as a single mass of people and giving each agent its own goals and behaviour.
‘What Buro Happold wants to be able to understand is the impact of a space on the way people move,’ said Julian Padget, project supervisor and senior lecturer in computer science at Bath University.
‘There’s also the related question of what happens when a large volume of people are all trying to get somewhere rapidly, such as in an emergency situation.’
While crowd simulation software has been developed before, the Bath/Bournemouth team hopes to use modern advances in processing power to create a more sophisticated program that models hundreds or thousands of individuals’ movements.
The project will tackle the problems of simulating the crowds and rendering them in a believable way, from both a wide-angle and a close-up view, meaning the individuals have to appear realistic and show how their movements affect the rest of the group.
‘You don’t want it to look like a bunch of automatons wondering around — the reason being that it distracts the viewer, because they find it unnatural,’ said Padget. ‘They pay attention to that rather than what the picture overall is showing them.’
Instead of programming the computerised people with specific instructions, the computer will give them a destination and a range of actions to choose from and leave them to determine their own route, partly based on data gathered from observing real crowds.
But there are still limits to computational power and simulating greater numbers of people will require each individual character to have less intelligent programming, said Padget.
‘Our challenge is to work out what we can throw away from the sophisticated model and still get plausible-looking behaviour when we’ve got a large number of individuals.’
The simulation software will also need to be compatible with a suitable platform to render buildings designed by Buro Happold.
The four-year research project will be carried out by an engineering doctorate student through the universities’ Centre for Digital Entertainment, funded by the EPSRC.