Cognitive Urban Design Computing



The computer is incredibly fast, accurate — and stupid. Man is unbelievably slow, inaccurate — and brilliant. The project aim is to marry these diverse capabilities in ways that can reveal urban design opportunities currently beyond imagination.

Project description

Cognitive Urban Design Computing (CoDeC) is a Principle Scientist-led project at AIT. The project aims to develop a future-oriented computational design assistance system that investigates a productive combination of the excellence of human cognition with the power of modern computing technology. The developers called this approach “cognitive design computing”. The primary project tasks are to: 1) achieve integrated planning; 2) plan with citizens and stakeholders; and 3) develop appropriate digital planning tools. The computational mission is to mimic the way a designer’s brain works by combining state-of-the-art optimisation and machine learning approaches with available simulation methods. The cognition domain respects the complex nature of design problems via the provision of models for human/computer interaction — meaning that design problems are distributed between the computer and the designer.

The project delivers an innovative technological and methodological basis, both for the planning of new cities and the transformation of existing ones. It also includes methods to predict quantitative, qualitative and subjective effects of urban interventions, even when explicit models are lacking. Furthermore, the results have enabled a new, digital semi-automated planning approach that can facilitate Backcasting strategies.

 Main conclusions/outcomes/achievements