"It is hard to design a space that will not attract people. What is remarkable is how often this has been accomplished”
stated William H. Whyte.
Humans possess an inherent inclination towards sociability, making us gregarious creatures. As Whyte aptly observes, "What draws people the most, it seems, is the presence of other people." Hence, the incorporation of social interaction is pivotal when designing public spaces.
One may ponder the reasons behind the vibrancy and bustling nature of certain plazas, while others remain devoid of activity. The functioning of identical designs in different locations can vary drastically. Could these variations be attributed to factors such as geographical placement, user characteristics, or the prevailing ambiance? When architects, designers, or planners undertake a commission, they develop hypotheses regarding what would work effectively at a specific site, drawing from their accumulated experience. While producing improved, human experience is the predominant objective, it is frequently overlooked due to its repugnance towards quantification or diagrammatic representation. In this regard, real-time strategy video games featuring AI systems suggest an avenue for incorporating human experience into the design process.
This course explores the potential for simulating and predicting human behavior within our built environments through the use of multiagent AI systems in the Unity game engine. By leveraging this technology, designers can gain valuable insights into human preferences and behaviors, aiding them in creating spaces catering to diverse needs and desires of individuals.
This project will focus specifically on experimenting with a multiagent AI system in a public space modeled within Unity. Students are required to adjust the weight of AI agents based on field observations of the assumed users. Each agent will behave differently and operate autonomously within a defined space with pre-scripted AI agents. The interactive and real-time simulation features will be the foundation for students to propose design options that alter and enhance how users behave in the public environment.
Students will be required to collect the data by exploring Seoul city, observing space, and analyzing human interactions.
This course will divide into three parts:
1. Data Collection: Explore the city, observe a space, and analyze human interaction.
2. Script Writing: Design AI agents based on fictional stories and evaluate the weight of each influence factor.
3. Simulation and Design via play.
Cell Phone, Camera
3D software (Rhino or Blender)
Course Objective 1: Observe the Social Interaction. Students will examine a space with a new point of view to immerse themselves in an open space in the city environment.
Course Objective 2: Learning Multi-Agent System. Students will have a better understanding of the multiagent system and be able to find the resource to write the AI code for agents.
Course Objective 3: Design public space options. Students will be able to propose design solutions based on the interaction with the simulated scenario.
The primary objective of this unit is to introduce to students how to incorporate AI in the design process and provide an understanding of data collection, and machine vision in assisting architectural design. This unit will mainly focus on ML agents in Unity.
At the end of this course, students should be able to:
1. To understand how to digitalize analog observations.
2. To explore ideas through simulation games.
3. To train their own AI agents with a particular behavior.
Whyte William H., The social life of small urban spaces, 1980, Publisher: Project for Public Spaces.
Lally Sean, chapter 3: material energies, The Air From Other Planets, 2013, Publisher: Lars Muller.