Crowd-driven Mid-scale Layout Design

Tian Feng1

Lap-Fai Yu2

Sai-Kit Yeung1

KangKang Yin3

Kun Zhou4

1Singapore University of Technology and Design

2University of Massachusetts Boston

3National University of Singapore

4Zhejiang University

Given a layout domain from a real world layout, our approach synthesizes crowd-aware layouts by considering the crowd flow properties of visitors: mobility, accessibility and coziness. Evaluation by crowd simulation software shows that our synthesized layouts exhibit improved crowd flow properties compared to the input real world layouts. Three-dimensional visualization on the right shows the flow of human crowds in a shopping mall created using the synthesized layout on the left.


We propose a novel approach for designing mid-scale layouts by optimizing with respect to human crowd properties. Given an input layout domain such as the boundary of a shopping mall, our approach synthesizes the paths and sites by optimizing three metrics that measure crowd flow properties: mobility, accessibility, and coziness. While these metrics are straightforward to evaluate by a full agent-based crowd simulation, optimizing a layout usually requires hundreds of evaluations, which would require a long time to compute even using the latest crowd simulation techniques. To overcome this challenge, we propose a novel data-driven approach where nonlinear regressors are trained to capture the relationship between the agent-based metrics, and the geometrical and topological features of a layout. We demonstrate that by using the trained regressors, our approach can synthesize crowd-aware layouts and improve existing layouts with better crowd flow properties.

Keywords: layout design, agent-based crowd simulation



We are grateful to the anonymous reviewers for their constructive comments. We also thank Michael S. Brown for narrating the video; Zhipeng Mo and Jay Daligdig for providing help on evaluation and teaser; Keng Hua Chong, Sawako Kaijima and Bige Tunçer for consultation on user experience of our research prototype; Roland Bouffanais and Zheng Cui for providing advice on crowd simulation techniques; and NVIDIA Corporation for the graphics card donation. Sai-Kit Yeung is supported by Singapore MOE Academic Research Fund MOE2013-T2-1-159 and SUTD-MIT International Design Center Grant IDG31300106. We acknowledge the support of the SUTD Digital Manufacturing and Design (DManD) Centre which is supported by the National Research Foundation (NRF) of Singapore. This research is also supported by the National Research Foundation, Prime Minister's Office, Singapore under its IDM Futures Funding Initiative. Part of the work was done when Tian was visiting UMass Boston. Lap-Fai Yu is supported by the UMass Boston StartUp Grant P20150000029280, and the Joseph P. Healey Research Grant provided by the Office of the President, and the Office of the Vice Provost for Research and Strategic Initiatives & Dean of Graduate Studies of UMass Boston. Kun Zhou is supported by the National Natural Science Foundation (NSF) of China (No. 61272305).


Example layouts for different scenarios synthesized by our approach: