| id |
ecaade2023_247 |
| authors |
Wang, Jinyu, Huang, Chenyu, Zhu, Elaine, Shen, Yanting, Yao, Jiawei, Shi, Hang and Peng, Rui |
| year |
2023 |
| title |
Enhanced Crowd-Driven Retail Counter Layout Design Using Generative Adversarial Network |
| source |
Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 511–518 |
| doi |
https://doi.org/10.52842/conf.ecaade.2023.2.511
|
| summary |
In the design of retail counter layout, visitor flow is crucial as it greatly impacts the product exposure, sales expectation, and shopping experience. These factors can be expressed through crowd flow-related indicators, including flow speed, acceleration, visit count, and demand fulfillment degree. Although these indicators can be obtained through crowd simulation and be optimized with genetic algorithm, layout optimization may require hundreds of iterations. This means that simulation can take a long time, hindering the efficiency of layout optimization. To address this issue, we accelerated simulation through a surrogate model and proposed a data-driven layout design and optimization workflow. Firstly, we generalized common plan in the real world and designed an automatic generative parametric model to generate random layouts. Next, we obtained multiple crowd flow-related indicators through batch simulation with PedSim Pro. We then collected data and trained a generative adversarial network (GAN) as a surrogate model to capture the relationship between multiple indicators at different positions of regions of interest and the geometric features of counter layout. The trained model can be used with genetic algorithms for automatic optimization to assist designers in obtaining the best layout. Compared to crowd simulation, our trained GAN model is hundreds of times faster in predicting crowd flow-related indicators and has a high predictive accuracy performance with R2=0.7. The proposed workflow can significantly improve the optimization process in retail counter layout design. |
| keywords |
Retail Layout Optimization, Crowd Flow Simulation and Prediction, Generative Adversarial Network |
| series |
eCAADe |
| email |
|
| full text |
 file.pdf (2,180,266 bytes) |
| references |
Content-type: text/plain
|
| last changed |
2023/12/10 10:49 |
|
