JSAI2024

Presentation information

General Session

General Session » GS-10 AI application

[4L3-GS-10] AI application: General

Fri. May 31, 2024 2:00 PM - 3:40 PM Room L (Room 52)

座長:五十嵐康彦(筑波大学)

2:40 PM - 3:00 PM

[4L3-GS-10-03] Agent-based simulation of in-store customer flow using human trajectory generation AI based on deep learning

〇Taizo Horikomi1, Takayuki Mizuno2 (1. The Graduate University for Advanced Studies, Sokendai, 2. National Institute of Informatics)

Keywords:GPT, human trajectory generation, in-store customer flow, agent-based simulation, deep learning

An agent-based simulation of customer flow in a retail store was conducted by incorporating a human flow generation AI using GPT architecture into the agent. The simulation takes into account the congestion during store visits and interactions with neighboring agents from time to time. The obtained results are compared with conventional agent-based simulations.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password