Automatic Parameter Tuning via Reinforcement Learning for Crowd Simulation with Social Distancing

Yiran Zhao, Roland Geraerts

Research output: Contribution to conferencePaperAcademic

Abstract

Reinforcement learning (RL) has been applied to a variety of fields such as gaming and robot navigation. We study the application of RL in crowd simulation by proposing an automatic parameter tuning system based on Proximal Policy Optimization (PPO). The system can be used with any crowd simulation software to improve the quality of the simulation by automatically assigning parameters to each agent during the simulation. Our experiments indicate that the automatic parameter tuning system can reduce unexpected congestions in counterflow scenarios. In addition, by utilizing the improved commonly used crowd simulation algorithms and our parameter tuning system, we can represent social distancing behavior of pedestrians under COVID-19, where pedestrians comply to the suggested social distance when they have enough space to move while they reduce their social distances to others when there is limited space.
Original languageEnglish
DOIs
Publication statusPublished - Aug 2022
EventInternational Conference on Methods and Models in Automation and Robotics - Miedzyzdroje, Poland
Duration: 22 Aug 202225 Aug 2022
http://mmar.edu.pl/

Conference

ConferenceInternational Conference on Methods and Models in Automation and Robotics
Abbreviated titleMMAR
Country/TerritoryPoland
CityMiedzyzdroje
Period22/08/2225/08/22
Internet address

Fingerprint

Dive into the research topics of 'Automatic Parameter Tuning via Reinforcement Learning for Crowd Simulation with Social Distancing'. Together they form a unique fingerprint.

Cite this