Learning to Simulate Crowds with Crowds

Bilas Talukdar, Yunhao Zhang, Tomer Weiss

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Controlling agent behaviors with Reinforcement Learning is of continuing interest in multiple areas. One major focus is to simulate multi-Agent crowds that avoid collisions while locomoting to their goals. Although avoiding collisions is important, it is also necessary to capture realistic anticipatory navigation behaviors. We introduce a novel methodology that includes: 1) an RL method for learning an optimal navigational policy, 2) position-based constraints for correcting policy navigational decisions, and 3) a crowd-sourcing framework for selecting policy control parameters. Based on optimally selected parameters, we train a multi-Agent navigation policy, which we demonstrate on crowd benchmarks. We compare our method to existing works, and demonstrate that our approach achieves superior multi-Agent behaviors.

Original languageEnglish (US)
Title of host publicationProceedings - SIGGRAPH 2023 Posters
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9798400701528
DOIs
StatePublished - Jul 23 2023
EventSpecial Interest Group on Computer Graphics and Interactive Techniques Conference - Posters, SIGGRAPH 2023 - Los Angeles, United States
Duration: Aug 6 2023Aug 10 2023

Publication series

NameProceedings - SIGGRAPH 2023 Posters

Conference

ConferenceSpecial Interest Group on Computer Graphics and Interactive Techniques Conference - Posters, SIGGRAPH 2023
Country/TerritoryUnited States
CityLos Angeles
Period8/6/238/10/23

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Learning to Simulate Crowds with Crowds'. Together they form a unique fingerprint.

Cite this