Skip to main navigation Skip to search Skip to main content

FindMe: A Prototype Videogame AI based on CTL with an Optimized Synthesis Algorithm

  • Marco Aruta
  • , Vadim Malvone
  • , Aniello Murano
  • , Vincenzo Pio Palma
  • , Salvatore Romano
  • University of Naples Federico II

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

We present FindMe, a prototype tool that enhances AI-driven decision-making in Non-Player Characters (NPCs) within Unreal Engine 5.4. Our approach utilizes formal verification techniques, specifically Computation Tree Logic (CTL), to enable real-time adaptive behavior in NPCs. Additionally, we employ an innovative model optimization technique to enhance our verification process. Our in-engine implementation of CTL model checking outperforms existing tools like NuSMV, even in more complex scenarios.

Original languageEnglish
Title of host publicationProceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025
EditorsYevgeniy Vorobeychik, Sanmay Das, Ann Nowe
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages2997-2999
Number of pages3
ISBN (Electronic)9798400714269
Publication statusPublished - 1 Jan 2025
Event24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 - Detroit, United States
Duration: 19 May 202523 May 2025

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Conference

Conference24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025
Country/TerritoryUnited States
CityDetroit
Period19/05/2523/05/25

Keywords

  • Gaming
  • Model Checking
  • Reactive Synthesis
  • Strategic Reasoning

Fingerprint

Dive into the research topics of 'FindMe: A Prototype Videogame AI based on CTL with an Optimized Synthesis Algorithm'. Together they form a unique fingerprint.

Cite this