NarrativePlay: An Automated System for Crafting Visual Worlds in Novels for Role-Playing

Authors

  • Runcong Zhao King's College London
  • Wenjia Zhang King's College London University of Warwick
  • Jiazheng Li King's College London
  • Lixing Zhu King's College London
  • Yanran Li Independent Researcher
  • Yulan He King's College London University of Warwick The Alan Turing Institute
  • Lin Gui King's College London

DOI:

https://doi.org/10.1609/aaai.v38i21.30589

Keywords:

Artificial Intelligence, AI for games, Human-AI interaction (including Human-robot interaction), Educational software and hardware tools for AI

Abstract

In this demo, we present NarrativePlay -- an innovative system enabling users to role-play a fictional character and interact with dynamically generated narrative environments. Unlike existing predefined sandbox approaches, NarrativePlay centres around the main storyline events extracted from the narrative, allowing users to experience the story from the perspective of a character they chose. To design versatile AI agents for diverse scenarios, we employ a framework built on a Large Language Models (LLMs) to extract detailed character traits from text. We also incorporate automatically generated visual displays of narrative settings, character portraits, and character speech, greatly enhancing the overall user experience.

Downloads

Published

2024-03-24

How to Cite

Zhao, R., Zhang, W., Li, J., Zhu, L., Li, Y., He, Y., & Gui, L. (2024). NarrativePlay: An Automated System for Crafting Visual Worlds in Novels for Role-Playing. Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23859-23861. https://doi.org/10.1609/aaai.v38i21.30589