Action-based Character AI in Video-games with CogBots Architecture: A Preliminary Report

TL;DR

This paper introduces CogBots, a modular architecture inspired by autonomous agent AI, for NPC behavior in video games, enhancing abstraction, reusability, and personalization, demonstrated through a navigation scenario under incomplete information.

Contribution

Proposes a novel architecture for NPC interaction in video games, emphasizing modularity and personalization, inspired by autonomous agent AI research.

Findings

Architecture improves NPC navigation under incomplete information

Enhances modularity and reusability of NPC behaviors

Demonstrates effective handling of obstacle scenarios

Abstract

In this paper we propose an architecture for specifying the interaction of non-player characters (NPCs) in the game-world in a way that abstracts common tasks in four main conceptual components, namely perception, deliberation, control, action. We argue that this architecture, inspired by AI research on autonomous agents and robots, can offer a number of benefits in the form of abstraction, modularity, re-usability and higher degrees of personalization for the behavior of each NPC. We also show how this architecture can be used to tackle a simple scenario related to the navigation of NPCs under incomplete information about the obstacles that may obstruct the various way-points in the game, in a simple and effective way.