Implementation of Fuzzy Logic Algorithm to Improve NPC Decision-Making in 2D Adventure Games Using Unity

Abstract

In 2D adventure games, Non-Playable Characters (NPCs) play a crucial role in creating a more immersive and interactive experience. However, static and non-adaptive NPC behavior may reduce the game quality. This study aims to enhance NPC artificial intelligence by implementing the Fuzzy Logic algorithm in decision-making processes. The input parameters include the distance between the NPC and the player, the player's health level, and the player's level, with four possible outputs: chase, evade, defend, and wait. A fuzzy rule base consisting of 27 rules was developed and implemented in a Unity-based game. Testing was conducted on various input combinations to evaluate the NPC’s responses. Results indicate that NPCs respond more adaptively, such as evading when the player has high health and level at a close range, or waiting when the situation is unfavorable. This implementation improves interaction dynamics between NPCs and players, and adds strategic depth to the gameplay.