Generic Guard AI in Stealth Game with Composite Potential Fields

TL;DR

This paper introduces a flexible, explainable, and training-free guard AI framework for stealth games that combines global and local information through Composite Potential Fields, improving patrol naturalness and efficiency.

Contribution

The authors present a novel Composite Potential Fields approach that integrates multiple interpretable maps for guard behavior, eliminating the need for retraining and enabling easy customization.

Findings

Outperforms classical methods in capture efficiency.

Produces more natural patrol behaviors.

Easily integrates stealth mechanics like distractions.

Abstract

Guard patrol behavior is central to the immersion and strategic depth of stealth games, while most existing systems rely on hand-crafted routes or specialized logic that struggle to balance coverage efficiency and responsive pursuit with believable naturalness. We propose a generic, fully explainable, training-free framework that integrates global knowledge and local information via Composite Potential Fields, combining three interpretable maps-Information, Confidence, and Connectivity-into a single kernel-filtered decision criterion. Our parametric, designer-driven approach requires only a handful of decay and weight parameters-no retraining-to smoothly adapt across both occupancy-grid and NavMesh-partition abstractions. We evaluate on five representative game maps, two player-control policies, and five guard modes, confirming that our method outperforms classical baseline methods in both capture efficiency and patrol naturalness. Finally, we show how common stealth mechanics-distractions and environmental elements-integrate naturally into our framework as sub modules, enabling rapid prototyping of rich, dynamic, and responsive guard behaviors.