Efficient Visibility Approximation for Game AI using Neural Omnidirectional Distance Fields

TL;DR

This paper introduces a neural Omnidirectional Distance Field method for fast, scalable visibility approximation in game AI, significantly reducing computation time compared to traditional raycasting.

Contribution

It presents a novel neural representation of scene visibility that enables real-time approximation without raycasting, improving efficiency and consistency.

Findings

Achieves 9.35x cold start speedup in in-game tests

Achieves 4.8x warm start speedup in in-game tests

Evaluation time remains constant regardless of scene complexity

Abstract

Visibility information is critical in game AI applications, but the computational cost of raycasting-based methods poses a challenge for real-time systems. To address this challenge, we propose a novel method that represents a partitioned game scene as neural Omnidirectional Distance Fields (ODFs), allowing scalable and efficient visibility approximation between positions without raycasting. For each position of interest, we map its omnidirectional distance data from the spherical surface onto a UV plane. We then use multi-resolution grids and bilinearly interpolated features to encode directions. This allows us to use a compact multi-layer perceptron (MLP) to reconstruct the high-frequency directional distance data at these positions, ensuring fast inference speed. We demonstrate the effectiveness of our method through offline experiments and in-game evaluation. For in-game evaluation, we conduct a side-by-side comparison with raycasting-based visibility tests in three different scenes. Using a compact MLP (128 neurons and 2 layers), our method achieves an average cold start speedup of 9.35 times and warm start speedup of 4.8 times across these scenes. In addition, unlike the raycasting-based method, whose evaluation time is affected by the characteristics of the scenes, our method's evaluation time remains constant.