arXiv cs.AI· Ross Mawhorter, Matthew Guzdial·· 14 小时前AI 评分20
基于感知距离的电子游戏关卡句法分割与拼贴生成
Syntactic Segmentation and Collage Generation for Videogame Levels with Perceptual Distance
AI 导读
研究提出“感知距离”概念，借鉴建筑学空间句法分析技术，用层次聚类从现有游戏关卡设计中自动完成句法分割，并据此构建拼贴式关卡生成算法。该方法与过往《星际争霸》关卡分析工作进行了对比，在《超级银河战士》的房间数据上给出结果，并展示了基于该分割方法的关卡生成概念验证。
正文 · 原文
Abstract:In procedural videogame level design, many existing techniques combine hand-authored level chunks. Some existing analysis techniques also rely on a higher-level graph structure which abstracts the level design. In this paper, we explore techniques for computing both of these things automatically from an existing design. We introduce the concept of perceptual distance, based on analysis techniques from the architecture subfield of Space Syntax. We use this perceptual distance to segment level designs with hierarchical clustering. We compare with past work on StarCraft analysis, show results on rooms from Super Metroid, and also demonstrate a proof-of-concept level generation algorithm based on this segmentation method.
| Comments: | 11 pages, 12 figures, 22nd Artificial Intelligence and Interactive Digital Entertainment Conference |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.38987 [cs.AI] |
| (or arXiv:2610.38987v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38987 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Matthew Guzdial [view email]
[v1]
Wed, 28 Oct 2026 22:11:42 UTC (1,968 KB)
来源：arXiv cs.AI · arxiv.org