An Exploration of Collision-based Enemy Morphology Generation
An Exploration of Collision-based Enemy Morphology Generation
基于碰撞的敌人形态生成探索
Abstract: Despite a great deal of prior research into Procedural Content Generation (PCG), relatively little prior work has explored generating enemies for video games. In particular, there is almost no work on generating enemy morphologies, the basic body plan or collision information for in-game enemies, despite the existence of related morphology generation work in robotics.
摘要： 尽管在程序化内容生成（PCG）领域已有大量研究，但针对电子游戏敌人生成的研究却相对较少。特别是在敌人形态（即游戏内敌人的基本身体结构或碰撞信息）生成方面，几乎没有任何相关工作，尽管在机器人领域已经存在类似的形态生成研究。
In this paper, we explore three different novel approaches to generate enemy morphologies based on player collision information. We found that each approach provides different strengths and weaknesses, but all had equivalent or better performance than an evolutionary baseline adapted from prior robotics morphology work.
在本文中，我们探索了三种基于玩家碰撞信息生成敌人形态的新颖方法。研究发现，每种方法各有利弊，但所有方法的表现均优于或等同于从机器人形态研究中改编而来的进化基准模型。
Paper Details:
- Authors: Johor Jara Gonzalez, Matthew Guzdial
- Subject: Artificial Intelligence (cs.AI)
- arXiv ID: 2606.02832
- Submission Date: 1 Jun 2026
论文详情：
- 作者： Johor Jara Gonzalez, Matthew Guzdial
- 学科： 人工智能 (cs.AI)
- arXiv ID： 2606.02832
- 提交日期： 2026年6月1日