用游戏引擎复现真实场景，高效生成复杂测试环境
Exploring Flexible Scenario Generation in Godot Simulator
- 通过图像重建技术在Godot中还原测试场景
- 支持大规模、多样化场景的自动化生成
- 适合自动驾驶等复杂系统的安全验证
网络物理系统（CPS）融合了网络与物理组件，在动态环境中做出决策并进行交互。保障CPS的安全性至关重要，需在多样且复杂的场景下进行充分测试。以往方法多采用形式化语言描述场景以生成测试环境。本文提出新思路：利用开源游戏引擎Godot重建场景。我们构建了一条流水线，可直接从提供的场景图像重建测试场景，并部署至仿真环境中评估CPS表现。该方法为在真实感环境中测试CPS提供了可扩展、灵活的解决方案。
原文摘要 · Abstract (English)
Cyber-physical systems (CPS) combine cyber and physical components engineered to make decisions and interact within dynamic environments. Ensuring the safety of CPS is of great importance, requiring extensive testing across diverse and complex scenarios. To generate as many testing scenarios as possible, previous efforts have focused on describing scenarios using formal languages to generate scenes. In this paper, we introduce an alternative approach: reconstructing scenes inside the open-source game engine, Godot. We have developed a pipeline that enables the reconstruction of testing scenes directly from provided images of scenarios. These reconstructed scenes can then be deployed within simulated environments to assess a CPS. This approach offers a scalable and flexible solution for testing CPS in realistic environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。