Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Exploring Flexible Scenario Generation in Godot Simulator

Daniel Peraltai, Xin Qin

TL;DR

The paper tackles CPS safety verification by requiring diverse testing scenarios across dynamic environments, noting that current simulators struggle with flexible map customization. It proposes a pipeline that reconstructs road models inside the Godot game engine directly from images, enabling real-time, controllable scenario generation for CPS testing. The approach leverages Signal Temporal Logic (STL) to constrain road perturbations and uses spline representations to quantify variations, providing a formal-method-guided pathway to generate varied, testable environments. Feasibility is demonstrated through image-based reconstructions and synthetic roads, with discussion of limitations (e.g., contour-detection accuracy) and potential paths to integrate with broader scenario-generation methods for CPS reliability.

Abstract

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.

Exploring Flexible Scenario Generation in Godot Simulator

TL;DR

The paper tackles CPS safety verification by requiring diverse testing scenarios across dynamic environments, noting that current simulators struggle with flexible map customization. It proposes a pipeline that reconstructs road models inside the Godot game engine directly from images, enabling real-time, controllable scenario generation for CPS testing. The approach leverages Signal Temporal Logic (STL) to constrain road perturbations and uses spline representations to quantify variations, providing a formal-method-guided pathway to generate varied, testable environments. Feasibility is demonstrated through image-based reconstructions and synthetic roads, with discussion of limitations (e.g., contour-detection accuracy) and potential paths to integrate with broader scenario-generation methods for CPS reliability.

Abstract

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.

Paper Structure

This paper contains 16 sections, 1 equation, 3 figures.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Signal Temporal Logic
  4. Distance Metrics
  5. Flexible Scenario Generation in Godot
  6. Extract the road
  7. Modifying the Road
  8. Experiments and Results
  9. Scenario Reconstruction Using Image
  10. Scenario Reconstruction Using Synthetic Roads
  11. Discussions
  12. Related Work
  13. 2D Image to 3D Photorealistic Scene Generation.
  14. 3D Scene Synthesis.
  15. Game engines
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Extract the road from the image and recreate it Godot.
  • Figure 2: Extract the contour splines and apply modifications to them.
  • Figure 3: The first figure shows the pixelated version generated using OpenCV. The third figure illustrates how it is reconstructed in the Godot simulator.