Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go?
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916869327290368 |
|---|---|
| author | Li, Shuqing Chen, Qiang Ren, Xiaoxue Lyu, Michael R. |
| author_facet | Li, Shuqing Chen, Qiang Ren, Xiaoxue Lyu, Michael R. |
| contents | Physics Engines (PEs) are fundamental software frameworks that simulate physical interactions in applications ranging from entertainment to safety-critical systems. Despite their importance, PEs suffer from physics failures, deviations from expected physical behaviors that can compromise software reliability, degrade user experience, and potentially cause critical failures in autonomous vehicles or medical robotics. Current testing approaches for PE-based software are inadequate, typically requiring white-box access and focusing on crash detection rather than semantically complex physics failures. This paper presents the first large-scale empirical study characterizing physics failures in PE-based software. We investigate three research questions addressing the manifestations of physics failures, the effectiveness of detection techniques, and developer perceptions of current detection practices. Our contributions include: (1) a taxonomy of physics failure manifestations; (2) a comprehensive evaluation of detection methods including deep learning, prompt-based techniques, and large multimodal models; and (3) actionable insights from developer experiences for improving detection approaches. To support future research, we release PhysiXFails, code, and other materials at https://sites.google.com/view/physics-failure-detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22099 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go? Li, Shuqing Chen, Qiang Ren, Xiaoxue Lyu, Michael R. Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Software Engineering Physics Engines (PEs) are fundamental software frameworks that simulate physical interactions in applications ranging from entertainment to safety-critical systems. Despite their importance, PEs suffer from physics failures, deviations from expected physical behaviors that can compromise software reliability, degrade user experience, and potentially cause critical failures in autonomous vehicles or medical robotics. Current testing approaches for PE-based software are inadequate, typically requiring white-box access and focusing on crash detection rather than semantically complex physics failures. This paper presents the first large-scale empirical study characterizing physics failures in PE-based software. We investigate three research questions addressing the manifestations of physics failures, the effectiveness of detection techniques, and developer perceptions of current detection practices. Our contributions include: (1) a taxonomy of physics failure manifestations; (2) a comprehensive evaluation of detection methods including deep learning, prompt-based techniques, and large multimodal models; and (3) actionable insights from developer experiences for improving detection approaches. To support future research, we release PhysiXFails, code, and other materials at https://sites.google.com/view/physics-failure-detection. |
| title | Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go? |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Software Engineering |
| url | https://arxiv.org/abs/2507.22099 |