Towards certifiable AI in aviation: landscape, challenges, and opportunities
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914948687331328 |
|---|---|
| author | Bello, Hymalai Geißler, Daniel Ray, Lala Müller-Divéky, Stefan Müller, Peter Kittrell, Shannon Liu, Mengxi Zhou, Bo Lukowicz, Paul |
| author_facet | Bello, Hymalai Geißler, Daniel Ray, Lala Müller-Divéky, Stefan Müller, Peter Kittrell, Shannon Liu, Mengxi Zhou, Bo Lukowicz, Paul |
| contents | Artificial Intelligence (AI) methods are powerful tools for various domains, including critical fields such as avionics, where certification is required to achieve and maintain an acceptable level of safety. General solutions for safety-critical systems must address three main questions: Is it suitable? What drives the system's decisions? Is it robust to errors/attacks? This is more complex in AI than in traditional methods. In this context, this paper presents a comprehensive mind map of formal AI certification in avionics. It highlights the challenges of certifying AI development with an example to emphasize the need for qualification beyond performance metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08666 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards certifiable AI in aviation: landscape, challenges, and opportunities Bello, Hymalai Geißler, Daniel Ray, Lala Müller-Divéky, Stefan Müller, Peter Kittrell, Shannon Liu, Mengxi Zhou, Bo Lukowicz, Paul Machine Learning Artificial Intelligence Artificial Intelligence (AI) methods are powerful tools for various domains, including critical fields such as avionics, where certification is required to achieve and maintain an acceptable level of safety. General solutions for safety-critical systems must address three main questions: Is it suitable? What drives the system's decisions? Is it robust to errors/attacks? This is more complex in AI than in traditional methods. In this context, this paper presents a comprehensive mind map of formal AI certification in avionics. It highlights the challenges of certifying AI development with an example to emphasize the need for qualification beyond performance metrics. |
| title | Towards certifiable AI in aviation: landscape, challenges, and opportunities |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2409.08666 |