Towards certifiable AI in aviation: landscape, challenges, and opportunities
This addresses the challenge of ensuring AI safety in critical aviation systems, but it is incremental as it focuses on mapping and identifying issues rather than proposing new solutions.
The paper tackles the problem of certifying AI systems in aviation for safety, presenting a comprehensive mind map of formal AI certification in avionics and highlighting challenges with an example to emphasize the need for qualification beyond performance metrics.
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.