AI comments on EASA’s 2nd issue paper on Artificial Intelligence
Artificial Intelligence has shown to be a hot topic on the JDA Journal—many clicks, a large number of sharing’s and more than usual comments. So, when EASA posted ISSUE 2 OF ITS CONCEPT PAPER ON ARTIFICIAL INTELLIGENCE (AI) AND MACHINE LEARNING (ML), it seemed appropriate to share this leading edge of regulatory AI reading (see below).
The Journal has commented on and/or provided insights on a wide variety of aviation safety issues. AI is beyond my ken. So, in recognition of the dearth of my knowledge and consistent with a paper on AI, Microsoft Copilot was asked to deliver comments on this EASA paper on AI and here are its thoughts:
EASA, the European Union Aviation Safety Agency, has taken a significant step in the implementation of its AI Roadmap by releasing Issue 2 of its Concept Paper on Artificial Intelligence (AI) and Machine Learning (ML). This paper is open for consultation over a period of 10 weeks1.
Here are the key highlights from the EASA AI Concept Paper:
- Machine Learning in Aviation: Machine learning has gained prominence in recent years, with applications spanning from predictive maintenance to image and speech recognition. In the aviation industry, machine learning holds the potential to enhance safety, efficiency, passenger experience, and cost reduction. However, ITS ADOPTION PRESENTS UNIQUE CHALLENGES RELATED TO OPERATIONAL SAFETY.
- Guidance for AI-Based Systems: The revised EASA AI Concept Paper provides guidance for the development and deployment of Level 1 and Level 2 AI-based systems for safety-related applications. These levels are defined as follows:
- Level 1 AI: Applications of human augmentation or assistance.
- Level 2 AI: Driven by the concept of ‘human-AI teaming’ (HAT), where AI systems perform automatic decision-making under human oversight.
- Level 1 AI: Applications of human augmentation or assistance.
- Human-AI Interaction: Level 2 AI applications necessitate novel human factors guidance and design principles to ensure safe human-AI interaction (HAII). This includes addressing aspects like learning assurance, AI explainability, and ethics-based assessment.
- Towards Responsible Adoption: The proposed Issue 2 of the EASA AI Concept Paper represents a crucial step toward the safe and responsible adoption of machine learning in the aviation industry.
- Level 2 AI: Driven by the concept of ‘human-AI teaming’ (HAT), where AI systems perform automatic decision-making under human oversight.
Hope these computer-generated COMMENTS are useful. For certain, they are more intelligent than this human could provide. In any event, sharing another interesting document on AI and aviation safety merits this post.
06 Mar 2024
Related domains
In a significant next step on its ARTIFICIAL INTELLIGENCE (AI) ROADMAP, the European Union Aviation Safety Agency (EASA) has published ISSUE 2 Of its Concept Paper on Artificial Intelligence (AI) and Machine Learning (ML). This second issue offers the potential to enhance four aviation pillars – safety, efficiency, sustainability, and passenger experience – and positions ML at the forefront of aviation innovation. At the same time, the path to ML deployment is bringing unique challenges, particularly in safeguarding operational safety.
This issue of the EASA AI Concept Paper refines the guidance for Level 1 AI applications (those enhancing human capabilities) and deepens the exploration of ‘learning assurance’, ‘AI explainability’ and ‘ethics-based assessment’. These foundation concepts are crucial for the safe and trustworthy development and implementation of AI technologies in aviation.
Going one step further, this new issue provides comprehensive guidance for the development and deployment of Level 2 AI-based systems. Level 2 AI introduces the groundbreaking concept OF ‘HUMAN-AI TEAMING’ (HAT), setting the stage for AI systems that automatically take decisions under human oversight. This advancement in the authority level of AI-based systems shows the need for human guidance and design principles to ensure safe ‘human-AI interaction’ (HAII).
Issue 2 of the EASA AI Concept Paper marks the entry of the EASA AI Roadmap into its second phase (framework consolidation), where Rulemaking Task (RMT).0742 will facilitate the integration of the anticipated guidance from the AI Concept Paper into a comprehensive framework of generic rules and acceptable means of compliance (AMC). These rules and AMC are precisely tailored to accommodate the unique requirements of each aviation domain impacted by these new technologies.
Overall, this new AI Roadmap deliverable UNDERSCORES EASA’S COMMITMENT TOWARDS A FUTURE WHERE AI AND ML ARE INTEGRATED IN AVIATION’S SUCCESSES. This vision is not just about technological advancement, but mainly about building trust in AI applications, ensuring they complement human expertise and enhance overall aviation safety and sustainability.
EASA would like to thank all the stakeholders who participated in the public consultation phase and, in so doing, contributed to the maturity of this new publication.
