AI and Neural networks can obtain state-of-the-art performance in various tasks, including image classification, object detection, speech recognition, and machine translation. Due to this impressive performance, there has been a desire to utilize neural networks for applications in industries with safety-critical components, such as aerospace, automotive, and healthcare. However, while these industries have established processes for verifying and validating traditional software, it is often unclear how to verify the reliability of neural networks.
Outline
- Introduction to AI Certification in Airborne Systems
- Certification process for a low criticality application with a case study for a runway sign classifier
- Certification of higher criticality levels
HIGHLIGHTS
- Learn about gaps between Machine Learning (ML) development and Certification (e.g., for DO-178C, ISO26262).
- Learn about a custom ML certification workflow designed to tackle these certification challenges within the framework of existing standards.
- Explore a case study of an airborne system developed in compliance with the proposed custom ML certification workflow.
Outcome
By the end of this webinar, participants will:
- Understand the challenges of integrating machine learning (ML) into safety-critical systems like aviation, automotive, and healthcare.
- Identify the gaps between traditional software certification processes (e.g., DO-178C, ISO 26262) and ML development workflows.
- Gain insight into a real-world case study of an airborne ML-based system for runway sign detection.
- Learn how to define, implement, and validate a certification workflow tailored for ML in safety-critical applications.
- Explore strategies to manage data, model performance, explainability, and hardware integration in compliance with emerging certification needs.
ABOUT THE PRESENTER
Anila Benny is an Electronics Engineer with a Masters in Biomedical Engineering and over 10 years of experience across multiple domains, including automotive embedded software development and testing using Model-Based Design, biomedical engineering, spectroscopic research, teaching, and application engineering. Since joining CES as an Application Engineer in 2024, Anila has been actively collaborating with customers in the automotive, aerospace, robotics, defense, and renewable energy sectors.