CS&E Colloquium: AI for Safety-Critical Systems

The computer science colloquium takes place on Mondays from 11:15 a.m. - 12:15 p.m. This week's speaker, Darren Cofer (Collins), will be giving a talk titled "AI for Safety-Critical Systems"

Abstract

AI and ML are dominating headlines, boardrooms, social media, and computing research with promises of a utopian future of unimaginable productivity and scientific breakthroughs -- or possibly the end of humanity.  But when we cut through the hype, there are real engineering problems to be solved before we reach the promised land.  Suppose we want to use machine learning technologies in safety-critical systems.  In aviation, for example, the reasons for doing so range from increasing autonomy and easing pilot workload to simply reducing the computing resources required by onboard equipment.  Can these benefits be realized while maintaining or even improving safety?  What are the barriers and how might they be overcome?  Researchers, regulators, and industry have been working to answer these questions, developing new guidance for certification of ML-based systems and creating new technologies and processes for meeting those certification objectives and satisfying safety requirements.

 

Biography

Darren Cofer is a Principal Fellow at Collins Aerospace. He earned his PhD in Electrical and Computer Engineering from The University of Texas at Austin.  His area of expertise is developing and applying advanced analysis methods and tools for verification and certification of high-integrity systems. He is currently leading the Collins team on DARPA’s PROVERS program, developing and applying formal methods for verification of safety and security properties in autonomous air vehicles. He served on RTCA committee SC-205 developing new certification guidance for airborne software (DO-178C) and was one of the developers of the Formal Methods Supplement (DO-333). He is currently a member of SAE committee G-34 developing certification guidance for the use of machine learning technologies onboard aircraft. 
 

Category
Start date
Monday, Nov. 3, 2025, 11:15 a.m.
End date
Monday, Nov. 3, 2025, 12:15 p.m.
Location

Share