Mykel Kochenderfer: AI and safety-critical systems

Artificial intelligence can help us design safety-critical systems for aircraft and other vehicles that are more robust to the many sources of uncertainty in the real world, says aerospace professor Mykel Kochenderfer.

Building systems that meet the exceptionally high level of safety expected of commercial air transport is challenging, but Kochenderfer says that the key is in modeling the likelihood of the full spectrum of outcomes and planning accordingly. Validating the safety of these systems is also difficult, often requiring billions of simulations. He tells Stanford Engineering’s The Future of Everything how AI, empowered by algorithms such as “dynamic programming,” can make autonomous systems safer.

Related | Russ Altman, the Kenneth Fong Professor of Bioengineering, of genetics, of medicine (general medical discipline), of biomedical data science and, by courtesy, of computer science.

Related | Mykel Kochenderfer, associate professor of aeronautics and astronautics and, by courtesy, of computer science, director of SAIL-Toyota Center For AI Research and co-director of Center for AI Safety.