Transportation and AI: Building Safe Systems in the Air and on the Road
Advances in artificial intelligence are leading to greater autonomy and improved safety in systems ranging from air traffic control to automated driving.
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.
This episode is part of the Stanford Engineering's Future of Everything podcast, hosted by Russ Altman, HAI associate director and the Kenneth Fong Professor of Bioengineering, of genetics, of medicine (general medical discipline), of biomedical data science and, by courtesy, of computer science.
Related News
The two-year fellowship supports PhD researchers across law, medicine, physics, statistics, education, and engineering.
The two-year fellowship supports PhD researchers across law, medicine, physics, statistics, education, and engineering.
Benchmarks — the standardized tests that rank AI models on safety, bias, and reasoning — drive markets and shape regulation. New Stanford research finds they often don't measure what they claim to.
Benchmarks — the standardized tests that rank AI models on safety, bias, and reasoning — drive markets and shape regulation. New Stanford research finds they often don't measure what they claim to.
In a new series called Prompt Response, Stanford’s Surya Ganguli, Diyi Yang and Rob Reich examined emergent agent behavior, recursive self-improvement, independent evaluation and whether a kill switch can make advanced AI safer.
In a new series called Prompt Response, Stanford’s Surya Ganguli, Diyi Yang and Rob Reich examined emergent agent behavior, recursive self-improvement, independent evaluation and whether a kill switch can make advanced AI safer.