The FAA's SMART program utilizes AI and machine learning systems to analyze flight trajectories months in advance, strategically deconflict flight paths, and balance airspace demand with capacity, thereby reducing controller workload while improving safety and efficiency. The program exemplifies how advanced technology can optimize complex systems like national airspace without replacing human operators.
Deep Dive
Prerequisite Knowledge
- No data available.
Where to go next
- No data available.
Deep Dive
'Would You Talk A Little Bit About FAA's SMART Program?': Budd Asks FAA Head About ATCs Using AIAdded:
mix back. Thank you. Thank you.
Thank you for that answer. Thank you for being here, Administrator. And I thank the families for being here as well.
Administrator, you mentioned the idea of treating the national airspace system as a single complex organism and shifting toward a more optimized airspace.
Would you talk a little bit about FAA's SMART program and how FAA is considering the use of AI systems not to replace controllers, but to increase their situational awareness and reduce their workload and to make the airspace safer and more efficient?
Yes, well, you have some handouts that are on your desk. If you would go to page two, what we would see is a depiction of what will be the June 24 June 4th, 2026 schedule for the DCA airport.
You see that today that the the hourly staffing limits for DCA airport are 30 arrivals and departures. And if we look at the bar chart on the left on the hour to by hour basis, we would think that the amount of capacity and the amount of demand are in balance with the FAA's limitations for arrivals and departures at the Capital Region Airport. We move to the quarter hour on the right, what we see are several peaks. A dozen different peaks where the traffic management demands in the Capital Region are well in excess of what the authorized limits are. This is a front flaw. And if we wait until day of departure in order to correct it, we lose the ability to take half of the solution set with us, meaning the ability to actually fill in the gaps moving things to the left.
So, we can use a smart system that will analyze flights 6 months into the future, 3 months into the future, 3 days into the future, and we can analyze all the flight trajectories using advanced machine learning and AI. We can strategically deconflict those flight trajectories and balance demand with our ability to satisfy that capacity. We can do that all by reducing controller workload.
Okay, that's a great example.
Um, the NTSB report uh points to airborne collision avoidance system X or ACAS X including variants designed to enhance safety while on approach and a rotorcraft specific variant as crucial technology for preventing future mid-air collisions.
Can you give us an update on FAA's efforts to accelerate the completion of ACAS X in the technical standards?
Well, thank you for the question, Senator. Uh ACAS X was a development project over a decade ago.
Um and one of my first experiences at the FAA was actually going into the office of uh NextGen because we had a statutory requirement to sunset it by the end of the year and transfer those operations to our uh new AMO organization. So, working with the uh the team at NextGen just to see what was there, what went wrong, why wasn't it working. ACAS X was certainly one of those issues which the the uh career officials uh running that operation told me that they had missed the demand signal. They had not issued a demand signal to the market to implement ACAS X and so the market went to TCAS II from TCAS I. Um do I believe ACAS X would have been a better tool than TCAS II? Absolutely. The algorithms are more sophisticated which allows us to have greater um attenuate attenuated to the traffic needs around the aircraft in question.
Um but we're probably, even if we finalize the MOPS which we're ready to do, but we have to go through a rule making process. We and then rule making will be three to four years long and then ultimately we're talking about a decade long implementation. Yes, we can do that and and I don't object that we should try, but we can actually take commercially available off-the-shelf resources today and we can bring ADSB in through electronic flight bag and through high-speed data connectivity, which we're now rolling out into the commercial fleet. We can do that in the next 2 years. So, yes, we can do all of these things to answer Senator Duckworth's question, but what should our priority be in terms of creating creating better situational awareness in the cockpit? There are great solutions that we can we can attack quickly.
Thank you.
Since January 2020, the FAA has required that most aircraft operating in the national air airspace that they broadcast ADSB out to increase situational awareness and safety.
Would you agree that ADSB in is the most effective when all aircraft are consistently broadcasting ADSB out?
I have said consistently that greater pilot situational awareness is always better than less, but again, I would hate to let the perfect be the enemy of the good.
There are good solutions that we can integrate quickly.
Again, a rulemaking around ADSB in and the equipage adoption of an integrated flight deck solution, easily a decade.
Thank you. My time is expired and while we take a short recess for other members to arrive, we are the committee stands in recess subject to the call of the chairman.
Thank you.
Related Videos
OpenHuman VS Hermes AI: Who Wins?
JulianGoldieSEO
285 views•2026-05-29
Long-Running Agents — Build an Agent That Never Forgets with Google ADK
suryakunju
142 views•2026-05-30
This computer is made from real human brain cells. And you can buy it.
Talktmsmedia
3K views•2026-05-28
BREAKING: Microsoft’s New Image Generating Model Beat Out GPT 1.5 and Nano Banana 2
aimmediahouse
122 views•2026-06-03
I Made the Same Anime Fight Scene in Every AI Video Generator
NobleGooseAnime
295 views•2026-05-30
Nvidia Bets Big On AI PCs | New Chip To Power Windows Laptops | Technology | AI Updates | N18S
cnnnews18
3K views•2026-06-01
I Tested NEW Opus 4.8 on Four Projects (Updated LLM Leaderboard)
AICodingDaily
298 views•2026-05-29
3D Platformer Update - NO CAPES
SolarLune
294 views•2026-05-30











