SpaceX Edges Closer to the Moon

Plus, an AI-generated version of the same article

Joanna Andreasson/DALL-E4

In the June 2024 issue, we explore the ways that artificial intelligence is shaping our economy and culture. The stories and art are about AI—and occasionally by AI. (Throughout the issue, we have rendered all text generated by AI-powered tools in blue.) To read the rest of the issue, go here.

ARTEMIS II is a crewed moon flyby mission, the first in a series of missions meant to get American astronauts back to the moon and eventually to Mars. In early January, NASA announced that it would be delayed until September 2025—a year later than originally planned. The announcement came after Lockheed Martin's Orion capsule, which will carry the crew through space, burned more than anticipated during a reentry test. The project continues to balloon in price with seemingly endless delays.

The latest delay means Artemis III, a crewed lunar landing mission, will be delayed until 2026—at least. It seems doubtful NASA will be able to apply what it learns from Artemis II to an Artemis III mission in less than a year.

Orion is not the only element that could hold up Artemis indefinitely. The later Artemis missions are relying on SpaceX's Starship—but Federal Aviation Administration (FAA) investigations can add weeks or months between Starship tests. So far SpaceX has been able to test the spacecraft three times, most recently on March 14.

The test did not completely fulfill its mission as intended but was still deemed a success by both SpaceX founder Elon Musk and NASA Administrator Bill Nelson. Both rocket and spacecraft were supposed to have controlled splashdowns in wide-open waters, but the rocket disintegrated about 1,500 feet over the Gulf of Mexico, while the separate Starship spacecraft burned up during reentry.

The good news is that none of the previous issues flagged by the FAA occurred on this latest test. But with every rocket mishap, the FAA will open a new investigation, with new parameters for SpaceX to meet before the next test.

In January, Jessica Jensen, a vice president at SpaceX, told NASA's Nelson that the company will need "ten-ish" tests to get the rocket perfect for Artemis III. It took the FAA two years to approve the first test of Starship and its second test wasn't approved until nearly five months later. The FAA investigation into the second Starship flight test (which resulted in a successful separation of rocket and spacecraft but ended in both exploding soon after) took more than three months.

Musk is hoping to run six Starship test launches this year, but there's no telling how long the FAA will drag its feet between tests. Each FAA delay is another delay for SpaceX, Artemis, and man's return to the moon.

---

(Illustration: Joanna Andreasson/DALL-E4)

• What we asked for:
  A photo of the Artemis II rocket on launchpad in an open landscape at dawn from slightly above
• What DALL-E says it gave us:
  Here's the Artemis II rocket on the launchpad in an open landscape at dawn, with the first light of the day illuminating the scene, captured from a slight elevation.

Launch Approved? Not So Fast, Says Sluggish FAA

Reason asked Claude 3 Sonnet to write an article about the same topic as the human-written article above. All AI-generated text is shown in blue. Read more about what we asked for.
By Claude 3 Sonnet

Most Americans are eager to see NASA astronauts return to the moon and push humanity's boundaries with future exploration of Mars. But those sky-high ambitions are being severely grounded by the plodding pace of rocket launch approvals from the Federal Aviation Administration (FAA).

Every vehicle soaring into space must first secure licensing from the FAA, an oversight process intended to ensure safety. For SpaceX, the current industry leader launching crews and payloads roughly every four days, the government's bureaucratic inertia has become a highly problematic bottleneck.

This red tape has directly impacted testing of SpaceX's Starship, the vehicle that NASA is relying upon to carry cargo and crew for the Artemis program's later missions to the lunar surface. To date, there have been three orbital test flights of the massive rocket–in April and November 2023, and March of this year.

Each of those Starship test launches prompted the FAA to launch a mishap investigation stalling subsequent flights. After the first test in April 2023, the FAA probe lasted five months before approving the next launch[1]. The investigation following November's flight dragged on over three months[2]. Incredibly, it took the FAA more than two years just to greenlight that initial Starship test back in 2023[3].

Jessica Jensen, a SpaceX vice president, has stated that approximately "10-ish" Starship test launches are needed before the system will be proven and ready to support the crewed Artemis III moon mission[4]. At the FAA's current pace of reviewing and approving those test flights, NASA's hope of returning Americans to the lunar surface by 2025 is looking increasingly unlikely.

"We'd very much like the government to be able to move as quickly as we are," Tim Hughes, SpaceX's senior vice president, told the Washington Post[5]. "If you're able to build a rocket faster than the government can regulate it, that's upside down, and that needs to be addressed. So we think some regulatory reforms are needed."

SpaceX has suggested doubling the FAA's licensing staff as one possible solution. At this point, any efforts to "streamline the cumbersome approval process," as Hughes put it, would help accelerate both the private space industry and NASA's exploration roadmap[5].

"Next year could be a pretty dynamic time with lots of providers in spaceflight," a SpaceX official told Ars Technica[6]. But unless the FAA addresses its pacing problems soon, the agency will continue irreparably hindering those new aerospace opportunities - and keep kicking the can down the road on NASA's bid to take astronauts farther into the cosmos.

CITATION KEY:
[1] SpaceX internal record
[2] FAA public statement, 
Dec 2023
[3] FAA memo, April 2023
[4] Jensen quote to 
NASA Admin.
[5] Hughes interview, Washington Post
[6] SpaceX statement to 
Ars Technica.

CLAUDE 3 SONNET is a free large language model developed by Anthropic, an AI startup. 

• What we asked for:
  An article about FAA mishap investigations delaying launch tests of SpaceX's Starship, and, as a result, delaying NASA's Artemis missions and man's return to the moon.
• What Claude asked for and we provided:
  1. What specific SpaceX mishaps or incidents is the FAA investigating that are causing delays?
  2. How much of a delay are we talking about for Starship test launches and the Artemis missions?
  3. Do you have any quotes from officials at SpaceX, NASA, or the FAA commenting on the situation?
• What else we gave Claude:
  1. A writing sample for analysis and replication: Natalie Dowzicky's October 2023 reason.com article headlined "SpaceX: FAA Is Slowing Progress to the Moon"
  2. For the headline: six headlines from the TOPICS section of the May issue.

—JASON RUSSELL

Comments

[sarcasmic]

Job opening!

[Don't look at me!]

AI writing always comes across as unnatural for some reason.

[jonnysage]

That was my thought. I think its uses too many words, too many creative words. Like its TOO clever.

[Moderation4ever]

"Most Americans are eager to see NASA astronauts return to the moon "

I doubt this very much. People don't need to go to the Moon or Mars. We are far better off putting the energy and resources in robotic missions. Leave human space travel to the private sector.

[Syd Henderson]

The overruns and delays in the Mars Sample Return mission argues otherwise.

[Zeb]

But imagine how bad they'd have been for a manned mission.

[Earth-based Human Skeptic]

'The project continues to balloon in price with seemingly endless delays.'

How much for a balloon ride to the moon?

[B G]

"How much for a balloon ride to the moon?"

Be careful where you make these kinds of jokes. There's at least 40 members of Congress who'd likely try to earmark funding to issue the RFP for a balloon-based launch option, and as long as the contract is funded, LMT would bid at it.

[jimc5499]

If the FAA was around in 1900 the Wright Brothers would still be trying to get approval for their Kitty Hawk flight.

[B G]

To the extent that the FAA has any kind of division or process around approving private sector rocket launches, they're probably accustomed to the rockets involved either having been built/certified to some NASA or USAF spec/contract. Even the original set of rockets sold by ULA were initially developed under the requirements of the USAF EELV project which was supposed to be a transition to private development funding for rockets that the USAF would buy launches on; the private satellite market cratered in the tech crash of 2000, though which left the government as their primary customer for a number of years while French and Chinese rockets consolidated the bulk of the remaining commercial launch market.

I doubt that anyone at FAA has much of an idea how to begin to "regulate" something like SpaceX, who is to some extent creating a new version of an industry, but who also eschews the idea of hiring experienced engineers to develop their products (not only do the younger engineers have gaps in knowledge of what's been tried by others in the past and why the things that failed did so, many of them "don't know what they don't know") as well as apparently preferring to "test-launch" a full rocket multiple times as opposed to ground testing critical components and systems.

The problem with simply building large rockets for multiple flight-tests at scale is the possibility that one which goes out of control could land in a populated area, at which point it becomes a kind of incendiary bomb (especially the kerosene-fueled ones that SpaceX flies). The closest thing to a precedent might be the Apollo program from 60 years ago, but even that project included a lot of ground testing before they attempted a first launch, and a lot more testing before they launched the second one without astronauts on board; also, nobody who worked for FAA or NASA (who were likely exempted from FAA regulation, being a government agency themselves), or in the aerospace industry at that time is still working now, and very few are likely still alive. There were a couple of engineers at my first job in the industry who had been involved with Apollo (one I think had even worked on Gemini), but they were at or past "retirement age" in 1997.

[Kansasquaker]

How many orbital class rockets did you and the rest of the boomers land and reuse? Let's not knock the most successful rocket development program in human history because you don't have experience with rapid prototyping.

[rbike]

A couple were done, lifting off of the moon after landing successfully under rocket power. 1969-1974. I watched it on TV.

The technology existed back then. Give Musk credit to have the courage to implement it. He made the rest of the world's rocketmen look like losers.

[B G]

The Apollo LEM being able to set down, and then a portion of it lifting back off from the surface of the moon isn't a re-usable system.

It is a lot more than SpaceX has managed to do in less time, and with not only a nearly infinitesimally small fraction of the electronic/mechanical computing power that Elon has access to but also that it was done by people who didn't know for a fact that it was possible at the time. On the other hand, SpaceX started with different initial priorities and ended up re-treading a lot of known ground through their policy against hiring experienced engineers in general, and probably not starting with enough understanding of the differences between working with physical "hardware" products vs dealing with software products; it's just not possible to fix a leak in a tank or a collapsed strut tube by doing a software push from 1000 miles away in the same way that a code patch can be instituted into a smartphone app via over-the-air updates.

[B G]

I'm GenX (hence the part where I graduated college in the mid 1990s), my parents were boomers. If you're going to throw out generational slurs, at least bother to get them right.

Rapid prototyping is great, but just firing off full-scale rockets at $30-50Million per unit as a "test" is not only a huge waste of resources, it's a bad way to do physical hardware testing because the data you have to determine the cause of any potential failure is limited to the capability of your telemetry systems. Compare that to a ground test article where if/when there's a failure, the engineers involved have access to the failed parts, and can do detailed inspections to figure out what went wrong and how best to correct the issue with higher confidence and precision. Not to mention that ground testing the various components allows for that level of troubleshooting to be done on multiple critical systems without having to get one portion fixed before the parts that become critical later on can be tested.

Also, it's worth noting that the Apollo program reached the moon using a level of computer technology where a bank of computers half the size of Wyoming might have have been able to have half the power of a modern smartphone.

As far as landing and re-using orbital rockets, it's an interesting accomplishment in terms of a technical achievement, but it's not necessarily an improvement in terms of performance or cost; at the risk of sounding condescending, the people who think that it's some kind of quantum improvement in performance generally "don't know what they don't know" about how to move weight from the ground into orbit (or deeper into space). Making a rocket multi-use adds weight to the structure, and making it capable of surviving re-entry adds weight in terms of whatever system is employed to make that happen, and when it comes to getting stuff into orbit weight = cost.

Despite the weight penalties the Falcon 9 is paying for being multi-use, SpaceX is much less expensive for launch than comparable offerings from ULA for one reason. ULA is using Liquid Hydrogen as their primary fuel, and SpaceX is using Kerosene; LH2/LOX rockets were required by the original government specs (courtesy of Al Gore himself) for the Delta 4 and Titan V rockets because they create no CO2 emissions from their direct operation and emit only water vapor (producing, transporting, storing and handling Liquid Hydrogen in huge quantities OTOH is very energy-intensive, but politically inspired requirements rarely consider the whole picture). By contrast, the fossil fuel that SpaceX burns in their rocket is far easier and less expensive to handle, transport, and store as well as costing much less to produce and being able to produce far more total energy through burning an equivalent volume of fuel (which is probably how they're able to carry the weight penalties of all the re-use tech), but it does spit a considerable amount of CO2 out the "tailpipe" on every flight.

[Bill Falcon]

CO2 is not a pollutant. Necessary for photosynthesis to occur. And SpaceX is shaving decades from the MIC cost plus insanity which took over after Apollo...really since Sky Lab NASA has wasted tens or more of billions on stuff that never flew or if it did was ridiculously over cost and years late.

[CE]

Hooray, 21st century technology has almost caught up with Apollo 8 in 1968.

[Bill Falcon]

Artemis is a waste of money. Using the little Orion to dock in some mini lunar space station for the crew to get into a massive Starship is beyond idiotic. Here is what actually will occur.

China will announce a manned lunar orbital mission. Washinton will freak out and SpaceX will be asked if they can get a Dragon on a Falcon Heavy ready for a lunar mission circa Apollo 8. Then Starship will actually do the lunar landing w/o the moronic Orion/SLS stupidity. The GOP Bama Senators be damned.

A manned Boeing Starliner hasn't launched yet and likely will be another money pit (if it has more than 3 manned missions I would be surprised) despite being 7 years late and billions over budget compared to SpaceX. Orion is another Lockmark overpriced, behind schedule MIC special just like the F35.

Just hand the keys to Elon Musk and get out of the way NASA

[B G]

SInce SpaceX never had to enter a bid with a proposed budget and/or schedule for their manned lunar/mars launches, how do they measure being over budget/or past "schedule"? Since SpaceX isn't publicly traded, and isn't techincally part of Testla, there's very few, if any reporting requirements for them to publish status on their major projects; if Starship has currently cost 70% or 150% of what it was originally estimated to, only a handful of people inside the company would actually know that

Also, when judging government projects for going over their proposed budget or schedule, it's important to keep in mind that due to the mechanics and politics of federal procurement, nobody ever submits a bid on a major RFP which reflects anything like a realistic budget/schedule for the scope of whatever the project is. Because the government (whether it's DoD or NASA) is required to pick the "lowest bid which meets requirements", it's been decades since any bid at more than 60% of the actual cost/time that a major project will take would never make it through the initial round "downselect". Because the system is set up to reward "lowball" bids, and everyone bidding knows this (most of the people doing the selecting know it as well, the Pentagon has entire departments who don't do much more than to calculate what sort of "overruns" they should expect on a given bid by calculating the gap between a realistic estimate and each bid estimate.

There's no question that SpaceX is able to avoid a lot of the built-in inefficiencies inherent in doing "government work", such as having to split work packages among multiple states/congressional districts to protect funding in congress (and not always in ways that make much sense technically), and not having to spend nearly as much time doing incremental and "milestone" progress reports (on some projects I've worked in the past, writing status/progress reports and/or sitting in "tag-up" meetings can get to take up half of more of the working day for a lot of the engineers involved in R&D). On the other hand, 95% of the major technical issues on something like Starship could be discovered and corrected by doing a more extensive ground testing program for the cost of 2-3 of the 10+ "test launches" that Elon intends to conduct.