Author Topic: How Can AI Be Used for Space Applications?  (Read 71576 times)

Offline ppnl

  • Full Member
  • ***
  • Posts: 312
  • Liked: 209
  • Likes Given: 19
Re: How Can AI Be Used for Space Applications?
« Reply #100 on: 12/08/2022 09:20 am »



I was not attempting to claim that the alternatives (async digital and analog) are useful. I'm just pointing out that the flat assertion that a UTM can do any computing task is not strictly true in theory. Furthermore, biological intelligence appears to use both. Note that async digital is continuous in the time domain, so it is basically analog in the time domain.

And I am flatly asserting that a UTM can do any computational task that is doable. It can simulate asynchronous or analog systems to any level of fidelity you want. It can almost always do it cheaper and easier than the analog or asynchronous system that it is replacing.
 

But unless you also claim that this is relevant to the power of AI then it might also be off topic.
Remember that a UTM is a computational architecture (or at least, a reductive basis for actually reasonably implementable architectures like Von Neumann), not a collection of hardware. It can be an electronic digital computer, but it could be an optomechanical computer running up and down a stupendous strip of paper and would be computationally equivalent. A UTM can simulate other TMs, but cannot simulate all possible computer architectures (digital or otherwise). Likewise, the same electronics components that can be used by build a Turing-Complete computer can also be used to built a computer for Non-Turing Computation.

We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving, and without positing some 'inscrutable particle of consciousness' at play or similar supernatural element, that means there exists computational architectures implementable in out universe that are not UTMs.

If there were some other type of device that could calculate a function that a UTM could not then it would be what is called a hypercomputer. There has been an extensive search both physically and theoretically and no hint of such a think has been found. If humans were known to be able to solve the halting problem then we would be such a hypercomputer.

In computer complexity theory hypercomputers are called oracles and are used as mathematical devices to make arguments about the time/memory complexity of different problems. For example if I assume I have a device that can solve the halting problem then I can explore what other problems it allows me to solve. But no such oracles actually exist as far as we know.

So no, UTMs are universal in the sense that no other device of any type can produce results that a UTM can't as far as we can see. And people have tried really really hard. It really is well explored territory and there does not seem to be any way to exceed UTMs. Quantum computers come the closest in that it may exceed the extended time version of the Church-Turing thesis. As a result they may be able to factor large numbers in polynomial time.

Offline JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10975
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1258
  • Likes Given: 724
Re: How Can AI Be Used for Space Applications?
« Reply #101 on: 12/08/2022 11:54 am »
But it is hard to see how a warm wet brain could be a quantum computer.

Allow me to help out by first pointing out that ALL wet brains that we know of exist in the quantum foam...

All objects in the universe exist in a quantum fog. The atoms, molecules and tiny conglomerate structures exist close to the scale of quantum events. That just isn't good enough.

Existence is not good enough for ya, eh?

Quote from: ppnl
You should look into the subject of [quantam] decoherence to see how the macro scale world arises from the quantum foam.

Been there, done that.  As long as we're using the word "should", perhaps you should not imply that you know all.  Quantum "supremacy" much?  We simply do not know how the macro scale world arises.  Go ahead and tell yourself the words you want to hear.

https://en.wikipedia.org/wiki/Quantum_supremacy
 
Quote from: JF
Remember how they used to talk about "junk" DNA?  ... it's there for a reason; just because you don't know how it works is not excuse for calling it "junk".

Quote from: ppnl
Junk DNA is junk in the sense that it is noncoding. ... Evolution sucks.

Now you're just looking for clicks.

Quote from: JF
Now, that we exist in a quantum universe doesn't solve the problem of simulating a sentient intelligence, but it does at least help you understand where the simulation needs to take place.

Quote from: ppnl
It does not seem relevant at all as there are no large scale coherent phenomena in the brain. I really like the idea of a quantum brain and would be glad to be proven wrong. But the judgment of physics is harsh.

Are you "the physics" as Pfauci is "the science"?  You are correct, IMO, in that Hoffstader's book does a good job discussing these things.

Back to the OP. 

That plausible list that RobotBeet [sorry] offered up thread is very good.  Of course it is incomplete, and no one on this thread yet has addressed its components other than Greg, who takes a first stab at the effort.
« Last Edit: 12/08/2022 11:56 am by JohnFornaro »
Sometimes I just flat out don't get it.

Offline Greg Hullender

  • Full Member
  • ****
  • Posts: 621
  • Seattle
    • Rocket Stack Rank
  • Liked: 450
  • Likes Given: 343
Re: How Can AI Be Used for Space Applications?
« Reply #102 on: 12/08/2022 01:36 pm »
To try and get back on topic, let me summarize a few rules that I think determine when a problem is a suitable candidate for an AI solution.

1) There is no other way to solve it. AI is very, very hard. You don't want to go that way unless you absolutely have to.

2) The problem does not require perfection. A system that's wrong 10% of the time would be an absolute disaster for many applications, but it's quite difficult to design a system that's that accurate.

3) The problem is worth doing. A surprising number of people pick problems that look to be well-suited for a particular algorithm, but they never ask whether there's any value to solving that problem.

An ideal problem is one where the computer can amplify the work of human beings. For example, humans can sift through data returned from a mission looking for (say) white dwarf stars, but doing this by hand might take decades (or centuries). An AI solution that made judgments on the easy cases and passed the hard ones to the human judges would be very valuable, even if it initially passed on 90% of the candidates, provided it was at least as accurate as a human being on the other 10%. If you had a team of ten people, adding software like that would be like hiring another team member. Over time, you could work to improve the software. If it you it to where the rejection rate was 10%, it would be like multiplying your team from 10 to 100. The US Postal Service did exactly this with their software to read zip codes from envelopes.

Are there any space applications that seem to fit the bill?
« Last Edit: 12/08/2022 01:36 pm by Greg Hullender »

Offline ppnl

  • Full Member
  • ***
  • Posts: 312
  • Liked: 209
  • Likes Given: 19
Re: How Can AI Be Used for Space Applications?
« Reply #103 on: 12/08/2022 01:53 pm »
Quantum "supremacy" much?  We simply do not know how the macro scale world arises.  Go ahead and tell yourself the words you want to hear.

https://en.wikipedia.org/wiki/Quantum_supremacy

For what its worth I hope you are correct that the brain is a quantum device. It would solve some philosophical problems with consciousness, make quantum computers far easier to construct than we currently believe and greatly advance the field of computational complexity. Also it would greatly increase the usefulness of AI in space.

But the problem of coherence time is pretty devastating. In any case we should perhaps move on before the fun police arrive.

Offline JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10975
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1258
  • Likes Given: 724
Re: How Can AI Be Used for Space Applications?
« Reply #104 on: 12/08/2022 02:03 pm »
Edit:12-16-22:  LQP = Linear Quadratic Programming. Not LPQ.  Somebody remind me to watch my P's and Q's.]

This entire post (besides the quotes), by the way, is the output of ChatGPT when provided the quotes as prompts. ... I guess that counts as a kind of informal “Turing Test.”

Bravo! Well played!

I'll confess I just skimmed over the bullet list at the bottom. They all sounded plausible, but ... my eyes glazed over, and I didn't read it very closely. So let's take a close read.

"Designing and optimizing spacecraft systems and components" seems really far-fetched. I'm not aware of any issues there that need more than linear or quadratic programming [LQP]--if that. (But I'd be interested to learn otherwise.)

I approach this issue [the utility of AI] and similar issues [the 'why' of spaceflight and colonization] from the viewpoint that first came language, and then came math, in the course of human events.LQP becomes appropriate and necessary only after the "spacecraft systems" are presented and defined in concise language.  To use the JFK example:

"We choose to go to the Moon" must, in all cases, predate the the LQP thereof:

Quote
Reference system   Selenocentric
Periselene altitude   100.9 kilometers (54.5 nmi)[6]
Aposelene altitude   122.4 kilometers (66.1 nmi)[6]
Inclination   1.25 degrees[6]
Period   2 hours[6]
Epoch   July 19, 1969, 21:44 UTC

https://en.wikipedia.org/wiki/Apollo_11#Launch_and_flight_to_lunar_orbit

AI can never suggest the goal, at least in my telling.

Quote from: Greg
Same comment for "Planning and executing space missions." Neither of these is an area where I expect to see AI make an impact.

Agree in principle, but:  The planning can be expressed in an English language summary, including at least the intuitive methods of prioritizing those mission elements; AI could analyze the interplay of those elements, and maybe suggest element parameters that the human analysts may have overlooked.

As to the "execution" component, AI could rank those components, based on comparative LQP calculations.  In the case of a ring station [RS] at EML-1 [the reader is invited to suggest their own mission here], AI could be used to create a spreadsheet predicting the torque requirements for maintaining the Sun Synchronous Precession Orbit [SSPO] to maintain the RS orbit.

Quote from: Greg
"Analyzing data from space missions" is where I'd expect to see the biggest impact. ...  "Analyzing data" is definitely a problem that seems tailor-made for modern AI. But I think we all already knew that.

Agree.
« Last Edit: 12/16/2022 03:25 pm by JohnFornaro »
Sometimes I just flat out don't get it.

Offline JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10975
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1258
  • Likes Given: 724
Re: How Can AI Be Used for Space Applications?
« Reply #105 on: 12/08/2022 02:08 pm »
A surprising number of people pick problems that look to be well-suited for a particular algorithm, but they never ask whether there's any value to solving that problem.

Something something carts and horses.
Sometimes I just flat out don't get it.

Offline sanman

  • Senior Member
  • *****
  • Posts: 6009
  • Liked: 1324
  • Likes Given: 8
Re: How Can AI Be Used for Space Applications?
« Reply #106 on: 12/16/2022 01:54 pm »
I was playing with ChatGPT from OpenAI, and if nothing else, Machine Learning can be used to re-hash well-worn space debates like the kind we have on NSF:



« Last Edit: 12/16/2022 02:17 pm by sanman »

Offline Greg Hullender

  • Full Member
  • ****
  • Posts: 621
  • Seattle
    • Rocket Stack Rank
  • Liked: 450
  • Likes Given: 343
Re: How Can AI Be Used for Space Applications?
« Reply #107 on: 12/16/2022 04:38 pm »
It's cute, no question. Look at what I got when I asked why SpaceX was so far ahead of Blue Origin, despite have started later.
Quote
Blue Origin and SpaceX are both private aerospace manufacturers and spaceflight services companies that were founded around the same time, with Blue Origin being founded in 2000 and SpaceX in 2002. Both companies have made significant progress in the development of their rocket technology and have conducted a number of successful test flights.

However, there are a few factors that may have contributed to SpaceX's more rapid development and success in launching rockets into orbit. One key factor is funding: SpaceX has received a greater level of funding from private investors, which has allowed the company to invest more heavily in research and development and pursue more ambitious projects.

Another factor is experience: SpaceX was founded by Elon Musk, who had previously co-founded PayPal and had experience in the tech industry. This background may have given him a different perspective and set of skills that have helped him navigate the complex and competitive world of rocket development.

Finally, SpaceX has a clear focus on developing reusable rockets, which has the potential to significantly reduce the cost of space travel. This focus has allowed SpaceX to make rapid progress in this area and gain a competitive advantage over other companies.

That being said, Blue Origin has made significant progress in its own right and has a strong vision for the future of space exploration. The company has developed the New Shepard suborbital rocket, which has conducted several successful test flights, and is also working on the larger New Glenn rocket, which is intended to be capable of launching payloads into orbit. I believe that both Blue Origin and SpaceX have the potential to make significant contributions to the field of space exploration in the coming years.
Now, of course, this is pretty much 100% false, but what's interesting is what happened when I challenged it.
I told it, "But this isn't true! Blue Origin had far greater funding at the start, Musk has no greater understanding of Technology than Bezos, and both companies were focused on reusability from the start."

I'll confess, I didn't expect much, but I was quite impressed with the response:
Quote
I apologize for the misinformation in my previous response. You are correct that Blue Origin had a significant amount of funding at the start, as it was founded by Jeff Bezos, the CEO of Amazon, who has a net worth in the billions of dollars. Additionally, both Blue Origin and SpaceX were focused on developing reusable rockets from the start, as this has the potential to significantly reduce the cost of space travel.

It's also true that both Elon Musk and Jeff Bezos have a strong understanding of technology and have made significant contributions to the field. Both have founded successful tech companies and have demonstrated an ability to think outside the box and push the boundaries of what is possible.

It's difficult to say exactly why one company has progressed faster than the other, as there are many factors at play. Both Blue Origin and SpaceX have faced challenges and setbacks in the development of their rocket technology, and both have made significant progress in their own right. It's important to recognize that developing rockets and launching them into space is an incredibly complex and challenging task that requires a high level of expertise, resources, and perseverance. Both Blue Origin and SpaceX have demonstrated these qualities and have the potential to make significant contributions to the field of space exploration in the future.
Note that it still didn't give a decent answer to the question, but the quality of the response is quite impressive nevertheless.

Maybe I should ask it to give the answer from a SpaceX perspective. (To be authentic, that response would probably never mention Blue Origin at all.) :-)

But when I ask the original question again, I get the exact same response--word for word--with the exact same misinformation. That is, the system doesn't really learn anything. Not in real-time, anyway.
« Last Edit: 12/16/2022 04:40 pm by Greg Hullender »

Offline sdsds

  • Senior Member
  • *****
  • Posts: 7221
  • “With peace and hope for all mankind.”
  • Seattle
  • Liked: 2072
  • Likes Given: 1978
Re: How Can AI Be Used for Space Applications?
« Reply #108 on: 12/16/2022 11:42 pm »
More from ChatGPT from OpenAI.
— 𝐬𝐝𝐒𝐝𝐬 —

Offline Twark_Main

  • Senior Member
  • *****
  • Posts: 3754
  • Technically, we ALL live in space
  • Liked: 1950
  • Likes Given: 1216
Re: How Can AI Be Used for Space Applications?
« Reply #109 on: 12/17/2022 12:11 am »
And who's "Fornarno"?

That's your superhero/supervillain name.  8)

Offline JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10975
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1258
  • Likes Given: 724
Re: How Can AI Be Used for Space Applications?
« Reply #110 on: 12/17/2022 10:33 am »
It's cute, no question. Look at what I got when I asked why SpaceX was so far ahead of Blue Origin, despite have started later. ... But when I ask the original question again, I get the exact same response--word for word--with the exact same misinformation. That is, the system doesn't really learn anything. Not in real-time, anyway.

As you know, or may have suspected, people come with different degrees of intelligence.  Turing certainly knew this to be the case.  Some of the many things that Turing didn't know, was the direction that human tech would be "nudged" into following; the future capabilities, to him, that computers based on the Von Newman design would accomplish; and the future politics of the world in general.  Would Turing have questioned the AI as you did? 

A lot of people would take that first answer as evincing definite intelligence.  Does the T-Test need to be fine tuned somehow?

Quote from: Greg
Now, of course, this is pretty much 100% false ...

It all sounded plausible to me;  what do you mean "pretty much 100% false"? 

Quote from: that AI
SpaceX has a clear focus on developing reusable rockets...

Which of its statements are "pretty much 100% false"?
Sometimes I just flat out don't get it.

Offline JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10975
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1258
  • Likes Given: 724
Re: How Can AI Be Used for Space Applications?
« Reply #111 on: 12/17/2022 10:35 am »
And who's "Fornarno"?

That's your superhero/supervillain name.  8)

Ivan Oranrof, actually.  You need to do your homework.  Check out my twit account.
Sometimes I just flat out don't get it.

Offline edzieba

  • Virtual Realist
  • Senior Member
  • *****
  • Posts: 6308
  • United Kingdom
  • Liked: 9631
  • Likes Given: 41
Re: How Can AI Be Used for Space Applications?
« Reply #112 on: 12/17/2022 12:20 pm »
More from ChatGPT from OpenAI.
Like other GPT language models, ChatGPT clearly makes for a good politician: provides a few paragraphs of waffle without meaningfully answering the question.
« Last Edit: 12/17/2022 12:20 pm by edzieba »

Offline Robotbeat

  • Senior Member
  • *****
  • Posts: 39283
  • Minnesota
  • Liked: 25278
  • Likes Given: 12124
Re: How Can AI Be Used for Space Applications?
« Reply #113 on: 12/17/2022 08:19 pm »
More from ChatGPT from OpenAI.
Like other GPT language models, ChatGPT clearly makes for a good politician: provides a few paragraphs of waffle without meaningfully answering the question.
LOL, absolutelyThere are ways to get it to summarize information, though. Just tell it to be concise and not use any extra words to explain the concept.
Chris  Whoever loves correction loves knowledge, but he who hates reproof is stupid.

To the maximum extent practicable, the Federal Government shall plan missions to accommodate the space transportation services capabilities of United States commercial providers. US law http://goo.gl/YZYNt0

Offline Greg Hullender

  • Full Member
  • ****
  • Posts: 621
  • Seattle
    • Rocket Stack Rank
  • Liked: 450
  • Likes Given: 343
Re: How Can AI Be Used for Space Applications?
« Reply #114 on: 12/17/2022 11:17 pm »
Quote from: Greg
Now, of course, this is pretty much 100% false ...

It all sounded plausible to me;  what do you mean "pretty much 100% false"? 

Quote from: that AI
SpaceX has a clear focus on developing reusable rockets...

Which of its statements are "pretty much 100% false"?
I'm afraid this is the point where I write you off. Your post is so clearly in bad faith, it doesn't merit a response.

Offline JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10975
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1258
  • Likes Given: 724
Re: How Can AI Be Used for Space Applications?
« Reply #115 on: 12/18/2022 12:15 pm »
https://forum.nasaspaceflight.com/index.php?topic=57207.msg2442219#msg2442219

A few thoughts about being mostly true or false.

Quote from: ChatBot thingie up thread
Blue Origin and SpaceX are both private aerospace manufacturers and spaceflight services companies that were founded around the same time, with Blue Origin being founded in 2000 and SpaceX in 2002. Both companies have made significant progress in the development of their rocket technology and have conducted a number of successful test flights.

I assume the two numbers, 2000 and 2002, are accurate.  The term "significant progress is true.  Before 2000 and 2002, neither company had made any notable "progress" in their respective fields of endeavor.  SpaceX is ahead of BO; that BO started two years later is NOT the reason they're behind SpaceX.  The chat bot has a lot in common with the facile analyst.

Quote from: ChatBot thingie up thread
However, there are a few factors that may have contributed to SpaceX's more rapid development and success in launching rockets into orbit. One key factor is funding: SpaceX has received a greater level of funding from private investors, which has allowed the company to invest more heavily in research and development and pursue more ambitious projects.

The word "may" is a squishy term, which provides cover for extravagant claims like "rapid development" and "invest more heavily" and "more ambitious projects".  The statement should only be interpreted as an opinion.

From the oracle:

Quote
On July 20, 2021, Blue Origin sent its first crewed mission into space via its New Shepard rocket and spaceflight system.]

https://en.wikipedia.org/wiki/Blue_Origin


SpaceX has launched astros to the ISS before BO and BO has yet to orbit in LEO, AIUI.  This could be referred to as a "more rapic development".  As to the "greater level of funding from private investors", this too is a squishy, undefined term.

Quote from: ChatBot thingie up thread
Another factor is experience: SpaceX was founded by Elon Musk, who had [blah blah blah]. This background may have given him a different perspective and set of skills that have helped him navigate the complex and competitive world of rocket development.

Yet another editorial comment, not worthy of the label "truth" or "falsehood".  So, Musk has a "different perspective" than Bezos.  The field cannot be said to be non-competitive.  At the moment, Musk is ahead.  The bot provides no new insight into either company.

Quote from: ChatBot thingie up thread
Finally, SpaceX has a clear focus on developing reusable rockets, which has the potential to significantly reduce the cost of space travel. This focus has allowed SpaceX to make rapid progress in this area and gain a competitive advantage over other companies.

Obviously, SpaceX is focusing on re-usability.  Does that focus allow them to "make rapid progress"?  It helps, for sure.  "Allow"?  Well the chatbot was written by people who studied PR language.  The bot's statement is basically a PR statement.  I'd "allow" it the choice of doing what it does.

Quote from: ChatBot thingie up thread
That being said, Blue Origin has made significant progress in its own right and has a strong vision for the future of space exploration. The company has developed the New Shepard suborbital rocket, which has conducted several successful test flights, and is also working on the larger New Glenn rocket, which is intended to be capable of launching payloads into orbit.

Broadly "true", if one wanted to carry on a friendly discussion.

Quote from: ChatBot thingie up thread
I believe that both Blue Origin and SpaceX have the potential to make significant contributions to the field of space exploration in the coming years.

I like the way the bot says "I".  When you call up your ISP on a technical issue, do you really believe that when the bot says, "I have your account information here...clickity-clikity-click". that it really is a sentient being? And that it's really typing on a keyboard?

Some people do.
« Last Edit: 12/18/2022 12:19 pm by JohnFornaro »
Sometimes I just flat out don't get it.

Offline Twark_Main

  • Senior Member
  • *****
  • Posts: 3754
  • Technically, we ALL live in space
  • Liked: 1950
  • Likes Given: 1216
Re: How Can AI Be Used for Space Applications?
« Reply #116 on: 12/18/2022 02:48 pm »
And who's "Fornarno"?

That's your superhero/supervillain name.  8)

Ivan Oranrof, actually.  You need to do your homework.  Check out my twit account.

Nice save. It's hard work maintaining a secret identity!

Offline Twark_Main

  • Senior Member
  • *****
  • Posts: 3754
  • Technically, we ALL live in space
  • Liked: 1950
  • Likes Given: 1216
Re: How Can AI Be Used for Space Applications?
« Reply #117 on: 12/18/2022 02:52 pm »
More from ChatGPT from OpenAI.
Like other GPT language models, ChatGPT clearly makes for a good politician: provides a few paragraphs of waffle without meaningfully answering the question.

Of course.

There's an outcry any time an AI doesn't emit a "politically correct" answer. It's no wonder engineers train their AI to talk like a politician.

Offline sanman

  • Senior Member
  • *****
  • Posts: 6009
  • Liked: 1324
  • Likes Given: 8
Re: How Can AI Be Used for Space Applications?
« Reply #118 on: 12/19/2022 01:43 am »
It's a little prone to repetition, but it does show a lot of potential as an early product

« Last Edit: 12/19/2022 01:45 am by sanman »

Offline JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10975
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1258
  • Likes Given: 724
Re: How Can AI Be Used for Space Applications?
« Reply #119 on: 12/19/2022 10:33 am »
Little Jack Horner
Sits in a corner
Extracting cube roots to infinity.
An activity for boys
Which will minimize noise
And produce a more peaceful vicinity.

-A Space Child's Mother Goose
Sometimes I just flat out don't get it.

Tags:
 

Advertisement NovaTech
Advertisement Northrop Grumman
Advertisement
Advertisement Margaritaville Beach Resort South Padre Island
Advertisement Brady Kenniston
Advertisement NextSpaceflight
Advertisement Nathan Barker Photography
1