Author Topic: How Can AI Be Used for Space Applications?  (Read 72413 times)

Offline edzieba

  • Virtual Realist
  • Senior Member
  • *****
  • Posts: 6325
  • United Kingdom
  • Liked: 9662
  • Likes Given: 41
Re: How Can AI Be Used for Space Applications?
« Reply #80 on: 12/07/2022 11:40 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.

Offline Robotbeat

  • Senior Member
  • *****
  • Posts: 39286
  • Minnesota
  • Liked: 25283
  • Likes Given: 12125
Re: How Can AI Be Used for Space Applications?
« Reply #81 on: 12/07/2022 12:40 pm »
Quote
We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving
No, we don’t.
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 edzieba

  • Virtual Realist
  • Senior Member
  • *****
  • Posts: 6325
  • United Kingdom
  • Liked: 9662
  • Likes Given: 41
Re: How Can AI Be Used for Space Applications?
« Reply #82 on: 12/07/2022 02:24 pm »
Quote
We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving
No, we don’t.
We can, because we can conclude a problem's solution is undecidable. One of the fundamental tenets of a UTM is that it can solve any decidable problem (any algorithm that produces an output). That is not a limitation possessed by humans.

Offline Robotbeat

  • Senior Member
  • *****
  • Posts: 39286
  • Minnesota
  • Liked: 25283
  • Likes Given: 12125
Re: How Can AI Be Used for Space Applications?
« Reply #83 on: 12/07/2022 02:41 pm »
Quote
We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving
No, we don’t.
We can, because we can conclude a problem's solution is undecidable. One of the fundamental tenets of a UTM is that it can solve any decidable problem (any algorithm that produces an output). That is not a limitation possessed by humans.
Nope. Humans are not currently provably able to solve any problem that a UTM is provably unable to solve. Provide an exact counter-example and citation for your assertion humans can do better than an arbitrarily UTM.

This is considered a somewhat open problem, meaning no one has ever produced an example of a problem a human could solve that a UTM cannot, nor (more generally) has any physical process been found which a UTM cannot simulate.

Discussion here:
https://en.wikipedia.org/wiki/Halting_problem
« Last Edit: 12/07/2022 02:47 pm by Robotbeat »
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 Twark_Main

  • Senior Member
  • *****
  • Posts: 3767
  • Technically, we ALL live in space
  • Liked: 1950
  • Likes Given: 1220
Re: How Can AI Be Used for Space Applications?
« Reply #84 on: 12/07/2022 02:52 pm »
Quote
We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving
No, we don’t.
We can, because we can conclude a problem's solution is undecidable.

Determining decidability for some subset of problems is not, by itself, undecidable. Humans can do that.

Determining decidability for all possible problems is equivalent to the halting problem, so it is undecidable. But humans can't do that, because ultimately they'd be following some algorithm, and such an algorithm is provably impossible.

One of the fundamental tenets of a UTM is that it can solve any decidable problem (any algorithm that produces an output).

That's not the definition of a "decidable problem."

That is not a limitation possessed by humans.

No.  [/Jim]
« Last Edit: 12/07/2022 02:53 pm by Twark_Main »

Offline Barley

  • Full Member
  • ****
  • Posts: 1049
  • Liked: 715
  • Likes Given: 390
Re: How Can AI Be Used for Space Applications?
« Reply #85 on: 12/07/2022 02:56 pm »
Quote
We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving
No, we don’t.
We can, because we can conclude a problem's solution is undecidable. One of the fundamental tenets of a UTM is that it can solve any decidable problem (any algorithm that produces an output). That is not a limitation possessed by humans.
No, we don’t.

Mathematics like Cantor's diagonal argument and Godel's incompleteness theorem are compatible with a UTM.  If you're talking about "knowing" things without proof, ask ChatAPT if a peregrine falcon is a mammal.

Offline Greg Hullender

  • Full Member
  • ****
  • Posts: 621
  • Seattle
    • Rocket Stack Rank
  • Liked: 450
  • Likes Given: 344
Re: How Can AI Be Used for Space Applications?
« Reply #86 on: 12/07/2022 03:13 pm »
Quote
We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving
No, we don’t.
We can, because we can conclude a problem's solution is undecidable. One of the fundamental tenets of a UTM is that it can solve any decidable problem (any algorithm that produces an output). That is not a limitation possessed by humans.
There is a really deep philosophical rathole here, that I think we'd do best not to get into. We're already very far afield from the question in the original post, which actually does have some merit.

Offline leovinus

  • Full Member
  • ****
  • Posts: 1156
  • Porto, Portugal
  • Liked: 909
  • Likes Given: 1794
Re: How Can AI Be Used for Space Applications?
« Reply #87 on: 12/07/2022 03:14 pm »
Quote
We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving
No, we don’t.
We can, because we can conclude a problem's solution is undecidable. One of the fundamental tenets of a UTM is that it can solve any decidable problem (any algorithm that produces an output). That is not a limitation possessed by humans.
There is a really deep philosophical rathole here, that I think we'd do best not to get into. We're already very far afield from the question in the original post, which actually does have some merit.
My thoughts exactly.

Offline Robotbeat

  • Senior Member
  • *****
  • Posts: 39286
  • Minnesota
  • Liked: 25283
  • Likes Given: 12125
Re: How Can AI Be Used for Space Applications?
« Reply #88 on: 12/07/2022 03:20 pm »
Quote
We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving
No, we don’t.
We can, because we can conclude a problem's solution is undecidable. One of the fundamental tenets of a UTM is that it can solve any decidable problem (any algorithm that produces an output). That is not a limitation possessed by humans.
There is a really deep philosophical rathole here, that I think we'd do best not to get into. We're already very far afield from the question in the original post, which actually does have some merit.
It’s factually incorrect to assert what he asserted (as established fact), though. If he were right, he’d be able to provide an example (and probably win some international mathematics or computer science award).

It’s fine to claim it as *maybe possible* that humans could exceed an UTM in decidability, using some sort of non-algorithmic manner that can’t be written down in any formal process. That can’t be ruled out so far (and I’m holding myself back here…), but he asserted that it was KNOWN that humans can do something UTMs are incapable of, which is factually incorrect.
« Last Edit: 12/07/2022 03:29 pm by Robotbeat »
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 Robotbeat

  • Senior Member
  • *****
  • Posts: 39286
  • Minnesota
  • Liked: 25283
  • Likes Given: 12125
Re: How Can AI Be Used for Space Applications?
« Reply #89 on: 12/07/2022 03:26 pm »
I came across this interesting article about how AI is being used to conjure up completely new proteins very quickly.
https://www.nature.com/articles/d41586-022-02947-7


It occurred to me that this could enable all sorts of designer bugsorganisms for ISRU purposes, and maybe even terraforming.

Perhaps we could have bugsorganisms designed to survive the Martian day/night cycle, which would come alive during the day, to perform useful conversion of natural resources, like through Sabatier or whatever.

Could we even use AI to design complex ecosystems of organisms that would cope with the existing Mars conditions while working to transform the environment into one that's more human-friendly?
Yes, AI could potentially be used in a variety of ways for space applications, including for ISRU (in-situ resource utilization) and terraforming. For example, AI could be used to design and optimize proteins for specific conditions, such as the extreme temperatures and radiation levels on Mars. These proteins could be used in organisms that are capable of surviving and thriving on the Martian surface, and potentially even converting natural resources into usable materials.

In addition, AI could be used to design complex ecosystems of organisms that could adapt to the existing conditions on Mars and work to transform the environment over time. This could involve developing algorithms that can simulate and predict the behavior and interactions of different species, and optimize their performance in a given environment.

Overall, AI has the potential to greatly accelerate and improve our ability to utilize and explore space, by enabling us to design and optimize complex systems that can survive and thrive in challenging environments.
Quote
Tell me more, with specifics on the engineering involved.

In terms of specific engineering applications, AI could be used in a variety of ways to support space exploration and utilization. Some examples include:

* Designing and optimizing spacecraft systems and components: AI algorithms could be used to design and optimize spacecraft systems and components, such as propulsion systems, power systems, and communication systems, to improve performance and reduce costs. For example, AI could be used to model and simulate the behavior of different spacecraft components, and identify optimal configurations and designs that meet specified performance criteria.

* Planning and executing space missions: AI could be used to plan and execute space missions, by developing algorithms that can generate and evaluate potential mission plans, and identify optimal strategies for achieving mission objectives. This could involve simulating the behavior of spacecraft and other systems, and optimizing their performance to achieve desired outcomes.

* Analyzing data from space missions: AI could be used to analyze data from space missions, such as sensor data from spacecraft, to identify patterns and trends, and make predictions about future events. This could involve developing algorithms that can process and interpret large amounts of data, and extract useful insights and knowledge from it.

* Developing and deploying intelligent robots: AI could be used to develop and deploy intelligent robots that are capable of autonomously exploring and operating in space. This could involve developing algorithms that enable robots to perceive and interact with their environment, and make decisions based on that information. For example, AI could be used to enable robots to navigate and manipulate objects, and perform tasks such as collecting samples or repairing equipment.

Overall, AI has the potential to greatly enhance our ability to explore and utilize space, by enabling us to design and optimize complex systems, plan and execute missions, analyze data, and deploy intelligent robots.
This entire post (besides the quotes), by the way, is the output of ChatGPT when provided the quotes as prompts.

The first one is primarily just restating the (larger than necessary) input prompt which I took from the first post in this thread, but the second half is an impressive synthesis of exactly the answer to this thread’s question. JohnFornarno “liked” it, even. I guess that counts as a kind of informal “Turing Test.” ;)
« Last Edit: 12/07/2022 03:30 pm by Robotbeat »
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: 344
Re: How Can AI Be Used for Space Applications?
« Reply #90 on: 12/07/2022 04:11 pm »
This entire post (besides the quotes), by the way, is the output of ChatGPT when provided the quotes as prompts.

The first one is primarily just restating the (larger than necessary) input prompt which I took from the first post in this thread, but the second half is an impressive synthesis of exactly the answer to this thread’s question. JohnFornarno “liked” it, even. 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 the challenge would be in finding a way to "featurize" the input data in such a way that it actually enabled one or another AI algorithm to work. (AI can't, in general, handle raw data as input.) The other thought I had (which I've had about a lot of ChatGPT's output) is that it was way too wordy. (Or TLDR, as the young people say.) :-) 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--if that. (But I'd be interested to learn otherwise.) Same comment for "Planning and executing space missions." Neither of these is an area where I expect to see AI make an impact.

"Analyzing data from space missions" is where I'd expect to see the biggest impact. As a target for AI, it has a lot going for it. First, it's not mission-critical. If it doesn't work, it spoils someone's paper--it doesn't waste billions of dollars and/or cost people their lives. Second, there is a lot of data to work with. Contrast the first two proposed areas, where there really isn't a lot of data. Finally, the need find information in vast tracts of data is a real problem that isn't easily solved by other means. (You should never use AI when there's a conventional solution.)  "Analyzing data" is definitely a problem that seems tailor-made for modern AI. But I think we all already knew that.

"Developing and deploying intelligent robots." Here's where ChatGPT shows its weaknesses. The paragraph isn't about designing and deploying: it's about navigation systems. (How would AI help you deploy anything?!) Navigation is definitely an area where there's been a lot of AI work here on the ground, and the lack of pedestrians, road rules, and other vehicles on other planets makes the problem even simpler (although the lack of roads makes it harder).  The question is, does it make it so much simpler that you don't need AI to do it?

I think this illustrates where ChatGPT could make a big difference. It did a nice job of picking a set of plausible areas that could then be the basis of intelligent discussion. Like a database search, but through unstructured data. Augmenting what people do, but not replacing it.

Offline Robotbeat

  • Senior Member
  • *****
  • Posts: 39286
  • Minnesota
  • Liked: 25283
  • Likes Given: 12125
Re: How Can AI Be Used for Space Applications?
« Reply #91 on: 12/07/2022 04:20 pm »
…well, it can probably replace what SOME people do… 🤣
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 Robotbeat

  • Senior Member
  • *****
  • Posts: 39286
  • Minnesota
  • Liked: 25283
  • Likes Given: 12125
Re: How Can AI Be Used for Space Applications?
« Reply #92 on: 12/07/2022 04:21 pm »
I should’ve told ChatGPT to make it a lot more concise. It’s also very good at producing a “tl:dr” version of some input text.
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: 344
Re: How Can AI Be Used for Space Applications?
« Reply #93 on: 12/07/2022 04:38 pm »
…well, it can probably replace what SOME people do… 🤣
It's definitely a first-rate bullsh*t generator. It can definitely replace those people who have to produce dreary reports that seem reasonable but which no one actually reads.

Now we need an AI solution that identifies this type of output. Perhaps by taking pieces and relating them to existing online documents. "Highlight the portions that are potentially original."

Sigh. We may have to have that soon . . .

Online DanClemmensen

  • Senior Member
  • *****
  • Posts: 5720
  • Earth (currently)
  • Liked: 4489
  • Likes Given: 1873
Re: How Can AI Be Used for Space Applications?
« Reply #94 on: 12/07/2022 04:41 pm »
…well, it can probably replace what SOME people do… 🤣
It's definitely a first-rate bullsh*t generator. It can definitely replace those people who have to produce dreary reports that seem reasonable but which no one actually reads.

Now we need an AI solution that identifies this type of output. Perhaps by taking pieces and relating them to existing online documents. "Highlight the portions that are potentially original."

Sigh. We may have to have that soon . . .
It should also work really well for press releases. PR flacks should be trying to re-train for more productive work. this may extend to other marketing jobs.

Offline Robotbeat

  • Senior Member
  • *****
  • Posts: 39286
  • Minnesota
  • Liked: 25283
  • Likes Given: 12125
Re: How Can AI Be Used for Space Applications?
« Reply #95 on: 12/07/2022 06:18 pm »
…well, it can probably replace what SOME people do… 🤣
It's definitely a first-rate bullsh*t generator. It can definitely replace those people who have to produce dreary reports that seem reasonable but which no one actually reads.

Now we need an AI solution that identifies this type of output. Perhaps by taking pieces and relating them to existing online documents. "Highlight the portions that are potentially original."

Sigh. We may have to have that soon . . .
It’s pretty good at summarizing, so that may help:

https://beta.openai.com/examples/default-tldr-summary
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 JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10986
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1261
  • Likes Given: 725
Re: How Can AI Be Used for Space Applications?
« Reply #96 on: 12/07/2022 07:59 pm »
This entire post (besides the quotes), by the way, is the output of ChatGPT when provided the quotes as prompts.

The first one is primarily just restating the (larger than necessary) input prompt which I took from the first post in this thread, but the second half is an impressive synthesis of exactly the answer to this thread’s question. JohnFornarno “liked” it, even. 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

Turns out that I "like" "plausible" lists.  Ask it if it likes my ring station.  And who's "Fornarno"?

Quote from: Greg
How would AI help you deploy anything?!
  By designing, building, and operating the deployment apparatus.
« Last Edit: 12/07/2022 08:02 pm by JohnFornaro »
Sometimes I just flat out don't get it.

Offline Robotbeat

  • Senior Member
  • *****
  • Posts: 39286
  • Minnesota
  • Liked: 25283
  • Likes Given: 12125
Re: How Can AI Be Used for Space Applications?
« Reply #97 on: 12/07/2022 08:54 pm »
I wasn’t trying to make a dig at you, John. ChatGPT is pretty good at summarizing topics.
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 ppnl

  • Full Member
  • ***
  • Posts: 312
  • Liked: 209
  • Likes Given: 19
Re: How Can AI Be Used for Space Applications?
« Reply #98 on: 12/08/2022 08:12 am »
Quote
We also have the existence-proof that humans can sole Halting problems that UTMs are fundamentally incapable of solving
No, we don’t.
We can, because we can conclude a problem's solution is undecidable. One of the fundamental tenets of a UTM is that it can solve any decidable problem (any algorithm that produces an output). That is not a limitation possessed by humans.

Treading lightly here because the fun police are threatening...

You should read "Gödel, Escher, Bach: an Eternal Golden Braid" by Douglas Hofstadter to see why you are almost certainly wrong in this claim.

I agree that there are deep and profoundly interesting philosophical issues with uncomputability that are off topic for this thread. But the base claim and its simple refutation seem relevant. 

Offline ppnl

  • Full Member
  • ***
  • Posts: 312
  • Liked: 209
  • Likes Given: 19
Re: How Can AI Be Used for Space Applications?
« Reply #99 on: 12/08/2022 08:52 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.  Consider also the fact that the neuron is very close to the scale of quantum events.  Several billion years of evolution within a quantum universe cannot be disposed of with a wave of the hand, simply because the connection is not well known.

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.

In order to have a macro scale quantum phenomena you need quantum coherence. That is the quantum bits have to interact with each other without interacting with the rest of their environment. That is about as impossible as actually performing Schrödinger's cat experiment. You should look into the subject of decoherence to see how the macro scale world arises from the quantum foam.

 
Quote
Remember how they used to talk about "junk" DNA?  I was always like, it's there for a reason; just because you don't know how it works is not excuse for calling it "junk".

Junk DNA is junk in the sense that it is noncoding. Some of it can have structural uses but a lot of it is clearly broken genes, old viral remains and such. About half of the junk in humans is jumping genes that can break other genes around them. This may produce variations for natural selection to operate on but most of those variations are cancers and genetic diseases. Evolution sucks.

But the fun police are probably going to label this off topic so we should move on.

Quote
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.

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.

Tags:
 

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