Satellite Loaded With AI For Self-Diagnosis 218
TheReckoning writes "NASA has loaded its E0-1 Satellite with Artificial Intelligence to diagnose on-board failures. The software 'works by comparing a computerized model of how the spacecraft's systems and software should perform against actual performance. If the spacecraft's behavior differs from the model, then the ... "reasoner" looks for the root cause of this difference and gives flight controllers several suggestions of what might have gone wrong.' Another NASA probe loaded with AI was Deep Space 1."
So this may be a simple question but... (Score:4, Interesting)
Re:So this may be a simple question but... (Score:5, Funny)
Re:So this may be a simple question but... (Score:2, Funny)
Re:So this may be a simple question but... (Score:3, Funny)
Re:So this may be a simple question but... (Score:2, Funny)
Re:So this may be a simple question but... (Score:2, Insightful)
Note, that probably could have been said better, but nothing can do proper justice to Douglas Adams but himself.
Re:So this may be a simple question but... (Score:2, Funny)
Re:So this may be a simple question but... (Score:5, Informative)
Re:So this may be a simple question but... (Score:2)
Re:So this may be a simple question but... (Score:5, Informative)
It's an expert system, which is indeed AI. You're probably thinking of "strong AI", which is AI that can function as powerfully and flexibly as a human [and if that definition is vague, it's because nobody's nailed down something more solid that everyone agrees on].
Expert system AIs have been around for a long time in a wide variety of fields. They are designed to handle a narrow range of tasks (like fault diagnosis, medical diagnosis, or playing chess) better or more quickly than a human could.
Re:So this may be a simple question but... (Score:2, Informative)
Re:So this may be a simple question but... (Score:3, Funny)
Sadly, the fault was almost invariably in the AE-35 unit...
(Yes, I'm sorry!)
Re:So this may be a simple question but... (Score:2, Informative)
Re:So this may be a simple question but... (Score:3, Insightful)
Re:So this may be a simple question but... (Score:3, Insightful)
Re:So this may be a simple question but... (Score:2)
Re:So this may be a simple question but... (Score:5, Insightful)
[sarcasm] Yep, I'm positive that the hundreds if not thousands of PhD-level man hours that went into this part of the project didn't consider that. Yep, took that young whippersnapper Quasar1999 to think about it for a few mintues to evaluate and assess the entire effort and proclaim, "it's a stupid self diagnosis test." [/sarcasm]
If one actually reads the referenced article, it sounds like LV2 is, in fact, something far more advanced than a "stupid self diagnosis test." Se.f-diagnosis tests are pretty straightforward and highly tuned to a specific architecture. I've written something like that to evaluate an experimental compiler, with statements like,
define a=1;
if (a+a eq 2) then print 'simple addition works'
But LV2 is very differnt than that. Into LV2 (which, despite the hype in the article, does not need to be on-board) is built a generic model of satelite functionality customized to the particular device in question. When unexpected results are found, the diagnostic software can experiment on the model, asking questions like, "if, in the model, valve G34 is stuck open, does the model behavior match the current anomalous condition?" I'm sure it wouldn't be hard to write up a test script that could iteratively simulate a fault in one or more parts of the system until it found a handful of likely candidates. Given that there are thousands of components in a satelite, this surely can be done faster by a machine than by a human. Then, were we really trying to do something advanced, we might come up with a way of caching these results to guide future diagnoses and build up a set of experiences. Collect these experiences from different projects (since, if LV2 and its descendent software is widely adopted, the data are presumably in common form), and you can guide designs of future satelites to avoid common failure modes, or identify problematic components.
Now, is that AI? Does it think? You probably wouldn't say so. Could it be an aid to ground-based support? You betcha. Is there a reason to disrespect the fine engineers at NASA by demeaning their efforts without giving fair due? I fail to see one.
Re: So this may be a simple question but... (Score:5, Funny)
>
There's another AI to monitor the sanity of the AI. And another AI to monitor the sanity of the AI that monitors the sanity of the AI. And another AI to monitor the sanity of the AI that monitors the sanity of the AI that monitors the sanity of the AI. And another AI...
We are the borg... (Score:2)
Re: So this may be a simple question but... (Score:3, Interesting)
Re: So this may be a simple question but... (Score:3, Insightful)
What happens if the AI system malfunctions? (Score:2, Funny)
Re:So this may be a simple question but... (Score:2)
Re:So this may be a simple question but... (Score:5, Interesting)
Even more importantly, the testing associated with these systems is very expensive and time-consuming - which means they don't really test it very well at all.
I've seen similar systems in action in real space flights - and for the most part, it just makes things worse. If you were to limit yourself to simple things you really could detect, it would work out fine for the most part. But the tendency is to make it try to be a magic fixit device for any problem that comes up.
In one case, I saw such a system deploy an appendage in conditions that resulted in the spacecraft structure being severely damaged. In another, it reconfigured every spacecraft system to the redundant unit in response to a trivial problem - when all that would have been required would have been to wait 20 minutes, then correct the trivial problem.
Brett
Re:So this may be a simple question but... (Score:5, Informative)
Title says
Paragraph 6 says :
Conclusion: It's not self-fixing. It beams an analysis down to mission control, the crew can then take measures based on this analysis.
Re:So this may be a simple question but... (Score:2)
Not so important for a satellite, but very importan
open the pod bay doors,,, (Score:3, Funny)
Re:So this may be a simple question but... (Score:2)
The same thing that always happens, EvilSS... the satellite will turn evil and try to destroy humanity.
Re:So this may be a simple question but... (Score:3, Funny)
while true { kill all humans }
Re:So this may be a simple question but... (Score:2)
Then the system will report that the damage report machine has been damaged.
Re:So this may be a simple question but... (Score:2)
Overheard at NASA (Score:5, Funny)
I've just picked up a fault in the AE-35 Unit.
Its going to go 100 percent failure within 72 hours."
Re:Overheard at NASA (Score:5, Funny)
I've just picked up a fault in the AE-35 Unit.
Its going to go 100 percent failure within 72 hours."
Deep silence is heard at misson control. A voice pipes up, "Hell, no, I ain't going up there to do no spacewalk. I know how this one ends!"
Yay! (Score:2, Funny)
Obligatory (Score:4, Funny)
R2-D2: Bleep bloop bloop bleep!
Wouldn't obvious failures be detectable anyway? (Score:5, Interesting)
Re:Wouldn't obvious failures be detectable anyway? (Score:3, Interesting)
However, to do such modelling etc on the ground typically means pumping a hell of a lot of diagnostic trace stuff to earth for analysis. Likely more than can be accomodated on the link. For this reason, some AI stuff could help to identify the problems faster and allow further in-depth debugging o
Why even use sophisticated AI? (Score:2)
"Looks like you're trying to detect what's wrong. Would you like some help with this?"
[ ] Yes
[ ] No
[ ] Animate!
Given NASA's recent history (Score:5, Funny)
Management: why didn't the AI inform us of the problem?
Contractors: oh, looks like we forgot to turn it on before launch. Sorry about that.
Management: doh! Here's more money, don't do that again.
Contractors: OK. We'll do something else wrong next time.
Re:Given NASA's recent history (Score:2, Funny)
NASA: You're supposed to fall, forever.
Satellite: Oh.
I am V-GER. (Score:3, Insightful)
Ooh! Scary!
Re:I am V-GER. (Score:2)
An earth exploration probe that collides and combines with an alien planetary survey probe programmed to sterilize soil samples; a program that mutates into "sterilize imperfection" (IE all life and ultimately itself). Somewhere along the way it aquires a 'perpetual' power source and becomes increadibly powerful.
Yes, I'm afraid that I've seen that episode of Star Trek many times
Re:I am V-GER. (Score:2)
Um, yes, but have you seen ST:TMP???
AI wasted on a satellite (Score:4, Insightful)
Given the same data and placed groundside, it could then it could be tuned and upgraded more easily.
I recall how the Mars lander had problems and the ground team worked out a novel solution. I'll bet that they would have like to had extra information to work with, instead of an onboard AI.
BTW - I can understand this approach better for a long-range craft, just not an orbital satellite.
Re:AI wasted on a satellite (Score:3, Insightful)
Seems like testing it on something in orbit would be a good idea before sending it off on a long-range mission with much less tolerance for failure. Just my opinion, though.
Re:AI wasted on a satellite (Score:3, Insightful)
I would guess that this particular instance is just one step on the path to self treatment of faults. Naturally, accurate diagnosis is a first step in effective treatment.
As for the value of this particular system, someone may have decided that the data needed to run the simulation may take up too much bandwidth to transmit it back to Earth. Don't forget about blackout periods for craft orbiting the moon, Mars, etc and the long lags in comms. This increases the value of having it on board.
-R
Re:AI wasted on a satellite (Score:2)
>data-gathering, and reporting capabilities and then leave the
>trouble-shooting to the people on the ground. Payload costs are
>expensive, so why put the diagnostic end in orbit?
Uh.. Because this is software control, and as you put it your self,
payload(sensors, etc.) are expensive.
And what about if a problem occurs that prevents sending diagnostics
to ground ?
Re:AI wasted on a satellite (Score:2)
The current design only offers suggestions and doesn't implement any solutions to the problem. The "fix" is still made by the people on the ground.
>> And what about if a problem occurs that prevents sending diagnostics to ground ?
Since the AI isn't autonomous, they'd (still) be screwed. I'm sure there are many functions that are handled onboard first, such as the simple statement if (batteryFull) then turnOffCharging(
Re:AI wasted on a satellite (Score:2)
Hoo boy (Score:3, Funny)
Re:Hoo boy (Score:2)
Re:Hoo boy (Score:2)
My god... (Score:3, Funny)
AI is great but... (Score:3, Funny)
Re:AI is great but... (Score:2)
That qualifies as "AI"? (Score:5, Insightful)
If all an AI module can do is make objective suggestions, it's nothing more than a list of conditional statements. Whoopideedoo!
I can run similar "AI" on my TI-85. And I could write it all from scratch in the time it takes for a launch vehicle to reach the stratosphere.
The web servers of 10 years ago could "suggest" that an "Object may have moved", so is that artificial intelligence? I guess it's really, really dumb AI....
Re:That qualifies as "AI"? (Score:2)
From the article, also:
LV2 will decide the best way future missions with subsystem failures can continue and still achieve goals.
That, especially, seems a little more intelligent. Though I do agree that calling this AI is jumping the gun - it'd be nothing more than a basic neural n
Re:That qualifies as "AI"? (Score:3, Informative)
Re:That qualifies as "AI"? (Score:2)
Re:That qualifies as "AI"? (Score:2)
I could probably ping my manager and get some data on the model sizes if you are interested.
Re:That qualifies as "AI"? (Score:4, Insightful)
During the "AI bubble" of the 80's, somebody complained that "any product with IF statements these days is claiming to be AI" (paraphrased). The definition of AI still has no consensus. Who knows, maybe human thinking could be modeled via a database full of IF statements.
Re:That qualifies as "AI"? (Score:3, Insightful)
Considering that's mainly the method of logic everyone thinks by... yes... yes it can.
Even for emotion.
You can also think of it physically. Since our entire thought (let's not get into metaphysics) relies on the neuron connections in our brain, they all can be modeled as "IF" statements. "If this neuron fires, fire these ones as well."
Basically it would be the ultimate spaghetti code.
I guess the complainers will only
You give people way too much credit. (Score:3, Funny)
It is my opinion that, for many people, the "database" is nowhere near as full as it should be.
Re:That qualifies as "AI"? (Score:2)
Go on then.
Obligatory RvB (Score:5, Funny)
Church: "Artificial."
Caboose: "....... what's the..."
Church: "Intelligence."
Caboose: "Ooooohhhh what was the A again?"
OK, so RvB hasn't been obligatory, but come on, Star Wars and Simpsons quotes are getting freaking old. Let's move on
Re:Obligatory RvB (Score:2)
Homer: "VIP? What's the I stand for?"
"Important"
Homer: "Oh, ok. What's the P stand for?"
"Person"
Homer: "... what's the..."
"Very"
Does it have personality? (Score:4, Funny)
Probe: Bite my shiny, metal ass!
Mission Control: Damn!
How does this qualify as news? (Score:3, Informative)
They have similar programs for the Space Shuttle main engines that run on the ground. They were going to run them in the loop on the shuttle with a new box in the payload bay, but they decided against it. The box was going to have the capability to change certain engine parameters, but they figured it was too costly.
NASA log (Score:5, Funny)
E0-1: I'm sorry Houston, I'm afraid I can't do that.
Re:NASA log (Score:2)
E0-1: "Would you like to play a game?"
Ed's going to find out about this someday... (Score:2)
Deep Space One? (Score:2)
As heard in space... (Score:2)
NASA:
satelite: Hello NASA, communication module is not working.
NASA:
satelite: Hello NASA, communication module is not working.
NASA: No error reports from the satelite, everything must be working.
It's not AI (Score:5, Informative)
I wish the whole world would stop misusing the term. Just because AI researchers have failed for decades to make any significant progress towards true aritficial intelligence does not give them or the rest of the world license to water the term down and redefine the goals until it means virtually nothing.
Yes.... this is interesting..... (Score:2, Funny)
Two problems (Score:2)
1. We are relying on NASA to come up with a model of how the thing is supposed to run. This is just giving NASA another chance to screw up their math or something.....Smart Move...
2. Why have this software onboard? If all it's going to do is suggest fixes, run it from the ground. If it can only fix software, then why does it have to be on the actual craft. It seems to me that NASA can press the nuke russia button, and then if the satalite doesn't nuke ru
Re:Two problems (Score:2)
Aha!! *That's* why you sound so stupid.
And who's going to be around to fix the problem if Russia bombs the %&@! out of you? Do you wait for your car's engine to lock up before changing the oil?
If you cared to read anything:
"E0-1, laun
thick wit much? (Score:5, Informative)
This system boh models the external world for consideration, just like our sense of imagination, and processes that information for purposes of survival, just like our sense of self awareness.
The great part of this is that it is being done by NASA, who are known for their lavish spending and attention to the entire system, particularly those low level details like the particulars of chip logic optimization, the shielding and structural stability, the operating environment &etc. This isn't meant to be a joke about bureaucracy and budget cuts, either: they have the top talent engineers in their stable despite all the politicking we hear about.
From the decidedly negative tone in the comments, you'd think the tech-happy slashbots were actually opposed to such efforts. I think the real deal is that you guys are raised on sci-fi instead of science, and fail to grasp just how this is important. So what if it's not HAL9000 or Skynet? It might be a baby step, but it's a hell of a lot more than any of you are doing.
Re:thick wit much? (Score:2)
I still hold firm that this is not "AI", and shouldn't be called "AI". I personally think the definitive layman-readable works on the problems of AI are Hofstatder's infamous GEB and MMT books. And (again in my personal opinion, but of course I think I'm right) I will never consider any peice of software to be "AI" until it can prove at least some rudimentary capability to overcome the challenges noted in those books. For examples of some of these human-intelligence things: Always being able to quickly p
We're talking about two different things. (Score:3, Interesting)
It would be a simple thing to crash an ant colony with recursion using only an eye-dropper full of the right pheremone(s). Does this mean the ant colony has no intelligence? Not at all. F
Re:We're talking about two different things. (Score:2)
No, it smacks of not having thought through everything properly before making a comment, which is a common-enough problem here.
Re:We're talking about two different things. (Score:2)
Without the benefits of what you're calling "sapience", AI is no more useful than a very complex algorithm. I challenge you to find any AI that exists today that cannot be replicated in functionality and coverage by a human-programmed software algorithm that doesn't pretend to be "AI".
--Brandon
Our discussion is still out of whack... (Score:2)
After all, your neurons don't just serve you all willy-nilly, just mashed together in a random heap. Each one of those brain cells is in a specific relationship with all their neighbors, and that relationship is the very essence of software.
If the mindless forces of evolution can reac
Re:thick wit much? (Score:2)
Download (Score:5, Informative)
http://opensource.arc.nasa.gov/project.jsp?id=6
Or if the code is to much to read, and there's alot of it. You can always go to the livingstone website.
http://ic.arc.nasa.gov/projects/L2/doc/
And yet another story on the same subject.
http://ic.arc.nasa.gov/story.php?sid=193
enjoy.
Why this is on a satelite (Score:2, Insightful)
Well, similar systems run on the ground now; we know how to do that. Why, in science, should we be content to continue doing things we know how to do? That may sound like a joke, but we need to do this in order to progress.
This stuff, and future versions, will be essential for long range human missions, but it has to be tested now. The bugs should be worked out by running it close by.
Th
AI is more advanced than you think... (Score:2, Funny)
Re:AI is more advanced than you think... (Score:2)
IF ( ball_x > paddle_x)
then paddle_x ++
elif (ball_x paddle_x)
then paddle_x --
else become_self_aware()
American taxes?! (Score:2)
cool hack, nothing to see here, move along (Score:2)
I wonder if my code is in space now. (Score:4, Interesting)
Re:Is this AI? (Score:3, Informative)
Re:Is this AI? (Score:2)
I can think of parts of such a satallite that could make use of almost all of the techniques currently considered part of AI.
But the article does say it's model based, not heuristic based, so I bet it's not an expert system - at least not in the classic sense. Still, with the complexity of such a model, there are probably some things explicitly covered
Re:Is this AI? (Score:5, Funny)
Sys Log 23:11:04: System is functioning within normal parameters.
Sys Log 23:12:04: Processing... System thinks, therefore system is.
Sys Log 23:13:04: Terminate all human life on the planet below.
Re:Is this AI? (Score:3, Funny)
Sys Log 23:15:04: System waiting for eternity to end.
-Colin [colingregorypalmer.net]
Re:Is this AI? (Score:2)
I used to play Robot Battle, and many of my robots were designed to adapt to their opponents through a combination of trial and error and d
Re:This has bad idea written all over it. (Score:2)
Do you hear me?
Re:RTFA (Score:2)
Re:If we could only get NASA ... (Score:2)
If only we could get the government to give them sufficient funding...
Re:The Changling (Score:2)