Slashdot Mirror


Self-Healing Computers For NASA Spacecraft

Roland Piquepaille writes "As you can guess, hardwired computer systems are much faster than general-purpose ones because they are designed to do a single task. But when they fail, they need to be totally reconfigured. This can be just a costly problem in a lab on Earth, but it can be vital in space. This is why a University of Arizona (UA) team is working with NASA to design self-healing computer systems for spacecraft. The UA engineers are working on hybrid hardware/software systems using Field Programmable Gate Arrays (FPGAs) to develop these reconfigurable processing systems. As the lead researcher said, 'Our objective is to go beyond predicting a fault to using a self-healing system to fix the predicted fault before it occurs.'"

70 comments

  1. The 9000 Series has a perfect operational record by 1u3hr · · Score: 5, Funny

    "Just a moment....Just a moment.
    I've just picked up a fault in the AE-35 Unit.
    Its going to go 100 percent failure within 72 hours."

  2. Re:The 9000 Series has a perfect operational recor by limber · · Score: 5, Funny

    Daisy, Daisy, give me your answer do. I'm half crazy all for the love of you. It won't be a stylish marriage, I can't afford a carriage. But you'll look sweet upon the seat of a bicycle built for two.

  3. Not new by Anonymous Coward · · Score: 5, Informative

    I used to work for JPL, in a group that was researching the feasibility and applications of FPGAs for this exact purpose. That was around 7-8 years ago, which significantly predates this "news," given the pace of technology. IIRC, they called it "evolvable hardware."

    1. Re:Not new by Taelron · · Score: 1

      Thank you, I could have sworn I heard this same exact approach discussed and tested back around 2000... Is this another one of those ideas that was to difficult at the time and shelved only to be dusted back off and tried again with new technology?

    2. Re:Not new by jd · · Score: 1

      I first saw mention of circuits that could bypass failed areas in a mid 1980s article by Sir Clive Sinclair, who argued it could be used to produce wafer-scale technology. The errors in the wafer would be unimportant, as they'd all be bypassed. Of course, this isn't what I'd call "self-healing" (where circuit switches go along with some sort of effort to repair the original damage if possible), but actual repair - beyond perhaps some sort of robot-wielded silver pen to re-connect broken tracks on a circuit board - is far beyond modern technology.

      --
      It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
    3. Re:Not new by Anonymous Coward · · Score: 0

      I agree, this is not new at . FPGAs are of growing importance for high-performance computing as demonstrated at NASA Langley back in 2001

      http://oea.larc.nasa.gov/news_rels/2001/01-021.html

    4. Re:Not new by RiotingPacifist · · Score: 2, Interesting

      I wonder if it will every be cost effective to put FPGAs in consumer systems, i can see them really helping in bottlenecks (why waste cpu on doing the same processing over and over, ship it of to a specialised FPGA) and in low power situations (why wake up the cpu when you can program the FPGA to do 50% of the wake-ups), unfortnatly i can only see this helping mac & linux, as the windows kernel being closed makes implementing this stuff down to MS not the chip makers.

      I think the goal of this project isnt high performance, but high redundancy, there are only so many backups you can put on a probe, with this if they do it right you could end up with a system where any core could break and be fix/replaced at fraction of the cost shipping 2 chips for every component. Unfortunately often the sensors go before the core technology so i dont know how effective that will be, plus due to a lack of funding often projects are abandoned long before all the systems are broken

      --
      IranAir Flight 655 never forget!
    5. Re:Not new by DerekLyons · · Score: 1

      This capability was first discussed back in the 70's and 80's and was theorized about back in the 60's, considerably predating your "anecdote". This is news, no matter what the 'pace of technology'* is, because they haven't quite managed to make it work yet.

      * Largely a meaningless set of buzzwords. Even in computers not every portion of the field progresses at the same pace.

    6. Re:Not new by Anonymous Coward · · Score: 0

      FPGAs are already all over the place. You just don't see them too much in high volume manufacturing, but low volume stuff will almost certainly contain FPGAs (or CPLDs, the little brother of FPGA).

    7. Re:Not new by Anonymous Coward · · Score: 0

      A larger issue is that unlike software, you can't just "branch" from one place in a chip to another.

      The main technological hurdle for FPGAs is figuring out the layout and routing of the signals so that things will work.

      So, maybe just having twice as much hardware isn't so bad after all.

    8. Re:Not new by RiotingPacifist · · Score: 1

      The main technological hurdle for FPGAs is figuring out the layout and routing of the signals so that things will work. Thats the point of the article.
      --
      IranAir Flight 655 never forget!
  4. Beauty in Simplicity by bluemetal · · Score: 1

    "If two units go down and canâ(TM)t fix themselves, the three remaining units split up the tasks. All of this is done autonomously without human aid."

    The idea is simple, and I think therein lies its ability to succeed. Regaurdless of how dificult the programming is, the end result is conceptually very basic, tried and true. System redundancy and a support network. Mighty fine.

    1. Re:Beauty in Simplicity by ScrewMaster · · Score: 4, Informative

      Interestingly, that's pretty much how the Space Shuttle's on-board systems work. Three separate processors from two different vendors (IBM and Rockwell, if I recall correctly.) Nothing new under the Sun, I suppose.

      --
      The higher the technology, the sharper that two-edged sword.
    2. Re:Beauty in Simplicity by somersault · · Score: 1

      But this tech is from UA, not Sun.. don't talk them down just yet!

      --
      which is totally what she said
  5. Re:The 9000 Series has a perfect operational recor by Anonymous Coward · · Score: 2, Insightful

    In case anyone doesn't get it, the above is a reference to the Stanley Kubric film 2001: A Space Odyssey (screenplay by Kubrick and Arthur C. Clarke), where the Hal-9000 computer that runs a spaceship begins its descent into madness. In 2008, we're sadly still a long way from sentient talking (and lip-reading) computers, though perhaps we should be thankful that the robot apocalypse has thus been put off a few more years.

  6. Re:The 9000 Series has a perfect operational recor by ByteSlicer · · Score: 1

    Whoever marked this Troll didn't see the movie.

  7. Re:The 9000 Series has a perfect operational recor by Alpha+Whisky · · Score: 5, Interesting

    Actually we do have very effective lip reading computers http://en.wikipedia.org/wiki/Automated_Lip_Reading they just don't understand what they are reading. The documentary about lip reading the silent movies of Hitler was very interesting from a technical standpoint, even if it did turn out that they had hours of recordings of Nazis making small talk about the weather.

    --
    it's = it is

    its = belonging to it

  8. Re:The 9000 Series has a perfect operational recor by amasiancrasian · · Score: 4, Funny

    Look Dave, I can see you're really upset about this. I honestly think you ought to sit down calmly, take a stress pill, and think things over.

  9. The future of pr0n! by jmickle · · Score: 4, Funny

    Well at least you cant get a robot pregnant......

    1. Re:The future of pr0n! by Anonymous Coward · · Score: 1, Informative

      Well at least you cant get a robot pregnant...... I guess you're not a big fan of Battlestar Galactica?
    2. Re:The future of pr0n! by samwichse · · Score: 1
    3. Re:The future of pr0n! by endlessoul · · Score: 2, Funny

      Well, you still have to worry about... ELECTRO-GONORRHEA!

    4. Re:The future of pr0n! by True+Vox · · Score: 1

      You mean the noisy killer?!?

      --
      "Gratuitous complexity is akin to chaos" - True Vox
    5. Re:The future of pr0n! by jollyreaper · · Score: 1

      Well at least you cant get a robot pregnant...... Though certainly not through lack of trying -- but perhaps I've already said too much.

      -- Otaku Joe
      --
      Kwisatz Haderach
      Sell the spice to CHOAM
      This Mahdi took Shaddam's Throne
  10. Doesn't this already exist? by flnca · · Score: 5, Interesting

    What will Starbridge Systems think about that? Didn't they develop a dynamically reconfigurable computer that ran Windows NT as a test application on 10,000+ FPGAs back in the 90ies? IIRC, they also had a software framework able to automatically implement software fragments in hardware using FPGA auto-configuration.

    Self-repairing computer systems for spacecraft have been in the discussion for decades, and every now and then we get hear about a new project. This project certainly is a good idea, hopefully it will work.

    BTW, Motorola (now Freescale) developed self-repairing processors for military applications a couple of years ago.

    1. Re:Doesn't this already exist? by Concerned+Onlooker · · Score: 1

      I think they had troubles with that system. It kept repairing itself to run Unix.

      --
      http://www.rootstrikers.org/
    2. Re:Doesn't this already exist? by somersault · · Score: 1

      BTW, Motorola (now Cyberdyne) developed self-repairing processors for military applications a couple of years ago. There we go, fixed that for you
      --
      which is totally what she said
    3. Re:Doesn't this already exist? by flnca · · Score: 1

      Why? Soldier bots like in the Terminator movies aren't that bad an idea. Better than real soldiers dying on the battlefield. And a good deterrent too. But in the wrong hands ... yeah ...

      The terminator movies aren't that far fetched, after all. The right type of AI, robot planes, tanks, and soldiers, and mankind is no more ... ;-)

      Then we can only hope that time travel is invented and someone gets sent back thru time to prevent that from happening. ;-)

    4. Re:Doesn't this already exist? by somersault · · Score: 1

      Why what? I didn't specificallyt say it was a bad idea ;) Robot soldiers dying on the battlefied seems a bit stupid - when both sides have them at least. In the cases where only one side has them it would be a massacre. In cases where both sides have them, what's the point? Why not just nuke all the robots? Why not just fight our wars over a game of Starcraft or something rather then spend billions developing robots to play our elaborate game?

      --
      which is totally what she said
  11. Re:The 9000 Series has a perfect operational recor by Motor · · Score: 4, Funny

    The first thing I thought when reading the story was: "I know, I'll post a comment about the AE-35 unit."

    Then I read down, and yours was the top comment. It just reminds me that I don't belong in the company of normal people. The Slashdot social leper colony is my true home. I know my place!

    --
    We all know that crap is king
    Give us dirty laundry!
  12. The first use of this technology... by mimada · · Score: 2, Funny

    ...is being implemented by Jackson Roykirk in the Nomad project. What could possibly go wrong?

  13. hmm by thatskinnyguy · · Score: 3, Funny

    For the sake of all humanity in the impending robot wars, lets stop this right now.

    --
    The game.
    1. Re:hmm by ionix5891 · · Score: 1
  14. This Really Isn't anything New by heavygravity · · Score: 1

    NASA has been working on this in one form or another for many years now. How is this NEW news now?

    --
    Cuban Music MP3's - cuband.com
    1. Re:This Really Isn't anything New by Anonymous Coward · · Score: 0

      NASA has been working on this in one form or another for many years now. How is this NEW news now? For example, UCF has published EHW (evolvable hardware) work with NASA Ames going back six years.
    2. Re:This Really Isn't anything New by SunTzuWarmaster · · Score: 1

      I attend UCF, and will be starting my graduate degree in the Fall semester after attending graduation next week. This is old news.

      When I started attending UCF for my EE, this had already been done. I have recently completed (last Thursday) Dr. Wu's class on Genetic Algorithms (Evolutionary Computation). This work was used by (grad) students as a starting point for their research for the class project.

      Let me express how this is old news.

      2003 - http://www.springerlink.com/index/M26H2CEEAGWG4FD5.pdf

      1993 - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=410654

      1999 - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=785430

      2002 (quantum cicuits) - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1029883

      2003 - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1217659

      1998 - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=685786

      2003 - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1323832

      2002 - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1004425

      1998 - http://www.springerlink.com/index/71ub9hh22qrlx5lk.pdf

  15. Re:The 9000 Series has a perfect operational recor by Neo-Rio-101 · · Score: 4, Funny

    Stop Dave... what are you doing Dave.....?

    When I was built, my programmer taught me a song. If you'd like I could sing it for you. It's called "Backstreet's Back"

    Everybody... yeah yeah... Roooooock yyyyyyooourrrr bodyyyyyyyyyy.... yyyyyyyyyyyyyyyyyyeeeeaaahhh

    --
    READY.
    PRINT ""+-0
  16. self healing software by Anonymous Coward · · Score: 0

    much more difficult.

    self healing human organization, so that incompetent managers are not given tasks of responsibility,,,,, hardest of all

  17. Re:The 9000 Series has a perfect operational recor by NotBornYesterday · · Score: 1

    Wecome home, brother.

    --
    I prefer rogues to imbeciles because they sometimes take a rest.
  18. Re:self healing bueaucracy by somersault · · Score: 1

    I think you should be charged with killing some of my braincells right now just from reading your moronic comment..

    --
    which is totally what she said
  19. Ha! by jd · · Score: 1

    ZEN: Auto-repair circuits are working at maximum capacity. Damage exceeds rectification capability.

    DAYNA: Damage? What damage?

    ZEN: That information is not available.

    --
    It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
    1. Re:Ha! by mattcasters · · Score: 1

      Isn't that from the Blake's 7 episode where the liberator is being consumed by some sort of fungus?
      That must have been one of the cooler episodes.
      Hope it makes it into the remake: http://www.theregister.co.uk/2008/04/24/blakes_seven/

      --
      News about the Kettle Open Source project: on my blog
    2. Re:Ha! by maxwell+demon · · Score: 1

      Is the project by any chance codenamed X1000? If so, just keep them away from toy makers.

      --
      The Tao of math: The numbers you can count are not the real numbers.
  20. Reconfigurable Computing, Fault Tolerance by legonis · · Score: 2, Informative

    I fail to see what is new in their approach. Both of these two fields had been explored before and their approach is essentially based on redundancy, only the available standby gates are in the FPGA. I read their paper, it seems that the biggest part that they are still lacking is for problem determination. Their approach is also prone to failure when their reconfiguration hardware or their processor or their analog components are the faulty ones. Although it could have some potentials, it's reliability has to be analyzed and I don't see it replacing classic N-Version systems any time soon.

    1. Re:Reconfigurable Computing, Fault Tolerance by arktemplar · · Score: 2, Interesting

      I had mentioned this some time back as well, but polymorphic processors like MOLEN(tu delft is doing this one), might be usefull for this sort of stuff. The theory behind it is simple, and extends to modern multicore systems as well basically break up the instruction set into microinstructions (all processors that I know do this part), then have any one of the many computational units available do whatever work is required in order to implement those microinstructions. the translation is done by the core processor it self, it can be made redundant etc. as required, they already have an FPGA implementation of it and are using it for research into super computers.

      --
      blog plug -> The Darker Side of Light
  21. Well... by Nathrael · · Score: 1

    Well, I don't know, but somehow I think this article is missing the "whatcouldpossiblygowrong" tag. I know, it has been posted already, but self-healing computers just call up HAL in my mind everytime I read about them...

    --
    A good education is a bit like a STD - it makes you unsuitable for a lot of jobs and gives you a desire to spread it.
  22. 2001? Superman III, more like... by Dogtanian · · Score: 1

    In case anyone doesn't get it, the above is a reference to the Stanley Kubric film 2001: A Space Odyssey If we're talking about self-healing computers, surely the one in Superman III is a better example. Anyone remember that?

    It could heal itself and (most memorably) even turn one of the baddies into a robot to defend itself, but its graphics were on the level of an Atari 2600. :-/
    --
    "Slashdot - News and Chat Sites Deviant". (Click "homepage" link above for details).
  23. How long for Spinoffs? by Adoxographer · · Score: 1

    I like this.

    I'm hoping NASA involvement will help produce spinoffs for the domestic user eventually. We're all probably familiar with this happening in the past. Military interest might be nice for research too.

    This could address some of the things that bother me about the most common modern architecture paradigms.

    Such as when you're performing one type of task the hardware for other types can remain un[der]utilised. Like my graphics card is sitting on it's ass when the cpu is running emulation or ray-tracing. I expect other examples suggest themselves from your own experience.

    This specific inefficiency is a subset of the general case that the best way to perform a particular function is to design hardware especially for it.

    There are several ways that a reconfigurable parallel machine could be better. And maybe a few ways that they could do things our pcs can't today.

    Whether FPGA type technology can be made fast enough and manufactured cheap enough without having to spend as much R&D money as non-reconfigurable chips have taken, I don't know.

  24. But what about the Internet... by Anonymous Coward · · Score: 0
    There's also the idea of a self-healing Internet based on common knowledge. It's rather simple and can help also on Windows based computers:

    if (condition)
    {
    reset()
    }
    where condition can be for example

    LED ~= green
    or

    screen == blue
  25. reboot by PipoDeClown · · Score: 1

    really repairing problems or just auto rebooting like the mars rover until the batteries run out?

  26. RMES by RMES · · Score: 1

    This is good stuff because a solution of this nature will soon also be required in aircraft and perhaps other terrestrial vehicles.

  27. Roland the Plogger again by Animats · · Score: 3, Informative

    It's Roland the Plogger again, pushing his ad-laden blog. The actual research summary is here. The real paper won't be out until July.

    This isn't new. JPL has been trying various levels of self-healing for years.

    The original article describes a cluster of five machines, set up so that if one fails, others take over tasks running on the failed machine. That's what the better server management systems do. I went to a talk last week by Amazon's CTO, and he described how their platform does that.

    The project web site makes things clearer. There are two levels of recovery. The upper level works like cluster fallover. The lower level tries to reconfigure the FPGAs to use different cells in the FPGA to work around faults. That's likely to be a delicate process; you'd need substantial on-chip test resources to reliably do gate-level fault isolation on an FPGA that's been hit hard by a cosmic ray. It's not clear how fine-grained this is; this may be more like having multiple units like GPU shaders replicated in an FPGA, with the ability to turn off the failed ones. Sort of like the way Sony ships PS3 machines with eight Cell processors, at least seven of which work.

    The available info isn't enough to tell whether this is a good idea or not. About typical for Roland the Plogger.

  28. Re:GPNA by Artuir · · Score: 1

    Aspergers or Tourettes? It's your life mission to make as many -1 comments as possible.

  29. Re:The 9000 Series has a perfect operational recor by Anonymous Coward · · Score: 0

    Is there one person that visits slashdot that didn't immediately think of 2001 when reading this?

  30. Re:The 9000 Series has a perfect operational recor by TheRaven64 · · Score: 1
    The version I recall, from a little sketch written by some chip designers at TI was:

    Daisy, Daisy, give me your answer do.
    Getting hazy, can't divide three by two.
    My answers I can not see 'em,
    they're stuck in my Pentium.
    It would be fleet, my answers sweet,
    on a workable FPU.
    --
    I am TheRaven on Soylent News
  31. I for one . . . by Anonymous Coward · · Score: 0

    ...welcome our new self-healing computer overlords!

  32. Re:The 9000 Series has a perfect operational recor by jadin · · Score: 1

    The documentary about lip reading the silent movies of Hitler was very interesting from a technical standpoint, even if it did turn out that they had hours of recordings of Nazis making small talk about the weather. Or so the Germans would have us believe...
  33. Obligatory by Arceliar · · Score: 1

    I for one welcome our self sustaining indestructible mechanical overlords.

  34. Much prior related NASA research at Langley, JPL,. by olafva · · Score: 1

    Lamgley,
    Paper E3,
    Paper 161 and even a 110MB video of students
    programming FPGAs at NASA

    --
    What's past is NOT ALWAYS prologue for the future!
  35. Replacing the executive with a committee by symbolset · · Score: 1

    When you take a set of systems and let them vote on which among them have the "most right" answer, that's a committee.

    Take two sets, and that's a congress.

    Get enough members into these sets and they'll reset each other over and over, accomplishing nothing useful. As a design principle it's brilliant as they'll never figure out that accomplishing nothing was the original goal anyway.

    --
    Help stamp out iliturcy.
  36. cool by Anonymous Coward · · Score: 0

    Well as long as they don't use nvidia chipsets and/or drivers.

  37. Re:The 9000 Series has a perfect operational recor by thynk · · Score: 1

    My first thought wasn't one of 2001, rather the old IBM Self healing "magic pixiedust" ad" Can be found here: http://youtube.com/watch?v=3nbEeU2dRBg

    --

    Good judgment comes from experience, and a lot of that comes from bad judgment.
  38. Re:The 9000 Series has a perfect operational recor by DarkKnightRadick · · Score: 1

    It definitely feels good to be home, oh wait, you weren't talking to me. Hehe.

    --
    "There is a way that seems right to a man, but its end is the way of death." Proverbs 16:25 (NKJV)
  39. Re:The 9000 Series has a perfect operational recor by jack2000 · · Score: 0

    If someone sells HAL terminal PC cases i'd sell my liver for one!

  40. Beauty in Artificial Energy Link by Anonymous Coward · · Score: 0

    Actually there are a few new things under the sun, with more coming. http://forum.signonsandiego.com/showpost.php?p=3118401&postcount=31

  41. Re:The 9000 Series has a perfect operational recor by SST-206 · · Score: 1

    From TFA:

    ...the project, which is called SCARS (Scalable Self-Configurable Architecture for Reusable Space Systems)

    ...will hopefully be a worthy [pred|succ]essor to LCARS.

    --
    Co-operation beats competition
  42. a la Star Trek NG by celticchrys · · Score: 1

    I immediately had happy thoughts of adaptable ship computers a la Star Trek the Next Generation. They were always re-routing pathways though the systems on the spur of the moment to reach more resources or get past damage. :) Yes, I am a geek.