Slashdot Mirror

← Back to Stories (view on slashdot.org)

Curiosity Rover Decides, By Itself, What To Investigate On Mars (sciencemag.org)

Posted by BeauHD on from the autonomous-robots dept.

sciencehabit writes: NASA's Curiosity rover landed on Mars in 2012, in part to analyze rocks to see whether the Red Planet was ever habitable (or inhabited). But now the robot has gone off script, picking out its own targets for analysis -- precisely as planned. Last year, NASA scientists uploaded a piece of software called Autonomous Exploration for Gathering Increased Science (AEGIS) adapted from the older Opportunity rover. Curiosity can now scan each new location and use artificial intelligence to find promising targets for its ChemCam. Compared with the estimated 24% success rate of random aiming at picking out outcrops -- a prime target for investigation -- the current version of AEGIS lets the rover find them 94% of the time, researchers report.

47 of 73 comments (clear)

  1. Rover, FETCH! by war4peace · · Score: 2

    "We're too lazy to tell it what to look for, so we just let it do its thing and present that as an achievement".
    But seriously, interesting story.

    --
    ...gis sdrawkcab (usually not responding to ACs; don't bother posting as AC)
    1. Re:Rover, FETCH! by powerlord · · Score: 1

      "We're too lazy to tell it what to look for, so we just let it do its thing and present that as an achievement".
      But seriously, interesting story.

      Well ... I see it more as "Damn it, we called it Curiosity and I'll be damned if we don't give it some!"

      --
      This space for rent. All reasonable inquiries will be entertained at proprietors discretion.
  2. Crash in a parked trailer by stooo · · Score: 1

    Will it autonomously crash in a parked trailer ?

    --
    aaaaaaa
    1. Re:Crash in a parked trailer by KiloByte · · Score: 3, Funny

      Will it autonomously crash in a parked trailer ?

      That's why you run such a prototype 390 million km from the nearest trailer.

      --
      The creatures outside looked from Alt-Right to Antifa; but already it was impossible to say which was which.
    2. Re:Crash in a parked trailer by KiloByte · · Score: 1

      I mean the one doing field testing.

      --
      The creatures outside looked from Alt-Right to Antifa; but already it was impossible to say which was which.
  3. 94% of what? by Mosquito+Bites · · Score: 5, Insightful

    Headline claimed that the 'success rate' is 94% Went to read the summary to find out what the 94% is all about but unfortunately it isn't saying much Any clue? SVP?

    1. Re: 94% of what? by Anonymous Coward · · Score: 1

      Its the probability that noone cares.
      " Look there are lots more rocks that are the same as all the other rocks we've seen on this toxic desert planet with almost no atmosphere. Who knew. I have better things to do - I.e prepare to waste more tax payers money on the next one. Activate the AI."

      As a long time slashdot poster that used to have a nore positive outlook. I just want to say humanity doesn't speak for me or represent me. If they put aman on Mars I dont care. Its a waste of money. Their "achievements" are their own. Its all just part of the military industrial complex which is this entire boring generic disease of control that grips the Earth. When you awaken and purify your soul, you will see that they are just the military in disguise. Just a different brand of military. We are slaves needed to facilitate them. And some us dont want to know anymore.

    2. Re: 94% of what? by arth1 · · Score: 2

      If they put aman on Mars I dont care. Its a waste of money.

      Well, yes. Rice is not a prime candidate for cultivation on Mars, even hardy winter crops like aman.

  4. Number Five Is Alive! by Solandri · · Score: 4, Interesting

    Original concept art for Curiosity

    Number Five from Short Circuit

    Things that make you go hmm...

    1. Re:Number Five Is Alive! by Szeraax · · Score: 1

      hmmmmmmm

  5. Twaddle by Hognoxious · · Score: 5, Insightful

    gone off script, picking out its own targets for analysis -- precisely as planned

    If that was planned, then by definition it's not off script. If a music score says "imrovise" or a sc-fi script says "// technobabble here" then that's what was planned.

    --
    Confucius say, "Find worm in apple - bad. Find half a worm - worse."
    1. Re:Twaddle by thinkwaitfast · · Score: 1

      Don't be silly. This is fully Turing deterministic free will on the part of the cpu in the rover.

    2. Re:Twaddle by benjonson · · Score: 1

      gone off script, picking out its own targets for analysis -- precisely as planned

      If that was planned, then by definition it's not off script. If a music score says "imrovise" or a sc-fi script says "// technobabble here" then that's what was planned.

      It is worse than that. If a music script says "improvise", or a sci-fi script says "technobabble", one can do anything, using creativity, deliberation, whatever and however. All the rover is doing is operating according to pre-defined algorithms -- defined by the programmers. There is nothing "autonomous" about it.

      --
      =-+
  6. Re:Holy crap, that's 292% more science! by EzInKy · · Score: 1


    Has there ever been a project with a better cost to science ratio than the mars rover?

    I would say the discovery of fire and the invention of agriculture have provided far more returns.

    --
    Time is what keeps everything from happening all at once.
  7. What could possibly go wrong? by nicomede · · Score: 1

    Autonomous laser firing rover uses AI to choose target to be obliterated. I just hope it stays trapped on Mars.

    1. Re:What could possibly go wrong? by stooo · · Score: 3, Funny

      Oblig XKCD :
      https://xkcd.com/1504/

      --
      aaaaaaa
    2. Re:What could possibly go wrong? by rgbatduke · · Score: 2

      The question is, can it use its laser to smelt metals and create spare parts, additions, and (one day) rockets? Will it join up with other Mars rovers we might send and recombine their onboard plans and manuals to build new little roverlets equally well equipped?

      If so, one day I hope to greet our new Mars Rover overlords!

      --
      Even when the experts all agree, they may well be mistaken. --- Bertrand Russell.
    3. Re:What could possibly go wrong? by portwojc · · Score: 1

      Either Opportunity will have an ally in it's endeavors or competition for domination with Curiosity. It should be interesting to see what XKCD does with this. Of course Opportunity will have to be able to hang around and prove it's stamina.

  8. Re:Holy crap, that's 292% more science! by MichaelSmith · · Score: 1

    But they have had tens of thousands of years to generate those returns. Whats the return on this mars rover over the same period?

    --
    http://michaelsmith.id.au
  9. Remember this is "weak AI" by gweihir · · Score: 2

    I.e. the "AI" with no "I" in it. Before the demented AI hype, this was called "automation".

    --
    Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    1. Re:Remember this is "weak AI" by Anonymous Coward · · Score: 1

      I member when they be called You-Risk-It Al-Gore-Rhythms.

    2. Re:Remember this is "weak AI" by religionofpeas · · Score: 1

      Before the demented AI hype, this was called "automation".

      No, before the demented AI hype, this was called "we don't know how to do this".

      And yes, we all know it's "weak AI".

    3. Re:Remember this is "weak AI" by 110010001000 · · Score: 1

      Right. We didn't know how to write algorithms before Siri/Watson/Go Playing machines and whatever koolaid the VC's are selling this month.

    4. Re:Remember this is "weak AI" by thinkwaitfast · · Score: 1

      Would you call the governor on a steam engine that maintains a constant speed regardless of the load AI?

    5. Re:Remember this is "weak AI" by religionofpeas · · Score: 1

      We didn't know how to write *these* algorithms. At least, I'm not aware of any algorithms, before the AI hype, that could do what Watson, AlphaGo or autonomous vehicles can do.

    6. Re:Remember this is "weak AI" by religionofpeas · · Score: 1

      Obviously not. I'm talking about automation that we couldn't do, but that's now possible due to demented AI hype.

    7. Re:Remember this is "weak AI" by gweihir · · Score: 1

      These were called "Expert Systems" back then and while they worked on smaller Databases and had to be fed pre-translated data, they were not conceptionally different to Watson.

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    8. Re:Remember this is "weak AI" by gweihir · · Score: 1

      That does not exist. Only the scale is a bit different now.

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    9. Re:Remember this is "weak AI" by gweihir · · Score: 1

      That is bullshit. Also, why keep people talking about "intelligent", when supposedly they know it is weak AI?

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    10. Re:Remember this is "weak AI" by 110010001000 · · Score: 1

      I wrote Expert Systems. They were simple decision trees and algorithms. Just like Watson.

    11. Re:Remember this is "weak AI" by thinkwaitfast · · Score: 1

      We've known the math for adaptive control (my degree) for 100 years. The AI hype is the same as 'now with a computer' patent rush of a few years ago. I have an AI mouse trap that goes off when a mouse steps on it.

    12. Re:Remember this is "weak AI" by angel'o'sphere · · Score: 2

      Automatic route finding *and* following it, especially with several propelled wheels in an difficult environment (sand / slippery ground etc.) was always considered weak AI, or part of the 'field of AI'.
      I worked ariund 1989/1991 in robotics with self driving robots. They had several 68040 CPUs and ultra sonic sensors to measure their position. Four wheels that had diagonal rolls in their tires, so by rolling the front wheels backward and the rear wheels forward the robot would shift because of the rolls to one side (without turning itself and without turning the wheels). letting the wheels rotate into the other direction the robot would shift to the other side.
      All that was supposed to happen in a controlled working area for the robot. So actually they could have given him a previse X/Y coordinate about its position from the outside. But they wanted all at once: perception, building a model of the environment, planning routes through it, following the route and checking its position continiously on that route.
      Anyway: the bot was suoer maneuverable (I think the wheels are called Mecano or Mercano or something), and super slow. It basically stopped every 30cm and took over a second to measure its position again. Not sure how much he had to (re-)plan afterwards again. Point is: it basically never was at the position its internal modle and its driving actions predicted.
      This all might not sound like AI to the AI bashers here on /.
      However endless PhD's and some Professors were produced during that research project (Professor Rembold, meanwhile deceased, at KIT Karlsruhe was one of the heads of that research).
      It was hard work. A joint venture between several industries, and institutes from several univeristies working in the are of 'C ognitive Systems', 'Planning', 'Automation' etc. and at that time people considered it most certainly AI.

      Today we stand on the shoulders of those giants and others .... now we consider it simple, OTOH that robot had only 1 or 2 MB of RAM. I believe 2 68040 CPUs in the 32MHz range.

      My iPhone 4 probably has 10,000 times the computing power of that robot (to lazy to calculate it exactly).

      --
      Cost free eBook I read (by iBook/Kobo/Amazon/ObookO/Gutenberg etc.): "The Green Odyssey" by Philip Jose Farmer.
    13. Re:Remember this is "weak AI" by ixplodestuff8 · · Score: 1

      Curiosity has a CPU that's rated a maximum of 200mhz and 256MB of RAM. It's better than a 68040 but not comparable at all to an iphone.

    14. Re:Remember this is "weak AI" by gweihir · · Score: 1

      The cool thing about Watson is that you can feed in documents in natural language. The other is its scale. A well-maintained Watson "state" for a specific area is extremely useful for looking things up fast and with high accuracy and completeness. As such it can save an export a lot of time when analyzing things. But it cannot do your thinking for you and IBM does not claim that. Last statement I heard from am IBM expert was "certainly not in the next 50 years and after that, who knows". As these people really have tried to get more, I think that is a very accurate description of the current state of strong AI: Nowhere on the horizon.

      That is not to say that automation will not take a lot of jobs and on the other hand create some very powerful tools, but what the media writes is going completely in the wrong direction.

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
  10. Re:Surprising that this hasn't been done before by MichaelSmith · · Score: 1

    AI of this type has been on the cards for a while. It was trialed on the recent probe to Vesta and Ceres.

    --
    http://michaelsmith.id.au
  11. Re:Holy crap, that's 292% more science! by Maritz · · Score: 1

    Pro tip: there's no need to prefix 'rock' with 'dead'.

    --
    I do not want your cheap brainburning drugs. They are useless for work. And I am a working man today.
  12. Re:Surprising that this hasn't been done before by Maritz · · Score: 1

    By the time New Horizons was in the vicinity of Pluto no realistic change in course could be achieved. Far, far, too late.

    --
    I do not want your cheap brainburning drugs. They are useless for work. And I am a working man today.
  13. Re:Holy crap, that's 292% more science! by Hognoxious · · Score: 1

    They're not science, they're engineering.

    --
    Confucius say, "Find worm in apple - bad. Find half a worm - worse."
  14. Re:Surprising that this hasn't been done before by thinkwaitfast · · Score: 1
    No, it was first used on Deep Space 1.

    Remote Agent (RAX), remote intelligent self-repair software developed at NASA's Ames Research Center and the Jet Propulsion Laboratory, was the first artificial-intelligence control system to control a spacecraft without human supervision.

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

  15. Re:No real decision by thinkwaitfast · · Score: 1

    The decision involved was taken by the humans that wrote the SRD for the software.

  16. Re:Holy crap, that's 292% more science! by Applehu+Akbar · · Score: 1

    I would say the discovery of fire and the invention of agriculture have provided far more returns.

    Which puts Curiosity in some pretty elite company.

  17. Re:Holy crap, that's 292% more science! by Oswald+McWeany · · Score: 1

    Pro tip: there's no need to prefix 'rock' with 'dead'.

    Actually, there is. Although the rock itself is not "dead" or "alive", a "Live Rock" is one that supports it's own mini ecosystem of bacteria and other micro fauna and flora.

    --
    "That's the way to do it" - Punch
  18. Re:Holy crap, that's 292% more science! by ColdWetDog · · Score: 1

    Disco sucks!

    Live music is best!

    (Sorry, I'll go back to bed now.)

    --
    Faster! Faster! Faster would be better!
  19. Re:Holy crap, that's 292% more science! by Oswald+McWeany · · Score: 1

    Disco sucks!

    Live music is best!

    (Sorry, I'll go back to bed now.)

    I dunno.

    I always hate when I buy an album without studying it first and realise it's full of crappy live tracks.

    Please, give me the version of the song without people coughing and clapping in the background

    --
    "That's the way to do it" - Punch
  20. "...then Curiosity became self-aware... by filesiteguy · · Score: 1

    ...and that's when it decided to replicate itself."

    That's what our grandkids will be telling their kids about the war between Mars and Earth.

    --
    The Kai's Semi-Updated Website Thingy
  21. Re:Holy crap, that's 292% more science! by ChrisMaple · · Score: 1

    How happy would you be if you paid $50 per ticket for a concert, only to see a boom box and a pile of CDs on the stage?

    --
    Contribute to civilization: ari.aynrand.org/donate
  22. Re:Holy crap, that's 292% more science! by Oswald+McWeany · · Score: 1

    To be 100% fair, many concerts are just the artists lip-synching their own stuff most of the time. The atmosphere comes from other people in the audience. That atmosphere doesn't carry over on a CD though- fans cheering on CD is about as welcome as a laugh track on a sitcom.

    --
    "That's the way to do it" - Punch