Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
Mars AI Robotics Software Space Hardware Technology

Curiosity Rover Decides, By Itself, What To Investigate On Mars (sciencemag.org) 73

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.
This discussion has been archived. No new comments can be posted.

Curiosity Rover Decides, By Itself, What To Investigate On Mars

Comments Filter:
  • by war4peace ( 1628283 ) on Thursday June 22, 2017 @02:05AM (#54666459)

    "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.

    • 94% of what? (Score:5, Insightful)

      by Mosquito Bites ( 4975333 ) on Thursday June 22, 2017 @02:21AM (#54666497)
      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?
      • by Anonymous Coward

        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 "achievemen

        • by arth1 ( 260657 )

          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.

    • "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!"

  • Will it autonomously crash in a parked trailer ?

  • by Solandri ( 704621 ) on Thursday June 22, 2017 @02:23AM (#54666509)
    Original concept art for Curiosity [nasa.gov]

    Number Five from Short Circuit [ssl-images-amazon.com]

    Things that make you go hmm...
  • Twaddle (Score:5, Insightful)

    by Hognoxious ( 631665 ) on Thursday June 22, 2017 @02:30AM (#54666517) Homepage Journal

    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.

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

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

  • by gweihir ( 88907 ) on Thursday June 22, 2017 @04:38AM (#54666849)

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

    • by Anonymous Coward

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

    • 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".

      • 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.
        • 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.

          • by gweihir ( 88907 )

            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.

            • I wrote Expert Systems. They were simple decision trees and algorithms. Just like Watson.
              • by gweihir ( 88907 )

                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 rea

      • Would you call the governor on a steam engine that maintains a constant speed regardless of the load AI?
      • by gweihir ( 88907 )

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

    • 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

      • 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.
  • We know how it ended. [xkcd.com] Now we know where /how it started.
  • ...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.

"If value corrupts then absolute value corrupts absolutely."

Working...