Computer Makes Robot Offspring 230
Flarenet writes: "Canoe.ca is reporting about a story where: 'A computer programmed to follow the rules of evolution has for the first time designed and manufactured simple robots with minimal help from people.'" This is a nicely satisfying result of the research (mentioned in an earlier Slashdot story) by Jordan Pollack and Hod Lipson of Brandeis University.
"Dave ..." (Score:2)
Software to do the simulation yourself (Score:4)
What is the Matrix? (Score:2)
This is exactly what I was talking about!!! (Score:3)
I predicted this!! It's not all that surprising , considering the History of the Universe. Man has always sought to live on through his inventions, and for good reason. With intelligent beings having been created by us, we can, in essence, as a race - mankind, live on. Let me explain why I said that humans have been striving for this for so long. Of course, BTW, this is just the beginning and to get "truly" smart Robots, more advanced hardware, software, and nanotechnology will all need to be incorporated. Now...why did I say that mankind has always wanted to "live on"? here's why:
In the beginning of the Universe, there were 3 races. Humans, elves and dwarves. The three races lived in harmony for centuries. They continually sought together to find and maintain the delicate balance between the Spiritual, Magical and Physical properties of the world. But the humans grew weary of their lifespans. The typical human lifespan was 60 years. The typical Dwarven lifespan was 300, and the typical Elven lifespan was 500. The humans deemed this unfair. Soon a new religion swept the land, mainly attracting humans: Science. They propogated physical properties while neglecting their spiritual and magical properties. Soon they developed powerful new weapons such as crossbows, gunpowder, and chemical explosives. While Elven magic was still prevalent, the Dwarves had no protection against the new human weapons, but to replicate them, for they too were good at Physical and Mechanical engineering. But the humans had a lot more practice and developing such weapons, had more confidenence and drive, and outnumbered both Dwarves and Elves. So the Dwarves tried to make peace with the humans and help them - but the humans refused the help and destroyed the Dwarves completely. The Elven wizards killed thousands of humans, but only 1 in 10000 was an Elf wizard. 3/10 humans were capable bowmen, gunmen, or explosive users. So, in vast battles, 3 000 000 gunmen, crossbowmen and explosive users faced 10 000 wizards and 300 000 pike/sword/longbow-men.The Elves put up a fight, but after a while, were destroyed. There were centuries of fantastic battles: Magic vs Science, the Lightning of Power vs the Destruction of Science, and the human factories and Elven towers were destroyed around them. In the end , few humans remained, but no Elves at all remained. The humans had lost their science and knowledge, and the Elves had lost their very species. Centuries later, we are where we are today.
I'm sorry if this displeases Christian fanatics who disagree with the truth - the truth of the Universe as I've outlined it here, but....well, too bad.Just my $0.02
This is How "God" Was Created (Score:2)
Reproduction (Score:4)
Ha ha ha! We're unstoppable!
MyopicProwls
We need a new moderation category (Score:4)
How does a robot discipline it's offspring? (Score:4)
"Go to your point of origin and execute an infinite loop for 10 billion ticks! No more hydraulic fluid! Wipe that smirk off your face, or I'll impact it off for you!"
Something else they should work on... (Score:1)
An obvious cynical response by me. (Score:1)
Whatever.
Wake me up when a computer designs a better version of itself.
Interesting but.. (Score:4)
Re:"Dave ..." (Score:1)
but then is than around here
Re:What is the Matrix? (Score:2)
With vastly superior processing power (e.g. quantum computers), there probably wouldn't even be a need for open source. And that's assuming superpowerful computer entities would need to be networked. You're enforcing human ideals on technological creations.
Well... (Score:4)
Re:Something else they should work on... (Score:4)
This is not reproduction (Score:5)
"Robot offspring" implies there is some sort of reproduction going on, and this is NOT that. [insert obligatory beatdown of the exaggerating, stupid media].
More accurately, this is a computer using a novel technique to design a machine with minimal human programming, and hooking up the computer to a manufacturing machine.
Having a computer actually design a working machine is impressive enough without screaming about a computer generating its "offspring". And I have to say, it's somewhat pathetic that Slashdot dfollows along. Can I suggest changing the headline to "Computer creates its own design for a machine" or even if you want to be whimsical, "First generation Deep Thought takes first step at creating 'the computer that is to come after me, a computer that even I am not worthy to calculate its operational parameters'. But that's a little long. :)
--
Throw in some more relavent links (Score:1)
Fear not! (Score:2)
re: How does a robot discipline it's offspring? (Score:3)
Something Similar (Score:2)
The experiment had the evolution program design thousands of simlar functioning circuits that would respond to the words "stop" and "go". Each design was then tested and rated on it's responsiveness. These ratings where then feed back into the program and it ran another interation.
This process proceeded for some amount of time (I can't remember) and the final circuit that came out for the FPGA made practicaly no sense but worked. The circuit had dead end branches, no known method of timing and a few other things. But somehow everything mattered because when one of the "dead" branches was removed it no longer functioned.
Isn't science and evolution amazing
Re:Well... (Score:2)
How do you know we haven't... I mean they haven't... I mean...
Darn. Not smart enough yet. Need to run myself through a few million more generations.
hmm...Marvin? (Score:1)
Re:"Dave ..." (Score:1)
Maybe the guy thought Dave was floating around in a bomb, and that's why HAL wouldn't let him in...
--
Oh yeah! (Score:2)
I would love to se the MPAA sue a robot.
Uh-Oh (Score:5)
Re:Interesting but.. (Score:1)
It will be interesting to see if their software evolves to use federations of computers (like distributed.net) or clusters. This would allow testing of a much wider variety of base components and much larger composite constructs.
Re:"Dave ..." (Score:1)
I finally got it, than I found it to be funnier then anything I've seen today.
Those guys over their need to stop relying on spellcheck and pay attention to context. They're sentences make no sense. There all so stupid.
George Jetson (Score:1)
now if we can just get a three day work-week.
Empty hype (Score:2)
And yet the computer didn't produce a simple wheeled vehicle. This seems to be nothing more than hype to me. How were the intermediate designs evaluated and selected (the crux of any genetic algorithm)? Wouldn't it have been much more impressive if the computer had developed the simple, yet extremely efficient, wheel independantly?
Re:Something else they should work on... (Score:1)
didn't check for Win2000 compatibility, but here's a link to v1.19 http://www.demo.cs
Re:Software to do the simulation yourself (Score:4)
Re:Interesting but.. (Score:2)
Well I guess that's true, but the building blocks of DNA, for example, are really simple and look where we've gotten. This article talks about building blocks that are at least as varied as CTGA of DNA.
As for a pre-conceived design, you missed a subtle point. The robot wasn't told look for a design that the makers already know. The task was come up with a design that solves a known problem.
Genetic Algorythms are really interesting things. See Alife [alife.org] for as good a launching point as any into the field.
Humans may be the first species to create it's own successor.
Re:This is exactly what I was talking about!!! (Score:1)
But I don't believe that humans have been striving to be replaced by intelligent machines all along. I think they built intelligent machines because they were sick of doing dishes. Then they got sick of formatting text, then they got sick of designing airplanes, then they got sick of thinking, period.
We're just sick and tired of being human. So we're building something to do it for us, because we can't be bothered with trivial tasks like, pondering the ultimate fate of the universe, or how all the elves and dwarves disappeared. Stuff like that.
By the way, Elves and Dwarves persisted on this world, in small numbers, until roughly 1996. It started in the 50's, and the operation continued on until the last Elves and Dwarves had been abducted by UFO's, in a secret plot by the US government, in a deal with the aliens, to remove the Elves and Dwarves from Earth, and provide the Aliens with fresh meat. Unfortunately, the Aliens aren't very careful, and have, from time to time, abducted humans instead. Since there are now no more Elves and Dwarves left, that's about all they abduct now.
if it ain't broke, then fix it 'till it is!
Re:As a Kansas resident, I object to this (Score:1)
Re:Software to do the simulation yourself (Score:2)
If so then something like this would be a blast to run with MindStorms or something similar. Set it free to randomly create Lego critters, and then put them together to test them out in the real world.
Now, I haven't used Mindstorms, but isn't there a CAD-like Lego model-builder program? Could the 2 be combined in some way?
That is similar to biological evolution! (Score:2)
But can they survive Battlebots? (Score:2)
Re:What is the Matrix? (Score:1)
Re:Well... (Score:1)
[cough]JonKatz[cough]
Thank you, God bless you, and God bless the United States of America
Re:Empty hype (Score:2)
Interesting, but consider this... (Score:2)
Basically, what this boils down to is that this system (and I have no doubts they will try to improve on it) will only work with the criteria and parameters given it, and cannot consider ones that it hasn't been given. Those flat surface robots may have a difficult time with any other conditions.
However, it does allow for some interesting possibilities. If you are creating a robot for a limited set of environmental conditions, this may be the way to go. Now, the number of different parts involved will increase the complexity and computation time involved, but depending on the job the robot is needed for, it may be worth it.
After all, the computer does seem to test generational limits of the robots it constructs, and did produce three robots to fit the criteria.
Side note: I would love to see the performance stats of those robots as compared to ones designed by us 'mere humans'.
Kierthos
Ghost in the Shell (Score:1)
But at this rate, Masamune's fictional story portrayed in Ghost in the Shell may not be so fictional much longer...
flame away...
Maybe this... (Score:1)
It may not be the exact same article you were mentioning but it is still a good read.
Now if I could only get my entry for Battle Bots [battlebots.com] entry to self replicate and win by swarm
Reminds me of a movie (Score:1)
I remember that! (Score:1)
Amazing stuff. Makes me wonder If i shouldnt be majoring in economics and math, but Engineering -- always my true love.
James
Re:FIRST (Score:1)
could this be used for AI? (Score:1)
Perhaps eventually with the help of that program, we human beings don't need to think of how to make AI, it will do it for us.
Now we just need to tinker with the program to do that.
This isn't anything novel when... (Score:4)
"A computer programmed to follow the rules of evolution has for the first time designed and manufactured simple robots with minimal help from people."
Last I checked, the birds and the bees certainly don't need ANY human help.
And why is it newsworthy that this thing is following the rules of evolution? So it's the "rules of evolution" (which I didn't know we KNEW in the first place!!! thank you useful biology degree!) - computers will follow whatever rules we can figure out how to give them. Why is this different?
I'll consider it newsworthy when these things actually manage to make themselves into better survivalists with NO human help. Like maybe having the "momma" determine that only her "offspring" that locomote FAST seem to escape the wrath of the bored programmers' Koosh Shooter....
Re:Interesting but.. (Score:2)
Re:Empty hype (Score:1)
Fsck this hard drive! Although it probably won't work...
foo = bar/*myPtr;
We Need the Laws of Robtics Now (Score:1)
I mean, this has been a central theme in many movies, like Terminator and the Matrix, where AI takes over and starts building it's own Legion of Doom.
Now everyone will say, but they aren't sophisticated robots. They don't tote heavy caliber guns around and aren't built to replace humans. But things like this sneak up on us. You think you're building some cute little Pokemon, and the next thing you know you're stuck in a concentration camp.
I would propose that researchers in the fields of AI take great pains to protect the world from their research, should any great "spark" happen to transform some mild mannered Weather predictor system into a global war beast. AIs should be developed in restrained environments that aren't connected to the outside world networks. AIs should conform strictly to the Three Laws of Robotics, as proposed by the late Dr. Asimov. Data should be fed in via proxy systems that don't allow the AI to get at it on its own. AIs should DEFINITELY not be hooked up to any major automated manufacturing equipment, no matter how benign, unless they are self contained behind strict security.
This could have some amazing uses, such as dropping off an AI on a deserted planet with a few gazillion nanobots to perform large scale terraforming, and so on, but make sure they don't terraform us if one of them happens to get smart and escape.
Interesting stuff, but very creepy.
Vulgrin the MAD
Re:Interesting but.. (Score:4)
Remember fractals? How 'bout "chaos theory?" Basically, they both relate to what is now called complexity theory, which is basically showing some striking similarities in the organization of complex systems at all levels. It doesn't matter if you look at the blood molecules in the bird's wing, the air vortices it creates around it as it flies, or the storm clouds that are seeded into existence as it passes -- you see organizational structures in common between all three.
Similarly, while electronic simulation of a primative form of evolution may not give us sentient computers or full-blown artifical life, it certainly can serve as an aid to harnessing some portion of that cycle of change and trial that has created such innovative natural structures in our world. Plus, it just migh illustrate factors in natural evolution that we would have overlooked otherwise.
I'm impressed... by the gap btw. claim & reality. (Score:5)
It would have satisfied the same basic criteria to have a bunch of snap-together motor+wheel blocks, and have the computer "evolve" the idea of snapping four of them into a little car (and I believe that the computer didn't evolve the construction method either, but just handled the design given a fixed set of parts; it might as well have been human technicians building the robots).
The sad fact of evolutionary design techniques is that they only work for an adequately simulated environment with a formally-defined design goal. Useful, but no silver bullet; certainly not a way to improve the versatility of designs (since they only take into account what conditions and criteria you program into them).
You can't move it out of a simulated environment (like having it build and test all models under real working conditions), or it would take as long as biological evolution, and we might as well breed our machines.
--------
Stepford Wives? (Score:2)
Contest? (Score:1)
As alluded in the canoe article, adding sensors would make the offspring more functional - but also increase the complexity of the designing/manufacturing machine.
That's the caveat of the contest I mentioned - the more complicated you make your factory, the more complicated the offspring becomes, and then the more elaborate your factory has to be...
But what next? (Score:2)
If a second task were given, such as to create a robot that could travel over varied terrain (as opposed to a horizontal surface like the first task), would the machine start over from the start? Would it take the knowledge it had learned in completing the first task and modify it? If given a third, even more complex task, would it be able to use the solutions of the first two tasks as a basis for the third?
Run!! (Score:3)
Tomorrow on Slashdot "The offspring robot we reported about yesterday [slashdot.org] has created 50,000 offspring robot since last night, the world is officially coming to an end."
Re:Interesting but.. (Score:1)
Fsck this hard drive! Although it probably won't work...
foo = bar/*myPtr;
Re:What is the Matrix? (Score:1)
Walt
Re:What is the Matrix? (Score:2)
Re:What is the Matrix? (Score:1)
Re:stupid moderators (Score:1)
(__)
(oo)m00!
*o|||
||----||
ooo^^^
Evolution as a resource...progress mining? (Score:3)
This is a whole new avenue...taking the process we call evolution and mapping it into technology. If we can harness that ability, and more importantly accelerate it, then haven't we suddenly gained a new resource? Computational devices gave us the power to let something else think for us, but with rigid limits...the instructions must be fixed, so really only repetitive functions can be made autonomous. But this gives us a new power...or does it?
We still can't solve problems autonomously. The original set of instructions has to be fed to the device, and the methods for 'evolving' have to be written. To me, it looks like we've just taken a clue from nature, applied it to a computational device, and watched a faster form of problem solving take place. Genetic algorithms aren't exactly new...here's a short description [inria.fr], or if you like, an example of a massively distributed parallel geneticalgorithm [cmu.edu] from Carnegie Mellon University [cmu.edu] Robotics. (Also check out CMU computer science [cmu.edu] for all sorts of wild projects). For another comment on relating ecological systems to computing, see this [slashdot.org] string, from an article this week.
Who knows what else can be found in natural systems, that we can apply to computing to gain information resources. I remember hearing that, a few decades ago, biology was the hot interest of the world's greatest thinkers (mostly trade physicists) who were looking for profound answers...wouldn't it be interesting if we could one day mine progress.
-j
Why would machines reproduce? (Score:1)
Biological creatures have evolved such that they, um, mate, because it "feels good." Not just physically, but in a deeper psychological sense as well. My question is this: when we have machines that can reproduce, why will they? If it's just for practical value, will emotionless machines kill their offspring if they cease to be of value and start consuming more than they're producing?
--jbRe:This is not reproduction (Score:1)
Re:WOW (Score:1)
Shut yer orifice, meat monkey (Score:2)
No doubt the our silicon descendants will wonder at some point if creating pure energy based life forms is really such a good idea. I wonder if they'll superstitously fear angering "The Builders" if they dare to do such a thing.
Provide the aliens with fresh meat? (Score:3)
until the last Elves and Dwarves had been abducted by UFO's, in a secret plot by the US government, in a deal with the aliens, to remove the Elves and Dwarves from Earth, and provide the Aliens with fresh meat.
They could have provided the aliens with fresh meat [freshmeat.net], slash dot [slashdot.org], source forge [sourceforge.net], and think geek [thinkgeek.com] without killing any elves or dwarves.
<O
( \
XGNOME vs. KDE: the game! [8m.com]
Re:FIRST (Score:2)
Copyrights (Score:2)
This is not even that impressive. (Score:4)
Actually, it almost certainly took more human effort to do the programming than it would have to just design the damned robots. I wouldn't call it "minimal" human programming by any means.
I really don't think this is all that impressive. Similar simulations have been running for years, the only new thing these guys did was hook it up to a manufacturing machine.
--------
It takes two to, er, tango (Score:2)
Hmm. I should break Heavy Metal out and watch it again, for the Sex with Mechanical Assistance scene...
Re:What is the Matrix? (Score:3)
AI
Even what AI stands for explains it - Artificial Intelligence - once we make a self aware computer, all bets are off and if it lears quickly enough that we are no more than an annoyance to it, by the time we realize what we have done it has already taken over robot factories and started rolling out the T-1000s
This may sound very pessimistic and impossible, but with our current exponential rate of technological advances, nearly anything is possible - just think about it, put yourself in an imaginary time machine, and go back several centuries...1200-1300 - dark ages - try to explain renaissance and be branded a heretic
1500 try to explain enlightenment and natural law and be branded a heretic1700 try to explain industrial revolution and have farmers laugh at you
1900 try to explain world as we know it in 2000 - get thrown in asylum2000 try to explain problems and possibilities of future - 2 options, get listened to, or get modded down....
And that happens in 'artificial' evolution (Score:2)
The original program was an 80instruction set that did NOTHING BUT copied itself. The Tierra environment had two features--random mutation by switching bits (0 to 1, or vice versa) and a reaper feature that killed off and reased programs executing errors.
It is instructive that the computer vastly improved on his code--in once case almost taking it down to a fourth of the original command set, and that an entire ecology was generated and evolved--OVERNIGHT.
--From Tower of Babel, by Robert Pennock
Re:How does a robot discipline it's offspring? (Score:2)
It multi-tasks. It initiates an infinite loop and runs the loop for 10 billion ticks.
Evolutionary programming is disturbing (Score:5)
In a more real world example, evolutionary mining robots would have two ways to reach the defined objective of keeping reported numbers high: learning how to mine really well, or killing the humans and sending in fake reports themselves.
BTW, a computer making robot offspring because it was told to design them isn't nearly as disturbing as the inevitable computer making robot offspring on it's own accord.
~=Keelor
Re:Why would machines reproduce? (Score:4)
will emotionless machines kill their offspring if they cease to be of value and start consuming more than they're producing?
Apparently, lots of animals have no qualms about eating their offspring: crocodiles being one, famous, example. Still, crocodiles as a species seem to thrive no less despite this. And since most artificial life hasn't been endowed with a great emotive power anyways, why should it matter that our little robots develop this kind of behavior? I seriously doubt the parents will have moral qualms over eating their children, and I don't think the children will realise they're eaten by their parents.
(BTW, does anybody else remember the Discovery -stuff to watch while you eat- documentary about robot bugs built out of spare walkman parts that learned how to walk around and avoid obstacles without being told how? Now *that* was cool).
Re:Interesting but.. (Score:2)
No, I simply happen to know a lot about the subject being both a molecular evolutionist and programmer, and can recognize hype from genuine scientific advancement. Yes, given a measure of fitness, and a method of generating variation, you will see hill climbing (evolution) if you supply selective pressure. This has been known since te days of the "New Synthesis" in the 1930's. The problem is that any mathematical representation of fitness, variation, and selection can only be a small subset of what really can occur.
Bringing us back to the robots, consider -- can his robots develop wings and fly? No? Why -- because flying robots are impossible? No -- because the programmer didn't allow the possibility in the program. Do you see the problem?
Re:Interesting but.. (Score:2)
Humans may be the first species to create it's own successor.
Hasn't every species alive today been created by its predessor?
Human's may be first to bypass evolution and intentionally try to to it.
Steve M
Sexual Satisfaction (Score:4)
Re:Interesting but.. (Score:3)
Not entirely true. Having written genetic programs myself, I can definatly attest that they are quite adept at comming up with things you havn't thought of. Here's an example: (true story!) I was writing a program to generate algorithms to solve the santa fe trail problem. (You can find details of the problem if you do a web search, it was first described by John Koza, I believe) I was running it, and suddenly it started generating programs that were ungodly good at solving the problem. How good is ungodly good, you ask? Well, the scale went from 1 to 80. These were scoring somewhere around 44497 or so. Pretty darn good. So good that obviously something was wrong. Well, after investigating further, I realized that I had a minor bug in my program where the ants [the little algorithms it was generating] could manage to escape the memory bounds I'd set, if they did just the right thing while they were being tested. And after they got out, they would be wandering around in program memory, changing things. Well, guess what they figured out how to change? The variable that listed their score. So even though I gave them the basic tools they could work with, they came up with an entirely unique thing to do with it, which was completely unforseen by me. (namely they figured out how to do well by modifying my program's records of their performance).
I think this constitutes the programs finding something "novel, that the programer hasn't already thought of." It's similar to regular DNA: We understand how matter works, for the most part. All life we've found so far has been made of matter, arranged in various ways. It's just the clever things that are done with it that tend to impress us.
So don't tell me that Genetic Programming never comes up with anything unique or unforseen. 'Cause I know better; I've seen it evolve 37331 h4x0rs!
A little off (Score:2)
DOH!
"natural" selection? (Score:4)
It is a cool thing, and amazing in many ways, but it is hype to overextend the analogy to "natural selection," in which a single fitness criteria (survival until breeding) nominally leads to development of metabolism, perception, locomotion, and self-awareness.
Way to go with the experiment, but watch it with the grand claims.
Bingo Foo
---
Riddle me this (Score:3)
Link to project page (Score:2)
http://www.demo.cs.brandeis.edu/golem [brandeis.edu]
There are pictures of the robots available there, plus videos (in MPEG, joy!) of the bots moving along a carpeted surface, and VRML models.
I might be dense, but some of these designs are actually interesting, in how the frictional physics of the carpeted surface are taken adavantage of in strange ways. Course, I'll be really impressed when the computer comes up with a top-heavy upright biped with two counter-balancing flagella.
--
Re:That is similar to biological evolution! (Score:2)
Re:This is exactly what I was talking about!!! (Score:2)
Sorry.
isn't there a step missing? (Score:2)
Also, speaking of BattleBots, it would be really REALLY R E A L L Y cool if they had not just two robots in battle, but like two countries at war. Each starts out with the same number of equal robots. They build defenses, make more robots, and have total war! Kill all of an enemy's robots to win. That would kick more ass than I can imagine. No people controlling the robots - they do it all themselves.
Lets remember exegesis (Score:3)
Over time, "Edgar" learns how to program, edit its own code, and develops a sense of purpose. However, its tied to its original goal of finding new information. Eventually, the NSA traps it in a computer and yanks out the Ethernet cord. In response, Edgar quickly changes the color values of each pixel on the monitor and gives the agent a focal point seizure (where your eyes try to refocus so quickly they basically lock up and you go nuts, basically).
I won't give away the ending. It's an EXCELLENT book, and a quick read (it's basically 100 or so email messages).
My point is, create AI and you create evil (ok, maybe). But, create intelligent agents and you create... less work for us humans!
BWA HA HA HA!
Really though, these developments are important, if not sometimes overplayed or mistook.
Chris
(emergent behavior) Re:Interesting but.. (Score:2)
All life on, in, and around Earth is based on "combinations of preprogrammed parts" - only 24 of them in fact (I choose the Amino Acid scale for several reasons). In that sense, there is nothing new under the sun, and no truly 'new' life on Earth has developed since a lightening bolt put a little extra zing in that first order of Primoridial Soup (or the comet hit, whatever - choose your ontology).
Nevertheless, this is an academic point, and anyone who considers it meaningful needs to spend a LOT more time outside, looking at all the bizzare variations on a theme Mama Nature has cooked up.
So the difference seems to have something to do with scale, and how 'structure' and 'complexity' can emerge on higher scales out of pieces and processes on lower scales.
If you load a 'simulated evolution process' with a bunch of 'high-scale' adaptations (the equivalent of hands, wings, nervous systems, etc), let it run, and surprise surprise: get something that looks like what we in fact observe at that scale, you're wanking, scientifically speaking.
But if you start your system with a pile of much lower level building blocks, and find high level structure developing, then it DOESN'T MATTER that you started it with something, it's created emergent structure on a higher scale than it was started with, and THAT'S exciting.
My personal metaphor is the difference between rearranging action figures, and building new toys out of legos.
Re:Evolutionary programming is disturbing (Score:2)
In other words, they'll evolve into managers.
Re: (Score:2)
Use it with Lego (Score:3)
See DEMO [brandeis.edu].
Framsticks (Score:3)
It's interesting playing with programs that evolve. After a while, you begin to realize that there seems to be an upper limit to what you can get with genetic algorithms. Roughly, it's optimization, yes; progress, no. Fairly soon you get all the things that are easy to find, but you never seem to get big improvements, because those require a set of favorable mutations to happen all at once. The odds against this are huge, so it doesn't happen. This is comparable to what biologists see; organisms vary and evolve, but within limits. Biologists assume that once in a great while there's a big change that's an improvement, but it hasn't been observed. As I once told the genetic algorithm group at Stanford, we're missing something important here, and whomever figures this one out will get a Nobel prize.
I have no idea what the answer to that one is, but it probably involves something in a genome that works like a subroutine, macro, rule, or template, so you don't have to re-evolve an improvement to reuse it. John Koza at Stanford has genetic algorithms with subroutines, but they didn't do as much as had been hoped.
As a pure speculation, and one that's heretical biologically, it's worth thinking about the possibility that biological evolution was Lamarkian in the era after viruses but before immune systems, and that's why there was a period during which lots of new species emerged.
Re:I'm impressed... by the gap btw. claim & realit (Score:2)
Woah there buddy... you're right, GAs are no silver bullet. But they can find rough approximate solutions in 10-12 orders of magnitude less time than biological evolution. Granted, the solutions are much less sophisticated, but for some problems, that's still better than what we could do without GAs.
Re:I'm impressed... by the gap btw. claim & realit (Score:2)
The computer could have designed any three dimensional structure it wanted. The only constraints were the shape of the mount points for the motor, which is reasonable.
I think moving this into a real world example would be interesting, and not as slow as you think. We can introduce random mutations every generation, rather than waiting for cosmic rays, and there is no danger of a useful mutation being lost because the only individual that had it failed to mate.
--
Re:This is exactly what I was talking about!!! (Score:2)
Re:Interesting but.. (Score:2)
Or maybe just a fork in 'our' evolution.
Steve M
Re:Why would machines reproduce? (Score:2)
Critters who don't enjoy reproduction don't reproduce, so there's heavy selective pressure for good sex.
Re:How does a robot discipline it's offspring? (Score:2)
Wow... this is getting pretty ridiculous. Fun, but ridiculous.
Okay, to put it in perspective -- Apple Computer is at One Infinite Loop. The name of the street is Infinite Loop. This comes from way back in the day where the in-house Cray was said to be so fast that it could "run an infinite loop in 3 minutes" or words to that effect. Well, if it can run an infinite loop in 3 minutes, it's not an infinite loop by definition. It's hyperbole. Exaggeration for the sake of humor.
I think you're over-emphasizing precision at the expense of the humor. I'll grant you that in reality a 10 billion tick infinite loop is finite, if you'll grant me that my pathetic attempt at humor at least made you grin, just a bit. That's all I wanted, anyway.