When Robots Play Games 184
Roland Piquepaille writes "If the theory of evolution has worked well for us -- even if this is arguable these days -- why not apply it to mobile robots?, asks Technology Research News. Several U.S. researchers just did that and trained neural networks to play the Capture the flag game. Once the neural networks were good enough at the game, they transferred them to the robots' onboard computers. These teams of mobile robots, named EvBots (for Evolution Robots), were then also able to play the game successfully. This method could be used to build environment-aware autonomous robots able to clear a minefield or find heat sources in a collapsed building within 3 to 6 years. But the researchers want to build controllers for robots that adapt to completely unknown environments. And this will not happen before 10 or maybe 50 years. You'll find more details and references in this overview, including a picture of EvBots trying to find their way during a game." Read on for a similar robot competition held this weekend in France.
saunabad writes "The annual Eurobot autonomous robot contest for amateurs is held this weekend on La Férte-Bernard, France. This year's theme is 'coconut rugby,' and the robots are collecting small stress balls from the field and carrying them to the opponent's end, or shooting them in the rugby goal, while avoiding the randomly placed obstacles at the same time. Each team has a one main robot and an optional small assisting robot."
Arguable? (Score:3, Insightful)
Do I detect the scent of an evolution denier? And it is interesting that you implicitly question the validity of a theory even as you cite an example of its successful application.
Strategy in Capture the Flag (Score:5, Insightful)
As someone who spent a considerable amount of my childhood less interested in 'organized' sports and instead playing this game, it seems the whole point of playing Capture the Flag was to develop strategies in how to win. We had a set of rules that evolved over the years, depending on how many kids were playing, what time sunset (or the first person called back to their house would be), etc. We even had evolving words that were based on nonsense - or the inability of one of the younger kids to say a word (for instance - in some "Steal the Flag" games - the term "electricity" is used to talk about a strategy that involved making a line of kids that attacked from one end - they all held hands in the stragegy so that if anyone was captured they would automatically be "freed" by the "electricity" back to their own side. We deemed this a violation of the intent of the game, so we had a *no electricity* rule some little kids couldn't pronounce right - so it became "no a-la-ca-triss" - or something like that).
The game wasn't about *object avoidance*, it was about kicking ass through completely ad hoc strategies that had to be original because the teams always traded players rapidly, so you didn't want to make a rule or come up with something that would come back to bite you.
In this way - the random nature of our game was more like evolution than the winning was (it shuffled the components and allowed for *mutations*). The fact that the model showed no improvements with greater numbers of computers is not in line with what actually happens. The best games were the huge ones.
This simulation was probably a lot of fun to watch once the program was transferred to the robots though...
Re:Caution (Score:2, Insightful)
Perhaps it is time to start applying a little caution in our ever forward moving technology push?
Thats perhaps a good idea, but how are you going to stop it? Its not like it matters whatever one country agrees to it because ppl who thinks that it is interresting might just move. And even if the whole world agreed to the law how would you write it? Its not as if you could use "Dont make anything dangerously with AI" After all Nobel said he made nitroglycin because he thought it would be safer...
Re:Caution (Score:3, Insightful)
Well, why shouldn't they? Evolution is survival of the fittest, and this `fittest' has many senses. For one: they will not take over unless they're just as smart as we are (if not smarter). I can certainly imagine them being much fitter physically (hey can already go to Mars!)
Humans place too much importance on themselves. What we can't get over is that we may just be a stepping stone on the evolutionary scale. Maybe it is our `destiny' (if there is such a thing) to create a `being' (robot, etc.) that's more advanced that we are, that can survive the harshness of space, and continue on our legacy for a billion years into the future possibly on another planet. I don't see humans surviving that long, but I can imagine that the machines we create might.
Re:Arguable? (Score:2, Insightful)
The current group of theories that make up evolutionary theory as a whole (from paleontology, biology, molecular biology, etc.) DO have some problems serious to warrant real discussion and investigation. But instead of recognizing this and just considering that there are parts of evolution that we don't understand yet, most evolutionists become extremely defensive whenever they are mentioned.
Sure, it's a reaction. But it's an overreaction and it is NOT helpful to the progress of science.
Furthermore, there is nothing odd about questioning a theory even while successfully applying it to solve a real-world problem. That's the difference between practical and theoretical science.
Most things ever created by humans were designed using theories that turned out to be wrong. That just doesn't mean they weren't helpful! For example, almost every large, complex structure on the planet was designed using the principles of Newtonian physics. As it turns out, Newtonian physics, in the real world, never has given us the exactly correct answer. But, it's good enough to tango.
There are thousands of other examples (Ptolmeaic astonomy, phlogiston, etc.) of completely discredited theories that nevertheless gave usable answers to practical users.
I would also like to add that the reason those theories were eventually discredited is because there were anomolies and counter-examples that could not be resolved. Ignoring the current anomolies and counter-examples of evolutionary theory does not help to resolve them, and only tends to make evolution appear to be a bad, or at least sub-par and questionable, field of science.
Robots coding and coding robots (Score:2, Insightful)
I'd like to see how a robot could work on his own code too, to try to always be faster.
Given the fact these robots (programs after all) can evoluate/learn and re-use this evolution, they should be able to learn until their hardware limis them.
As I see it, its all about a really basic but really well done base code, who will start the comparison, memory and self-modification of the comparison code that will make it evoluate.
Thats a really interesting subject
10 to 50 years? (Score:4, Insightful)
I disagree that it will necessarily take even 10 years and it will certainly take less than 50. Pathfinding and object search algorithms are strong even today. With a combination of radar, sonar, lidar, and optical recognition, I think we should be able to create robots which traverse formerly-unknown terrain in ten years or less.
I'm not trying to trivialize the difficulty of the problem, all the stuff we take for granted as we navigate a room is really quite a lot to deal with and it is only through practice that we are so successful, but an awful lot of effort is going into these problems (I know "more than ever before" is cliche and obvious but nonetheless...) and it is a top priority for so many very smart people that I cannot see it taking even a decade for useful robots with these capabilities to be in use.
Of course, it depends on what you want them to do when they get there...
Re:Arguable? (Score:2, Insightful)
Re:Arguable? (Score:3, Insightful)
(It's not quite that bad because our civilization has evolved to match us, but it's still not perfect; for instance, you can blame "lack of willpower" for the current obesity problem all you want, but in a very real way the blame lies equally on the fact that many common body metabolisms and brains are not adapted for the food in our civilization.)
Re:As long as... (Score:2, Insightful)
They can't do worse than the current crop of leaders. No evolving needed to match their ability
Re:"even if this is arguable these days"? (Score:2, Insightful)
Evolution always "works"; it's just that our actions are redefining what it means to be "fit". Of course, what it means to be "fit" is always being redefined on its own, as species interact within their own populations, co-evolve with other species, and environments change.
Similarly, what does it mean to "slow" evolution? Mutations occur at the same rate as before, reproductive rates (recombination events) aren't decreased by what you describe. I don't see how this is "slowing" evolution. If anything, it's increasing it, in that we're preserving a wider variety of genes.
Some people seem to forget that genetic diversity important to preserve. All the "bad" genes we short-sightedly weed out might have ended up helping us if circumstances change.
An example: sickle-cell anemia. It's a disease, but the gene responsible for it also protects against another disease, malaria. If we start wiping out genes from the population, who knows which ones would have saved us when the next plague strikes?
For that matter, would we want to remove Stephen Hawking from the gene pool just because he's an invalid?
Indeed. Even putting the moral objections aside, social Darwinists have poor reasoning on practical fronts, such as the gene diversity issue.
Some of these points were well summarized in an article I recently read [google.com] on talk.origins.
Re:Landmines? I don't think that's quite necessary (Score:5, Insightful)
- they picked the rats because they're too light to set off the mines and are single-minded enough that they work better/cheaper than sniffer-dogs.
- The article describes using cables/tethers to restrict the rats to a line of interest. Hopefully, you can extend this concept to multiple rats on parallel lines and see how that'd allow efficient mine-sweeps of areas of concern.
- The rats live 6 years and can be bred, travel lightly, etc. This is EXACTLY what the parent poster meant when they talked about evolutionarily handling a cool problem rather than expecting rapid results (cheaply) from robots.
- How little do you figure you can make your smart robot for? A few grand? And where will Afghani's (or third-world citizens anywhere, especially those recovering from the economic impact of the very wars that placed these mines) get that money, a steady source of repair parts, etc? Instructions on training, a pair of rats, and fifty yards of string/wire and a clicker could let any small village have their own demining capability. Somehow, I don't think robots are gonna be as versatile or cost-effective.
Seriously, the parent poster on this should have considered posting it as a story (unless it's old news). It sure seems to me to be a great blend of nerd-interest factor, news, and stuff that matters. Props to the parent poster and the involved researchers. Within my life, we'll likely have cheap devices with artificial noses or GPR or another solution. But abandoned mines are too wicked to wait that long.Even discounting these things, worrying about the ethical implications of hurting an animal by training it as a mine-sniffer ignores the huge ethical implications of going the other way: if nothing is done, people die or are maimed. We've had this argument: using animals to save human lives is not taken lightly, but it is ethically tenable.
Re:10 to 50 years? (Score:4, Insightful)
Back in the early days of Genetic Algorithms, there were experiments which tried to evolve robots in simulation to go to the end of a corridor and turn in a specified direction. However, once the robots were evolved and "built" in the real world, they often failed. The reasons for the failure were numerous, from not having the same dimensions for the corridor to different motor sensitivities in the robot itself.
They've gotten around this somewhat by feeding randomness into the simulation (see Nick Jacobi's Minimal Simulations). However, for any complex real world type problems, there just remains too many variables to vary and evolution doesn't work as efficiently.
Basic Fallacy (Score:3, Insightful)
This happened in computing in the 70s. Intel found it convenient to solve the problem of calculator design by buoilding the 4040 - the first microprocessor, But this was in no way *necessary* - Intel could have continued down the old line of discrete logic.
Evolution is a powerful tool - but not a panacea
No, dammit. (Score:3, Insightful)
Re:"even if this is arguable these days"? (Score:3, Insightful)