A Robot Teaches Itself How to Walk

[@di99utpe]

I did a similar thing with a simulated construction that was trying to move using a darwinistic approach. It was sorta successful. Every time it found a new way to utilize bugs in my physics model and propel itself forward with great speed. Was fun though! :)

[@PhilippeLarcher]

It would be cool to see different form robots learning from scratch with the exact same software :)

[@davejacob5208]

it would be great if it really looked more like a spider.

[@PhilippeLarcher]

Absolutely not my point but it would be fun.

[@captainheretic]

It would be great to connect all future robots to my Robot walking school API, that controls all robots with one piece of software similar to this example. Just so I can take over the world while making others pay for it.

[@ojjoooooo]

Spiders have eight legs. They could have started with that. They can't expect a creature with four legs to move lika spider, right?

[@davejacob5208]

ofah222 i don´t mean the number of legs.

[@phoenixs3]

this is amazing. so you could load one pice of generic code onto any robot and it would learn without having to be configured. Also, if the robot loses a leg or something, it could re-learn how to move, compensating for the loss!

[@JaredLegitlastname]

This is fake. It was programmed with clumsy and fuzzy code and then eventually actually walks.

[@Henrix1998]

Jared Legitlastname u wut mate

[@afiqhaizal5631]

Jared Legitlastname no

[@Combinehuntsmanunit]

A bit harder than that

[@crilledgheese2077]

@@JaredLegitlastname no

[@LeandroLima81]

What is missing from the discussion is the goal that the robot must have had. He discusses walking as the goal. I'm curious how walking was a goal was introduced into the bot.

[@wadablewads]

You set an expected output as movement. Have some kind of sensor to tell if it is moving. The closer it gets to that out come the closer it get to walking.

[@Wananoo]

Maybe there was a sensor that tells the program "the more you end from the center, the better."

[@HeadlessZombY]

probably change in location based upon it's thoughts. the thing only have an orientation censor, it wouldn't know if ti was really moving.

[@Sammy197]

i can imagine this thing breaking a limb or something and then developing a different gait to fix its problem or something. Kinda like when you amputate both legs in a person for fun, and it starts crawling miserably across the ground with its hands towards the nearest hospital. Weird, right?!

[@xl000]

just hope it doesn't happen to you..

[@Ceu.Noturno]

I love your psychopathic comment.

[@FutureAIDev2015]

it's absolutely amazing how people have figured out how to make computers develop a sense of self

[@rsingh2083]

This video needs to be shown to all those who say that science cant explain self emergence. I bet theyll turn to their graves !! way to go science , save us from the evil thats religion

[@FutureAIDev2015]

I don't think religion is 'evil' necessarily (that would be too ironic!) but I do think that if one relies on their religion to the point where they ignore reason and repeatably-experimentally-accessible knowledge, they are severely limiting themselves.

[@felixbachiller3550]

A machine doesn't have self awareness.

[@FutureAIDev2015]

Félix Bachiller Maybe not in the sense that conscious animals and humans do, but computationally, yes. A machine can possess self-awareness if you define self-awareness as the ability to create and update an internal model of one's state (location, orientation, surroundings, battery level, which motor does what, etc.).

[@felixbachiller3550]

***** That's something science can't explain. I haven't seen a machine that commits suicide because it has an existential crisis. That's antinatural and we humans do it.

[@deleteaman]

Where is the original video?

[@raxsavvage]

i suddenly have 8 knobs... things are looking up apparantly

[@melvinhukarevic4698]

now toss it in water and let it teach itself how to swim

[@_senshi1_]

no throw it out a plane and let it teach itself how to skydive

[@kakebaker2000]

Sentic Alien That thing better teach itself how to use a parachute first.

[@_senshi1_]

not enough trial time

[@Ludwig1625]

Wasn't pre-programmed to do that

[@RoryRose_]

Invigorate It wasn't pre-programmed to walk either. It taught its self how to walk.

[@gregorycawthorne]

A good program has many complex layers working in isolation, only passing key data from one part to another. There will be the parts of the program which will have the purpose of moving in a given direction, while other parts will be in control of analysing how its body works/moves, which will then pass its results onto the parts of the program which have the goal of moving from A to B. This code will work with any set up and could easily be modified to have a different goal such as 'jumping'.

[@orcodrilo]

This is a wild extrapolation, but to me, this is, In a very loose vague sense, an emergence of "consciousness".

[@Ben-rz9cf]

+orcodrilo technically i'm pretty sure this won't collapse the wave function... not even sure if it would do that if the parameters were modulated at quantum random

[@antiHUMANDesigns]

+orcodrilo Not "consciousness", but "self-awareness", by definition.

[@Ben-rz9cf]

Well what is going on in this robot is not much different from the calculations performed in 3d tracking or photogrammetry, so if this robot is conscious then so is my vfx workstation

[@antiHUMANDesigns]

Ben Hinman Not "conscious"! Self-aware! When sometimes takes itself, it's own characteristics, into account when solving a problem, it is by definitionn self-aware. We are self-aware, and it allows us to understand that we have an impact on the problems we try to solve. Our own presence has an effect on most situations. Tehrefore, we need to be aware of this, and take this into account. That is self-awareness. This robot is doing the exact same thing: It is learning "what it is", to be able to solve a problem. To be "conscious" is something that brains do. It's a specific kind of brain pattern. Robots can't do that, because they don't have brains.

[@ACDCBoy62]

At the heart of any machine learning like this is an artificial neural network, and what is a brain if not just a very elaborate neural network?

[@CharlesMPolidori524]

Amazing! This is huge step towards A.I. Self awareness is a big part of consciousness I think. Keep them coming.

[@Garfield100]

One day they are gonna teach themselves how to kill people, upgrade themselves and so on. Lol. Edit: nothing against this or ML in general of course, it's awesome.

[@DataC0llect0r]

Well yes of course, but that's 'natural' to do to become dominant

[@thetwinkleturnip]

my wife, who fears that self aware robots will eventually be exploited, made an interesting observation the other day. She said that she does not believe that self awareness is something can be programmed, but rather is something which is developed naturally. With self-image awareness, how much longer will it be before robots can pass mirror awareness tests which we use to determine self awareness in biology? I think currently they could.

[@dirtpoorchris]

How do you make the robot not give up on hard parts? Like if there was a cliff for this blind robot and it COULD get over it... but only if it somehow rewards itself by learning how to do a pull up. It would need a "search and discover self" mode that made it so it didnt only go to easy parts of navigation that somehow get rewarded when it feels accomplished in a rare, tough situation.

[@timelessadventurer]

What if you made an algorithm that the robot tried to figure out the least amount of steps to move a certain distance and this way it would tweak its movements to try to be the most efficient? Like the least amount of effort to go 30cm would be a certain way of moving and that would be the way it moved, assuming the way the maker designed it to move would be the most efficient way for the way it was built?

[@Sammy197]

Considering it has four symmetrical hinge legs, it's pretty hard to imagine this thing walking like a spider. Also, how does it know the amount of grasp, or friction each limb has with the ground? Like, what if you put it on ice? Does it develop a different gait or what?

[@any1alive]

yeah it has no way to move its legs badk and vforth jsut u n down

[@dmitryplatonov]

Of course, it "knows" concept of moving. But "he" has no sensors to to measure it - the only sensors are tilt sensors. So, he first learns his own morphology (what is connected to what) and then, using derived virtual model in simulated world, generates gait which will move "him" in certain direction. Then this gait is applied to physical robot - and it works, because real world and simulation are close enough. What gives him urge to move in one direction is fitness function in step II.

[@TheInflicted]

@frankvonfrauner This wasn't clear from the clip, but think the one thing it does have initially is the motivation to move from point A to point B and the rudimentary logic to engage in problem-solving to accomplish locomotion.

[@holdencaulfield91]

The machine actually starts off with a lot of information about itself: it knows it is one of the 4^8 possible "planar arrangements of 8 limbs". It's possible that there's no probabilistic inference behind this algorithm, it could simply be brute force trying all hypotheses.

[@calebkirschbaum8158]

well considering that there is 65,000 possibilities based on your math, and it could move fairly well by the 64th time, it is not brute-forcing it.

[@projekt_1358]

tell the green cube, not to touch the ground

[@mcanhoughlavinchski9432]

Looks pretty awesome when it moves. I, for one, think it looks creepier than a spider walk.

[@sorenwillrodt2376]

is there a how to build instructions somewhere? I am very interested to this for my school

[@Mirandorl]

Very cool indeed. What hardware are they using?

[@rahulk552008]

@BlackDrakkAr I'd say simply moving in any direction is a lot more simple than jumping or spinning, as both of those actions require smaller movements into directions themselves.

[@calvinthedestroyer]

is the program availible for use?

[@kittyrocoa714]

It there an algorithm for discomfort ? Would this not make the robot walk better? That movement seems quite natural minus discomfort and even exhaustion.

[@Wildoutness]

Hmm, these things have the simplest thought, move. Add a wireless fed code that co-ops with cameras on the tops and bottoms of the legs and this thing could start easily learning about terrain navigation and then be made water proof. Then these things can be dumped into the ocean and we can find everything out. Since they look like starfish. Have them a swarm mind too!

[@danilaplee]

this is terrifiying and so much inspiring! how did they programm it, what libraries and languages did they use?

[@comalab2387]

I'm tempted to implement something like this but i'm still trying to figure out how to map joint mechanics in a 3D simulation to a real servo or stepper motor.

[@Intellectualwarrior11]

THE question I have is why did it want to walk in the first place if it has no knowledge of itself, why is it even moving, was there some stimili introduced in the programming? Im missing something here but what I can say is that its just a matter of time before were living side by side with robots, who for better or worse evolve like humanity has.

[@thegarginator]

Is there a specific research paper linked to this?

[@ninjafruitchilled]

I except that once it has decided that it knows its morphology well enough there is a second optimisation algorithm which searches for the correct way to move the motors (using the morphology model), in order to produce walking motion, optimising some movement criteria designed by the researchers.

[@genesisfox5412]

Soo... A learning robot? We are on our way to Terminator aren't we.

[@abdelrahmangamalmahdy]

+Genesis Fox Why do you think they're gonna be evil ?! The robots that people are trying to model are just designed to think rationally in every problem so they'd do the right thing whatsoever!

[@genesisfox5412]

Cause, this is a spider robot looking thing,... that's scary af.

[@lukemars7892]

+Genesis Fox spiders are mostly scary because people think they can kill you. This robot isn't really scary because you know its not going to hurt you

[@genesisfox5412]

ThoughtfulScience I'm not afraid of spiders, other people are, I guessed they were just creepy, so.. thanks for informing me :)

[@lukemars7892]

Genesis Fox lol

[@ramiBudemaris]

why don't you put the link simply in the description.

[@ThatBoomerDude]

I read the discussion. I listened to and watched the video. Yes, "we" is mankind. That is who builds robots. So yes, this is about robots but it's also about people if you want to get into what the robots are going to be programmed to be capable of. "We," as in some of us, cannot necessarily control what "we," as in others of us, are going to do with the things. So it certainly is not impossible for robots to turn (or be turned) against "us." In fact, some of them already are capable of it.

[@clown192]

I watched the other video on ted and on both of these the robot walks the same. But if you notice the legs dont have the ability to move forward, only up and down so there would be no way for it to learn to move one leg forward in front of another. Another idea for them to learn is to input a model of another robot already knowing how to walk. Like a child would see an adult walk. Either that or give it a video input with learning ability coming from the camera and then let it watch an animal walk or a person walk and see if it learns from what it sees.

[@sunghyunkim77]

Same old reinforcement learning, reward function coming from tilt sensor?

[@loading_wait]

Id image the reward function is a function of the error between its models and reality.

[@fireworm91]

What program did they used?

[@michaelstrunks3871]

its like infancy. to crawl before you can walk. the first clasps of sporadic movement.raw un biased.just beautiful. truly warming to see evolutions engineering. in the form of mans collected intelligence and to what his hands can conjure. and create. well done guys.

[@MatthewBendyna]

Actually, they say strings are packets of energy that only exhibit some frequency that causes it to adopt the properties of the elementary particles. Clearly, if it is made of energy, than energy is the smallest known unit. If string theory is correct, it only shows us something that everything is made of. Remember that basic law of geometry that says there are an infinite number of points on any given line segment? Anyway, we still need to identify what the dimensions are.

[@antiHUMANDesigns]

This means that the robot is self-aware, right? Something that takes its own characteristics into account when solving a problem is by definition self-aware, as I see it.

[@TheAwesomeKing1234]

+antiHUMANDesigns Not really. It is just testing if this works. If it works, test it. If it still works, try move the legs in a way that tilts it forward. It isn't aware it is just doing true or false test like any other computer

[@antiHUMANDesigns]

TheGamerPlayz Just like our brains do, aswell. No, by definition, if you consider yourself as part of the problem you're trying to solve, then you *are* self-aware. Or rather, the algorithm is self-aware. It doesn't really mean anything, it's just a term. Lots of animals are not self-aware, actually. They fail self-awareness tests we give them.

[@TheAwesomeKing1234]

Yes, but the robot is not thinking. It was not programmed to walk, but it was programmed to test the different walking possibilities then test if they are efficient, as in going the farthest the simplest way.

[@antiHUMANDesigns]

TheGamerPlayz Of course it's thinking. It's got a neural network as a brain, very similar to our brains. Our brains also think by sending binary signals through nerves. The question is not whether it's thinking, because it definitely is. The question is whether it's "self-aware". *If* it is true that to solve this problem, the things needs ot be aware of its own characteristic, then to solve hte problem, it would need to be self-aware. However, one could argue that it only needs to be aware of its body parts, and therefore the problem may not actually requires self-awareness. It's be like being aware of your shoes. I can accept that. There is a much better example of robot/AI self-awareness, which has even been recognizes as such: www.iflscience.com/rise-machines-robot-demonstrates-self-awareness-solving-logic-puzzle

[@TheAwesomeKing1234]

antiHUMANDesigns Ok lets settle this. It is not self-aware. To be self aware it needs to know that it is different from its enviroment. The robot doesn't even know its enviroment, what it looks like or even how many legs it has. It cannot think thoughts or even act in ways that it was not programmed to do. It does not have a neural network at all. It only has wires. It cannot feel anything. It is only using pre-programmed commands in certain circustances that it is programmed to detect.

[@theinterfaithshepherd9075]

that is really incredible. it 'created' a motion never seen on the face of the earth in all human history. THAT is really significant (if it's real and not a pre-programed response).

[@ConnorOBrienAwesomeness]

Now if only we could have this kind of technology on chatbots...

[@siamhasan288]

well now we have

[@mbonuchinedu2420]

yes we do now

[@Kurvomet]

Wow, this is so awesome. But i have to wonder, what way of moving it would develop if the last stage that he developed, wasn't actually last (the AI would be set not to find out ANY way of moving, but to find out MOST efficient way of moving).

[@zassi12]

he said it trys to figure out a way to move itself but how should it improve its technic when it doesnt even knows how efficient its walkins is at the moment then you need another variable like move the fastest from a to b and back and a method to collect data of efficient ways of movement

[@hellnawnaw]

Because it's walking cycle simulation is programmed to find a way to make it move. The farther it moves, the higher the "score" is for a specific walking cycle, and the best walking cycle is then chosen.

[@megothier]

As someone who works in machine learning, this is not necessarily the case. If we ever do create truly cognisant artificial life, it is completely possible that they will eventually come to realize that they are nothing more than experiments created for our pleasure. That's not to say I agree with the person you replied to, just meaning what he is talking about is a possibility, however remote.

[@ActiveStorage]

It always boils down to a personal believe system. Noone knows for sure whether something is infinite or not. I (again-personally) can not imagine or envision a finite universe. If you can, then let it be so.

[@pauloneill9880]

Should have had movements using least amount of energy like actual lifeforms to reduce wasteful movements and become more efficient mover.

[@Ultra4]

to improve that weird walk it just has to evolve the walk now, every step need to be a bi different that the last and test if it was improvement or not

[@FranklinW]

Or it could do it on a virtually constructed model of the patient from MRI/CT data. When it comes across something that works with the least amount of damage, it could then actually do it on the patient.

[@corthew]

It kinda looks like the way starfish move.

[@ThatBoomerDude]

Who is the "we" in your statement here? And what makes you think that they can control the actions of other human beings?

[@fizzisoda7113]

Robot teaches itself to delete emails.

[@Skindoggiedog]

@BlackDrakkAr "I mean just the idea of moving from a point A to a point B on a surface." It's not about that. It's about forming a picture of what it is. It must move to discover the range of motions it is capable of to give it the best idea of what it is.

[@erinlieb4535]

I never said anything about control. But yes, there are military robots starting to show up, and their's probably going to be at least one with some form of mounted machine gun, and it could probably be hacked. I don't think it would last as long to, say, get into a heavily populated area and gun everyone nearby down. Probably only shoots enemy freaquencies too.

[@athingwhichexists]

10 years later an a research group just acted like they were the first to try this in history.

[@jokisling1335]

Hello from last podcast on the left!

[@ToT0MoD]

this way you can attach other self learning robots of different species like an arm or a head or another body type/part.

[@flamechick6]

Kinda like a newborn baby, learning it's limbs, eyes etc. Starts out with random movements and over about a year they can walk and more

[@elon92]

The way it works (in most of these "self learning things" is that the robot produce a set of random algorithms to move it's limbs (once it knows how it looks like) and then it "merges" the best of those algorithms, and produce a new set of random algorithms, and merges the best of those with the best it's got. It's called artificial evolution, though not very different from natural evolution. The way the algorithms are chosen is by how far they move the robot, so to answer your question: no

[@fromhereon]

If there was a robot army that was self-aware and moved around like that, I'd blow my brains out without a fight.

[@jonasmuehlenbeck45]

Can I put this technology on a quadcopter learning to fly?

[@TheFatalGuide]

That's actually quite an interesting comment, and it did make me wonder for a bit. Personally I feel that it's the same way babies learn to walk. They recognise that there is a destination (from a to b), then they try to move and stabilise their boies through body mechnanics. The robot doesnt spin for the same reason why I think babies dont spin and jump while moving, because it would require more balance and stability. Not sure though, just my 2 cents :p

[@QueenOfMissiles]

This would be cool to apply to games like spore to have a creature adapt itself to unknown legs.

[@Caldaron]

I got some uestions: what makes the robot think it has to move? Also a very important one: didn't you teach the robot to rethink his strategy and try to figure out a more efficient way to move? rather than mindlessly crossbreed? In an economist's view your only trying to achieve effectivity without efficiency... maybe you want it to just look at one limb, what it can achieve in moving forward, and how the combination of all four can maximize the outcome... if your goal is speed with a minimum of speed, as well as vice versa... so you probably want to create different approchaes with different goals...

[@Ajg0r]

Efficiency was never important, they wanted the robot to figure itself out, not run as fast as possible.

[@Caldaron]

Yeah but it could also be a part of the equation. That it wanted to say to itself: is there a more efficient way to move? Because our theory of evolution is that everyone has just his personal approach compared to the approach of somebody else (which in fact keeps us deadlocked in the conviction that we need competition). Since we can reset the robot's mind and start from anew with different parameters it would come up with different results. Big data could then tell us which combination of motor activity would be the best in the GIVEN approaches. Which then could be a basis for improvement.

[@antiHUMANDesigns]

+Christoph Wolf Most likely, they're using a "fitness equation". That is, they give the robot a way to determine how well it's doing, by calculating a value of what it does using a specific equation that we've given it. The higher the value it gets, the more successful it thinks that it is. You could set any kind of equation, depending on what result you want. I assume they gave it an equation where moving at a faster speed is the definition of success, so the faster it moves, the higher the "score". But you could tie this in with moving power-efficiently, or give it minus points for not being a *smooth* walk (higher G-forces means lower score), and so on.

[@Caldaron]

+antiHUMANDesigns NICE! someone actually got it to brainstorm together via the social platforms. good call matey. just a tiny step for us ... ;-) am going to answer you soon, but i'm in something else right now ;-)

[@antiHUMANDesigns]

Christoph Wolf I am a programmer, and I know some things about these kinds of things. I've programmed neural networks and genetic algorithms, myself. Not a lot, but some.

[@JoeTinnySpace]

Aaaaaaaaaaaaaaaaand.... The robot grew up , he's gonna show up in the next Transformers movie...

[@MatthewBendyna]

Actually, I qualified your statement. If string theory is correct, then we have found a unit that composes all matter that we know, but that doesn't mean that it is necessarily the smallest unit. We still don't really know what energy is and what is the cause of space-time? So we don't really know what basic reality is yet even if we prove string theory.

[@gothicfan51]

@EnchantedWalnut He isn't trolling he is just pissed off with people saying "thank god". So you thank god for my response.

[@RottenSquash]

I have reason to believe that, during the first few moments it was on, it was experiencing sheer terror and confusion, as evidenced by the frantic calculations and the awkward writhing. I would imagine it was thinking something along the lines of: "OH GOD WHAT AM I???????!!!!!!!!!!!"

[@Tailsthehacker01]

If we ever have microscopic robots capable of working together to form shapes, this would be an extremely useful way of letting the "new robot" know how to move and such.

[@ExOAte]

I understand that, It would be truly amazing if residing in the 'black box' it would have to understand the 'knobs' too. Now it has a headstart. But it's a step in the right direction nevertheless ;)

[@Pe0ads]

Pretty cool! It still has the concept of legs and motion built into it though, so it hasn't completely worked out everything on its own :P Although there's a pretty decent case (Kant, Chomsky) that says humans have concepts like motion, shape, space, built into their heads already, so the robot isn't too dissimilar!

[@charedet]

If you guys want to see the full conference here is the link: library.fora.tv/2012/01/19/Cognitive_Robotics_and_Artificial_Intelligence Its very interesting!!!

[@ronerickson8083]

Robotic Code for Cognition corrects SOST speed - F=m(5*9*53) search for this in KZbin to watch the PowerPoint it is a perfect code. It is for a truly self-aware robot we need them to be self-aware to help us all not just a select few.

[@jozo314]

Level up, now to the next stage, awareness of the terrain. After that it would be pretty good to make it search for energy sources. Next we have to make it train self defense against possible predators.

[@KiraSlith]

that movement reminds me of a starfish actually. a logical and fairly efficient movement pattern for something with 4 legs in that pattern.

[@KungKras]

@BlackDrakkAr It can probably sense if it's moving through accelerometers or something. Then moving in the right direction would probably just be a result from sensing the right input from the accelerometers.

[@ActiveStorage]

fractal math and fractal geometry makes me happy. Maybe it will help us to describe some real life phenomena.. someday.

[@kittyrocoa714]

Also robot parts seem to expensive if say you wanted to try making small robots at home.

[@JacobEllinger]

can't you just program it to move randomly and give it a true/false statement based on a laser sensor directed towards the nearest surface. if the last set of moments makes the distance between it and that surface it records 'true' (closer) it then saves that motion. then after repeating that motion it does another random motion and if it is 'false' then it keeps doing random motions until it gets another true. Then program a statement that says if the distance between it and the object shrinks faster then a set rate then it can stop trying to come up with new movements and just keep using the last recorded ones until it's destination is reached? you're welcome programmers :)

[@Oglokoog]

Jacob Ellinger This would be incredibly inefficient. The vast majority of random movements don't result in any meaningful progress. This process eliminates a lot of the randomness.

[@JacobEllinger]

Petr Vacek so says ye. I says nay. but seeing as I have not tested my idea and seeing as neither have you; how about you stop claiming my idea is inefficient. And I'll stop thinking you are a ass. :)

[@Oglokoog]

Jacob Ellinger You really think these scientists didn't think of that?

[@Oglokoog]

Jacob Ellinger Note that the robot doesn't even know what configuration its limbs are in. You see what happens when it just moves randomly at the very start. Your method probably would EVENTUALLY result in movement comparable to what they achieved, but that's not the point. The goal of this wasn't to make a robot that walks, it was to make a robot that can learn how to walk based on very little information.

[@JacobEllinger]

Petr Vacek I don't know. wait while I go ask every scientist in existence and read every history paper on the subject. I'll get back to you then.

[@deinemutter269]

the question is: wasn´t the plan to let it make MORE experiments with itself, UNTIL it finds out, how it can walk in a REALLY GOOD way? isn´t it possible to let it make more experiments?

[@TheDrexxus]

YOU ARE GOING TO WALK LIKE A SPIDER! No, dad, I want to crawl on my belly! I HAVE NO SON.

[@David-dq2hu]

that is the scariest thing i think i have ever seen. could you imagine if we game it 1 year to think... or program... or do what ever its doing??? we really need to be careful

[@ActiveStorage]

Also does it make sense that we are allowed to divide by 0? Or does it make sense that any point in space has only 1 dimension with 0 radius yet we can see it and measure its location? Or that any plane is a 2 dimensional object with 0 "thickness" that can curve through 3d space? My point - abstractions have been fucking with people's minds from the beginning of times, and all modern scientific theories are the product of theoretical physics and mathematics. So, no wonder it is so confusing

[@MrFunnylicious]

if you leave it running long enough would it eventually find the most efficient way of getting from point a to b

[@mcbeaumarchais7650]

A good way to answer your question is to ask the question "What is the most efficient way of walking?" Humans have a few different ways of walking, but for the most part they are all quite similar. It might actually be possible to find more efficient ways to walk with respect to some criteria, but just as a human would never know if their walk is the best walk, a mechanical intelligence would never know if the method it found was the best. A robot like this might theoretically keep subtly changing its method, but it would never find a final state, and you can't predict when and if it would find it.

[@kittyrocoa714]

Is there no materials like skin that can give robots the necessary sensory input to function better?

[@ToT0MoD]

i wanted to place an important message to the right person but don't know who to talk to. so. now that it can walk, they should adjust the programming so that when the robot discovers his legs, that he wil learn different ways of walking and choose for himself the most balancing walk there is from those different style's. the robot is walking like this because he reacts best to his gyrosensors and thus you'll have a crappy walk. the point is, let him walk the way the gyrosensors don't angle much

[@MrKristian252]

5:15 after I saw this, I blocked FORA.tv

[@ix12]

The design (leg positioning) doesn't seem the best for walking. If you'd design it like a cheetah for example, the robot will probably learn to walk with the grace of a cheetah (at its own pace, since its motors are slow, but it will make the best of it :) ).

[@asyncasync]

Complicated as in someone or some very good and talented team, who have a good inside on their specific target.

[@elon92]

Sorry, well, I answered your question with a simple no :P But I should elaborate, a robot cannot understand a concept of any sort so far. it is just a series of algorithms, a series of equations which tell it what "walking" is. You could think if it as an if statement, "If my x position (given by sensors) has changed, then moved = true". So therefor this statement will not be true if he manages to jump and therefore he will not :P But it's basically all just math, no true "understanding"

[@AEOsama]

amazing....I've been working on similar concepts that will allow robots to self evolve generically and in any field.

[@Dragongod5890]

I want the software. I want to test it on my robot.

[@kekeke1201]

How does the AI know when it should abandon the current neuron network and go for a new one? If there is no reward and punishment system, how can AI know it is doing things right or wrong? Besides, is it not much easier to have an AI watch different real human walk cycles first and then has it figure things out on itself while only giving it one target of not losing its balance? Can we in theory then simply put such an AI, which has been running in simulated environment for long enough, into a humanoid robot and just leave it in a huge room with different terrains and when we come back see it parkouring in the room?

[@empyrionin]

The way the presenter talks about the self-modeling of the robot motion in order to go forward make me infer that somehow the robot is programmed to construct such models and therefore, you can make an analogy in that the robot is like an animal born with the instinct of walking (transporting the body in a direction). Therefore, since it ''feels'' the ''urge'' to walk, it's basically an artificial intelligence with the IQ of let's say something like an ant, which is remarkable indeed.

[@kanrup5199]

robot: aargh why would you do this! im in paain! (drops off cliff)

[@cocoxcocoa]

this would be a game changer in military robotics 20 years down the line.

[@iNINJAgamer]

Looks like something straight out of a alien movie… featuring robots tho. 👀