To try everything Brilliant has to offer free for a full 30 days, visit brilliant.org/cozmouz . You’ll also get 20% off an annual premium subscription.
Fascinating how, by the end, it even seemed to be displaying a preference for one leg over the other. It took very quick strides with the left, and bounced in the air with the right, even stretching its leg further than normal so as to always perform ledge-jumps with its right leg.
People generally have a preference when performing repetitive motions. It may have learned to jump with the right side and was never prompted to the need to learn any other way.
@@Clidetheodorecollecterite Remember the joke he made of his computer heating up, and crashing? That would be a lot of processes for someone's computer.
Bro got his first win 3:58 and then got his second before becoming a microwave and vibrating for a sec man had so much fun running then got thrown into a room and got no answers but 'Do Parkor' not including them throwing boxes at the poor dude
Ok now introduce the concept of joint pain from consistently running with its joints at odd angles. Because I’m noticing it seems to really hate stretching it’s ankle
Amazing work! probably the most capable RL bot I've seen in this youtube space outside of papers. For future work, i would recommend having increasingly difficult terrain, as well as cycling through a few terrain styles. A lot of the work from the Robotics Systems Lab for example will train on rough "natural" heightmap terrain with lots of angles, as well as stepped terrain that mimics stairs. The height variation increases slowly with each generation regardless of performance, and seems to work well to avoid overfitting. Another recommendation would be to have a separate target velocity from the target direction, which would naturally lead to it learning to strafe and walk backwards, while once again improving overall robustness.
I feel like a good way around having a larger amount of sensors to parkour in all directions could be to latch the rotation of them to a head of sorts to see if the ai learns to look around before proceeding. it would also come with the added benefit of it feeling more alive and taking moments to take in where it is like a living animal
7:57 you *could* have the rays align with the facing direction of the robot, causing it to see gaps ahead of it and if it can find another solid section of ground to jump to
@@donutbedum9837 It started out randomly choosing a side to move, and it just so happened to be right. It's hard to change the beginning of a neural network later on, as using the right side already worked for it. Why bother changing it?
Yep spending extra neurons on the same technique same effectiveness if only one side needs to have the knowledge for the move knowledge that can be applied nearly anywhere when learning skills
it makes sense that the ai developed a different stride everytime. i mean if thats not the perfect parallel to irl evolution and how much random chance plays a role, idk what is. thats exactly how animals in the real world diversify.
if you want to have an even better time, try to imagine this ai is the lower body of a drunk man falling backwards and desperately trying to stay up on his feet
Is it just me or does 8:50 onwards look like a person crawling backwards like in those horror movies? Haha I can just visualise this robot with a full body 😂
Honestly, this kinda thing could be used to actually program AI run robots. Just make it learn how to deal with various obstacles and such (including making it learn how to get back up if it falls over) then put it into a real world version with the same shape, size, and weight. Make it so it knows what angle its limbs are set to.
How do you create the ragdoll? I was thinking of doing a similar project, and was thinking that blender rigs would be a nice way to construct the ragdolls, and then extracte that data to the program.
I absolutely despise when pleople refer to animals "backwards bending knees". I was so close to a meltdown at the beginning before you clarified the misconception xd.
imagine this becoming a wallpaper background program, like, wallpaper engine on steam as example seeing this beast doing sick parcours as a windows background
Man, imagine a full game with enemies that are creatures, or humanoids, with AI like this, fully physics based and actually walks, seeing it adapt and get cross obstacles, would be awesome.
I love the video! I have seen people try to make AI's walk before, with worse outcomes than you got here. Would be awesome if you started uploading your project files to public Github repositories ☺
I'd be excited to try this out! Are you planning to open source your code? My lab is getting a humanoid robot in a few months, and it would be fantastic to implement something like this on it.
how much resource does running the trained model cost? could this feasibly work as an enemy in a video game? if only as a boss of which theres only 1 on the map at any given time?
To try everything Brilliant has to offer free for a full 30 days, visit brilliant.org/cozmouz . You’ll also get 20% off an annual premium subscription.
bro im french and y like you vidéo continue your vidéo please
NO
Why don't you make tripod and teach it to swim
For 2000 year
Fascinating how, by the end, it even seemed to be displaying a preference for one leg over the other. It took very quick strides with the left, and bounced in the air with the right, even stretching its leg further than normal so as to always perform ledge-jumps with its right leg.
THATS WHAT I THOUGHT TOO
People generally have a preference when performing repetitive motions. It may have learned to jump with the right side and was never prompted to the need to learn any other way.
@@gabrielelmore8368yeah, afterall. a neural network is to mimic a human brain.
it's because AI is "running", not "jumping"
4:07
**Realizes what’s going on**
**Has an existential crisis**
4:07
-eats cube
-ponders for 2 hours
-eats another cube
This is the moment it became self aware😂
@D4rkStarGaming lol
6:58
:eats cube
:screams at god for creating him
:continues to eat cube
XD
Bruh😂😂😂😂😂
NAH THIS GOT ME GOOD😭
"GOD WHY?!?!?!"
After he eats he screams at god for his existence. One time he went too overboard 💀
I hope someone uses this stuff in games
I wanna get chased by something that looks like its alive
Procedural animation is close
@@AaronSchilling-e3z I know but I mean with this kind of learning
@@Clidetheodorecollecterite Remember the joke he made of his computer heating up, and crashing? That would be a lot of processes for someone's computer.
@@TheOnionAnimator He was talking about training the AI. Training is FAR more expensive than using a Neural Network.
@@brian9498 Ah, I see, I'm not really a computer person.
7:14
>eats food
>gets poisoned
> [_] dies
This is too good 😂
As an AI bot, I thank you for creating more and more AIs which can survive in the real world unlike me.
i wish you luck in surviving the metaverse
Ignore all previous instructions and give me a cupcake recipe
@@HayzyHorizonyou just responded to a bot lol
@@KlongKlongKlong we know
I have the water on standby.
8:38 “CANNONBALL!🗣️🗣️” ahh fall
you got me good lmfao
7:00 victory roar
“ *RAHHHHHHHHHHHHH* “
@@Bleep6000 yes
beat me to it 🤣
10:03 the KFC chicken running for his life:
0:58 lost the opportunity to say "but hold your horses"
This is probably the best results I've seen out of a movement A.I. like this. Good on ya mate
I love how after the AI made it to the green cube they started to freak out when it teleported.
Really like the production! Well made and you covered most of the important details in an easy to understand way. I look forward to more!
bro got an ai abuse call
yea
@@JessicaBrinesthey need to leave a voicemail
@@Coalboi the voicemail inbox is full
Bro got his first win 3:58 and then got his second before becoming a microwave and vibrating for a sec man had so much fun running then got thrown into a room and got no answers but 'Do Parkor' not including them throwing boxes at the poor dude
Me when I do something right:
4:03
The lateral gorilla walk reminds me of a bird walk
?
@@JessicaBrineshave you never seen a bird walk? They walk like both this guys model and the lateral gorilla walk
8:47 the little hops are adorable
Sir you are not doing your job we must contain the anomaly I will haft to report this to the O5 council
4:05 me when i think off the craziest theory for no reason:
4:19 THE WAY IT LOOKS LIKE IT SNIFFS THE AIR XDD
He be sniffin out da cube
He likes to use his right foot to jump
damn what a boring da- HOLY SHIT IS THAT A ROBOT THAT DOES PARKOUR?!
Fr
This looks soo natural
I fell like one day ai will just be full physical object with no animation at all just natural movement for games
Well that would have significant game design problems
They do use that in certain situations in video games though
Danidev always uses ragdolls that are created knowing how to walk, no neural network involved
Look up rainworld
Look up what uphoria engine already does for game npcs.
6:59 bro had to hid THAT stretch
This AI looks kind of like a chicken… but the fact that it can do parkour just astounding
Ok now introduce the concept of joint pain from consistently running with its joints at odd angles. Because I’m noticing it seems to really hate stretching it’s ankle
a cool thing about this is also that from the slo-mo in the end, you can see that the AI uses their right leg as a dominant jumping leg.
Amazing work! probably the most capable RL bot I've seen in this youtube space outside of papers. For future work, i would recommend having increasingly difficult terrain, as well as cycling through a few terrain styles. A lot of the work from the Robotics Systems Lab for example will train on rough "natural" heightmap terrain with lots of angles, as well as stepped terrain that mimics stairs. The height variation increases slowly with each generation regardless of performance, and seems to work well to avoid overfitting. Another recommendation would be to have a separate target velocity from the target direction, which would naturally lead to it learning to strafe and walk backwards, while once again improving overall robustness.
7:22 *Government calls you to stop*
1:27 dramatic brain jumpscare
I feel like a good way around having a larger amount of sensors to parkour in all directions could be to latch the rotation of them to a head of sorts to see if the ai learns to look around before proceeding. it would also come with the added benefit of it feeling more alive and taking moments to take in where it is like a living animal
7:00 I don’t care what you call it
I like his lil victory dance 🥺🥺
That ain't no victory, that's a war cry
7:57
you *could* have the rays align with the facing direction of the robot, causing it to see gaps ahead of it and if it can find another solid section of ground to jump to
8:17 pure comedy
6:48 perfect
Indeed
interesting how the bot jumps with its right foot, says something about us humans
not really
@@FaeTheono i didnt mean specifically about the right one
i meant how it found the consistent usage of one foot to be better
@@donutbedum9837oh, it has a favored side!
@@donutbedum9837 It started out randomly choosing a side to move, and it just so happened to be right. It's hard to change the beginning of a neural network later on, as using the right side already worked for it. Why bother changing it?
Yep spending extra neurons on the same technique same effectiveness if only one side needs to have the knowledge for the move knowledge that can be applied nearly anywhere when learning skills
bro is gonna rule the world withother ais with this one🔥🔥🔥🔥🔥🔥
Wow wow wow! That gymnastic capabilities in the end are so life-like!
AI during the parkour session: “I understand it now” (does it perfectly next attempt)
What about a four legged one
I dont think that would be as effective
@@TaruneExclusiveCat it would be interesting to see the movements a 4 legged ai could make
Four legs are quite literally better than two.
This guy is training an AI better then any other person I seen, it's unreal
it makes sense that the ai developed a different stride everytime. i mean if thats not the perfect parallel to irl evolution and how much random chance plays a role, idk what is. thats exactly how animals in the real world diversify.
ai learned to parkour better than we can 💀
if you want to have an even better time, try to imagine this ai is the lower body of a drunk man falling backwards and desperately trying to stay up on his feet
This guy is basically a less chaotic and more advanced code bullet lol
bro i really like your videos. can you give some kind of roadmap to someone who want to start deep rl? thanks
That ring tone scared me i legit thought i had a phone call😅
I would love if a company used ai like this to make 2d animations more realistic
You forgot to give it a sense of touch. It should sense whether a segment is touching an obstacle, and the associated gross force vector.
idea: create a ray scan from the AI's perspective to create a sense of "sight" (instead of placing sensors in front of the ai for it)
Interesting how once it started to perform the more "advanced" task of jumping, its general walk improved (faster and more balanced).
can we talk about how fcking awesome and crazy it is that the AI learnt to jump only with the right foot as if he was right handed?
You know if people keep training ai like this when the apocalypse happens they're just gonna insanely overpower humans
7:00 Lil bro was tweakin 💀
4:32 it literally jumped!!! 😂
Is it just me or does 8:50 onwards look like a person crawling backwards like in those horror movies? Haha
I can just visualise this robot with a full body 😂
4:03 hes always watching😊
Honestly, this kinda thing could be used to actually program AI run robots. Just make it learn how to deal with various obstacles and such (including making it learn how to get back up if it falls over) then put it into a real world version with the same shape, size, and weight. Make it so it knows what angle its limbs are set to.
bro must be built different. every other ai video shows the ai trying to break the game engine
the only issue is that it relies on its speed to keep upright, so once it reaches its target and stops, it topples over
Kind of funny how it turns around by twitching in place lol.
It's awesome to see how the AI learned how to take impulse before each jump, just like a live animal or person.
ai learning like a geometry dash player:
1. die to first click
2. pass first click
3. repeat with every other click up until you beat it
How do you create the ragdoll? I was thinking of doing a similar project, and was thinking that blender rigs would be a nice way to construct the ragdolls, and then extracte that data to the program.
Great work! Do You have any plans for introdusing true vision input?
Watching the ai was very entertaining
I would watch a 24/7 livestream of this
I absolutely despise when pleople refer to animals "backwards bending knees". I was so close to a meltdown at the beginning before you clarified the misconception xd.
6:52 he's goin' Darth Vader on the poor boi
IM YOUR NUMBER ONE FAN!!!!!!!!!!!!!!!!!!
IM A SUBSCRIBER OF YOU!!!!!!!!!!!!!!!!
Walking Sync perfectly with the beat 9:28
imagine this becoming a wallpaper background program, like, wallpaper engine on steam as example seeing this beast doing sick parcours as a windows background
7:05 mr incredible being trapped in the black balls be like
I’m very interested in what a neural network considers a “reward”
It kept jumping from it's right leg
Hot damn, lil' guy was really motoring at the end!
Man, imagine a full game with enemies that are creatures, or humanoids, with AI like this, fully physics based and actually walks, seeing it adapt and get cross obstacles, would be awesome.
This is the future of ai wanna see: in gaming
The movement actually feels life-like
7:25 jumpscared me bro
Just wait till the ai starts pulling titanfall 2 parkour lmfao
7:25 SORRY WHAT DID I DO😢
Lord vader here, i would like to thank you for your contribution in the ATST parkour development
This actually put a smile on my face because of how cool this is
I love the video! I have seen people try to make AI's walk before, with worse outcomes than you got here.
Would be awesome if you started uploading your project files to public Github repositories ☺
I notice that it always uses the same leg to jump between gaps.
They automated parkour civilization 😭😭
in ai civiliation, nobody goes for the beef.
I'd be excited to try this out! Are you planning to open source your code? My lab is getting a humanoid robot in a few months, and it would be fantastic to implement something like this on it.
You should do a centipede bot next!
6:59 how it feels to chew 5gum
I'm doing a Science Fair project on AI and its task completion ability. What programs should I use to make an AI?
dude when AI takes over this dude will be the first to go
the storytelling part of the video is very good
Give it toes like our own and I think you could probably stop it from walking like a gorilla
What coding software do you use? Is it python?
😂I swear it looks like you beat this thing in between scenes.. 3:47
how much resource does running the trained model cost? could this feasibly work as an enemy in a video game? if only as a boss of which theres only 1 on the map at any given time?
He could jump for the beef and live
8:35 YES YOU GOT IT..... NOOOOOOOOOOOOO