Perhaps if we had muscles with infinite expenditures of energy, the most efficient way of running would be this, but it must be extremely tiring to run raising the knee so much and with the arms dancing like this.
This tech would be super useful for a parkour game like the one Storror is working on. If this tech gets optimized to the point where it can run in the background of a game in real time, moving characters dynamically based on the environment would be so much easier!
Me vs research papers ~ sleeps in 5 minutes and thinks it’s fucking boring Me vs Two Minute Papers ~ watches the full video on something random and thinks it’s so cool. Videos are really well explained and visuals and presentation are incredible
With this stuff getting as advanced as it is, if RDR2 were made maybe 10 years later, all of the intense animation work that was put into it could probably have been handled by an AI that works in real time.
0:55 These funky walk procedurals will eventually stop happening when more factors are considered/added on; e.g. limb weight, resistances, stamina, muscular energy consumption, energy efficiency conscientiousness, etc. Eventually we'll see models figuring to run like Usain Bolt on their own
These kinds of things seem like such obvious innovations that could be employed to get better behavior. I wonder why they aren't already being done. Another consideration is frequency of movement. Energy consumption would guide this some, but energy isn't the only resource: the human brain can only put so much detail into a movement.
@@Taudris I bet somebody is working on it right now for sure. I think the thing is that there is a maximum speed with which things can progress because it still takes a human to write and run the code, to write the paper, get it reviewed and accepted at some conference etc. In AI there are a lot of things like the ones you name that are very obvious but also still to get it really right it takes some time to fix bugs and especially to tweak all the parameters involved in such a simulation. Cause my understanding is that still there is a lot of trial and error involved to get good results. Some AI researchers might get offended but probably lots of deep learning AI research is still more the result of intuition, exploration and trial and error rather than a solid science based in theory. I'm probably not qualified enough to make this a strong statement, just a hunch that I got as a student recently getting into the topic.
So, total energy use (enthalpy + potential energy + kinetic energy), accounts for limb weight, tries to minimise the amount of energy used per movement or stroke...
2:15 How I imagine doing backflips (Reference) 2:10 How It looked like when I tried to do it (Simulation) Jokes aside, this is a really great advancement in our virtual technology. Two Minute Papers's narration is great as well, clear and onpoint.
in order to make these fine algorithms truly wonderful (and usable across a wide spectrum of cases), is it yet possible to use 'straight' video (of a human or a cat or any animal) as the reference motion? that could mean, for instance, that a different algorithm parses the reference video motion into CG motion (ie mocap producing for example bvh, fbx) so that it can then be fed into this algorithm. from an admittedly quick glance at the paper and github i could not see what format the reference was supposed to be in, but it must be there somewhere. there are commercial mocap offerings for 'straight' video (with no depth cameras), but none that i have seen is good enough for this purpose - unless it was cleaned up by some other AI, possibly even a variation or adaptation of the one presented here?
maybe by using two different AIs together we could achieve that. One ai would find the position of the bones and joints to make a stick figure with different levels of tint/shade to indicate depth. Then a separate ai would create a 3d model and animation from the stick figure.
th-cam.com/video/F84jaIR5Uxc/w-d-xo.html ☝️ poses estimated from techniques like this should suffice. Even if the reference motions are "glitchy" (discontinuous in position through time) from the pose estimations, the mimicking RL agent will be forced to create a smooth approximation. This is due to the fact that the agent cannot produce discontinuous motions in the physical simulator while only having control over force applications at joints. Then you can optimize for minimum force applied at joints or for minimizing total kinetic energy to really get a nice looking result.
The author of this paper has published a follow up paper. xbpeng.github.io/projects/AMP/ The follow up paper uses GAIL. There is a separate critic model that tries to distinguish between the reference animations and whatever the physics rig is doing. The physics rig is trying to fool the critic. I think this could be used with your idea. As long as some physical measurements (rotations and velocities) could be estimated for the joints from the video sources (another model could be trained to do this). Then these measurements could be used as sources for the GAIL critic.
@@tchlux thanks for pointing out the 'AI-Based 3D Pose Estimation' paper/video. very promising. i would love to see mocap results for an animal such as a dog or a cat. the reason is that with good mocap and even better predictive motions (so that i can direct my animated cat to jump on a stool or stroke its whiskers etc) animated films could at last become affordable to make (thus, in theory, allowing for better and more original stories).
Hearing that a developers favorite past time is to throw boxes at AI characters to see what they can take somehow makes me feel better about my life and how far I’ve come.
The potential this software has in game development and animation is absolutely amazing. Imagine a player character with this backup ai and looser animations and unique interactions between the player and the environment.
Imagine having an AI controlled character in a video game that is able to attempt to maneuver in specified ways given any dynamic environment. It would look less programmatic and more flexible.
Rockstar did something like this when they used Euphoria engine to animate its human characters in GTA4. Characters would hold on to handrails as they stumbled, push themselves off your bumper if you nudged them with your car, all demonstrating incredible self-preservation that would be impossible with canned animations. I believe the series still uses the engine. Not all of the animations use the engine though, they're canned until the AI needs to kick it in to keep a character from falling over or doing something that would look silly. They called it "intelligent ragdoll".
0:45 once I saw this, I immediately went to grab a piece of paper for me to hold on to. Edit: having seen the entire video. I believe this would be very impressive for making procedural animations. some video games already use procedural animations, but this would allow for it to be used for the entire animation process, which would drastically cut down on time/effort.
I don't know why but that little guy trying to keep doing back flips even while sitting down and you saying A for effort had my laughing so hard I was crying.... really got me for some reason lol
Possible future development could include 'reflex response' characteristics, such as if a character is falling, that they try to grab out toward the edge or any protrusions etc. Another example would be if a projectile is coming toward a vital area, that the character flinches. When combined with the energy level simulation variables, it can create some very realistic behaviors. A character which is extremely tired (low energy) may not notice a projectile and therefore not flinch.
@@প্রীতমবিশ্বাস Google "Boston Dynamics robots" or look on TH-cam. He's suggesting their robots could be improved by applying such learning techniques (or the results).
The next step is obviously to give it the set of simulation options for locomotion and place it in a virtual level with obstacles and task them with making it to the end focusing on efficiency of action or speed of action. One option allows for low energy consumption for robotic ambulation, the other provides for emergency response movements.
Why not tie its motion to an energy expenditure function, so that it finds the most efficient way to move? Have it compromise on speed and energy consumption? Maybe it won’t run with its arms flailing about because it would get tired sooner.
Decrease body mass was a psycho walk. Also, i want to see a version of the human movement on MORE gravity, as well as seeing if a lion could do backflips (aka, non-humanoid figures trying to do nontraditional motions given the limitations of their body)
i gotta admit, i like the way the AI approaches running 0:55 😁 but jokes aside, this is an amazing paper! we are finally getting closer to robot pet buddies!
This would be really cool to see in more video games. I always thought that jumping and movement animations in platformers would be cool if they were more realistic. That way we could learn movements from them, since we’d be functionally learning from a master.
Some may be scared seeing a robot running and jumping, but the last part of this video shows the incredible application for future: robots can adapt to out-of-earth environments much much quicker than humans! Humanoid robots could even be sent to Mars before humans.
Ha, I saw the character running at 0:55 and wondered if it could be improved by considering energy usage, then at they end, they actually try it! It turns out it just makes the person look old.
I recall 2MP talking about a paper where they created a better way to simulate more realistic muscles. I wonder how long it'll be until this AI can be used to automate a hyper realistic body, frailty and all. Imagine it being able to automate say an elderly AI's ability to climb over say a log or something. Any sort of elderly AI. Human, fox, cat, dog, horse, dragon, whatever. Pretty cool stuff to think about.
4:16 I couldn't help but think of that old obstacle course show Most Extreme Elimination Challenge, and wonder if we are in a simulation where our overlords are testing our machine learned animation and physics.
I could see this replacing animation trees in AI for computer games. Instead of having to animate 50 different animation states, and blends. You can have the AI chose the reference motion from an entire list and have it dynamically blend with the environment and actions. Leading to more dynamic NPC enemy, friendly or neutral movement and interactions.
I could see this being used in multiplayer shooters to give player characters realistic animations to the environment. Battlefield 5 tried it but fell a little short. I can just imagine characters responding to the environment, position, velocity appropriately. It would do wonders for immersion
I'm very interested to see if you could pit two of these virtual people against each other in hand-to-hand combat to see what martial artistry they might come up with - you could increase their strength or speed to find out what a fight between superpowered humans might actually look at!
I love your enthusiasm. I still have no idea how you create these simulations, having only grasped the absolute basics of Convolutional Neural Networks looking at hand written digits. However, even that helps a little.
What would be interesting is tweaking point values based on energy used to resist gravity, possibly resulting in a more realistic run if the amount of energy expended is higher (no more arms in the air resisting gravity)
Given it is part physics simulation has anyone tried applying different weights to various models? Such as a heavy backpack or a light shopping bag. Perhaps coding where the model has to maintain the weight during the movement but also protect it in the case of fragile items.
6:09 the right character is the reference of actual ninja run that so many people think as "retarded" and "useless", it's actually using less body volume to move forward, which in the long run related to the total amount of energy needed to reach a certain distance, and you might hate this, the real life ninja run is not about speed but conserving energy, ..but yes in cartoon or anime since they rely on plot armor
That last bit, with high and low energy means that the energy that the character uses to move is kept track of right? Parkour, specifically jumping off high ledges is all about prolonging the dissipation of potential energy so that you body doesn’t absorb too much. During a backflip, you speed up your angular velocity by bringing the centroids of your limbs closer to the center of mass/rotation. This allows the smallest possible amount of angular momentum to creat a full flip. Running (or even standing) is just a rhythmic shifting of the centre of mass from one leg to the other, with children learning the most energy efficient way of remaining upright. Are there any papers that take the reference, then also tell the simulation hey this is the type of energy to dissipate or minimise or maximise, regardless of the amount of energy used in the other types of energy? Like you wouldn’t bother waving your arms around (give them angular momentum/energy) unless you were about to fall (lose potential/height energy)
This looks like the future of how games will implement physics and collisions with characters. Seeing as how it reacts with a dragon and non-humanoid, what if you made it a man-made object like... a car? a plane? helicopter? ... boat? I'm curious what'll happen since I believe it will need to define parts as muscles
So what I'm hearing is:
We could teach a robot dragon to walk near perfectly on the moon before the hardware ever leaves earth. Amazing.
What a time to be alive!
Profile picture checks out
even when space debri start hitting the robot
Exactly what I heard. :)
That's generally a good workflow honestly. Prove you can simulate it before you waste metal on an actual dragon.
I like the way the AI thinks that humans should run before it sees the reference. I think I’ll start running like that when I jog.
Perhaps if we had muscles with infinite expenditures of energy, the most efficient way of running would be this, but it must be extremely tiring to run raising the knee so much and with the arms dancing like this.
@@esleygonzaga1769 same with the arms. With infinite shoulder power you can raise your center of mass for finer grained control
@@esleygonzaga1769 Exactly what I was thinking. Add "tiredness" to the model, as well as "endurance" to the fitness score.
This is how Naruto runs when he goes super saiyan.
We know more, we evolved to run
AI-man lying on the floor trying to backflip: "Why was I created like this?"
Made me think of some people who tend to keep trying after the initial conditions for success are gone.
@@MartinHindenes That is an interesting way to put it. What do you mean? Like a guy born 5 feet tall trying to date?!
Existence is pain, Jerry
"why do we live, just to suffer?"
@@MartinHindenes That's right, this is life
I wanted to see the T-Rex doing a backflip :(
Me too
It would be interesting to see with which technique an AI would come up with, since the tail and other parts makes it non-trivial task to do
I think it failed to do a backfilp so they didn't show it on demo. I mean, I would definetly try it and show it if it works :D
And if it did a perfect backflip. What will the next Jurrasic Park be like? :)
@@jvankooo
TREX FLIP
BOTTOM TEXT
When I told my parkour and stunt friends that one day a robot will take their jobs soon they laughed at me. Well, here we are ...
Im a professional stunt man and this shit is both exciting and very worrying lol
@UC_9WEQOrt2m2Y7J4U7UElSg That was really interesting! Thank you for sharing
This tech would be super useful for a parkour game like the one Storror is working on. If this tech gets optimized to the point where it can run in the background of a game in real time, moving characters dynamically based on the environment would be so much easier!
Ministry of Silly Walks: Looks like we no longer have a place in this world.
They might have laughed at you for being a luddite😆
Me vs research papers ~ sleeps in 5 minutes and thinks it’s fucking boring
Me vs Two Minute Papers ~ watches the full video on something random and thinks it’s so cool.
Videos are really well explained and visuals and presentation are incredible
This one got me good. Thank you so much! 🙏
This could really speed up the animation process from movies and games.
I've been preaching about this for a long time. Every game studio needs an animation AI expert to help streamline their whole process.
Imagine a game where after shooting the enemy leg they start to stumble and limp realistically.
With this stuff getting as advanced as it is, if RDR2 were made maybe 10 years later, all of the intense animation work that was put into it could probably have been handled by an AI that works in real time.
@@godofthecripples1237 it's incredible, every time they say a job can't be automated boom!
@@The0Stroy Some games already have that, but this could be more easy if instead of coding it manually could be automated by the AI.
0:55 He looks so happy and careless.
Me on my first trip to the pub after lockdown
Underrated comment 😂😂
Narrator: "You can also see that the technique is robust against perturbations."
Atlas: *Gets buried.*
Boston dynamics robots vs boxes
rwby
6:10 - The Normie "Reference Motion" vs. The Chad "Use More Body Volume" vs. The Virgin "Use Less Body Volume"
lol, I had the same thought
One looks like a zombie. One looks like it's holding the biggest shit of his life
Normie VS Vince McMahon VS Post-Chipotle
Early termination
0:55 These funky walk procedurals will eventually stop happening when more factors are considered/added on; e.g. limb weight, resistances, stamina, muscular energy consumption, energy efficiency conscientiousness, etc.
Eventually we'll see models figuring to run like Usain Bolt on their own
These kinds of things seem like such obvious innovations that could be employed to get better behavior. I wonder why they aren't already being done.
Another consideration is frequency of movement. Energy consumption would guide this some, but energy isn't the only resource: the human brain can only put so much detail into a movement.
@@Taudris I bet somebody is working on it right now for sure. I think the thing is that there is a maximum speed with which things can progress because it still takes a human to write and run the code, to write the paper, get it reviewed and accepted at some conference etc. In AI there are a lot of things like the ones you name that are very obvious but also still to get it really right it takes some time to fix bugs and especially to tweak all the parameters involved in such a simulation. Cause my understanding is that still there is a lot of trial and error involved to get good results. Some AI researchers might get offended but probably lots of deep learning AI research is still more the result of intuition, exploration and trial and error rather than a solid science based in theory. I'm probably not qualified enough to make this a strong statement, just a hunch that I got as a student recently getting into the topic.
just imagine, the first AI that takes over the world won't figure out that its hard before it tries & fails miserably
So, total energy use (enthalpy + potential energy + kinetic energy), accounts for limb weight, tries to minimise the amount of energy used per movement or stroke...
It would be fun to see how fast a humanoid can run.
2:15 How I imagine doing backflips (Reference)
2:10 How It looked like when I tried to do it (Simulation)
Jokes aside, this is a really great advancement in our virtual technology. Two Minute Papers's narration is great as well, clear and onpoint.
0:55 what if that is actually the correct way to run?
yes, if we had infinite stamina and energy
Could be. I think it's the A.I's way to maintain perfect balance, possible more balanced that how humans do.
@@npc4416 lmao
Takeshi's Castle for AI. LETS GO!
Right you are, Ken!
bro that would be so fun tbh
Lmao should i create a project like that? 😂
Thanks for the idea sir noted.
And as I see this agent is blind! Imagine if it could scan the "game level" its progress would be superhuman! Great paper, thanks Károly!
in order to make these fine algorithms truly wonderful (and usable across a wide spectrum of cases), is it yet possible to use 'straight' video (of a human or a cat or any animal) as the reference motion? that could mean, for instance, that a different algorithm parses the reference video motion into CG motion (ie mocap producing for example bvh, fbx) so that it can then be fed into this algorithm. from an admittedly quick glance at the paper and github i could not see what format the reference was supposed to be in, but it must be there somewhere. there are commercial mocap offerings for 'straight' video (with no depth cameras), but none that i have seen is good enough for this purpose - unless it was cleaned up by some other AI, possibly even a variation or adaptation of the one presented here?
maybe by using two different AIs together we could achieve that. One ai would find the position of the bones and joints to make a stick figure with different levels of tint/shade to indicate depth. Then a separate ai would create a 3d model and animation from the stick figure.
th-cam.com/video/F84jaIR5Uxc/w-d-xo.html
☝️ poses estimated from techniques like this should suffice. Even if the reference motions are "glitchy" (discontinuous in position through time) from the pose estimations, the mimicking RL agent will be forced to create a smooth approximation. This is due to the fact that the agent cannot produce discontinuous motions in the physical simulator while only having control over force applications at joints.
Then you can optimize for minimum force applied at joints or for minimizing total kinetic energy to really get a nice looking result.
The author of this paper has published a follow up paper.
xbpeng.github.io/projects/AMP/
The follow up paper uses GAIL. There is a separate critic model that tries to distinguish between the reference animations and whatever the physics rig is doing. The physics rig is trying to fool the critic. I think this could be used with your idea. As long as some physical measurements (rotations and velocities) could be estimated for the joints from the video sources (another model could be trained to do this). Then these measurements could be used as sources for the GAIL critic.
@@yeatard interesting idea, thanks.
@@tchlux thanks for pointing out the 'AI-Based 3D Pose Estimation' paper/video. very promising. i would love to see mocap results for an animal such as a dog or a cat. the reason is that with good mocap and even better predictive motions (so that i can direct my animated cat to jump on a stool or stroke its whiskers etc) animated films could at last become affordable to make (thus, in theory, allowing for better and more original stories).
Hearing that a developers favorite past time is to throw boxes at AI characters to see what they can take somehow makes me feel better about my life and how far I’ve come.
i cant get enough of the ragdoll/humanoid ai papers. it’s just so interesting watching ai mimic humans, really eerie o.O
None of my friends can ever tell me a backflip is easy when even an A.I chickens out like i do
AI : Can't learn
You : Self preservation
When men leave the gym: 6:12
*Full body volume*
Me walking to the toilet: 6:12
*Discourage full body volume*
0:50 AYO! The Jack Sparrow run! 😭😂
my life when i try to learn backflip.
The creators of this paper should work with the pokemon company to animate their massive collection of 3d models.
😂😂😂
The potential this software has in game development and animation is absolutely amazing. Imagine a player character with this backup ai and looser animations and unique interactions between the player and the environment.
4:27 " this one is doing well" .......oh
I discovered your channel yesterday and i’ve been hooked. thanks 👍
i think the AI was just imitating me trying to do a back flip @1:52
Finally i can explain my professor how i lost my papers while rushing to his lecture.
this is now my favourite channel, but at the same time it scares me shitless, imagine jean claude van dam death robots and a t-rex
ONE OF THE BEST CHANNELS IN THE INTERNET!!! BRAVO!!! Greetings from Akon, temporal capital of Sanmartina!!!
the part where it uses more or less Kinect energy will make stamina in games a very cool mechanic
Oh man, I'd love to see some more follow up papers to this!
So... Unreal Engine 5 is going to be used in Video Games, Hollywood, and Robotics. Sweet.
Unity and unreal: "bout time. '
Imagine having an AI controlled character in a video game that is able to attempt to maneuver in specified ways given any dynamic environment. It would look less programmatic and more flexible.
Rockstar did something like this when they used Euphoria engine to animate its human characters in GTA4. Characters would hold on to handrails as they stumbled, push themselves off your bumper if you nudged them with your car, all demonstrating incredible self-preservation that would be impossible with canned animations. I believe the series still uses the engine. Not all of the animations use the engine though, they're canned until the AI needs to kick it in to keep a character from falling over or doing something that would look silly. They called it "intelligent ragdoll".
One day, such system will be able to develop a martial art that is better than the one Bruce Lee invented!
Well no, because Bruce Lee's was basically 'use whatever works, man.' It basically defines itself as the best.
That's amazing! I also love that Peter Lorre narrates it.
02:09 backflip. reality vs expectation
0:45 once I saw this, I immediately went to grab a piece of paper for me to hold on to.
Edit: having seen the entire video. I believe this would be very impressive for making procedural animations. some video games already use procedural animations, but this would allow for it to be used for the entire animation process, which would drastically cut down on time/effort.
I don't know why but that little guy trying to keep doing back flips even while sitting down and you saying A for effort had my laughing so hard I was crying.... really got me for some reason lol
Possible future development could include 'reflex response' characteristics, such as if a character is falling, that they try to grab out toward the edge or any protrusions etc. Another example would be if a projectile is coming toward a vital area, that the character flinches. When combined with the energy level simulation variables, it can create some very realistic behaviors. A character which is extremely tired (low energy) may not notice a projectile and therefore not flinch.
This is insane. If this applied to boston dynamics.
Could you please explain your comment i am physics student
@@প্রীতমবিশ্বাস Google "Boston Dynamics robots" or look on TH-cam. He's suggesting their robots could be improved by applying such learning techniques (or the results).
@@peter9477 you do know their vids are "fake" right? They use human model and edit the robot into it.
@@Crustee0 no... no... you are VERY WRONG!!
0:55 He looks so happy that he can run🤣
The next step is obviously to give it the set of simulation options for locomotion and place it in a virtual level with obstacles and task them with making it to the end focusing on efficiency of action or speed of action. One option allows for low energy consumption for robotic ambulation, the other provides for emergency response movements.
It's so hilarious to just see the models start getting peppered by boxes
„A+ for effort, little AI“ 😂
You are in history of the world. Both from virtual and real engineering sides. Congrats!
This paper is a giant leap
What a time to be alive. What a time to be born. I’d love to see more of the future!
Ah, reminds me back to the old Endorphin (software) days.
god i loved that program
The guy on the floor trying to backflup is the funniest thing I've seen in a while. It just looks so silly.
I'm just waiting to see what the military is doing with AI right now
exploring new ways of killing people of course
Not exactly something to get excited about.
@@Androidonator Now the military drones can fly autonomously and identify the target with computer vision.
Just look at Boston Dynamics...
@@martiddy "computer vision" -- more like skin colour classifiers. Brown == fire missiles...
You are hilarious. I will watch you forever.
You are too kind. Thank you so much! 🙏
@@TwoMinutePapers Jól sejtem az akcentusodból (No offense!), hogy magyar agysejtek is dolgoztak a probléma megoldásán? :)
6:10 The chad stride in the middle
0:56 When you try to catch that bus
That backflip is so realistic at the start. It was exactly how I (don't) do backflips.
Why not tie its motion to an energy expenditure function, so that it finds the most efficient way to move? Have it compromise on speed and energy consumption? Maybe it won’t run with its arms flailing about because it would get tired sooner.
Awesome video!
There is a little tiny error: The motion is not retargeted to the T-Rex and Dragon, those are based on keyframe animation.
I'm absolutely stealing the AI's first run animation for some kind of project. That's just too beautiful.
That running animation looks like something I've seen on stick figure animation forums, not gonna lie.
Decrease body mass was a psycho walk. Also, i want to see a version of the human movement on MORE gravity, as well as seeing if a lion could do backflips (aka, non-humanoid figures trying to do nontraditional motions given the limitations of their body)
Fascinated by these 2 minute papers.
Looking forward to the Two Minute Papers computer game as the AI will be immense and graphics amazing.
i gotta admit, i like the way the AI approaches running 0:55 😁
but jokes aside, this is an amazing paper! we are finally getting closer to robot pet buddies!
This would be really cool to see in more video games. I always thought that jumping and movement animations in platformers would be cool if they were more realistic. That way we could learn movements from them, since we’d be functionally learning from a master.
I am so ready for video game characters to move properly in melee situations based on the target point and terrain setting
This channel is pure gold.
This is really really cool. Human simulation has never been this automated before.
Some may be scared seeing a robot running and jumping, but the last part of this video shows the incredible application for future: robots can adapt to out-of-earth environments much much quicker than humans!
Humanoid robots could even be sent to Mars before humans.
Ha, I saw the character running at 0:55 and wondered if it could be improved by considering energy usage, then at they end, they actually try it! It turns out it just makes the person look old.
1:13 The AI is accurate, I mean it looks just like me trying to do a flip but is really afraid to fail lol
but it had to be learning from a first person perspective lol. Unless you have a camera tracking motion somewhere as a third person view
2018 paper if I remember correctly. Couldn't make the code work. The dependencies alone killed me.
Rats - I was really hoping to be able to use the code.
I recall 2MP talking about a paper where they created a better way to simulate more realistic muscles. I wonder how long it'll be until this AI can be used to automate a hyper realistic body, frailty and all.
Imagine it being able to automate say an elderly AI's ability to climb over say a log or something. Any sort of elderly AI. Human, fox, cat, dog, horse, dragon, whatever. Pretty cool stuff to think about.
4:16 I couldn't help but think of that old obstacle course show Most Extreme Elimination Challenge, and wonder if we are in a simulation where our overlords are testing our machine learned animation and physics.
The potential applications of this AI driven animation is just staggering. I hope I'm well alive and still kicking to see it in motion in the future.
00:23 everyone, even the AI, felt that.
6:09 the dude on the right is like when we need to go to the bathroom but we are coming home
the sad p
art is in the beginning the simulation trying to do a backflip is like a picture perfect representation of if i tried to do one
I would love to see this technique simulating downhill skateboarding, finding new and improved ways to race and find the perfect lines and stances.
Honestly the first backflip it did is the most human one, it's the way I would definitely do them, and probably most of the people
Wow. I never though the ideology of "machines will replace all human jobs" would apply to me, but here we are.
I could see this replacing animation trees in AI for computer games. Instead of having to animate 50 different animation states, and blends. You can have the AI chose the reference motion from an entire list and have it dynamically blend with the environment and actions. Leading to more dynamic NPC enemy, friendly or neutral movement and interactions.
Scar: Long live the king. 5:31
I could see this being used in multiplayer shooters to give player characters realistic animations to the environment. Battlefield 5 tried it but fell a little short. I can just imagine characters responding to the environment, position, velocity appropriately. It would do wonders for immersion
0:59 is Phoebe from FRIENDS isn't it?
I'm very interested to see if you could pit two of these virtual people against each other in hand-to-hand combat to see what martial artistry they might come up with - you could increase their strength or speed to find out what a fight between superpowered humans might actually look at!
I love your enthusiasm. I still have no idea how you create these simulations, having only grasped the absolute basics of Convolutional Neural Networks looking at hand written digits. However, even that helps a little.
It seems that the ai looks to make the most practical movement over time
What would be interesting is tweaking point values based on energy used to resist gravity, possibly resulting in a more realistic run if the amount of energy expended is higher (no more arms in the air resisting gravity)
These algorithms will be great for robots over building constructions, spacial exploration, factories and many other applications.
Given it is part physics simulation has anyone tried applying different weights to various models? Such as a heavy backpack or a light shopping bag. Perhaps coding where the model has to maintain the weight during the movement but also protect it in the case of fragile items.
what a great mix of much wow and lolz :)
drl with baseline policies? or some sort of reward partially based on baseline policies as "reference"
Imagine being chased by an AI lion in VR. The future is gonna be awesome.
0:21 I know it's a ai but man that gotta heart
6:09 the right character is the reference of actual ninja run that so many people think as "retarded" and "useless", it's actually using less body volume to move forward, which in the long run related to the total amount of energy needed to reach a certain distance,
and you might hate this, the real life ninja run is not about speed but conserving energy, ..but yes in cartoon or anime since they rely on plot armor
the simulated back flip from 2018 is a perfect simulation of me attempting a back flip
That last bit, with high and low energy means that the energy that the character uses to move is kept track of right? Parkour, specifically jumping off high ledges is all about prolonging the dissipation of potential energy so that you body doesn’t absorb too much.
During a backflip, you speed up your angular velocity by bringing the centroids of your limbs closer to the center of mass/rotation. This allows the smallest possible amount of angular momentum to creat a full flip.
Running (or even standing) is just a rhythmic shifting of the centre of mass from one leg to the other, with children learning the most energy efficient way of remaining upright.
Are there any papers that take the reference, then also tell the simulation hey this is the type of energy to dissipate or minimise or maximise, regardless of the amount of energy used in the other types of energy? Like you wouldn’t bother waving your arms around (give them angular momentum/energy) unless you were about to fall (lose potential/height energy)
Please where can I get the resources to produce and teach AI on various skills 🙏🏽
I like how AI learns without references. Also interesting if AI can evolve a body to move in different environments like Jupiter's atmosphere.
This looks like the future of how games will implement physics and collisions with characters. Seeing as how it reacts with a dragon and non-humanoid, what if you made it a man-made object like... a car? a plane? helicopter? ... boat? I'm curious what'll happen since I believe it will need to define parts as muscles