Jason Peng - 2018-04-08
Main video accompanying the SIGGRAPH 2018 paper: "DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills". Supplementary video: https://youtu.be/8KdDwRLtNHQ Project page: https://xbpeng.github.io/projects/DeepMimic/index.html Blog: http://bair.berkeley.edu/blog/2018/04/10/virtual-stuntman/
Great, now robots will know kung fu as well. Thanks guys.
01:17 "Yay! I have a consciousness! I love to run and feel the..."
...end of simulation.
Runs just like Steven Seagal.
Dude...
You had the chance to have a T-Rex do a roundhouse kick and you didn't take it. That's on you.
4:47, the simulated character naturally does a rasangan vs just throwing it!
no T-rex mocap?? amateurs.
4:47 CHEATER
4:14 why is it so satisfying to see the loin fall
because you thought they gave up throwing boxes at it
absolutely the future
Incredible! When will we see character motion like this in games?? Time to remake some classic martial arts video games!! :-D
Very important unanswered question for this: Is this real time?? If yes, then can someone please make a Unity plugin for this!
As matter of fact, GTA 4 used a simpler version of this for its NPC reactions. In fact, it has superior physics to GTA 5 in those terms, however, they removed this on GTA 5 because of the CPU load it had. But yes , this is not THAT hard to simulate and with upcoming 16thread CPU's, you should start seeing much better and realistic NPC AI. Not auto-aims but actual human-like realism
Navhkrin yeah, a lot has happened since Euphoria/Endorphin - recently, a lot of research has been done on optimizing the performance of AI, so that should help a lot too :-)
Wouldn't it be more logical to do the calculations on the GPU instead of the CPU?
@Irun S here you go https://github.com/Sohojoe/ActiveRagdollStyleTransfer
Excellent! Now if only I could learn to do a backflip too
when a computer can backflip better than you
6:58 the agent learns to complete the flip, but because of exploitation probably won't be able to learn good form. Notice that it sets a lot of flip during its set. For those unfamiliar with acrobatics terminology, all flips are composed of three phases: set, execution, and landing. The set is the initial jump to get height. The set should send the body's center of gravity as high as it can and then begin to execute the rotation. By leaning backwards like the agent is doing, it cuts a lot of the potential height it can get, which is bad technique. Although it's a hard problem even for humans to recognize how to set properly, the agent should learn the difference between good and bad technique. Perhaps one signal could be the amount of impact that agent takes in its joints. Bad sets can cause more compression where as when setting with a lot of height, you have enough time to flip and then open early enough to spot the ground. Opening early slows the body's rotation. Anyways, super dope stuff. Would be cool to see how much parkour theory agents can learn. ;)
There isnt enough variables to have to worry about most of those. Only criteria is to complete the flip at the moment .
holy cow. just apply it on real world atlas. i cant wait!
Already did, just google atlas backflip
Don't worry. Their weakness is cardboard boxes. We just have to throw 100 at the same time and we will defeat the uprising.
Miloš Ćirić well ya it did a backflip but it can’t cartwheel, sideflip, frontflip, or jump off stuff
Or kick stuff
Jason_ _parkour It can jump i guess soon it would be able to to all of that
4:47 The way baseball is meant to be played
1:17 The dude's happy to be alive.
1:18 accurate simulation of me running from life in general
Now have the reference fight the simulation to determine who is truly the best!
4:46 Awkward strategy... or most genius pitcher that ever played? Willing to bet no one's ever even tried a Naruto run towards the batter's face.
4:46 I died laughing
5:17 atlas just having fun.
oh my goodness, the future possibilities are expanding endlessly
I think you just love to throw boxes to robots xD. Well done, awesome research!
5:20 walks like a drunk!
This is super amazing. I'm excited for what will come out of this kind of technology.
this is a really amazing work, congratulations Jason, you really rock.
cant wait to see this on future videogames, in like 10 years.
its 99% reference.
Sounds like a very sensible approach. Learning is not just trial and error, imitation plays a huge role as well.
That's what i was thinking. :) Very interesting!! We could give robot arms in factory like references on how to do it. And then let it learn itself on how to perfect the task.
1:20 Victory lap baby!
Doomsday is near, I could feel it
wow this is amazing
Absolutely incredible!!
that lion ran into a cloud of cubes
I love the peculiar gait !!
I could do most of this stuff, but I keep sitting around eating Dunkin' Stix 😒😫
how can you do them even if you tried
Awesome! How do you make so many humanoid with fancy skills as reference?
It seems like motion capture.
Quote from the paper: ’We present a conceptually simple RL framework that enables simulated characters to learn highly dynamic and acrobatic skills from reference motion clips, which can be provided in the form of mocap data recorded from human subjects.‘
Thanks for your replay! It's very helpful for me.
Depending on the group of tired muscles, the way of walking and movement can be changed.
Waiting for something to beat the naturalmotion endorphin engine.
For some reasons, this seems overfitting?
Hey how did you compare the differences between the two states at 1:02?
Please make a fighting game with physics like this! Current fighting game engines have not advanced since they were first invented some 30+ years ago.
You taught it parkour and martial arts? That’s awesome!
1:17 Look at those dance moves! (dab dab dab dab)
1:26 Keep it coming, keep dancing! (backfall)
You've just created a dancing A.I.
This is amazing, this is going to make video game character animation 10x better.
Worker: Mr. Foreman sir! There is a robot outside doing sick flips!
Foreman: I can't have anyone show me up! Take one or two men and throw some boxes at it to mess it up.
3:00
Worker: Sir, we've thrown thrown some boxes, but... IT JUST KEEPS FLIPPING.
Foreman (on PA speaker system): Attention employees. I need all of you to stop what you are doing, and throw every box in the warehouse you can find at the robot outside.
3:08
amazing!! Is there any way to use in games ?
Will believe it when I see it in a robot
Great adaptation and generalization. Nice video too
I think that this is how neo learned so fast how to fight
Company of Heroes 3 is gonna be so DOPE!!!
Kanelel - 2018-04-11
Awfully rude of them to keep throwing boxes at them. :/