say I want to see if i can get a biped to walk upright with an ANN.
I have a fitness function, and how I plan on adjusting weights is for each output, i test random deviations of the output with the fitness function till i achieve a better result (just ever so slightly just for the next frame), then i back propagate this...
would this work?
0
trial and error ANN
Started by rouncer, Jan 11 2013 11:35 PM
7 replies to this topic
#1
-
- Members
-
- 2725 posts
Senior Member
Posted 11 January 2013 - 11:35 PM
you used to be able to fit a game on a disk, then you used to be able to fit a game on a cd, then you used to be able to fit a game on a dvd, now you can barely fit one on your harddrive.
#2
-
- Members
-
- 582 posts
Member
- LocationSouthampton
Posted 12 January 2013 - 08:30 AM
Have a look here
http://www.naturalmo...ducts/euphoria/
Can't find the original video at the moment where they start with a single legged creature and used GA to get it to hop around.
Then they did a biped
http://www.naturalmo...ducts/euphoria/
Can't find the original video at the moment where they start with a single legged creature and used GA to get it to hop around.
Then they did a biped
#3
-
- Members
-
- 2725 posts
Senior Member
Posted 12 January 2013 - 02:05 PM
wow i must say that truly is amazing, and just to think, it all came from a little laboratory back in 1957 with the first perceptron!
you used to be able to fit a game on a disk, then you used to be able to fit a game on a cd, then you used to be able to fit a game on a dvd, now you can barely fit one on your harddrive.
#4
-
- Members
-
- 939 posts
Senior Member
Posted 14 January 2013 - 11:47 PM
Euphoria is an amazing achievement, but the animations looks just like marionettes. The puppeteering engine needs to be way more proactive to look natural. The most convincing parts were the falling and stumbling, situations where a human would be caught off guard and only instinctively controlling their movement.
#5
-
- Members
-
- 582 posts
Member
- LocationSouthampton
Posted 15 January 2013 - 09:48 AM
The other product they do handles that.
You create networks of animations and it blends between them based on input events.
You create networks of animations and it blends between them based on input events.
#6
-
- Members
-
- 939 posts
Senior Member
Posted 15 January 2013 - 03:08 PM
Ah. The video gave me the impression it was a complete character animation package.
#7
-
- Members
-
- 2725 posts
Senior Member
Posted 15 January 2013 - 11:10 PM
I want to take this idea further!!! Id like a wrestling game or something (take ragdoll gaming to the next level) - it would be really cool.
But setting up the physics system and neural net learning is really challenging.
oh well, i guess god wanted it to be a challenge anyway...
But setting up the physics system and neural net learning is really challenging.
oh well, i guess god wanted it to be a challenge anyway...
you used to be able to fit a game on a disk, then you used to be able to fit a game on a cd, then you used to be able to fit a game on a dvd, now you can barely fit one on your harddrive.
#8
-
- Members
-
- 582 posts
Member
- LocationSouthampton
Posted 16 January 2013 - 09:27 AM
The system mixes generated animations and artist created animations based on events.
It's power comes from the fact that it can blend multiple animations in a realistic way.
The stuff that really makes a difference is the reaction system, for example someone getting shot. Traditionally we have one or two death animations, but with their system it actually has almost an infinite set of reactions depending on the nature of the event.
Makes a big difference.
It's power comes from the fact that it can blend multiple animations in a realistic way.
The stuff that really makes a difference is the reaction system, for example someone getting shot. Traditionally we have one or two death animations, but with their system it actually has almost an infinite set of reactions depending on the nature of the event.
Makes a big difference.
1 user(s) are reading this topic
0 members, 1 guests, 0 anonymous users
