IA, Python and Armory 3d/Blender


Have you already made some experiences with IA ( like with Python for Artificial Intelligence ; ref here https://wiki.python.org/moin/PythonForArtificialIntelligence )
for example and an implementation in a scene in Armory 3d/ Blender ?


On my side, what would interest me the most would be to look at a neural network and its learning into a 3D environment … before exporting it to a real environment.


This video could give you an idea of the great possibilities that your games with Armory could gain through the use of some deep learning technics

MarI/O is a program made of neural networks and genetic algorithms that kicks butt at Super Mario World


This could give you another ideas where a real-time character control mechanism is using a novel neural network architecture called a Phase-Functioned Neural Network. In this network structure, the weights are computed via a cyclic function which uses the phase as an input.



You will find in the excellent and sympathic blog of Greg, expert in game development,

the info on the Dense Human Pose Estimation In The Wild project… or how to use a new model of Deep Learning to estimate the 3D pose of multiple people in a video, using a simple GPU.

We can think on how to reuse this with an integration into our 3D animations in Armory, with a specific editor for Estimation de Poses 3D.

For example, you train your neural network with the different videos you created through Armory with your characters, into different situations that may occure then in you game.

Then you obtain an incredible coordinate prediction, by mapping each pixel of a detected set for your 3D model model in Armory.

(the source code and Database are open-source and available on Github; If you want to test, I advise you to install/use Anaconda and thus create a specific/isolated environment with all the necessary packages and Python version)

It could be a nice way to start with the IA inside Armory, with specialized nodes to make it easily … interested ?