I would like to share my recent works with you on my Genetic Neural Network. Deving this and debugging and testing was a bit up and down. But eventually I got it functional. Training done with 320 (adjustable) cars to go full path, took me approx 45 min. I need to say, that setting may not be optimal. But is functional. Plenty to be tweaked.

I would like to share my recent works with you on my Genetic Neural Network. Deving this and debugging and testing was a bit up and down. But eventually I got it functional. Training done with 320 (adjustable) cars to go full path, took me approx 45 min. I need to say, that setting may not be optimal. But is functional. Plenty to be tweaked.

Project goal is to simulate behavior of power grid (very simplified), using Evolving Neural Network approach.

PhD Conference 2017 - Autonomous mobile robotic systems for remote handling and decommissioning

Prototype based on initially made in Unity other voxel based prototype (IterOrbis: Space Dominum), using C# and classical Object Oriented Programming. This is important to mentions, since later I decided, that I want to convert whole game design, into ECS (Entity Component System), which is DOD (Data Oriented Design). Later known as Unity DOTS.

Presenting 3 Degrees of Freedom Gimbal Controller, based on thruster controller for spacecraft (i.e. satellite) applications in Unity3D, using Evolving Neural Network - NEAT.

Now discontinued, website and the project itself was about the space based game InterOrbis, where player can develop own vehicles and structures, with voxel system, fly and fight as desired and to conquer nearby planets. All physics based.