Skip to content

Neural Network smart UAV with reinforcement learning method

Notifications You must be signed in to change notification settings

eliaslawrence/smart_uav

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

smart_uav

Developed using P5.js. Program base on SNAKE game, Steering Behaviour and Smart Rockets to emulate a smart UAV that should visit determined points avoiding obstacles and the charge to end.

Neural Network

It was developed a simple Neural Network and the UAV learns through reinforcement method.

The vehicle receive as input distance in each direction to:

  • Obstacles
  • Recharge points
  • Waypoints (points it should visit)

Genetic Algorithm

Each generation the genes of the vehicles undergo mutation and crossover.

About

Neural Network smart UAV with reinforcement learning method

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published