Pendulum: Neural Network

 

 

Simulation of Inverted Pendulum using Neural Network

Matlab Simulation represents the inverted pendulum placed on a linear guide with only a motor and an encoder attached. The difficulty of this problem is unstabilizing the already stabilized pendulum to bring its nose to the top and stabilize it again.

The neural network was used to decide on when to transition from the unstabilized controller to the stabilized controller.

There is no teacher to this neural network. It learns by itself efficiently using Genetic Algorithm.

https://github.com/kandai-wata/pendulum_neuralnetwork

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s