Brain controlled robots

In our research, we are developing a brain waves classifier of the left, right, up, down, forward, backward movement imagery with portable electroencephalographs. We choose Muse, portable electroencephalographs to collect data which is a portable headband launched lately with a number of useful functions and channels and it is much easier for the public to use. Additionally, we choose the gamma wave channels to obtain data from the subjects. Final goal of our model is to be applied to control hardware (robots and drones).

The core components of our model are:

Recording component

Recording brain activities using Muse electroencephalographs

Preprocessing component

Reduces noise and artifacts present in the brain signals in order to enhance the relevant information hidden in the input signals.

Classifier model

Artificial Neural Network is used as the classifier of the extracted features.

Output device

The output device can be a robotic arm, drone etc. The output of the classifier is used as a command to control the output device.

In the future work we are planning to include Feedback function in our model, so that the user can make adjustments. Feedback can be in visual, auditory or tactile.

All components are highly important in the development of an efficient model in terms of accuracy, speed, and information transfer rate.