Published on November 13, 2017 by makemagazine

This is the final part of a 3 part series where Sean Hodgins is designing an open source Arduino based robot that will navigate using a neural network. Part 1 involved taking components to make a prototype for testing. Part 2 took the custom circuit board and populated it with components, adding some test firmware to make sure everything worked. Finally, in this video, Sean will discuss different methods of making the robot navigate using the photoresistors, and how the neural network works for navigation. By the end of this series you will be able to create your own neural network robot using the resources provided.

Watch Part 1 Here: www.youtube.com/watch?v=0D5lcNIEa24
Watch Part 2 Here: www.youtube.com/watch?v=fCmMrSfEsuU

Check out Sean’s Channel: bit.ly/SeanYTSub

You can find the project on GitHub Here: bit.ly/2yXcjEy
The circuit board on OSHPark Here: bit.ly/2ybEMJr

Arduino Artificial Neural Network Example: robotics.hobbizine.com/arduinoann.html

Instrumentals Produced By Chuki
www.youtube/user/CHUKImusic

Leave a Reply

243 Comments on "Arduino Neural Network Robot Part 3: Running Neural Networks on an Arduino"

Notify of
avatar

Ramila Kalasuva
Guest
Ramila Kalasuva
24 days 23 hours ago

make a quadcopter which fly over the head and follows you

Paulo Castro
Guest
Paulo Castro
29 days 4 hours ago

more hidden layer = more layers = more number manipulation (basically each layer is add, then multiply) = more closeness/percision.basically more hidden layers, the more complex logic it could handle.for example:summation = no hidden layers (its to simple you just add)multiplication = no hidden layers powerof = at least one hidden layerpythagoran theorm = at least four complex equations = more hidden layers

juschu85
Guest
juschu85
1 month 4 days ago

You could use a Raspberry Pi and the Google AIY Vision Kit to make a robot with a much more sophisticated neural network. Perhaps one with a rear facing camera that is trying to get away from a cat and not the light. The Vision Kit already comes with a pre-trained human-dog-cat-classifier.While the robot is in a turn a servo should turn the camera, so the robot can still see the cat.You should add proximity sensors to the front so it won't crash into the wall.www.blog.google/topics/machine-learning/introducing-aiy-vision-kit-make-devices-see/

Justin Chan
Guest
Justin Chan
1 month 12 days ago

cant wait to make this

hiddenotebook
Guest
hiddenotebook
1 month 22 days ago

This is a great job thank you. One robot with ultrasonic sensor will be nice proyect for me. Thanks to you I'm starting to understand this

SeanHodgins
Guest
SeanHodgins
1 month 18 days ago

Nice, do it!

hiddenotebook
Guest
hiddenotebook
1 month 22 days ago

This is a great job thank you. One robot with ultrasonic sensor will be nice proyect for me. Thanks to you I'm starting to understand this

Viktor Vano
Guest
Viktor Vano
1 month 24 days ago

I wanted to make my own neural network and this project was like a trigger, I did my neural network in Cpp and used it on STM32. ARM is more powerful than AVR :)Just watch my video

It is also available at github.com/viktorvano/STM32F103RET6_Neural_Network

SeanHodgins
Guest
SeanHodgins
1 month 18 days ago

ARM is more powerful, that is why I used it in this project. haha 🙂

Viktor Vano
Guest
Viktor Vano
1 month 24 days ago

I wanted to make my own neural network and this project was like a trigger, I did my neural network in Cpp and used it on STM32. ARM is more powerful than AVR :)Just watch my video

It is also available at github.com/viktorvano/STM32F103RET6_Neural_Network

Omadev
Guest
Omadev
2 months 4 hours ago

Dude thaks for this project it was really awesome! keep being so cool!

SeanHodgins
Guest
SeanHodgins
1 month 18 days ago

Thanks! You to man!

Omadev
Guest
Omadev
2 months 4 hours ago

Dude thaks for this project it was really awesome! keep being so cool!

1 2 3 11
wpDiscuz