Building an AI Robot that can be trained! || Using an NVIDIA single board computer

Offer: 20% Discount on Elektor Magazine Print -- Code: Great20P
Offer: 50% Discount on Elektor Magazine Digital -- Code: Great50D

Websites which were shown/used during the video:

In this video we will have a closer look at the concept of AI aka artificial intelligence and deep learning. As a practical example I will be building a small robot that comes with an NVIDIA SBC, a camera and two motors with wheels to drive around. I will show you how to use the SBC and its AI features in order to create an algorithm that avoids obstacles while the robot is driving around autonomously. Of course there is much more to learn when it comes to AI and deep learning. So let's get started!

Thanks to Elektor and SparkFun for sponsoring this video!

Music:
2011 Lookalike by Bartlebeats
Killing Time, Kevin MacLeod

0:00 This is why AI is WICKED!
1:54 Intro
2:44 Finding suitable hardware for AI tasks
4:06 Building the AI robot
6:06 Connecting the AI robot to the internet
6:44 Presenting the AI robots programming interface
7:26 First practical test
8:22 AI practical test
9:46 Conclusion

[NullPointer]

The thing about AI is that it's not creating an algorithm to compare the current image to the ones you fed it before, but instead creating a model that can generalize what "blocked" and "free" means, even for images or places that it has never seen before, that's the awesome thing with AI

[tafsirnahian]

NEXT EPISODE: HEART PACEMAKER 'DIY' or 'BUY'?

[syedsulaiman]

Never clicked faster before on a great Scott video

[reecejones]

This could be a really neat unsupervised learning project!

[jamesgrim]

From his first video to all of his videos always a joy to watch and learn something new. Keep up the awesome work you do Great Scott

[krn]

I like the fact that you face the camera to urself when doing the intro

[leonidsdreams]

Cool! It's amazing that people from all domains get interested in Machine Learning. Every domain of activity can benefit greatly from using these algorithms, but sometimes we underestimate the domain-specific knowledge needed to understand and solve the problem.

[alexwolfeboy]

A cool way to continue the project, is implementing a pathfinding algorithm. Use the object avoidance to have the robot navigate to a specific location within your house.

[peachpotatochips]

This Channel is like my second school because I learned a lot knowledge about electronics and stuff from here. You're awesome!

[existential_fred]

Explaining computers and Great Scott videos uploaded on the same day, what a treat!

[Enigma]

If the robot had an ultrasonic sensor, it seems as though it could take its own pictures and learn on it's own without having to be explictly trained.

[rpavlik]

Cool! Note that the raspberry pi, especially pi 4 can do deep learning tasks: Adafruit has a bunch of demos showing it off. But, I think they all use tensor flow lite, not pytorch.

[tanmay______]

Maybe the next step could be adding another camera for 3D vision.. Could the Jetson board handle that?

[jeffbrownstain]

Now this is quality youtube.
How to build an AI robot:
Buy a kit that does it for you.
Fūcking phenomenal m8.

[favouremmanuel]

I think ultrasonic sensor could be used with camera sensors to make the Robot notice objects and obstacles more efficiently

[lambsauce]

I just got into PyTorch and saw this. Perfect timing. Thanks.

[mr.coolio]

I love how Jeremy's German accent causes him to say *vikipedia*

[ThorstenDeuter]

You actually made a product video but I must admit a very good one :D

[ridinggoose]

Humans: *AI exists* we are going to die
AI: if picture equals to "blocked" turn, else drive

[dempleon]

My friend gave me his Jetson nano several months ago and I never had an idea of what i wanted to do with it. Im going to try this project out. Thnx for the vid.