SnowCron Robotics ×



3d printer DIY


Robotics: Hardware
Software: AI Related
Robotics: DIY


On this site I am going to publish my experiments with Robotics and related topics.

It includes Artifficial Intelligence, Neural Networks, computer and real life bots - anything loosely related to the subject. For example, the Melonaire project (see site menu) is an Android program that will help you to determine the quality of a water mellon. While VC (vacuum cleaner) is an offline "real world" device, that can (barely) be described as a "robot" of a sort.

A fair warning: Robotics does require certain knowleges. So when I say "take pliers", I assume you know which end to hold. In other words, Please read the disclaimer

Speaking of related topics: there are at least two that you might find useful. First, please take a look at Building your own 3d printer tutorial. Now, 3d printer is not a must. Anything you can print, you can cut using knife, cutter (looks like a drill your stomatologist uses, but way, way cheaper), and files. However, if you are serious about building robots, 3d printer is a real time saver. It is cheap (think 100 dollars as an entry level) and you can also build one from clay and sticks, so to speak. See the link above.

Once again: 3d printer is not a mandatory tool: you can cut all parts you need from plastic or wood. However, this is going to be much longer, not to mention, error-prone. Besides, 3d printed robot looks nicer. A standard size of print bed 3d printers use is 22x22 cm, which is sufficient for most tasks.

And do not be afraid: even if you never worked with gears, stepper motors and microcontrollers, you will learn fast enough: when I got my first 3d printer, it was like a miracle and black box in one. Two month later I built one of my own design, as I decides it can be improved.

This was about building a "real world" robots. Second, if you are serious about programming robotic "brains", you will have to invest some time in studying machine learning. I personally use Python plus Keras (Google's library) and find it great.

Deep Learning.

A rather large article about using Triplet Loss

Good luck.

(C), all rights reserved

Please read the disclaimer