Today let's show the unboxing and startup process of Jetbot MINI 2GB AI Robot Kit.
If you are looking for a good robot for your Jetbot 2GB development board. Don't miss it!
Unpacking show
For the packing list of this robot, as shown below.
Part 1-- About hardware configuration
There are 3 color tire for choice: Yellow, Green, Black. Which on did you like? I choose green.
Packing list include TF card(It has been written to the dedicated image file of Jetbot-MINI), 18650 battery pack(you didn’t prepare battery by yourself), USB3.0 wireless network card(which can help us transfer video quickly).
Part 2-- About AI visual recognition
Combined with high-definition camera and ROS system, it is programmed through Python3.
Yahboom has created a series of AI vision and intelligent recognition games for JetbotMINI, including: automatic driving, color tracking, object recognition, image beautification, gesture recognition, etc.
◆◆◆Color tracking
◆◆◆Automatic driving
◆◆◆AR Tag
For these gameplays and functions, they also provide detailed tutorial materials and open source code, which is convenient for users to refer to and expand more content.
Part3-- Remote control
Yahboom specially designed an iOS/Android remote control APP for it. We can remote control the car through the buttons on the APP or the gravity sensor of the mobile phone.
In addition, JetbotMINI also supports wireless controller, JupyterLab online programming and ROS operating system remote control.
Even mount your phone on the PS2 handle holder to control the Jetbot-MINI like a RC drone.
JETBOT MINI is a ROS artificial intelligence car developed based on NVIDIA JETSON NANO 2GB board. It has a built-in ROS robot operating system, OPENCV as the image processing library, and PYTHON3 as the main programming language. It can be developed through mainstream JUPYTERLAB online programming tools.
The camera can manually adjust the pitch angle, and can realize various functions such as automatic driving, color recognition, and face recognition.
The ROS robot operating system, visual recognition, and deep learning tutorials are fully covered, and the code is fully open source. Support mobile APP/handle/PC computer cross-platform interconnection control.
Many course documents and corresponding source codes to help you easily get started with ROS and AI artificial intelligence.