JETANK AI Kit

From Waveshare Wiki
Jump to: navigation, search
JETANK AI Kit
JETANK AI Kit

JETANK AI Kit, AI Tracked Mobile Robot, AI Vision Robot, Based On Jetson Nano Developer Kit
{{{name2}}}

{{{name3}}}

{{{name4}}}

{{{name5}}}

{{{name6}}}

Introduction

JETANK AI Kit, AI Tracked Mobile Robot, AI Vision Robot, Based On Jetson Nano Developer Kit.

Introduction

This is an intelligent crawler robot specially designed for the NVIDIA JetBot AI project, based on the Jetson Nano Developer Kit. The expansion board integrates OLED, motor drive circuit, servo drive circuit, power supply circuit, battery protection circuit, etc., which saves you the trouble of welding the circuit, supports unloading charging and does not need to repeatedly remove the battery. The software is fully compatible with the NVIDIA JetBot AI project and supports intelligent obstacle avoidance, autonomous line patrol, motion detection, color recognition tracking, and other functions. The robot is also equipped with a four-degree-of-freedom mechanical arm, which is controlled by a three-dimensional coordinate system and can be flexibly controlled by a wireless gamepad.

Expansion board Feature

  • Support three 18650 batteries (not included), up to 12.6V voltage output, and stronger motor power.
  • Onboard S-8254AA + AO4407A lithium battery protection circuit, with anti-overcharge, anti-over-discharge, anti-over-current and short-circuit protection functions.
  • The onboard APW7313 voltage regulator chip can provide a stable 5V voltage to the Jetson Nano.
  • The onboard SY8286 voltage regulator chip can provide a maximum current of 5A to the steering gear.
  • The onboard TB6612FNG dual H-bridge motor driver chip can drive the left and right motors to work.
  • Onboard 0.91-inch 128×32 resolution OLED, real-time display of car IP address, memory, power, etc.
  • The onboard INA219 acquisition chip is convenient for real-time monitoring of battery voltage and charging current.

Assembly Guides


We use the Jetbot image to setup for Jetank AI Kit, in this case, the default password for the image is jetbot

Step 1. Download the image
  • Download the newest jetbot image from jetbot.org which is provided by NVIDIA
  • You can also directly use the pre-configured image and skip the Step 4.
Step 2
Flash the JetBot image onto an SD card
  • Unzip the zip archive to get the .img file
  • Insert an SD card into the PC
  • Using the Win32DiskImager software tp write .img file onto the SD card
  • Eject and remove the SD card from the PC
Step 2. Boot the Jetson Nano
  • Insert the SD card into your Jetson Nano
  • Connect an HDMI display, keyboard, and mouse to the Nano
  • Connect a Power adapter to Jetson Nano (5V/4A) and start

Note, please test the Jetson Nano before you assemble the JETANK and test.

Step 3. Connect to WiFi
  • Boot the Jetson Nano, the default password is jetbot
  • To reduce CPU usage, the JetBot image disable the Desktop IU, enter the password and it goes into terminal directly
  • Use the following command to connect WiFi
sudo nmcli device wifi connect <SSID> password <PASSWORD>
Note that you need to modify the <SSID> to actual SSID of your wifi and the <PASSWORD> to the correct password of your wifi
  • Reboot the Jetson Nano, Jetson nano auto-connect to the WiFi (if it is accessible) the IP is shown in the OLED of JETANK
Step 4. Access JETANK by the Web browser

Note that you have to connect your PC to the same network as the JETANK, otherwise it cannot work.

  • Shut down the Jetson Nano and remove the display, keyboard, and mouse.
  • Assemble the JETANK according to the video
  • Connect the 12.6V power adapter to the Power interface of the JETANK
  • The Jetson Nano start and connect to WiFi automatically. the IP address is shown in the OLED
  • Open the Chrome browser, and navigate to <jetson_ip>:8888
    • For example, 192.168.1.76:8888
  • Access the Jupyter lab, the default password is jetbot
JetBot AI Kit Manual 2.jpg
  • Open a terminal and install the JETANK codes
git clone https://github.com/waveshare/JETANK.git
cd JETANK
chmod +x install.py
chomd +x config.py
./install.sh
./config.sh
  • The JETANK will auto-reboot

JETANK_1_servos

  • Navigate to http://<jetank_ip_address>:8888 to access JETANK by the browser.
  • Go to /JETANK/JETANK_1_servos and open the JETANK_1_servos_en.ipynb file
  • Follow the guides and run the cell one by one

This script shows you how the servo works.

JETANK_2_ctrl

  • Navigate to http://<jetank_ip_address>:8888 to access JETANK by the browser.
  • Go to /JETANK/JETANK_2_ctrl and open the JETANK_2_ctrl_en.ipynb file
  • Follow the guides and run the cell one by one

This script shows you how to control the arm and move the camera

JETANK_3_motionDetect

  • Navigate to http://<jetank_ip_address>:8888 to access JETANK by the browser.
  • Go to /JETANK/JETANK_3_motionDetect and run the JETANK_3_motionDetect_en.ipynb
  • Follow the guides and run the cell one by one

This script uses OpenCV to detect if objects move or change.

JETANK_4_colorRecognition

  • Navigate to http://<jetank_ip_address>:8888 to access JETANK by the browser.
  • Go to /JETANK/JETANK_4_colorRecognition and run the JETANK_4_colorRecognition_en.ipynb
  • Follow the guides and run the cell one by one

This script can recognize the HSV value of image captured by the camera

JETANK_5_colorTracking

  • Navigate to http://<jetank_ip_address>:8888 to access JETANK by the browser.
  • Go to /JETANK/JETANK_5_colorTracking and run the JETANK_5_colorTracking_en.ipynb
  • Follow the guides and run the cell one by one

This script can recognize the color of objects captured and trackes a specified color. Default to track yellow

JETANK_6_gampadCtrl

  • Navigate to http://<jetank_ip_address>:8888 to access JETANK by the browser.
  • Go to /JETANK/JETANK_6_gamepadCtl and run the JETANK_6_gamepadCtl_en.ipynb
  • Follow the guides and run the cell one by one
  • Connect the USB adapter of gamepad to the Jetson Nano

This script use the game pad to control the JETANK

Resources

Documentation

Datasheet

Related Tutorial

FAQ

 Answer:

Support three 18650 batteries (Not included) and the voltage of every battery is 3.7V. Generally, the voltage per battery is 4.2V when fully charged. Please use batteries without a protective plate. BTW, the Power of Kit is down when the voltage of the whole system is similar to 9V (it is not accurate), we recommend you charge batteries if the voltage displayed is lower than 10V.
We recommend you use high-quality batteries like Sanyo or Panasonic.
Batteries 18650 en.jpg

{{{4}}}

{{{5}}}


 Answer:
The 12V power adapter is used to charge the batteries. DO NOT directly connect it to the Jetson Nano Developer board.


 Answer:
Charging indicator is on the charger, green light full, red light charging.

{{{5}}}



 Answer:
The Linux system does not print the input when entering the password, which means you need to type it blindly. Keyboard directly enter jetbot and then enter.

{{{5}}}


 Answer:
If you are installing the battery for the first time, or have disassembled the battery, note that you need to connect the distributed power supply to charge the cart for a few seconds and open the protection circuit before normal use.

{{{5}}}


 Answer:

Due to the partitioning problem, the TF card with Jetson Nano image burned on a Windows computer can't recognize the disk letter normally, if you need to reformat, search for disk management in the search bar of Windows and open the disk management interface. Find the removable disk where the TF card is located (be careful not to mistake it for another disk), right-click and select Delete Volume, then create a new volume and format it by default. After the default format, the TF disk will be re-identified. At this time, the TF card space memory is not correct, note that you need to use the formatting software to do a quick format of the new disk letter again. After formatting, if the TF card memory space is normal, you can re-burn the new image normally.

{{{5}}}


 Answer:
The farthest is 235mm and the nearest is about 90mm.

{{{5}}}


Support



Technical Support

If you need technical support or have any feedback/review, please click the Submit Now button to submit a ticket, Our support team will check and reply to you within 1 to 2 working days. Please be patient as we make every effort to help you to resolve the issue.
Working Time: 9 AM - 6 PM GMT+8 (Monday to Friday)