UGV Beast PT Jetson Orin AI Kit

From Waveshare Wiki
Jump to: navigation, search
UGV Beast PT Jetson Orin AI Kit
UGV Beast PT Jetson Orin.jpg

I2C, UART
TTL Serial Bus Servo Control Interface
{{{name2}}}

{{{name3}}}

{{{name4}}}

{{{name5}}}

{{{name6}}}

Introduction

UGV Beast PT Jetson Orin, an off-road tracked open-source AI robot, features a dual-controller structure. The ESP32 slave computer controls the motor PID, IMU sensors, OLED screen, servo, LED ON/OFF, and so on, which greatly reduces the IO resources for the host computer and provides high-performance communication interfaces. Also, the host controller adopts Jetson Orin Nano, offering advanced features such as high computational power and specified strategies.
It is high-strength and more durable as the robot's body is made of a 2mm thick aluminum alloy casing. In addition, it adopts multiple dependent suspending systems, which greatly reduce the impact of complex terrains. It comes with two DC gear motor with encoders, functioning closed-loop speed control and reducing vibration. It enjoys a more excellent performance in movement with a maximum speed of 0.35m/s. With the built-in 3S lithium battery UPS power module, it offers robust and long-lasting motivation, supporting continuous use while charging to meet long-term development and usage requirements.
The Jetson Orin Nano paired with a USB camera provides users with a smooth visual experience through real-time footage with high frame rates and low latency. Users can enjoy capturing different wonderful moments through functions such as taking photos and recording videos. Additionally, various feedback information from the robot, including battery voltage and CPU usage, is displayed in real-time through a web application, allowing users to monitor the robot's status in real-time.
The robot's visual system is equipped with a 2DOF(degrees of freedom) high-torque flexible pan-tilt and a 160° ultra-wide-angle 5-megapixel camera, providing users with a wide field of view, flexible viewing angles, and various AI machine vision functions. The high-brightness LED spotlight next to the pan-tilt ensures clear visibility even in low-light environments. Additionally, the design with Picatinny rails allows users to easily expand more tactical accessories, further enhancing the robot's functionality.
To enable users to fully leverage the potential of this robot, we provide online documentation and tutorials, including a JupyterLab web application. Whether you're a beginner in robotics technology or an experienced developer, you can delve into learning, understanding, and creating step by step through these resources.

Features

  • High-performance Dual Controller: the slave computer is ESP32, responsible for precise motor PID control and multiple sensor readings; the host computer Jetson Orin Nano offers high computational power. The two-layer architecture makes the robot run more efficiently.
  • Open-source Code: The host controller is based on the latest version of the Raspberry Pi system (Debain Bookworm) development, WEB applications based on Flask, Python language, the software platform is all open source, easy for users to learn and secondary development.
  • Rich Tutorials: Offers rich JupyterLab, graphic and video tutorials covering various functionalities to help users quickly get started and use the robot, thereby accelerating the realization of innovative applications.
  • Wide Viewing Angle: Equipped with a 2-degree-of-freedom, high-torque, flexible pan-tilt that provides a wide 360° viewing angle horizontally, and a 5-megapixel camera with a 160° wide-angle, it captures a wider range of images.
  • Robot Vision: Integrated with machine vision functions such as color, object and gesture recognition, face and motion detection, it can be extended for more applications.
  • Abundant Interaction: Real-time video streaming, digital zoom, photo, video, and other functions, and WEB application of real-time video functions and robot information displayed on the screen to improve the user interaction experience.
  • Cross-platform Support: Supports cross-platform remote control without the need to install an app. You can follow tutorials to implement remote control beyond the local network using solutions such as Pgyer, Cpolar, LocalTunnel, and others.
  • Expandability: features a mounting plate and Picatinny rails, facilitating the attachment of additional tactical accessories. On the hardware side, there are spare interfaces available for LED lights, which can be used for expanding peripherals such as water guns. Additionally, the product can be expanded with 4G or 5G modules, enabling users to explore more possibilities.
  • Durable Structure: The 2mm thick aluminum alloy case provides outstanding structural strength and durability.
  • High-Performance Drive Motors: Equipped with four motors with encoders, enabling closed-loop speed control. With a maximum speed of 0.35m/s, it delivers robust power.
  • Multiple Dependent Suspending Systems: Featuring four dependent suspending systems on each side. When climbing with a heavy load, the suspension sytems shrinks, and the rear wheel provides extra support, ensuring excellent climbing ability.
  • Long Battery Life: Utilizing a 3S lithium battery UPS power system, it supports continuous use while charging, ensuring long-lasting endurance.

Product Assembly

This assembly tutorial mainly includes two parts. The first is a tutorial on installing Raspberry Pi 4B/5 for ACCE model products, and the second is a tutorial for installing lithium batteries.
[Assembly tutorial for ugv]

User Guide

Notices

Please read the following content before using:

  1. 3x 18650 lithium batteries are required and need to be purchased separately to ensure normal operation, a battery with a high discharge rate is recommended. And a Jetson Orin Nano is required and needs to be purchased independently if you are using ACCE version.
  2. When connecting the battery for the first time, pay attention to whether the LED light is on the battery module. If the LED light is on, it means that the positive and negative electrodes of the battery are connected inversely. If the battery is not connected inversely, the LED light will not be on. Do not charge the battery when it is reversed, otherwise it may cause an explosion.
  3. After connecting the battery for the first time, the product still does not work if you press the power button on it, and it is because there is no power output. You need to plug the matching 12.6V 2A power adapter into the power port of the product to activate the battery protection circuits before the power output is available.
  4. This product can not suffer severe impact and is not waterproof.

First Time Use

The product with Jetson Orin Nano 4GB Kit is shipped with configured software, and you can directly use it after powering on.
After turning on the power switch, the product will be initialized, and the OLED screen will display a series of initialization contents; Jetson Orin Nano will automatically establish a hot spot during startup, and the IP address will be displayed on the OLED screen after the main program of the project automatically runs. The content displayed on the OLED screen after startup is completed is as follows:

  • The first line E: the IP address of the Ethernet port for remotely accessing the Jetson Orin Nano. "No Ethernet" means that the Jetson Orin Nano has no Ethernet cable connection.
  • The second line W: In AP mode, the robot will automatically establish a hotspot and display the default IP: 192.168.50.5. In STA mode, the robot will connect to the IP address assigned by the known WIFI; The IP address displayed can be used to wirelessly connect to the Jetson Orin Nano.
  • The third line F/J: Network port number, "5000" is used to access the main program control page of the product, "8888" is used to access the JupyterLab page.
  • The fourth line AP: means the WIFI is in AP mode, and the time means the usage period of the robot, the value in dBm represents the signal strength RSSI of WIFI in STA mode.

You can use a mobile phone or PC to access this hotspot automatically created by the product, the name of the hotspot is AccessPopup, and the password of the hotspot is 1234567890. After connecting, open the browser, enter the default IP address of the device in AP mode (the address will be displayed at line W on the OLED screen), that is, enter 192.168.50.5:5000 in the URL bar to access the control interface of the main demo of the product.

Network Configuration

When configuring WIFI for the first time, you need to prepare a network cable or a USB cable, and a computer when using a USB cable.
Open the terminal and operate it as shown below:

  • Network cable: after booting the product, connect the network cable and then the OLED screen will automatically display the IP of the network cable. The IP after "E" is the wired IP; E represents "eth0". Enter this IP address: 8888 on the browser; open jupyterLa and then the Terminal.
  • USB cable: The Micro USB port of the Jetson Orin Nano is the default IP address "192.168.55.1". If you do not have a screen, you can remotely control Jetson Orin Nano through SSH.
    • After booting the product, connect the Micro USB port of the Jetson Orin Nano to the PC with a USB cable.
    • Remotely login to Jetson Orin Nano with the SSH IP "192.168.55.1" through Putty or MobaXteram software.
    • The default username and password of Jetson Orin Nano is "jetson".

After logging into the terminal and configuring the WIFI connection to a known hotspot for the first time, you need to close the AccessPopup recurring scanning task that is running in the background, and browse to the AccessPopup folder first.

cd ugv_jetson/AccessPopup/

Run AccessPopup configuration scrip:

sudo chmod +x installconfig.sh
sudo ./installconfig.sh

Type 7, enter, and uninstall AccessPopup. (When it connects to a known WIFI, and then you need the Jetson to automatically set up the hotspot again you can perform a similar step, but choose 1 to install AccessPopup, and then it will automatically set up the hotspot when you turn it on.)
Wait for the uninstallation to complete, press any key to exit, then enter 9, enter to exit AccessPopup.
Make sure WIFI is on:

sudo nmcli r wifi on

Lists the known WIFI networks around you:

sudo nmcli d wifi list

Connect to the known WIFI:

sudo nmcli d wifi connect <my_wifi_ssid> password <my_wifi_password>

You need to replace the above <my_wifi_ssid> and <my_wifi_password> with your own hotspot name and password depending on your situation, e.g. sudo nmcli d wifi connect wifi_name password 1234567890

Product Initialization

Note: The following steps are not necessary operations. If you need to restore the product's host computer to the factory setting or update the product's software, you can refer to the following guides.

System Installation

  • Ubuntu 22.04 host or virtual machine is required to burn the system.

Preparation

  1. UGV Rover PT Jetson Orin AI Kit.
  2. Ubuntu 22.04 virtual machine (or PC).
  3. Yellow jumper cap.
  4. USB cable (Type-C connector for data transmission).

Hardware Configuration (Enter Recovery Mode)

JETSON-XAVIER-NX-DEV-KIT-re.png

  • Short the FC REC and GND pins with jump caps or Dupont wires, positioned as shown above, located under the module.
  • Power on the product.
  • Connect the type C port of the Jetson board to the Ubuntu 22.04 host using a USB cable (make sure it's a data cable).

Software Cofiguration

  • Open the Ubuntu system and open the browser to download SDK Manager.
  • After downloading, we enter the download path to install, and input the following content on the terminal:
sudo dpkg -i sdkmanager_1.6.1-8175_amd64.deb (Enter according to your version)
  • After installing, the system may report the dependency file can not be found, and you can input the following commands to settle this issue:
sudo apt --fix-broken install
  • Open Ubuntu and run SDK Manager.
  • Click "LOGIN", log in to your NVIDIA account, the browser pops up the link, and enter your registered email and password to log in.

LOGIN NVIDIA.jpg

  • Then we successfully log in to SDK Manager.

LOGIN NVIDIA02.png

System Installation

  • Open the Ubuntu 22.04 terminal, and run sdkmanager to open the software.
  • Log in.
  • If the Jetson board is properly recognized as shown in the following figure, if it is connected but not displayed, please click refresh.

JETSON-ORIN-NX DEV-KIT006.png

  • Select the Jetson Orin Nano for the board type, and select the 8GB version or 4GB version according to your needs (if you are using the official kit, select "Developer Kit"), and uncheck the "Host Machine" option.
  • In the JetPack option, select the latest supported systems, leave the other SDKs unchecked, and click Continue.

Orin NX configuration.png

  • Select Jetson Linux, and remove the option of "Jetson Runtime Components" and "Jetson SDK Components". Check the first agreement at the bottom.

Orin NX Details and License.png

  • If it is the first time to flash the system, it will pop up a window as shown below after clicking on "Continue". Just click on "Create" to continue. If it is not the first time, you can wait for it after clicking on "Continue".

UGV Rover Jetson Orin Configuration.png

  • At last, click on "Continue" to wait for flashing the system. During this process, the window as shown in the following picture will pop up before the Installing progress bar reaches 50%.
  1. Here select the development board model by default. Please select the correct one.
  2. Select OEM Configuration -> Pre-Config, type username and password (define by yourself), and configure the module during the booting process.

UGV Rover Jetson Orin Configuration1.png

  • After flashing, it will show "INSTALLATION COMPLETED SUCCESSFULLY". Then, you can install software programs.

Orin Nano Installation Completed Successfully.png

Software Installation

There are two methods for this product to install software:

  1. Directly flash the pre-configured system image to the hard driver on the Jetson Orin Nano. Advantages: no more configuration is required anymore, and users can use it after installation.
  2. Configure it through software

Preparation

  • Remove the hard driver on the Jetson Orin Nano.
  • PC.

System Image Preparation

UGV Beast Program Configuration
The image we provided is based on UGV Rover. For UGV Beast, after burning the image to the Jetson Orin Nano's hard driver, turn on the product's power switch, configure the network according to the network configuration steps above, visit the product's main program page at IP address: 5000, and enter it into the input box on the WEB page:

s 30

After entering, you need to reboot the product. Then, you can see the image is for UGV Beast. You only need to modify it once.

Resource

2D Drawing

STEP Model

Schematic

Open-source Demo

Software

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)