yahboom
HomeLearn
Solution
Blog
Online Store
About Us
EN/中文
RDK X5 Board📖
1.Introduction to RDK X5 board
  • 1.Introduction to RDK X5 board
  • 2.Write system file
  • 3.Hardware interface description
  • 4.Install case and other accessories
  • 5.Use 7-inch display
2.Basic settings course
  • 1.Network configuration
  • 2.Remote login
  • 3.Update system
  • 4.srpi-config user guide
  • 5.config. txt configuration file
  • 6.Self-startup setting
  • 7.RDK exclusive command usage
  • 8.Linux command usage
  • 9.GPIO readwrite operation
  • 10.Image classification algorithm
  • 11.Use USB camera
  • 12.Use MIPI camera
  • 13.Binocular camera depth algorithm
3.Basic development course
C language
  • 1.Camera image display
  • 2.Local save camera images
  • 3.Camera image encoding
  • 4.Video file decoding
  • 5.RTSP streaming decoding
  • 6.VPS scaling example
  • 7.Target detection algorithm-fcos
  • 8.Target detection algorithm-YOLOv5s
  • 9.Using CAN
Python
  • 0.ReadMe
  • 1.Using GPIO
  • 2.Using PWM
  • 3.Using Serial port
  • 4.Using I2C
  • 5.Using SPI
4.ROS expansion board
Python basic control
  • 0.Bind PCB port devices
  • 1.Install the Rosmaster driver library
  • 2.Buzzer whistle
  • 3.Control PWM servo
  • 4.RGB colorful light bar special effects display
  • 5.Control the forward and reverse rotation of the motor
  • 6.Control the movement of the robot
  • 7.Control Serial Servo
  • 8.Update firmware of expansion board
  • 9.Drive OLED
ROS2 robot control
  • 1.Function package usage process
  • 2.Robot information release
  • 3.Robot keyboard control
  • 4.Robot state estimation
  • 5.Robot calibration
  • 6.URDF model
5.T-MINI PLUS Lidar
  • 0.Preparation before use(Must read)
  • 1.Environment setup
  • 2.T-MINI PLUS LiDAR drive
  • 3.Handheld LiDAR mapping
6.AI VIEW Depth camera
AI VIEW Depth camera use
  • 1.AI VIEW Depth camera use
  • 2.Camera internal parameter calibration
  • 3.Color tracking
  • 4.KCF object tracking
Mediapipe functions
  • 1.Hand detection
  • 2.Attitude detection
  • 3.Overall inspection
  • 4.Facial detection
  • 5.Facial recognition
OpenCV series courses
  • 1.ROS+opencv application
  • 2.QR code creation and recognition
  • 3.AR vision
7.Offline AI model course
Offline-LLM-Text-Interaction
  • 0.AI-Large-Model-Image-Description
  • 1.AI-Large-Model-Environment-Deployment
  • 2.LLM-Conversation-Platform-Installation
  • 3.Meta-AI-Llama3.2-Model
  • 4.Alibaba-Cloud-Qwen3-Model
  • 5.Microsoft-Phi-4-mini-Model
  • 6.DeepSeek-DeepSeek-R1-Model
  • 7.Alibaba-Cloud-Qwen2.5vl-Vision-Multimodal-Model
  • 8.Google-Gemma3-Vision-Multimodal-Model
  • 9.Llava-Vision-Multimodal-Model
  • 10.MiniCPM-V-Vision-Multimodal-Model
  • 11.Multimodal-Text-to-Image-Application
  • 12.Multimodal-Video-Analysis-Application
  • 13.Multimodal-Visual-Understanding-Application
  • 14.Multimodal-Visual-Localization-Application
  • 15.Multimodal-Table-Scanning-Application
  • 16.Multimodal-Autonomous-Agent-Application
Offline-LLM-Voice-Interaction
  • 0.Voice-Interaction-Hardware-Connection-Must-Read
  • 1.Offline-Speech-to-Text-ASR
  • 2.Offline-Text-to-Speech-TTS
  • 3.AI-Large-Model-Voice-Interaction
  • 4.Multimodal-Visual-Understanding-Voice-Interaction
  • 5.Multimodal-Text-to-Image-Application
  • 6.Multimodal-Video-Analysis-Application
  • 7.Multimodal-Visual-Localization-Application
  • 8.Multimodal-Table-Scanning-Application
  • 9.Multimodal-Autonomous-Agent-Application
  • 10.AI-Large-Model-Offline-Voice-Assistant
8.Online AI model course
Online-LLM-Text-Interaction
  • 1.OpenRouter-Large-Model-API-Aggregation-Platform
  • 2.Multimodal-Visual-Understanding-Application
  • 3.Multimodal-Visual-Localization-Application
  • 4.Multimodal-Table-Scanning-Application
  • 5.Multimodal-Autonomous-Agent-Application
Online-LLM-Voice-Interaction
  • 0.Voice-Interaction-Hardware-Connection-Must-Read
  • 1.Online-Speech-to-Text-ASR
  • 2.Online-Text-to-Speech-TTS
  • 3.AI-Large-Model-Voice-Interaction
  • 4.Multimodal-Visual-Voice-Interaction
  • 5.Multimodal-Visual-Localization-Application
  • 6.Multimodal-Table-Scanning-Application
  • 7.Multimodal-Autonomous-Agent-Application
  • 8.AI-Large-Model-Online-Voice-Assistant
9.YOLO26 tutorials
  • 01.YOLO environment construction
  • 02.CLI use
  • 03.Object detection
  • 04.Instance segmentation
  • 05.Pose estimation
  • 06.Image classification
  • 07.Oriented bounding box object detection
  • 08.Model conversion
  • 09.Dataset annotation
  • 10.Model training conversion
  • 11.Model prediction
10.OpenClaw Deployment and Basic Usagenew
  • 01.OpenClaw Quick Start
  • 02.OpenClaw Deployment
  • 03.OpenClaw WhatsApp Plugin Application
  • 04.OpenClaw WebChat Interaction
  • 05.OpenClaw TUI Interaction
  • 06.OpenClaw Tools Introduction
  • 07.OpenClawGate Gateway User Manual
  • 08.OpenClaw Features Overview
  • 09.OpenClawClawHub Introduction (Skill Installation)
  • 10.OpenClaw Application - File Management
  • 11.OpenClaw Application - Camera
  • 12.OpenClaw Application - Browser Control
  • 13.OpenClaw Application - Script Execution
  • 14.OpenClaw Application - AI Programming (Peripheral & GPIO Control)
  • 15.OpenClaw Application - Dedicated AI Assistant
  • 16.OpenClaw Web Search Capability Configuration
11.OpenClaw Advanced Developmentnew
1.Preparation Before Use
  • 01. Peripheral Hardware Configuration
  • 02. OpenClaw API-KEY Configuration
  • 03. OpenClaw Model Switching
  • 04. OpenClaw Prompts
  • 05. AI Voice Interaction Configuration
  • 06. Three Dialogue Configuration Tests
2.OpenClaw AI Programming Peripheral Control
  • 1. Servo Control
  • 2. RGB Strip
  • 3. OLED Display
  • 4. Temperature and Humidity Sensor
  • 5. Camera Application
  • 6. AI Script Peripheral Control
3.OpenClaw Peripheral Integration Applications
  • 1. Plant Care Assistant
  • 2. AI Calorie Estimation
  • 3. AI Rock Paper Scissors Game
  • 4. AI Pet
  • 5. AI Weather Station
  • 6. Temperature and Humidity Dashboard
  • 7. Scheduled Tasks
12.ROS2 basic course
  • 1.Introduction to ROS2
  • 2.ROS2 install Humble
  • 3.ROS2 development environment
  • 4.ROS2 workspace
  • 5.ROS2 function package
  • 6.ROS2 node
  • 7.ROS2 topic communication
  • 8.ROS2 service communication
  • 9.ROS2 action communication
  • 10.ROS2 custom interface message
  • 11.ROS2 parameter service case
  • 12.ROS2 meta-function package
  • 13.ROS2 distributed communication
  • 14.ROS2 DDS
  • 15.ROS2 time related API
  • 16.ROS2 common command tools
  • 17.ROS2 rviz2 use
  • 18.ROS2 rqt toolbox
  • 19.ROS2 Launch startup file configuration
  • 20.ROS2 recording and playback tool
  • 21.ROS2 URDF model
  • 22.ROS2 Gazebo simulation platform
  • 23.ROS2 TF2 coordinate transformation
Download
  • System_File
  • Code
  • Tools
Download ZIP

Welcome to RDK X5 Board repository

21.ROS2 URDF model

21. ROS2 URDF Model

1. Introduction to URDF

The modeling method in ROS is called URDF, which stands for Unified Robot Description Format. It not only clearly describes the robot model itself, but also describes the robot's external environment. URDF model files use the XML format.

SolidWorks model to URDF plugin: sw_urdf_exporter - ROS Wiki

2. Robot Components

When modeling and describing a robot, we first need to be familiar with the robot's components and parameters. For example, a robot is generally composed of four major components: hardware structure, drive system, sensor system, and control system. Common robots on the market, whether mobile robots or robotic arms, can be broken down into these four components.

image-20220528144350325

  • The hardware structure refers to the tangible components, such as the chassis, housing, and motors.
  • The drive system is the equipment that enables these components to function properly, such as the motor driver and power management system.
  • The sensor system includes encoders on the motor, an onboard IMU, installed cameras, radar, and more, enabling the robot to sense its own state and external environment.
  • The control system is the primary vehicle for our development process, typically a computing platform like a Raspberry Pi or a computer, along with its operating system and application software.

The robot modeling process follows a similar approach, using a modeling language to clearly describe each component of the robot and then assemble them.

3. URDF Syntax

3.1. Link Description

The tag is used to describe the appearance and physical properties of a robot's rigid body. Appearance includes size, color, and shape, while physical properties include mass, inertia matrix, collision parameters, and so on.

image-20220528144534685

Taking this robotic arm link as an example, its link description is as follows:

image-20220528144549092

The name in the link tag represents the name of the link. We can customize it, and this name will be used when connecting joints to links in the future.

The section of the link describes the robot's appearance. For example:

  • represents the geometric shape. is used to call a pre-designed blue appearance in 3D software. This is the STL file, which looks identical to the real robot.
  • represents the offset of the coordinate system relative to the initial position, including translation in the x, y, and z directions, and roll, pitch, and raw rotations. If no offset is required, all values are 0.

The second section, , describes the collision parameters. While the content appears to be the same as , including and , there are actually significant differences.

  • focuses on describing the robot's appearance, that is, its visual effects.
  • describes the robot's state during motion, such as how contact with the outside world is considered a collision.

In this robot model, the blue part is described using . In actual control, such a complex appearance requires high computational power for collision detection. To simplify the calculations, we've simplified the collision detection model to a cylinder outlined in green, which is the shape described by in . The coordinate system offset is similar and can describe the offset of the rigid body's center of mass.

image-20220528144603646

For mobile robots, links can also be used to describe the body, wheels, and other components of the robot.

3.2 Joint Description

Rigid bodies in a robot model must ultimately be connected through joints to generate relative motion.

Joints in URDF have six types of motion.

image-20220528144655899

  1. Continuous: This describes rotational motion. It can rotate infinitely around a specific axis. For example, the wheels of a cart fall into this category.
  2. Revolute: This is also a revolute joint. Unlike the continuous type, it cannot rotate infinitely but has angle limits. For example, the two links in a robotic arm fall into this category.
  3. Prismatic: This is a sliding joint. It can translate along a specific axis and also has position limits. Linear motors typically use this type of motion.
  4. Fixed: This is the only type of joint that doesn't allow for movement, but it's still quite commonly used. For example, a camera link mounted on a robot doesn't change its relative position. In this case, the connection type used is Fixed.
  5. Floating: This is a floating joint. The sixth type, Planar, is a planar joint. These two are relatively less commonly used.

image-20220528144722751

In a URDF model, each link is described using an XML file, such as the name of the joint and the type of motion.

image-20220528144729633

  • parent tag: describes the parent link;
  • child tag: describes the child link, which moves relative to the parent link;
  • origin: indicates the relationship between the two link coordinate systems, represented by the red vector in the image, which can be understood as how the two links are mounted together;
  • axis: indicates the unit vector of the joint's motion axis. For example, if z is equal to 1, the rotation is about the positive z-axis;
  • limit: indicates any limitations on the motion, such as minimum position, maximum position, and maximum speed.

4. Complete Robot Model

image-20220528144900705

Finally, all the link and joint tags describe and combine each part of the robot. Placed within a single robot tag, this forms the complete robot model.

image-20220528144824234

So, when looking at a URDF model, don't rush to delve into the details of each block of code. First, look for links and joints to understand the robot's components. Once you understand the overall picture, then delve into the details.

4.1. Creating a Robot Model

Using the muto model as an example, copy the yahboomcar_description package from this tutorial's folder to the src directory of your workspace:

image-20250905184735806

  • urdf: Stores the robot model's URDF or XACR file
  • meshes: Stores the model rendering files referenced in the URDF
  • launch: Stores the relevant startup files
  • rviz: Stores the Rviz configuration file

Then compile the package.

xxxxxxxxxx
colcon build --packages-select yahboomcar_description

image-20250905184908066

4.2. Model Visualization

  • Refresh the environment variables and run the launch command.
xxxxxxxxxx
ros2 launch yahboomcar_description display.launch.py

Rviz will automatically launch and display the robot model:

image-20250905185113862

ROS2 recording and playback tool
ROS2 Gazebo simulation platform

COMPANY

  • About us
  • Team Style
  • Blog

LEARNING & EXPLORATION

  • Tutorials
  • Edge AI hardware
  • Educational robots
  • Embedded intelligent hardware

WHERE TO BUY

  • Yahboom Online Store
  • Amazon
  • Alibaba
  • AliExpress
  • Mercado

TECHNOLOGY SUPPORT

  • Email: support@yahboom.com

BE A DISTRIBUTOR

  • Email: sales@yahboom.com
QR Code

Copyright © 2017-2026 Yahboom. All Rights Reserved.

EN/中文