yahboom
HomeTutorialsProduct
Solution
Blog
Online Store
About Us
EN/中文
Store
Jetson Orin NANO Developer Kit📖
01.Get started
  • 01. Learning route
  • 02. Get started quickly
  • 03. System Update Notes
  • 04. Disabling automatic updates and troubleshooting issues
  • 05. Jetson Orin Nano official kit screwdriver instructions
02.Jetson basic course
  • 01.Jetson board introduction
  • 02.Write Jetson original system
  • 03.Installing Jetson environment
  • 04.Backup SSD system
  • 05.Restore initial image system
  • 06.Upgrade to SUPER version (Optional)
  • 07.Write SUPER boot (Must read)
  • 08.SSD expansion
  • 09.Jetpack old system upgraded to Yahboom SUPER factory system
  • 10.Write the system onto your own SSD
03.Basic setting course
  • 01.Basic knowledge
  • 02.Network configuration
  • 03.SSH remote login
  • 04.VNC remote control
  • 05.RDP remote control
  • 06.Remote file transfer
  • 07.Jtop tool
  • 08.Exchange space expansion
  • 09.Use VSCode
  • 10.Use VMware
  • 11.Modify screen resolution
04.GPIO control course
  • 01.GPIO description
  • 02.GPIO library installation
  • 03.GPIO reading
  • 04.GPIO output
  • 05.Serial communication
  • 06.I2C communication
05.Vision basic course
  • 01.CSI camera preview
  • 02.USB camera preview
  • 03.Use Jupyter Lab
  • 04.Use JetCam
06.OpenCV basic course
  • 01.Image reading
  • 02.Image saving
  • 03.Image modification
  • 04.Image scaling
  • 05.Image cropping
  • 06.Image translation
  • 07.Image mirroring
  • 08.Image grayscale conversion
  • 09.Image binarization
  • 10.Image edge detection
  • 11.Add line segments
  • 12.Add rectangles
  • 13.Add circular shape
  • 14.Add ellipses
  • 15.Add polygons
  • 16.Add Text
  • 17.Preview USB camera image
  • 18.Preview CSI camera image
07.Vision advanced course
01.Environment construction
  • 01.TensorFlow
  • 02.PyTorch
  • 03.Torchvision
02.DeepStream development
  • 01.DeepStream environment
  • 02.License plate detection and recognition
  • 03.Parallel multi-model inference
  • 04.Object embedding vector generation
  • 05.Pose recognition
  • 06.NV optical flow anomaly detection
  • 07.Single-view 3D tracking
  • 08.Multi-view 3D tracking
03.NVIDIA TAO toolkit application
  • 01.Traffic scene object detection
  • 02.Person object detection
  • 03.Vehicle brand classification
  • 04.Vehicle model classification
  • 05.License plate detection and recognition
  • 06.Person semantic segmentation
  • 07.Retail product detection and recognition
  • 08.Person feature extraction and matching (ReID)
  • 09.Person action and pose classification
  • 10.Transformer-based person detection
  • 11.3D human skeleton detection
  • 12.LiDAR 3D point cloud detection
04.YOLO11 development
  • 01.YOLO environment construction
  • 02.CLI use
  • 03.Object detection
  • 04.Instance segmentation
  • 05.Pose estimation
  • 06.Image classification
  • 07.Oriented object detection
  • 08.Model conversion
  • 09.Dataset annotation
  • 10.Model training conversion
  • 11.Model prediction
05.Mediapipe development
  • 01.Mediapipe environment
  • 02.Hand detection
  • 03.Face detection
  • 04.Face effects
  • 05.3D object recognition
  • 06.Virtual brush
  • 07.Gesture recognition
  • 08.Finger control
  • 09.Posture estimation
  • 10.Face mask
  • 11.Overall detection
  • 12.Green scene removal(Human)
06.YOLO26 development
  • 01.YOLO environment construction
  • 02.CLI use
  • 03.Object detection
  • 04.Instance segmentation
  • 05.Pose estimation
  • 06.Image classification
  • 07.Oriented object detection
  • 08.Model conversion
  • 09.Dataset annotation
  • 10.Model training conversion
  • 11.Model prediction
07.QR code recognition
  • QR code recognition
08.Docker basic course
  • 01.Docker introduction
  • 02.Docker installation
  • 03.Docker command
  • 04.Docker usage
  • 05.Docker interaction
09.ROS2-Jazzy
01.ROS2 basic course
  • 1.Introduction to ROS2
  • 2.ROS2 install Jazzy
  • 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
02.ROS2 vision course
  • 01.Camera preview (USB)
  • 02.Camera preview (CSI)
  • 03.Camera calibration (USB)
  • 04.Camera calibration (CSI)
  • 05.AR vision (USB)
  • 06.AR vision (CSI)
10.Large model basic course
01.Offline large model
  • 01.AI large model environment deployment
  • 02.Install large model dialogue platform
  • 03.Meta AI - Llama model
  • 04.Alibaba Cloud - Qwen model
  • 05.Microsoft - Phi-4-mini model
  • 06.DeepSeek - DeepSeek model
  • 07.Alibaba Cloud - Qwen-VL visual multimodal large model
  • 08.Google - Gemma visual multimodal large model
  • 9.Llava visual multimodal large model
  • 10.MiniCPM-V visual multimodal large model
  • 11.High-quality vision-language grounding (LocateAnything)
02.Online large model
  • 01.Tongyi Qianwen large model
  • 02.OpenRouter large model API aggregation platform
11.Large model application practice
01.Voice interaction application
  • 1.Voice interaction hardware connection (Must read)
  • 2.Offline speech to text (ASR)
  • 3.Offline text to speech (TTS)
  • 4.AI large model voice interaction
  • 5.AI large model offline voice assistant
02.Multimodal large model application (Online_Offline large model + Text_Voice interaction)
  • 01.Multimodal visual understand application
  • 02.Multimodal text image application
  • 03.Multimodal video analysis application
  • 04.Multi module visual position application
  • 05.Multimodal table scanning application
  • 06.Multimodal autonomous agent application
12.NVIDIA Isaac ROS course
  • 01.Build Isaac ROS environment
  • 02.Deep segmentation
  • 03.DNN stereoscopic depth
  • 04.Free space segmentation
  • 05.Image distortion processing
  • 06.Image segmentation
  • 07.3D scene reconstruction and mapping
  • 08.Object detection
  • 09.3D attitude estimation
  • 10.Visual SLAM
13.OpenClaw deployment and basic usage
01.OpenClaw deployment and introduction
  • 01.Quick start with the pre-configured environment (Recommended)
  • 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.OpenClawHub Introduction (Skill Installation)
02.OpenClaw basic application
  • 01.OpenClaw Application - File Management
  • 02.OpenClaw Application - Camera
  • 03.OpenClaw Application - Browser Control
  • 04.OpenClaw Application - Script Execution
  • 05.OpenClaw Application - AI Programming (Peripheral & GPIO Control)
  • 06.OpenClaw Application - Dedicated AI Assistant
  • 07.OpenClaw Web Search Capability Configuration
03.NVIDIA official Agent Skills application
  • 01.AI-assisted development with VS Code or Cursor
  • 02.Jetson device skills
  • 03.Jetson BSP custom agent skills
14.OpenClaw advanced development
01.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
02.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
03.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 Humidity Dashboard
  • 7. Scheduled Tasks
Download
  • System_File
  • VMFile_BootFile
  • 3D Model File
  • DataSheet
  • Software_Tools
  • Code
  • Manual
Download ZIP

Welcome to Jetson Orin NANO Developer Kit repository

01.Build Isaac ROS environment

Isaac ROS Environment Setup (Jetson Orin Nano)

Isaac ROS Environment Setup (Jetson Orin Nano)1. Scope of Application2. Obtaining and Checking FilesDisk Space Requirements3. Importing the Docker Image4. Extracting the Course Workspace5. Starting the Container5.1 Preparing Fast DDS and the Terminal Environment5.2 Creating the Startup Script6. Checking the ROS Environment7. Model Preparation Rules8. Optional: Deleting the Archives After Deployment Is Confirmed9. Usage Notes10. Next Steps

1. Scope of Application

This tutorial is intended for deploying the Isaac ROS environment and the case workspace provided by the course on a Jetson Orin Nano 8GB. Before deployment, confirm that the device matches the table below; for other Jetson models or JetPack versions, image compatibility must be confirmed first.

Note: The remaining space of the factory image system is insufficient to set up the Isaac ROS environment. Use the dedicated Isaac image provided in the materials (the environment is already configured), or use another third-party system image with sufficient space to set up the environment. For a third-party system image, refer to the following tutorials: 【Chapter 2 Mainboard Basics: 02. Writing the Jetson Clean System】 -> 【Chapter 2 Mainboard Basics: 03. Installing the Jetson Environment】 -> 【Chapter 8 Docker Basics: 02. Docker Installation】

ItemRequirement
MainboardJetson Orin Nano 8GB, aarch64
JetPack / L4TJetPack 7.2.1 / L4T R39.2.1
SystemUbuntu 24.04
Docker environmentInstalled and runnable by the current user
NVIDIA Container ToolkitInstalled
Disk spaceMust hold the imported image, the extracted workspace, and runtime headroom at the same time; verify with the formula in this section

The environment consists of two parts: the Docker image provides ROS 2 Jazzy and the Isaac ROS software; the workspace archive provides the course models, data, and case files. The cases can only be run after both parts are deployed.

2. Obtaining and Checking Files

Disk Space Requirements

Before importing, the partition holding the Docker data directory and the partition holding the workspace target should satisfy the following respectively:

  • If both are on the same partition: the remaining space must be at least 65.3GB + the extracted workspace size + 20GB runtime headroom.

  • If the two are on different partitions: reserve at least 85GB on the partition holding the Docker data directory; reserve at least the extracted workspace size + 10GB on the partition holding the workspace

After confirming that the space is sufficient, place the following two files in the /home/jetson/ directory of the Jetson:

FilePurpose
my-isaac-ros-slam-4.6-all.tar.gzIsaac ROS Docker image, the archive is about 24.3GB; the Docker image after import is about 65.3GB
isaac_ros_workspaces.tar.gzCase workspace, models, and data; the archive size and the extracted size vary with the delivered content, subject to the actual files and the delivery list

If the files are on another computer, upload them from the terminal of that computer; replace <Jetson_IP> with the actual IP of the Jetson:

scp my-isaac-ros-slam-4.6-all.tar.gz jetson@<Jetson_IP>:/home/jetson/
scp isaac_ros_workspaces.tar.gz jetson@<Jetson_IP>:/home/jetson/

Then confirm the files, the system, and the disk space on the Jetson:

xxxxxxxxxx
uname -m
cat /etc/nv_tegra_release
docker --version
docker info --format 'DockerRootDir={{.DockerRootDir}} DefaultRuntime={{.DefaultRuntime}} Runtimes={{json .Runtimes}}'
df -h /var/lib/docker /home/jetson
ls -lh /home/jetson/my-isaac-ros-slam-4.6-all.tar.gz /home/jetson/isaac_ros_workspaces.tar.gz

The device should be aarch64, and the L4T version should be R39.2.1. The Docker runtime list should contain nvidia.

3. Importing the Docker Image

Execute on the Jetson host:

xxxxxxxxxx
docker load -i /home/jetson/my-isaac-ros-slam-4.6-all.tar.gz
docker image inspect my-isaac-ros-slam:4.6-all --format 'OS={{.Os}} Arch={{.Architecture}}'
docker images | grep my-isaac

After the import is complete, the image my-isaac-ros-slam:4.6-all should be visible, with the architecture arm64. Loading the image takes some time; do not close the terminal or delete the archive in the middle.

Expected output:

xxxxxxxxxx
OS=linux Arch=arm64
my-isaac-ros-slam:4.6-all    xxxxxxx   about 65.3GB

4. Extracting the Course Workspace

First view the directory structure in the archive:

xxxxxxxxxx
tar -tzf /home/jetson/isaac_ros_workspaces.tar.gz | head -n 30

The archive should contain the complete workspaces/isaac_ros-dev/ workspace, including at least:

  • isaac_ros_assets/: course models and rosbag data

  • launch/: case launch files

  • rviz/: RViz configuration

  • scripts/ and the case helper scripts in the root of the workspace

  • fastdds_no_shm.xml: the Fast DDS configuration used by the course

If the list is missing the directories or files above, obtain the complete workspace archive from the course provider first. Select the corresponding command according to the result of tar -tzf. If the paths in the archive start with workspaces/isaac_ros-dev/, extract to /home/jetson:

xxxxxxxxxx
mkdir -p /home/jetson/workspaces
tar -xzf /home/jetson/isaac_ros_workspaces.tar.gz -C /home/jetson
test -d /home/jetson/workspaces/isaac_ros-dev/isaac_ros_assets
test -d /home/jetson/workspaces/isaac_ros-dev/launch
test -d /home/jetson/workspaces/isaac_ros-dev/rviz

If the paths in the archive start directly with isaac_ros-dev/, extract to /home/jetson/workspaces and check:

xxxxxxxxxx
mkdir -p /home/jetson/workspaces
tar -xzf /home/jetson/isaac_ros_workspaces.tar.gz -C /home/jetson/workspaces
test -d /home/jetson/workspaces/isaac_ros-dev/isaac_ros_assets
test -d /home/jetson/workspaces/isaac_ros-dev/launch
test -d /home/jetson/workspaces/isaac_ros-dev/rviz

Before extracting, confirm that the target directory does not exist or contains no files that need to be kept; if a check fails, verify the directory structure of the archive first and do not continue starting the container.

5. Starting the Container

5.1 Preparing Fast DDS and the Terminal Environment

The workspace is located in a host-mounted directory, so a configuration file placed in the workspace is retained across container restarts. First check whether the workspace already has fastdds_no_shm.xml; if not, create it on the Jetson host:

xxxxxxxxxx
cat > /home/jetson/workspaces/isaac_ros-dev/fastdds_no_shm.xml <<'EOF'
<?xml version="1.0" encoding="UTF-8" ?>
<profiles xmlns="http://www.eprosima.com/XMLSchemas/fastRTPS_Profiles">
  <transport_descriptors>
    <transport_descriptor>
      <transport_id>udp_only</transport_id>
      <type>UDPv4</type>
    </transport_descriptor>
  </transport_descriptors>
  <participant profile_name="udp_only_participant" is_default_profile="true">
    <rtps>
      <userTransports>
        <transport_id>udp_only</transport_id>
      </userTransports>
      <useBuiltinTransports>false</useBuiltinTransports>
    </rtps>
  </participant>
</profiles>
EOF

The Fast DDS configuration uses the UDP transport and is the configuration of the container environment of this course. The startup script generates /tmp/.bashrc each time the container starts, which only contains the ROS and workspace environment settings; there is no need to create another environment file on the host, and the user configuration in the image is not modified.

5.2 Creating the Startup Script

On first use, create the startup script on the Jetson host:

​x
cat > /home/jetson/run_isaac.sh <<'EOF'
#!/bin/bash
set -e

ISAAC_ROS_WS="$HOME/workspaces/isaac_ros-dev"

if [[ ! -d "$ISAAC_ROS_WS" ]]; then
  echo "The workspace does not exist: $ISAAC_ROS_WS" >&2
  exit 1
fi
if [[ ! -f "$ISAAC_ROS_WS/fastdds_no_shm.xml" ]]; then
  echo "The Fast DDS configuration file does not exist: $ISAAC_ROS_WS/fastdds_no_shm.xml" >&2
  exit 1
fi

docker run --rm -it \
  --runtime=nvidia --gpus all \
  --network host --ipc host --privileged \
  -u 1000:1000 -e HOME=/tmp \
  -e DISPLAY="$DISPLAY" -e QT_X11_NO_MITSHM=1 \
  -v /tmp/.X11-unix:/tmp/.X11-unix:rw \
  -v "$ISAAC_ROS_WS:/workspaces/isaac_ros-dev" \
  --entrypoint /bin/bash \
  my-isaac-ros-slam:4.6-all \
  -c '
cat > /tmp/.bashrc <<'"'"'BASHRC_EOF'"'"'
source /opt/ros/jazzy/setup.bash
export ISAAC_ROS_WS=/workspaces/isaac_ros-dev
export FASTRTPS_DEFAULT_PROFILES_FILE=/workspaces/isaac_ros-dev/fastdds_no_shm.xml
BASHRC_EOF
exec /bin/bash --rcfile /tmp/.bashrc -i
'
EOF
xxxxxxxxxx
chmod +x /home/jetson/run_isaac.sh

The script is written for the jetson user with UID/GID 1000:1000; other users should run id first and then modify the -u parameter according to the actual result. When the container starts, the ROS and workspace environment is written to /tmp/.bashrc, and an interactive Bash is started with that file through --rcfile. --privileged is part of the current device configuration of the course and is not recommended to be applied directly to containers for other purposes.

Graphical cases must be started from the Jetson desktop terminal. First allow the local Docker container to access the current desktop, then run the startup script:

xxxxxxxxxx
xhost +local:docker
cd /home/jetson
./run_isaac.sh

After all graphical programs are closed, the authorization can be revoked:

xxxxxxxxxx
xhost -local:docker

Do not use xhost + to disable all graphical access control, and do not modify the global Docker runtime by yourself. If an error is reported at startup, record the complete error message and check the image, the workspace, and the desktop session configuration.

After the container starts, open another Jetson terminal to view the container name:

xxxxxxxxxx
docker ps --format 'table {{.Names}}\t{{.Image}}\t{{.Status}}'

When an additional container terminal is needed, execute on the Jetson host:

xxxxxxxxxx
docker exec -it <container name> bash

Replace <container name> with the name shown by docker ps.

6. Checking the ROS Environment

When entering the container with the startup script of this tutorial, the ROS and Fast DDS environment is loaded automatically by /tmp/.bashrc. Execute the following commands inside the container to check:

xxxxxxxxxx
echo "$ROS_DISTRO"
echo "$ISAAC_ROS_WS"
echo "$FASTRTPS_DEFAULT_PROFILES_FILE"
test -f "$FASTRTPS_DEFAULT_PROFILES_FILE"
test -d "$ISAAC_ROS_WS/isaac_ros_assets"
test -d "$ISAAC_ROS_WS/launch"

The expected ROS distribution is jazzy, the workspace is /workspaces/isaac_ros-dev, and the Fast DDS configuration file exists. Then check the core package:

xxxxxxxxxx
ros2 pkg prefix isaac_ros_visual_slam

The expected package path is located in /opt/ros/jazzy. If the container is started in another way, source /opt/ros/jazzy/setup.bash must be executed manually in each new terminal, and ISAAC_ROS_WS and FASTRTPS_DEFAULT_PROFILES_FILE must be set.

7. Model Preparation Rules

Case 5 uses the TensorRT plan in the optimized_deployable_shuffleseg_unet_amr_v1.0 directory, which is loaded directly by the launch file; case 7 uses the Triton model peoplenet. Cases 1–4, 6, 8, and 9 do not need to be switched in this way. Before switching, stop the current case first, check the two directories inside the container, and then execute as needed:

xxxxxxxxxx
cd /workspaces/isaac_ros-dev/isaac_ros_assets
ls models/triton/ models_pending/

# Move all current models under models/triton/ back to the pending directory
mv models/triton/* models_pending/

# Replace <model name> with the corresponding directory name above
mv models_pending/<model name> models/triton/
ls models/triton/

mv models/triton/* moves all models in the active directory away, so execute it only after confirming that no other model needs to be retained; if the target model is already in the active directory, no switch is required. Before moving, confirm that there is no directory with the same name in pending; if the command reports an error, check the directories first and do not hide the error with 2>/dev/null. The CenterPose FP32 plan of case 8 is specified by the startup script and is not switched here.

8. Optional: Deleting the Archives After Deployment Is Confirmed

After confirming that the image has been imported successfully, the workspace has been extracted, and the container and cases can start normally, the two archives can be deleted if the installation packages do not need to be retained. This operation does not delete the imported Docker image or the extracted workspace files; keep the archives while the deployment has not been confirmed successful.

xxxxxxxxxx
rm /home/jetson/my-isaac-ros-slam-4.6-all.tar.gz
rm /home/jetson/isaac_ros_workspaces.tar.gz

9. Usage Notes

  • Run only one high-load case at a time; start the next one after the current case is finished.

  • Start and stop the nodes of each case according to its operation instructions, and exit normally with Ctrl+C in the corresponding terminal; do not terminate processes in batches with clean_ros or a broad pkill.

  • After the container exits, the container itself is deleted automatically; the Docker image and the files in /home/jetson/workspaces/isaac_ros-dev/ on the host are retained.

  • If groups: cannot find name for group ID is displayed but the container, the ROS nodes, and the case checks are normal, this prompt usually does not affect operation.

  • If RViz or rqt cannot display, confirm that it was started from the Jetson desktop terminal and check whether the desktop graphical authorization has been set.

  • If Docker, image import, or workspace checks fail, record the complete error message and contact the course provider; do not delete the delivery archives or modify the system-level Docker configuration.

10. Next Steps

After the environment check passes, run the course content by referring to the operation instructions of cases 1–9 in the directory of this chapter.

Multimodal autonomous agent application
Deep segmentation

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