This repository is created for ROS Noetic and ROS2 Foxy / Eloquent containers for NVIDIA Jetson platform based on ROS2 Installation Guide, ROS Noetic Installing from Source, and dusty-nv/jetson-containers

NVIDIA Jetson provided various AI application ROS / ROS2 packages, please find here more information

This repository supports following docker images:

• ROS2 Eloquent / Foxy with PyTorch and TensorRT
  
  • DL Libraries: PyTorch, NVIDIA TensorRT
    
  • ML Libraries: scikit-learn, numpy etc
    
  • Widely used developer repositories: torch2trt, trt_pose
  • ROS2 Packages: (Foxy packages will be updated soon)
    • NVIDIA-AI-IOT/ros2_trt_pose
      
    • NVIDIA-AI-IOT/ros2_trt_pose_hand
      
• ROS2 Eloquent / Foxy with DeepStream SDK
  
  • NVIDIA DeepStream SDK for Classification, Object detection
    
  • ROS2 packages: (Foxy packages will be updated soon)
    • NVIDIA-AI-IOT/ros2_deepstream
      
    • vision_msgs
• ROS Noetic with PyTorch and TensorRT
  
  • DL Libraries: PyTorch, NVIDIA TensorRT
    
  • ML Libraries: scikit-learn, numpy etc
    
  • Cuda Acceleration Library: pyCUDA
  • Widely used developer repositories: torch2trt, trt_pose

• ROS2 Eloquent with PyTorch and TensorRT
  docker pull nvidiajetson/l4t-ros2-eloquent-pytorch:r32.5
• ROS2 Eloquent with DeepStream SDK
  docker pull nvidiajetson/deepstream-ros2-eloquent:5.0.1
• ROS2 Foxy with PyTorch and TensorRT
  docker pull nvidiajetson/l4t-ros2-foxy-pytorch:r32.5
• ROS2 Foxy with DeepStream SDK
  docker pull nvidiajetson/deepstream-ros2-foxy:5.0.1
• ROS Noetic with PyTorch and TensorRT
  docker pull nvidiajetson/l4t-ros-noetic-pytorch:r32.5

1. Enable Docker Default Runtime:
   

   • Add "default-runtime": "nvidia" to your /etc/docker/daemon.json $ vi /etc/docker/daemon.json

      {
        "runtimes": {
            "nvidia": {
                "path": "nvidia-container-runtime",
                "runtimeArgs": []
             }
        },
   
        "default-runtime": "nvidia"
      }
   
   • Restart docker or Reboot system $ sudo systemctl restart docker
     

2. Copy file needed for CV2 library installation
   $ cp /etc/apt/trusted.gpg.d/jetson-ota-public.asc .

3. Build Container
   

   • ROS2 Eloquent with PyTorch and TensorRT sh docker_build.sh eloquent l4tbase
   • ROS2 Eloquent with DeepStream SDK sh docker_build.sh eloquent deepstream
   • ROS2 Foxy with PyTorch and TensorRT sh docker_build.sh foxy l4tbase
   • ROS2 Foxy with DeepStream SDK sh docker_build.sh foxy deepstream
   • ROS Noetic with PyTorch and TensorRT sh docker_build.sh noetic l4tbase