NVIDIA ROS 2 Projects
NVIDIA Jetson is working towards developing ROS 2 packages to ease the development of AI applications for robotics.
Key Projects
ROS and ROS 2 Docker Images : Docker images for easy deployment on the NVIDIA Jetson platform, consisting of ROS 2, PyTorch, and other important machine learning libraries.
ROS and ROS 2 DockerFiles: Dockerfiles for ROS 2 based on l4t which all you to build your own Docker image.
ROS 2 Packages for PyTorch and TensorRT: ROS 2 packageis for classification and object detection tasks using PyTorch and NVIDIA TensorRT. This tutorial is a good starting point AI integration with ROS 2 on NVIDIA Jetson.
ROS / ROS 2 Packages for Accelerated Deep Learning Nodes: Deep learning image recognition, object detection, and semantic segmentation inference nodes and camera/video streaming nodes for ROS/ROS 2 using the jetson-inference library and NVIDIA Hello AI World tutorial.
ROS 2 Package for Human Pose Estimation: A ROS 2 package for human pose estimation.
ROS 2 Package for Accelerated NVAprilTags: ROS 2 package for NVIDIA GPU-accelerated AprilTags library to detect AprilTags in images and publish their pose, ids, and additional metadata.
ROS 2 Package for Hand Pose Estimation and Gesture Classification: A ROS 2 package for real-time hand pose estimation and gesture classification using TensorRT.
GPU accelerated ROS 2 Packages for Monocular Depth Estimation: ROS 2 package for NVIDIA GPU-accelerated torch2trtxb examples such as monocular depth estimation and text detection.
ROS 2 Package for Jetson stats: ROS 2 package for monitoring and controlling your NVIDIA Jetson [Xavier NX, Nano, AGX Xavier, TX1, TX2].
ROS 2 Packages for DeepStream SDK: ROS 2 package for NVIDIA DeepStream SDK.