NVIDIA ROS 2 Projects ===================== NVIDIA provides packages for the development of AI applications for robotics. ISAAC ROS Projects ------------------ * `Pre-built ROS 2 Humble support `__: Pre-built Debian packages for ROS 2 Humble on Ubuntu 20.04 for Jetson and other aarch64 platforms from the NVIDIA build farm. * `CUDA with NITROS `__: This helps users develop their own CUDA enabled nodes that work with NITROS, the Isaac ROS implementation of type adaptation & type negotiation which enables accelerated computing in ROS 2. * `Isaac ROS NITROS Bridge `__: NITROS bridge for optimized integration of Isaac ROS packages with existing ROS 1 applications. Use this to bridge your ROS applications to ROS 2 for accelerated computing with >2x speed up compared to using a traditional ROS bridge. * `Nova Carter `__: A reference AMR for robotics development and research, powered by Isaac ROS and Nav2, and tuned with Open Navigation for teleoperation, mapping, and navigation. * `Isaac ROS Nova `__: This repository provides a set of optimized packages to interface with the Isaac Nova Orin sensor suite. * `Isaac ROS Pose Estimation `__: This repository contains ROS 2 packages to predict the pose of an object. * `ROS2_Benchmark `__: ros2_benchmark provides the tools for measuring the throughput, latency, and compute utilization of these complex graphs without altering the code under test. * `Isaac ROS Benchmark `__: This package builds upon the ros2_benchmark to provide configurations to benchmark Isaac ROS graphs. * `Isaac ROS Map Localization `__: This module contains ROS 2 packages for lidar processing to estimate poses relative to a map. The occupancy grid localizer processes a planar range scan to estimate pose in an occupancy grid map; this occurs in less than 1 second for most maps. * `Isaac ROS Nitros `__: Isaac Transport for ROS package for hardware-acceleration friendly movement of messages. * `Isaac ROS Compression `__: Hardware accelerated NITROS packages to compress camera data capture and playback for development of AI models and perception functions, compressing 4x 1080p cameras at 30fps (>120fps total) reducing data footprint by ~10x. * `Isaac ROS DNN Stereo Depth `__: DNN Stereo Disparity includes packages for predicting disparity of stereo input. * `Isaac ROS Depth Segmentation `__: Hardware-accelerated packages for depth segmentation. * `Isaac ROS Nvblox `__ : Hardware-accelerated 3D scene reconstruction and Nav2 local costmap provider using nvblox. * `Isaac ROS Object Detection `__ : Deep learning model support for object detection including DetectNet. * `Isaac ROS DNN Inference `__ : This repository provides two NVIDIA GPU-accelerated ROS 2 nodes that perform deep learning inference using custom models. One node uses the TensorRT SDK, while the other uses the Triton SDK. * `Isaac ROS Visual SLAM `__ : This repository provides a ROS 2 package that estimates stereo visual inertial odometry using the Isaac Elbrus GPU-accelerated library. * `Isaac ROS Mission Client `__ : This repository receives state and error updates from ROS and converts them to VDA5050 JSON messages for transmission by the ROS 2 -> MQTT node to Mission Dispatch. * `Isaac ROS Argus Camera `__ : This repository provides monocular and stereo nodes that enable ROS developers to use cameras connected to Jetson platforms over a CSI interface. * `Isaac ROS Image Pipeline `__ : This metapackage offers similar functionality as the standard, CPU-based image_pipeline metapackage, but does so by leveraging the Jetson platform's specialized computer vision hardware. * `Isaac ROS Common `__ : Isaac ROS common utilities for use in conjunction with the Isaac ROS suite of packages. * `Isaac ROS AprilTag `__ : ROS 2 node uses the NVIDIA GPU-accelerated AprilTags library to detect AprilTags in images and publish their poses, ids, and additional metadata. Additional Projects ------------------- * `ROS and ROS 2 DockerFiles `__: Dockerfiles for ROS 2 based on l4t which all you to build your own Docker image. * `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 `__. Simulation Projects ------------------- * `Isaac Sim Nav2 `__ : In this ROS 2 sample, we are demonstrating Omniverse Isaac Sim integrated with the ROS 2 Nav2 project. * `Isaac Sim Multiple Robot ROS 2 Navigation `__ : In this ROS 2 sample, we are demonstrating Omniverse Isaac Sim integrated with the ROS 2 Nav2 stack to perform simultaneous multiple robot navigation.