Isaac Sim

NVIDIA Omniverse™ Isaac Sim , is a scalable robotics simulation application and synthetic data generation tool, built on the NVIDIA Omniverse™ platform. It leverages Omniverse Kit powerful simulation technologies including advanced GPU-enabled physics simulation with PhysX 5, photorealism with real-time ray and path tracing, and MDL material definition support for physically-based rendering. Isaac Sim is a physically-accurate virtual environment to develop, test, and manage AI-based robots, and provides the essential features for building virtual robotics experiments, including importing robot models, and simulating sensors such as RGB-D, Lidar, contact, ultrasonic, and IMU. Isaac Sim supports navigation, manipulation, deep learning applications through Python, ROS and Isaac SDK. For AI applications, Isaac Sim provides extensive tools for synthetic data generation such as domain randomization, ground truth labeling, segmentation, and bounding boxes.

Current release: 2021.2.1

This release is offered as a container that runs locally or on RTX equipped Amazon Web Services (AWS) or Microsoft Azure with streaming to the user’s desktop. This cloud-based delivery provides the latest RTX graphics and performance to any desktop system without requiring local NVIDIA RTX GPUs.

What's New in Isaac Sim 2021.2.1

• General
  • Nucleus and Cache included in the Docker container
  • Livestream WebRTC removed
  • Jupyter Notebook support
  • Faster Startup time
  • Reduced System memory usage
  • Improved Stability
  • Many new and updated extensions
• Standalone Samples and Tools:
  • Replicator Composer Data Generation Tools
  • Jupyter Notebook Samples
  • Simplified & combined synthetic data generation examples
• Documentation
  • Keyboard shortcuts Reference
  • Isaac Sim Conventions Reference
  • ROS & ROS2 installation Guide
  • Python Installation Guide
  • Riemannian Motion Policy Manual
  • Simplified Documentation structure and redirection
• New Tutorials:
  • Requried tutorials for all users
  • Advanced tutorials for specific topics
  • Replicator Tutorials for synthetic data generation
  • ROS & ROS2 tutorials
• Assets
  • Full Warehouse environment
  • Hospital environment
  • Office environment
  • Dofbot robot model
  • AWS robomaker jetbot

Running Isaac Sim

Requirements for local deployment:

• Ubuntu 18.04 Operating System
• NVIDIA GPU (RTX 2070 or higher)
• NVIDIA GPU Driver (minimum version 470.57)
• Docker CE 19.03
• NVIDIA Container Toolkit

Steps:

1. Run the command below to confirm your GPU driver version is 470.57 or later.

    $ nvidia-smi
    
   

2. Follow the steps in Generate Your NGC API Key.

3. Login into NGC to download the Isaac Sim container

   $ sudo docker login nvcr.io
    Username: $oauthtoken
    Password: 
    WARNING! Your password will be stored unencrypted in /home/username/.docker/config.json.
    Configure a credential helper to remove this warning. See
    https://docs.docker.com/engine/reference/commandline/login/#credentials-store
    Login Succeeded
   

4. Run:

    $ sudo docker run --gpus all -e "ACCEPT_EULA=Y" --rm --network=host nvcr.io/nvidia/isaac-sim:2021.2.1
   

This will download and launch the Isaac Sim container in headless mode. Note: By using the -e "ACCEPT_EULA=Y" flag, you are accepting the NVIDIA Omniverse License Agreement of the image.

Refer to our Isaac Sim User Guide for more information.

Livestreaming Isaac Sim remotely

See Livestream Clients in our User Guide to connect to Isaac Sim using the your desktop. The default livestream client is WebSockets.

License

NVIDIA Omniverse License Agreement is included with the product. This license is also available on the NVIDIA Developer Program download page, the user is required to read and accept the terms of condition before downloading.

Suggested readings:

• https://docs.omniverse.nvidia.com/isaacsim/index.html
• https://developer.nvidia.com/isaac-sim

Use the NVIDIA Devtalk forum for questions regarding this Software