NVIDIA announces the availability of the 2022.2 release of NVIDIA Isaac Sim. As a robotics simulation and synthetic data generation (SDG) tool, this NVIDIA Omniverse application accelerates the development, testing, training, and deployment of intelligent robots.
With NVIDIA Isaac Sim, you can easily import the robot model of your choice. Use it to build realistic environments for validating a robot’s physical design and fully exercise its software stack to ensure performance. Synthetic datasets can also be generated during simulation to train the robot’s AI models used in the robot’s perception systems. Use the reinforcement learning API to train models in the robot control stack.
Accessible from the cloud, NVIDIA Isaac Sim can be used by cross-functional teams located across the world and on any device with a web browser.
The latest version is focused on improving performance and functionality for manufacturing and logistics robotics use cases. Adding people and complex conveyor systems to the simulation environments is now supported. More assets and popular robots are pre-integrated to reduce the time until simulation.
For ROS developers, there is added support for ROS2 Humble and Windows. For robotics researchers, there are a host of new capabilities aimed at advancing reinforcement learning, collaborative robot programming and robot learning.
Here are some highlights of the new release.
Warehouse logistics is one of the most important areas of robotic innovation. NVIDIA Isaac Sim has several tools that address the needs of robotic simulation in the warehouse.
Previously, a tool was released to generate digital twins of warehouses. Now, NVIDIA Isaac Sim includes a tool to build realistic conveyor belts. Also included is a people simulator to add digital humans to the warehouse environment. This tool is useful for validating the perception and safety systems of robots that work near humans.
Manufacturing environments have long embraced manipulator robots to automate their processes. The 2022.2 release has several new capabilities for handling motion control in manipulator robots. The updated motion generation extension in NVIDIA Isaac Sim now simplifies the integration and benchmarking of motion control algorithms. The included algorithms, RMPFlow, create smooth trajectories for the robots with intelligent collision avoidance.
In addition to improved performance, this release features a number of usability improvements including a graphics editor for Lula robot description files. A new set of manipulators has also been added.
The cuOpt for Isaac Sim extension is a deployment of the NVIDIA cuOpt engine integrated directly with NVIDIA Isaac Sim. NVIDIA cuOpt is an operations research optimization API to help you create complex, real-time fleet routing. These APIs can be used to solve complex routing problems with multiple constraints and deliver new capabilities, like dynamic rerouting, job scheduling, and robotic route planning while using subsecond solver response time.
Improved ROS support
ROS support has been upgraded to support ROS 2 Humble. Isaac ROS, which is also based on the Humble release, can now be easily simulated and tested in this release. ROS 2 support is also added on Windows machines.
Significant new capabilities for robotics researchers include performance improvements for Isaac Gym (reinforcement learning). Isaac Cortex, for collaborative robot programming, has new examples. Finally, a new open-source tool, Isaac ORBIT, provides simulation operating environments and benchmarks for robot learning and motion planning.
With cloud access and its expansive set of photoreal and physically accurate simulation capabilities, NVIDIA Isaac Sim is set to establish new methodologies for the development of intelligent robots.
- Download NVIDIA Isaac Sim or read the 2022.2 release notes
- Ramp up your skills with this DLI course, Introduction to Robotic Simulations with Isaac Sim