NVIDIA Drives Next-Gen Robotics Forward with Key Open-Source Contributions and Isaac ROS 4.0 Release

At the recent ROSCon conference in Singapore, NVIDIA unveiled a series of significant contributions aimed at advancing the Robot Operating System (ROS) 2 framework and bolstering the broader robotics developer community. These announcements, which include support for the Open Source Robotics Alliance’s (OSRA) new Physical AI Special Interest Group and the latest release of NVIDIA Isaac ROS 4.0, are designed to accelerate the development of next-generation robotics.

The global robotics community converged at ROSCon to discuss the future of ROS, the world’s most widely adopted open framework for building robots. NVIDIA’s strategic collaborations with partners and OSRA underscore its commitment to open standards and the rapid acceleration of robotics development.

NVIDIA is actively supporting OSRA’s new Physical AI Special Interest Group. This group is focused on critical areas such as real-time robot control, accelerated AI processing, and developing superior robotics tools for autonomous behavior.

These efforts are integral to establishing ROS 2 as the premier open, high-performance framework for real-world robotic applications, ensuring robust and efficient operation in diverse environments.

A core contribution from NVIDIA involves integrating GPU-aware abstractions directly into ROS 2. This enhancement allows the framework to intelligently understand and efficiently manage various types of processors, from traditional CPUs to integrated and discrete GPUs.

Such capability guarantees consistent, high-speed performance and effectively future-proofs the entire ROS ecosystem, enabling it to keep pace with rapid innovations in hardware technology. Additionally, to further optimize robot performance and reliability, NVIDIA is open-sourcing Greenwave Monitor, a valuable tool that helps developers quickly identify and resolve performance bottlenecks.

NVIDIA also announced the immediate availability of NVIDIA Isaac ROS 4.0, a new collection of ROS-compatible, GPU-accelerated libraries and AI models. This powerful suite is now accessible on the NVIDIA Jetson Thor platform, specifically designed for deploying physical AI and robotics solutions.

Developers can leverage these Isaac CUDA-accelerated libraries, AI models, and workflows to enhance robot manipulation and mobility capabilities, streamlining the creation of advanced robotic systems.

NVIDIA’s open-source contributions are already empowering a wide array of developers and partners globally, facilitating the training, simulation, and deployment of advanced robots:

AgileX Robotics utilizes NVIDIA Jetson modules for AI autonomy and vision in its mobile robots, alongside NVIDIA Isaac Sim, a simulation framework built on NVIDIA Omniverse, for robust simulation environments.

Canonical simplifies robot development by offering a demo of a fully open observability stack for ROS 2 devices on Ubuntu, now available for the NVIDIA Jetson AGX Thor platform, ideal for robotics and edge computing.

Ekumen Labs has integrated NVIDIA Isaac Sim into its robotics development workflows, enabling high-fidelity simulations for system testing, validation, and the generation of photorealistic synthetic data.

Intrinsic is incorporating NVIDIA Isaac foundation models and Omniverse simulation tools into its Flowstate platform. This integration enables advanced robot-grasping capabilities, real-time digital twin visualization, and seamless AI-driven automation for industrial robotics.

KABAM Robotics’ Matrix robot employs NVIDIA Jetson Orin and NVIDIA Triton Inference Server on ROS 2 Jazzy, providing advanced security and facility management in complex outdoor environments.

During ROSCon, Open Navigation showcased NVIDIA technologies, including NVIDIA Isaac Sim and NVIDIA SWAGGER. Open Navigation founder Steve Macenski’s keynote, “On Use Of Nav2 Route,” demonstrated advanced route navigation for autonomous mobile robots.

Robotec.ai and NVIDIA are collaborating on a new ROS simulation standard, now integrated into Isaac Sim. This initiative aims to streamline cross-simulator development and enable more robust, automated testing for robotics.

ROBOTIS uses NVIDIA Jetson for on-board computing and Isaac Sim for simulation and validation. Its AI Worker, powered by the Isaac GR00T N1.5 model, delivers enhanced autonomy and scalable edge AI solutions.

Stereolabs’ ZED cameras and ZED SDK offer full compatibility with the NVIDIA Jetson Thor platform, supporting high-performance multi-camera capture, low-latency perception, and real-time spatial AI vision for general-purpose robotics.

From foundational contributions to powerful simulation tools and production-ready hardware, NVIDIA remains deeply committed to providing the open-source community with the comprehensive platform required to build the future of physical AI. Robotics developers are encouraged to learn more about these advancements by joining NVIDIA at ROSCon.