NVIDIA has unveiled significant contributions to the global robotics community, focusing on open frameworks and accelerated computing. At the ROSCon conference in Singapore, the company announced key advancements to the Robot Operating System (ROS 2) framework and the Open Source Robotics Alliance’s (OSRA) new Physical AI Special Interest Group, alongside the latest release of NVIDIA Isaac ROS.

These initiatives underscore NVIDIA’s dedication to accelerating robotics development by fostering open standards and providing powerful software and hardware tools. The ultimate goal is to establish ROS 2 as the premier, high-performance framework for real-world robotic applications.

Enhancing ROS 2 with GPU-Aware Abstractions

A cornerstone of NVIDIA's announcement is the direct contribution of GPU-aware abstractions to ROS 2. This crucial integration enables ROS 2 to intelligently recognize and efficiently manage diverse processors, spanning from traditional CPUs to integrated and discrete GPUs.

This enhancement guarantees consistent, high-speed performance across the ROS ecosystem and future-proofs it against rapid hardware innovation. Robotics developers can now leverage NVIDIA's powerful GPUs more effectively within their ROS 2 projects.

New Tools for Accelerated Development

To further empower developers, NVIDIA has open-sourced Greenwave Monitor, a valuable tool designed to optimize robot performance and reliability. Greenwave Monitor allows developers to quickly pinpoint and address performance bottlenecks, significantly speeding up the robot development cycle.

Additionally, NVIDIA announced the availability of NVIDIA Isaac ROS 4.0, a comprehensive suite of ROS-compatible, GPU-accelerated libraries and AI models. This release is now optimized for the NVIDIA Jetson Thor platform, facilitating the deployment of physical AI and advanced robotics. Developers can access and utilize Isaac CUDA-accelerated libraries, AI models, and workflows for complex robot manipulation and mobility tasks.

Industry Leaders Leverage NVIDIA AI for Robotics

NVIDIA's open-source contributions are already driving innovation among developers and partners globally, enabling them to train, simulate, and deploy the next generation of robots. Several key industry players are integrating NVIDIA's technology into their solutions:

AgileX Robotics powers its mobile robots with NVIDIA Jetson modules for AI autonomy and vision, also utilizing NVIDIA Isaac Sim for advanced simulation.
Canonical simplifies robot development with a fully open observability stack for ROS 2 devices on Ubuntu, now available for the NVIDIA Jetson AGX Thor platform.
Ekumen Labs has integrated NVIDIA Isaac Sim into its workflows, allowing for high-fidelity simulations, rigorous system testing, and photorealistic synthetic data generation.
Intrinsic integrates NVIDIA Isaac foundation models and Omniverse simulation tools into its Flowstate platform for advanced robot grasping, real-time digital twins, and AI-driven industrial automation.
KABAM Robotics’ Matrix robot employs NVIDIA Jetson Orin and NVIDIA Triton Inference Server on ROS 2 Jazzy for enhanced security and facility management in demanding outdoor environments.
Open Navigation showcased NVIDIA technologies, including Isaac Sim and NVIDIA SWAGGER, demonstrating advanced route navigation for autonomous mobile robots.
Robotec.ai and NVIDIA are collaborating on a new ROS simulation standard, integrated into Isaac Sim, to streamline cross-simulator development and enable more robust, automated robotics testing.
ROBOTIS uses NVIDIA Jetson for on-board computing and Isaac Sim for simulation. Its AI Worker, powered by the Isaac GR00T N1.5 model, achieves greater autonomy and scalable edge AI.
Stereolabs’ ZED cameras and 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 open-source contributions to powerful simulation tools and production-ready hardware, NVIDIA is steadfast in its commitment to providing the necessary platform for building the future of physical AI. Robotics developers are encouraged to learn more about these advancements by joining NVIDIA at ROSCon.