Accelerating and improving robotics -
from development to simulation to deployment

From intelligent automation in manufacturing to robots in last-mile delivery, robots are becoming more ubiquitous in everyday life. However, developing industrial and commercial robots can be complex, time-consuming, extremely challenging and expensive. In addition, unstructured environments are common in many use cases and scenarios. The NVIDIA Isaac™ Robotics Platform can address these challenges with an end-to-end solution to reduce costs, simplify development, and accelerate time to market.


See how NVIDIA's Isaac platform is being used in autonomous mobile robotics,
industrial automation, healthcare, retail, agriculture and more.

more and more ROS developers are using hardware platforms that contain additional computing capacity to offload the host CPU. ROS continues to evolve to facilitate the efficient use of these advanced hardware resources," said Brian Gerkey, CEO of Open Robotics. "Working with a leader in accelerated computing like NVIDIA and their tremendous experience in AI and robotics innovation will bring significant benefits to the entire ROS community.
Brian Gerkey, CEO and co-founder of Open Robotics

The end-to-end robotics platform from Isaac

Accelerate the development process with improved robotics design, simulation, and deployment.



Robots offer endless opportunities to increase efficiency and improve the quality of life for people in industries such as manufacturing, logistics, and services. NVIDIA Isaac accelerates this process through improvements in robot design, simulation, and deployment.

The new Isaac AMR platform

The Isaac Autonomous Mobile Robots (AMR) platform extends NVIDIA Isaac capabilities to developers building and deploying robotics applications, bringing mapping, location analysis, and fleet and route optimization to NVIDIA EGX servers. The new platform will help improve and accelerate AMR applications for the logistics industry - from warehouses to retail. It leverages NVIDIA's GPU-accelerated AI technologies such as Metropolis, ReOpt, DeepMap and others on NVIDIA's AI and Omniverse platforms.


Omniverse Replicator
for Isaac Sim

Isaac Sim now offers developers a data cockpit for synthetically generating machine learning (ML) model datasets with easy-to-understand parameters. Powered by Omniverse Replicator, Isaac Sim generates synthetic data that can be used to train DNNs running on an AMR. This helps developers design and deploy AI-enabled robots that operate safely and avoid common mishaps, such as in factories when robots collide with forklift tines.


isaac Perception via ROS

NVIDIA brings hardware-accelerated GEMS to scale and makes AI algorithms open source to the ROS community. NVIDIA announced a collaboration with OSRF to help robotics customers using ROS get the best performance from their robots.



Jetson AGX Xavier is the world's first computer designed specifically for robotics. With more than nine billion transistors, it delivers 32 trillion operations per second for Deep Learning, as well as 10x the power efficiency and more than 20x the performance of its predecessor, the NVIDIA Jetson™ TX2.

Jetson AGX Xavier helps robots understand what is happening in their environment. To do this, it uses six high-performance processors, a 512-core tensor-core GPU that matches the NVIDIA Volta™ architecture, an eight-core Carmel ARM64 CPU, a dual NVIDIA Deep Learning accelerator, and processors for image, vision and video data.


Unleash the power of
an accelerated platform for robotics and AI

Data generation

Collecting and labeling datasets is time-consuming and prohibitively expensive. More diverse training data leads to more accurate AI models. Improve training with synthetic data with NVIDIA Isaac Sim.

Simulate and test

Robots are trained and tested virtually in photorealistic and physically accurate environments using NVIDIA Isaac Sim in the NVIDIA Omniverse™ virtual environment.

Train your robot

Choose the optimal NVIDIA platform for training your AI model - from local workstations to large-scale AI in the data center and cloud.
NVIDIA can also accelerate development with the TAO Toolkit
, which includes production-quality pre-trained models that you can use directly or fine-tune with a fraction of the data needed to train from scratch.

Develop applications

High-performance robotics applications can be developed using hardware-accelerated SDKs such as Isaac ROS GEMs for ROS-based robots, Deepstream SD K for streaming video understanding, NVIDIA Riva for natural language processing, and Isaac SDK for a complete framework.

Insert and manage

Only NVIDIA offers a complete end-to-end workflow for seamless deployment. Robotics applications can be ported to NVIDIA Edge devices, from NVIDIA Jetson to EGX Edge computers, to create truly autonomous machines. Scaling services across distributed edge cases are also available on EGX Fleet Command.