Developer Resources for Robotics and Edge AI Applications

A hub of news, SDKs, technical resources, and more.

App Frameworks and SDKs

Robotics and Automation

NVIDIA Isaac™ Sim built on NVIDIA Omniverse™ provides access to NVIDIA PhysX and RTX ray-tracing technologies for photo-realistic robotic simulations for training and testing in virtual industrial environments. It includes enhanced synthetic data generation capabilities and supports ROS/ROS2 applications.

Get Started with

NVIDIA Isaac SDK™ enables you to build and deploy commercial-grade, AI-powered robots. The toolkit includes building blocks and tools that accelerate robot developments that require the increased perception, navigation, and manipulation features enabled by AI.


Edge AI and IoT

NVIDIA JetPack™ SDK is a comprehensive solution for building Edge AI applications. All NVIDIA® Jetson™ hardware modules and developer kits are supported by JetPack SDK. Jetson is a complete System on Module (SOM), and comes with various power, performance, and form factors to help you build autonomous and intelligent machines according to your needs.

Get Started with

NVIDIA Fleet Command is a hybrid-cloud platform for centralized management at scale at the edge. From one control plane, anyone with a browser and internet connection can deploy applications, update software over the air, and monitor location health.

Learn About
Fleet Command

AI-Powered Computer Vision

Pre-trained models for computer vision and the TAO Toolkit TAO Toolkit enable quick development and adaptation of highly accurate AI models for robotics and autonomous machine use cases.

Access Pre-Trained Models

NVIDIA DeepStream lets you build and deploy AI-powered intelligent video analytics apps and services across a broad range of automation applications.

Learn About the


NVIDIA® TensorRT™ is an open-source platform for high-performance deep learning inference, which includes an inference optimizer and runtime that delivers low latency and high throughput for your healthcare applications.

Learn About TensorRT

High-Performance Computing

TheNVIDIA HPC Software Development Kit NVIDIA HPC Software Development Kit (SDK) includes the proven compilers, libraries, and software tools essential to maximizing developer productivity and the performance and portability of HPC applications.

Learn About The HPC SDK

NVIDIA® Triton Inference Server

Simplifies the deployment of AI models at scale in production. It is an open source inference serving software that lets teams deploy trained AI models from any framework on any GPU- or CPU-based infrastructure (cloud, data center, or edge).

Learn More

Real-Time Collaboration

NVIDIA Omniverse™ powers real-time collaboration in a single, interactive, simulated environment and instant photorealistic output to ultra-high-fidelity, ray-traced, and path-traced rendering with one click.

Get Started with OMNIVERSE

Conversational AI, Pose and Gaze Estimation

NVIDIA Riva is an SDK for building and deploying AI applications that fuse vision, speech, and other sensors. It offers a complete workflow to build, train, and deploy GPU-accelerated AI systems that can use visual cues, such as gestures and gaze, with speech in context.
Pre-trained models and scripts used in Riva are freely available in the NVIDIA® NGC™ catalog.

Apply For Eearly Access

On Demand Talks

Sim-to-Real in Isaac Sim

Train and test robots in virtual environments with Isaac Sim on Omniverse, then transfer to a physical Jetson-powered robot. This webinar, presented at GTC 2021, will review the latest features offered in Isaac Sim.

Watch Now

Building Robotics Applications Using NVIDIA Isaac SDK

This session covers the NVIDIA Isaac SDK robotics platform and its benefits for developers, including the engine, perception GEMS (packages with high-performance robotics algorithms), and workflows and what’s coming in the next release.

Watch Now

Create Gesture-Based Interactions with a Robot

Learn how to train your own gesture recognition deep learning pipeline. We’ll start with a pre-trained detection model, repurpose it for hand detection, and use it together with the purpose-built gesture recognition model.

Watch Now

Accelerating Vision AI Applications Using NVIDIA TAO Toolkit and Pre-trained Models

Learn how to make the process of creating vision AI models quicker and easier with NVIDIA TAO Toolkit and pre-trained models.

Watch Now

How to Train Your Robot: A Simulation-First Approach

This session covers BMW Group’s research and development in one of their most recent applications: the Smart Transport Robot (STR), focusing on the simulation environment and how it’s involved in the development process of the STR.

Watch Now

Optimizing for Edge AI on NVIDIA Jetson

Deepdive session on workflows optimizing deep learning models for inference at the edge with NVIDIA Jetson.

Watch Now
View all GTC talks

NVIDIA Deep Learning Institute

Nvidia DLI

The NVIDIA Deep Learning Institute (DLI) offers hands-on training in AI and accelerated computing to solve real-world problems. Training is available as self-paced, online courses or in-person, instructor-led workshops.

Applications of AI for Predictive Maintenance

Learn how to identify anomalies and failures in time-series data, estimate the remaining useful life of the corresponding parts, and use this information to map anomalies to failure conditions, minimizing unplanned downtime.

Learn More

Getting Started with DeepStream for Video Analytics on Jetson Nano

In this course, you’ll learn to extract meaningful insights from video streams through deep learning video analytics using JupyterLab notebooks on an NVIDIA Jetson Nano™.

Learn More

Deep Learning for Industrial Inspection

Explore how convolutional and recurrent neural networks can be combined to generate effective descriptions of content within images and video clips by combining computer vision and natural language processing. Solve deep learning problems that require multiple types of data inputs.

Learn More

Deep Learning for Robotics

Follow along to create robotics solutions on NVIDIA Jetson™ for embedded applications and train a robot to actuate the correct output based on the visual input.

Learn More

NVIDIA Robotics News

Implementing Robotics Applications with ROS 2 and AI on the NVIDIA Jetson Platform

Deep learning is being adopted in robotics to accurately navigate indoor environments, detect and follow objects of interest, and maneuver without collisions.

Read Blog

What Is Synthetic Data?

Synthetic data generated from computer simulations or algorithms provides an inexpensive alternative to real-world data that’s increasingly used to create accurate AI models.

Read Blog

Automatic Defect Inspection Using the NVIDIA End-to-End Deep Learning Platform

Learn about the problems with traditional quality inspection and how deep learning can address and solve these industrial inspection tasks.

Read Blog

Rapid Prototyping on NVIDIA Jetson Platforms with MATLAB

Create a prototype and deploy deep learning algorithms on hardware like the NVIDIA Jetson Nano™ Developer Kit with MATLAB.

Read Blog

Building a Multi-Camera Media Server for AI Processing on the NVIDIA Jetson Platform

Build a simple, real-time multi-camera media server for AI processing on the NVIDIA Jetson™ platform. By using GStreamer Daemon (GstD), GstInterpipe GStreamer Daemon (GstD), GstInterpipe, and the NVIDIA DeepStream SDK, you can develop a scalable and robust prototype that captures video from several different sources.

Read Blog

Introducing Jetson Xavier NX, the World’s Smallest AI Supercomputer for Autonomous Systems

Explore how NVIDIA Jetson Xavier™ NX allows you to deploy next-generation autonomous systems and intelligent edge devices that require high-performance AI and complex deep neural networks (DNNs) in a small, low-power footprint—mobile robots, drones, smart cameras, portable medical equipment, embedded Internet of Things (IoT) systems, and more.

Read Blog

Sign up for the latest developer news from NVIDIA