Embedded Systems for Next-Generation Autonomous Machines

NVIDIA Jetson: The AI platform for autonomous everything

Embedded Systems for Next-Generation Autonomous Machines

NVIDIA Jetson: The AI platform for autonomous everything

NVIDIA® Jetson™ systems provide the performance and power efficiency to run autonomous machines software, faster and with less power. Each is a complete System-on-Module (SOM), with CPU, GPU, PMIC, DRAM, and flash storage—saving development time and money. Jetson is also extensible. Just select the SOM that’s right for the application, and build the custom system around it to meet its specific needs.

Scalable, Flexible Hardware Solutions

Whether for enterprise, small to medium business, or research, the Jetson family has a solution to meet specific performance and budget needs. They all share the same architecture and SDKs, allowing for one code base and seamless deployment across the entire product portfolio.

Jetson Nano

£95.00

NVIDIA Maxwell™ architecture with 128 NVIDIA CUDA® cores

Jetson TX2 Series

Starting at £369.00

NVIDIA Pascal™ architecture with 256 NVIDIA CUDA cores

Jetson AGX Xavier Series

Starting at £649.00

NVIDIA Volta™ architecture  with up to 512 NVIDIA CUDA cores and up to 64 Tensor cores

NVIDIA JetPack SDK - Unified software release across all Jetson products

* Local pricing will vary due to currency and VAT.

See which Jetson is right for your application.

COMPARE

JETSON PORTFOLIO

Jetson modules power a range of applications that require various performance levels and prices—from AI-powered Network Video Recorders (NVRs) to automated optical inspection (AOI) in high-precision manufacturing to autonomous mobile robots (AMRs). Jetson modules pack unbeatable performance and energy efficiency in a tiny form factor, effectively bringing the power of modern AI, deep learning, and inference to embedded systems at the edge.

Jetson Nano

Jetson Nano

The Jetson Nano module is a small AI computer that has the performance and power efficiency needed to run modern AI workloads, multiple neural networks in parallel and process data from several high-resolution sensors simultaneously. This makes it the perfect entry-level option to add advanced AI to embedded products.

Learn more
Jetson TX2

Jetson TX2 Series

The Jetson TX2 series embedded module for edge AI applications now comes in three versions: Jetson TX2, Jetson TX2i, and the newly available, lower-cost Jetson TX2 4GB. Jetson TX1-based products can migrate to the more powerful Jetson TX2 4GB at the same price.

 

Learn more
Jetson AGX Xavier

Jetson AGX Xavier Series

Jetson AGX Xavier is the first computer designed specifically for autonomous machines. It has six Engines onboard for accelerated sensors data processing and running autonomous machines software, and offers the performance and power efficiency for fully autonomous machines.

Jetson AGX Xavier 8GB is a lower-power lower-price Jetson AGX Xavier offering full hardware and software compatibility with the existing Jetson AGX Xavier. It consumes a maximum of 20W for the full module whilst delivering up to 20 TOPS of AI performance and is available starting August, 2019.

 

Learn more

The Jetson TX1 module is the first generation of Jetson module designed for machine learning and AI at the edge and is used in many systems shipping today. However, new designs should take advantage of the Jetson TX2 4GB, a pin- and cost-compatible module with 2X the performance. Learn more about Jetson TX1 on the NVIDIA Developer Zone.

A SINGLE, UNIFIED SOFTWARE STACK

All three generations of Jetson solutions are supported by the same software stack, enabling companies to develop once and deploy everywhere. The Jetson platform is supported by the Jetpack SDK, which includes the board support package (BSP), Linux operating system, NVIDIA CUDA®, and compatibility with third-party platforms. DeepStream SDK enables developers to quickly build and deploy efficient video analytics pipelines on Jetson.

embedded-jetson-sw-stack-diagram-update-white

JetPack comes with libraries for deep learning, computer vision, accelerated computing, and multimedia and supports drivers for a wide range of sensors. Plus, NVIDIA develops GPU-accelerated IP for critical autonomous machine tasks like depth estimation, path planning, and object detection.

As part of Jetpack, NVIDIA provides has a rich set of developer tools that accelerate development and provide detailed information about application and system power and performance, helping developers quickly optimize and tune their code.

Find everything you need to get started and download the SDK at the NVIDIA Developer Site.

Documentation

DOCUMENTATION

Tools

TOOLS

Lastest news

LATEST NEWS

Forums and Community

FORUMS & COMMUNITY

Compare NVIDIA Jetson Module Specifications

 

  Jetson Nano Jetson TX2 Series

TX2 4GB TX2 TX2i
Jetson AGX Xavier Series

Jetson AGX Xavier 8GB Jetson AGX Xavier
GPU NVIDIA Maxwell™ architecture with 128 NVIDIA CUDA® cores NVIDIA Pascal™ architecture with 256 NVIDIA CUDA cores NVIDIA Volta™ architecture with 384 NVIDIA CUDA cores and 48 Tensor cores NVIDIA Volta™ architecture with 512 NVIDIA CUDA cores and 64 Tensor cores
0.5 TFLOPs (FP16) 1.3 TFLOPS (FP16) 5.5 TFLOPS (FP16)
11.1 TOPS (INT8)		 11 TFLOPS (FP16)
22 TOPS (INT8)
CPU Quad-core ARM® Cortex®-A57 MPCore processor Dual-core Denver 2 64-bit CPU and quad-core ARM A57 complex 6-core ARM v8.2 64-bit CPU, 8MB L2 + 4MB L3 8-core ARM v8.2 64-bit CPU, 8MB L2 + 4MB L3
DLA - - 4.1 TFLOPS (FP16)
8.2 TOPS (INT8)		 5 TFLOPS (FP16)
10 TOPS (INT8)
Memory 4 GB 64-bit LPDDR4 4 GB 128-bit LPDDR4 8 GB 128-bit LPDDR4 8 GB 256-bit LPDDR4x 1333MHz - 85GB/s 16 GB 256-bit LPDDR4x 2133MHz - 137GB/s
Storage 16 GB eMMC 5.1 16GB eMMC 5.1 32GB eMMC 5.1 32GB eMMC 5.1
Video Encode 250MP/sec
1x 4K @ 30 (HEVC)
2x 1080p @ 60 (HEVC)
4x 1080p @ 30 (HEVC)		 500MP/sec
1x 4K @ 60 (HEVC)
3x 4K @ 30 (HEVC)
4x 1080p @ 60 (HEVC)
8x 1080p @ 30 (HEVC)		 2x464MP/sec
2x 4K @ 30 (HEVC)
6x 1080p @ 60 (HEVC)
14x 1080p @ 30 (HEVC)		 2x1000MP/sec
4x 4K @ 60 (HEVC)
8x 4K @ 30 (HEVC)
16x 1080p @ 60 (HEVC)
32x 1080p @ 30 (HEVC)
Video Decode 500MP/sec
1x 4K @ 60 (HEVC)
2x 4K @ 30 (HEVC)
4x 1080p @ 60 (HEVC)
8x 1080p @ 30 (HEVC)		 1000MP/sec
2x 4K @ 60 (HEVC)
4x 4K @ 30 (HEVC)
7x 1080p @ 60 (HEVC)
14x 1080p @ 30 (HEVC)		 2x690MP/sec
2x 4K @ 60 (HEVC)
4x 4K @ 30 (HEVC)
12x 1080p @ 60 (HEVC)
24x 1080p @ 30 (HEVC)
16x 1080p @ 30 (H.264)		 2x1500MP/sec
2x 8K @ 30 (HEVC)
6x 4K @ 60 (HEVC)
12x 4K @ 30 (HEVC)
26x 1080p @ 60 (HEVC)
52x 1080p @ 30 (HEVC)
30x 1080p @ 30 (H.264)
Camera 12 lanes (3x4 or 4x2) MIPI CSI-2, DPHY 1.1 (1.5 Gbps) 12 lanes MIPI CSI-2, D-PHY 1.2 (30 Gbps) 16 lanes MIPI CSI-2, 8 lanes SLVS-EC
D-PHY (40 Gbps), C-PHY (64 Gbps)		 16 lanes MIPI CSI-2, 8 lanes SLVS-EC
D-PHY (40 Gbps), C-PHY (109 Gbps)
Power 5W | 10W 7.5W | 15W 10W | 20W 10W | 20W 10W | 15W | 30W
Connectivity Wi-Fi requires external chip Wi-Fi requires external chip Wi-Fi onboard Wi-Fi requires external chip Wi-Fi requires external chip
10/100/1000 BASE-T Ethernet 10/100/1000 BASE-T Ethernet 10/100/1000 RGMII
Gigabit Ethernet
Mechanical 69.6 mm x 45 mm
260-pin edge connector		 87 mm x 50 mm
400-pin connector		 100 mm x 87 mm
699-pin connector
Products
Resources
Community