ThinkRobotics Edge AI Device with NVIDIA Jetson Orin™ NX 8GB / 16GB module
ThinkRobotics Edge AI Device is built with Jetson Orin NX 8GB or 16GB - a powerful and compact intelligent edge box to bring up to 100 TOPS modern AI performance to the edge, which offers up to 5X the performance of Jetson Xavier NX and up to 3X the performance of Jetson AGX Xavier. Combining the NVIDIA Ampere™ GPU architecture with 64-bit operating capability, Orin NX integrates advanced multi-function video and image processing, and NVIDIA Deep Learning Accelerators.
The full system includes one NVIDIA Jetson Orin™ NX 8GB or 16GB production module, Waveshare Jetson Orin Nano/NX Development Board carrier board, a heatsink, AW-CB375NF Dual-Band Wireless NIC WiFi5 module, a power adapter installed in a 3D printed carbon fiber case or a metal case. The device is preinstalled with JetPack 6.2 on the included 240GB NVMe SSD, simplifies development, and fits for deployment for edge AI solution providers working in video analytics, object detection, natural language processing, medical imaging, and robotics across industries of smart cities, security, industrial automation, smart factories.
Features
| AI Performance | Brilliant AI performance for production with on-device processing delivering up to 100 TOPS AI performance with low power consumption and low latency. |
| Compact Edge AI Device | Hand-size edge AI device with compact dimensions of 130mm × 120mm × 58.5mm. Includes NVIDIA Jetson Orin™ NX 16GB production module, cooling fan with heatsink, enclosure, and power adapter. Supports desktop and wall mounting for flexible deployment. |
| Expandable I/O | Expandable with rich I/Os (Waveshare SBC2152): 4 × USB 3.2 Type-A, 1 × USB Type-C (system burning), DisplayPort for 4K output, RJ45 Gigabit Ethernet, 2 × 4-Lane CSI, M.2 Key E, 2 × M.2 Key M (for NVMe SSDs), and 40-Pin GPIO. |
| Software & Development | Accelerate solution deployment with pre-installed JetPack including NVIDIA JetPack™ 5.1 on the bundled 240GB NVMe SSD. Includes Linux OS BSP and supports Jetson software, leading AI frameworks, and development platforms. |
| Certifications | Comprehensive certifications including FCC, CE, and RoHS compliance. |
Description
With rich extension modules, industrial peripherals, and thermal management, the Edge AI Device with the Waveshare SBC2152 carrier board is ready to help you accelerate and scale the next-gen AI product by deploying popular DNN models and ML frameworks to the edge and inferencing with high performance, for tasks like real-time classification and object detection, pose estimation, semantic segmentation, and natural language processing (NLP).
The Waveshare Jetson Orin Nano/NX Development Board provides almost the same peripheral interfaces, size and thickness as the official Jetson Orin Nano Developer Kit, making it ideal for users to develop and deploy their AI applications.
Guides and resources are available to get started with NVIDIA Jetson using leading AI frameworks and software. For example, with Deepstream and TensorRT, developers can deploy custom YOLOv5 models on Jetson Orin at over 100FPS
Developers Tools
Pre-installed Jetpack for fast development and edge AI integration
Jetson software stack begins with NVIDIA JetPack™ SDK which provides a full development environment and includes CUDA-X accelerated libraries and other NVIDIA technologies to kickstart your development. JetPack includes the Jetson Linux Driver package which provides the Linux kernel, bootloader, NVIDIA drivers, flashing utilities, sample filesystem, and toolchains for the Jetson platform. It also includes security features, over-the-air update capabilities, and much more.
Computer Vision and embedded machine learning
| Platform / Toolkit | Description |
| NVIDIA DeepStream SDK | NVIDIA DeepStream SDK provides a complete streaming analytics toolkit for AI-based multi-sensor processing, enabling video and image understanding on NVIDIA Jetson platforms. |
| NVIDIA TAO Toolkit | NVIDIA TAO Toolkit, built on TensorFlow and PyTorch, offers a low-code framework that accelerates AI model training and optimization for deployment on edge devices. |
| alwaysAI | alwaysAI enables developers to build, train, and deploy computer vision applications directly at the edge of reComputer devices. It provides access to 100+ pre-trained computer vision models and supports cloud-based training of custom AI models through enterprise subscription. |
| Edge Impulse | Edge Impulse provides an embedded machine learning pipeline for deploying audio processing, classification, and object detection applications at the edge with zero dependency on the cloud. |
| Roboflow | Roboflow offers tools to convert raw images into custom-trained computer vision models for object detection and classification, and deploy them for use in applications on NVIDIA Jetson devices. |
| YOLOv5 (Ultralytics) | YOLOv5 by Ultralytics supports transfer learning for few-shot object detection, allowing models to be trained using a small number of samples for rapid deployment. |
| Deci | Deci provides tools to benchmark and optimize AI model runtime performance on NVIDIA Jetson platforms such as Jetson Nano and Xavier NX. |
Speech AI
NVIDIA® Riva is a GPU-accelerated SDK for building Speech AI applications that are customized for your use case and deliver real-time performance.
Remote Fleet Management
Enable secure OTA and remote device management with Allxon. Unlock 90 days free trial with code H4U-NMW-CPK.
Robot and ROS Development
| Platform / Toolkit | Description |
| NVIDIA Isaac ROS GEMs | NVIDIA Isaac ROS GEMs are hardware-accelerated packages designed to help ROS developers build high-performance robotic solutions on NVIDIA hardware. These packages provide optimized algorithms and tools to accelerate perception, navigation, and robotics workflows on NVIDIA Jetson platforms. |
| Cogniteam Nimbus | Cogniteam Nimbus is a cloud-based platform that enables developers to manage and deploy autonomous robots efficiently. The Nimbus platform supports NVIDIA® Jetson™ devices and NVIDIA ISAAC SDK and GEMs out-of-the-box, allowing seamless integration between robotics applications and cloud infrastructure. |
Hardware Overview
Waveshare Jetson Orin Nano/NX Development Board
The Waveshare carrier board for Jetson Orin Nano/NX provides a comprehensive set of interfaces, offering a robust platform for edge AI development. It is compatible with both the Jetson Orin Nano and Jetson Orin NX modules. Key features include:
|
1. 260PIN DO-DIMM socket For connecting Jetson Orin Nano/NX module |
9. USB Type-C port For system burning and data communication |
|
2. 12PIN header Adapting pins for power supply, reset button, force recovery setting, serial port debug, auto power-up enable, and power indicator functions |
10. 40PIN header |
| 3. Power button | 11. 4PIN PWM fan header |
|
4. 2 × 22PIN CSI camera interfaces 2 × MIPI CSI 4-lane camera interfaces |
12. M.2 Key E For connecting wireless NIC |
|
5. DC Power jack Supports wide range 9V–19V power supply, compatible with 5.5 × 2.5 mm male plug |
13. 2 × M.2 Key M For connecting NVMe solid state drives |
|
6. HDMI display interface HDMI output |
14. RTC backup battery header PH1.25 2PIN |
|
7. 4 × USB 3.2 Gen2 Type-A ports Supports up to 10 Gbps data transmission |
|
| 8. RJ45 Gigabit Ethernet port |
Take advantage of the small form factor, sensor-rich interfaces, and big performance to bring new capabilities to all your embedded AI and edge systems.
Part List
| NVIDIA Jetson Orin™ NX 16GB / 8GB | x1 |
| Waveshare Carrier Board | x1 |
| 240GB NVMe SSD | x1 |
| Aluminum Heatsinks with Fan | x1 |
| 3D Printed Case / Aluminium Case | x1 |
| Wi-Fi Module with Antenna | x1 |
| 12V / 5A Power Adapter | x1 |
FAQ
What type of RTC is recommended for RTC socket?
The Waveshare SBC2152 provides an RTC backup battery header. CR1220 and ML1220 batteries are typically compatible for RTC backup.
Documentations
Want to buy in bulk?
Custom Requirements?
Discussion Forum
Feel free to ask questions, share tips or report issues.
