New industrial board from NVIDIA
NVIDIA has released Jetson AGX Xavier Industrial Module, that adds two Cortex-R5 functional safety cores (FuSa), with 32GB ECC RAM, 64GB eMMC, and shock and vibration resistance to the original design.
Robotics and automation are increasingly used in manufacturing, agriculture, construction, energy, government, and other industries, but many companies struggle to incorporate the benefits of AI and deep learning into their most demanding applications. doing.
With the new NVIDIA Jetson AGX Xavier Industrial module, NVIDIA can deploy AI to edge devices in harsh environments where security and reliability are important priorities.
AI performance is listed at 30 TOPS. The original AGX Xavier was announced with the same rating but is now listed at 32 TOPS. The module supports the same CUDA-X accelerated computing stack, JetPack SDK, and Ubuntu-based BSP as the other Jetson modules.
Source: http://linuxgizmos.com/jetson-agx-xavier-industrial-adds-ruggedization-and-fusa-cores/
New features of AI brought to ModBerry series
In October 2020, with the release of the latest Compute Module 4 from Rasbperry Pi Foundation, TECHBASE announced an upgraded device from ModBerry 500 series, called ModBerry 500 CM4. Thanks to the high-performance PCI-Express bus introduced in Compute Module 4 and Raspberry Pi community, the device itself presents support for a wide range of new applications, such as use of Google’s Artificial Intelligence modules at ease.
Therefore, TECHBASE designed a new device, called ModBerry AI GATEWAY 9500-CM4, utilizing the vertical format of ModBerry 9500, latest Compute Module 4 and Google’s Coral TPU. Installation-ready AI GATEWAY allows direct application in industrial fields.
AI GATEWAY with Coral TPU enhancement
Neuron network capabilities enhance CM4-based devices, not only collecting and sending data, but also allows local data change predictions and allows direct management on-site. This feature gives the possibility for various applications, such as data analysing and establishing trends predictions, smart alarms and smart monitoring, local notification control, etc.
Used Edge TPU coprocessor via PCI-Express bus is capable of performing 4 trillion operations per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). Google Coral easily integrates with Raspberry Pi Compute Module in Linux and optionally in Windows with full support of TensorFlow Lite framework and AutoML Vision Edge solution.
AI GATEWAY with available expansion cards
ModBerry AI GATEWAY 9500-CM4 can be equipped with serial RS-232/485 ports, range of digital and analog I/Os, USB, HDMI and Ethernet. Interfaces can be expanded with additional I/Os and opto-isolation, relays, Ethernet, 1-Wire, CAN, M-Bus Master and Slave, accelerometer, OLED screen and many more features like TPM Security Chip, eSIM and SuperCap backup power support.
ModBerry AI GATEWAY 9500-CM4 series also offers a standard PCI module support for various wireless communication protocols, such as:
- GSM modem (4G/LTE and fast 5G modem, interchangeable with Coral TPU)
- economic NarrowBand-IoT technology
- LoRa, ZigBee, Sigfox, Wireless M-Bus
- secondary Wi-Fi/Bluetooth interface or Wi-Fi Hi-Power
- custom wireless interfaces
ModBerry AI GATEWAY 9500-CM4 availabilityFirst prototypes are being developed, since Compute Module 4 is already available for the purchase. Delivery time for various configurations of AI GATEWAY will be approximately 2 months, depending on the CM4 supply on the market and chosen expansion cards. For more information contact TECHBASE’s Sales Department via email or Live Chat here.
