{"id":50635,"date":"2025-03-20T15:43:08","date_gmt":"2025-03-20T13:43:08","guid":{"rendered":"https:\/\/www.cqdx.ru\/ham\/?p=50635"},"modified":"2025-03-20T16:18:19","modified_gmt":"2025-03-20T14:18:19","slug":"first-artificial-intelligence-radio-transceiver-air-t","status":"publish","type":"post","link":"https:\/\/www.cqdx.ru\/ham\/new-equipment\/first-artificial-intelligence-radio-transceiver-air-t\/","title":{"rendered":"First Artificial Intelligence Radio Transceiver (AIR-T)"},"content":{"rendered":"

 <\/p>\n

\"\"The Artificial Intelligence Radio Transceiver (AIR-T) is a high-performance software-defined radio (SDR) seamlessly integrated with state-of-the-art processing and deep learning inference hardware. The incorporation of an embedded graphics processing unit (GPU) enables real-time wide-band digital signal processing (DSP) algorithms to be executed in software, without requiring specialized field programmable gate array (FPGA) firmware development. The GPU is the most utilized processor for machine learning, therefore the AIR-T significantly reduces the barrier for engineers to create autonomous signal identification, interference mitigation, and many other machine learning applications. By granting the deep learning algorithm full control over the transceiver system, the AIR-T allows for fully autonomous software defined and cognitive radio.<\/p>\n

 <\/p>\n

\n
\u201cThe AIR-T board allows researchers and developers to experiment and build artificial intelligence and high performance compute solutions at the RF edge.\u201d<\/em><\/div>\n
-Arjun Dutt, Director of the Inception program at NVIDIA<\/em><\/div>\n<\/blockquote>\n

\"\"<\/p>\n

Three Integrated Processors<\/strong><\/span>
\nDeepwave s AIR-T is the first software-defined radio (SDR) with embedded high-performance computing. The AIR-T lowers the price and performance barriers to autonomous signal identification, interference mitigation, and much more. The AIR-T allows for a fully autonomous SDR by giving the AI engine complete control over the hardware. Whether your background is in electrical engineering, applied physics, or a related field, AIR-T will open up new possibilities for your work. It does this by uniquely integrating three digital processors that provide the functionality needed for any signal processing application:<\/p>\n

FPGA for strict real-time operations<\/span><\/p>\n

GPU for highly parallel processing<\/span><\/p>\n

CPU for control, I\/O, DSP, and software applications<\/span><\/p>\n

This unique combination brings you the worlds of high-performance computing (HPC), artificial intelligence, deep learning, and advanced graphics and rendering on one embedded platform. The system has the versatility to function as a highly parallel SDR, data recorder, or inference engine for deep learning algorithms. The embedded GPU allows your SDR applications to process bandwidths greater than 200 MHz in real-time.<\/p>\n

\"\"<\/p>\n

 <\/p>\n

\"\"<\/p>\n

 <\/p>\n

\"\"Features & Specifications<\/h2>\n

For a complete list of features, see the\u00a0AIR-T Product Guide here<\/a><\/p>\n

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
RF Transceiver<\/td>\n<\/td>\n<\/td>\n<\/tr>\n<\/tbody>\n
<\/td>\nManufacturer<\/td>\nAnalog Devices 9371<\/a><\/td>\n<\/tr>\n
<\/td>\nNumber of Receive Channels<\/td>\n2<\/td>\n<\/tr>\n
<\/td>\nNumber of Transmit Channels<\/td>\n2<\/td>\n<\/tr>\n
<\/td>\nMaximum Bandwidth<\/td>\n100 MHz<\/td>\n<\/tr>\n
<\/td>\nMaximum Sample Rate<\/td>\n125 MSPS<\/td>\n<\/tr>\n
<\/td>\nFrequency Tuning Range<\/td>\n300 MHz – 6 GHz<\/td>\n<\/tr>\n
<\/td>\nReceiver Power Level Control<\/td>\nAGC or manual gain control<\/td>\n<\/tr>\n
<\/td>\nTransmitter Power Level Control<\/td>\nTPC or manual gain control<\/td>\n<\/tr>\n
<\/td>\nExternal Reference Input<\/td>\nYes<\/td>\n<\/tr>\n
<\/td>\nBuilt in Calibrations<\/td>\nQuadrature error correction<\/td>\n<\/tr>\n
<\/td>\n<\/td>\nLO suppression<\/td>\n<\/tr>\n
<\/td>\n<\/td>\nLO leakage correction<\/td>\n<\/tr>\n
Processors<\/strong><\/td>\n<\/td>\n<\/td>\n<\/tr>\n
<\/td>\nManufacturer<\/td>\nNVIDIA Jetson TX2<\/a><\/td>\n<\/tr>\n
<\/td>\nCPU 1<\/td>\nARM A-57 (4-core)<\/td>\n<\/tr>\n
<\/td>\nCPU 2<\/td>\nARM Denver2 (2-core)<\/td>\n<\/tr>\n
<\/td>\nGPU<\/td>\nPascal (256-core)<\/td>\n<\/tr>\n
<\/td>\nMemory<\/td>\n8 GBytes shared memory<\/td>\n<\/tr>\n
<\/td>\nStorage<\/td>\n32 GBytes flash<\/td>\n<\/tr>\n
FPGA<\/strong><\/td>\n<\/td>\n<\/td>\n<\/tr>\n
<\/td>\nManufacturer<\/td>\nXilinx Artix-7 FPGA<\/a><\/td>\n<\/tr>\n
<\/td>\nLUTs<\/td>\n47.2k<\/td>\n<\/tr>\n
<\/td>\nDSP Slices<\/td>\n180<\/td>\n<\/tr>\n
<\/td>\nRAM<\/td>\n3.75 kbits<\/td>\n<\/tr>\n
Networking<\/strong><\/td>\n<\/td>\n<\/td>\n<\/tr>\n
<\/td>\nEthernet<\/td>\n10\/100\/1000 BASE-T<\/td>\n<\/tr>\n
<\/td>\nWLAN<\/td>\n802.11a\/b\/g\/n\/ac dual-band 2×2 MIMO<\/td>\n<\/tr>\n
<\/td>\nBluetooth<\/td>\nVersion 4.1<\/td>\n<\/tr>\n
Display<\/strong><\/td>\n<\/td>\n<\/td>\n<\/tr>\n
<\/td>\nHDMI<\/td>\n3840 x 2160 (4k)<\/td>\n<\/tr>\n
Peripheral Interfaces<\/strong><\/td>\n<\/td>\n<\/td>\n<\/tr>\n
<\/td>\nSATA<\/td>\nVersion 3.1<\/td>\n<\/tr>\n
<\/td>\nSD Card<\/td>\nSD 3.0 or SD-XC cards up to 2 TB<\/td>\n<\/tr>\n
<\/td>\nUSB<\/td>\nUSB 3.0 Super Speed mode (up to 5Gb\/s)<\/td>\n<\/tr>\n
<\/td>\n<\/td>\nUSB 2.0 High Speed mode (up to 480Mb\/s)<\/td>\n<\/tr>\n
<\/td>\n<\/td>\nUSB On-The-Go<\/td>\n<\/tr>\n
<\/td>\nUART<\/td>\nSee\u00a0NVIDIA Jetson TX2 datasheet<\/a>\u00a0for information<\/td>\n<\/tr>\n
<\/td>\nGPIO<\/td>\nSee\u00a0NVIDIA Jetson TX2 datasheet<\/a>\u00a0for information<\/td>\n<\/tr>\n
<\/td>\nSPI<\/td>\nSee\u00a0NVIDIA Jetson TX2 datasheet<\/a>\u00a0for information<\/td>\n<\/tr>\n
<\/td>\nI2C<\/td>\nSee\u00a0NVIDIA Jetson TX2 datasheet<\/a>\u00a0for information<\/td>\n<\/tr>\n
<\/td>\nAudio<\/td>\nSee\u00a0NVIDIA Jetson TX2 datasheet<\/a>\u00a0for information<\/td>\n<\/tr>\n
Power<\/strong><\/td>\n<\/td>\n<\/td>\n<\/tr>\n
<\/td>\nInput<\/td>\n8-15 VDC<\/td>\n<\/tr>\n
Mechanical<\/strong><\/td>\n<\/td>\n<\/td>\n<\/tr>\n
<\/td>\nBoard Form Factor<\/td>\nMini-ITX<\/td>\n<\/tr>\n
<\/td>\nDimensions<\/td>\n170 \u00d7 170 x 35 mm (6.7″ \u00d7 6.7″ x 1.4″)<\/td>\n<\/tr>\n
<\/td>\nWeight<\/td>\n285 grams (0.63 pounds)<\/td>\n<\/tr>\n
Software<\/strong><\/td>\n<\/td>\n<\/td>\n<\/tr>\n
<\/td>\nOperating System<\/td>\nUbuntu (Linux)<\/td>\n<\/tr>\n
<\/td>\nDrivers<\/td>\nAirStack<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

 <\/p>\n

Price: \u20ac 6 470,17<\/p>\n

To buy here<\/a><\/strong><\/p>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

  The Artificial Intelligence Radio Transceiver (AIR-T) is a high-performance software-defined radio (SDR) seamlessly integrated with state-of-the-art processing and deep learning inference hardware. The incorporation of an embedded graphics processing unit (GPU) enables real-time wide-band digital signal processing (DSP) algorithms to be executed in software, without requiring specialized field programmable gate array (FPGA) firmware development.…<\/p>\n","protected":false},"author":1,"featured_media":50636,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[8],"tags":[421],"class_list":["post-50635","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-new-equipment","tag-sdr","category-8","description-off"],"_links":{"self":[{"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/posts\/50635","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/comments?post=50635"}],"version-history":[{"count":0,"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/posts\/50635\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/media\/50636"}],"wp:attachment":[{"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/media?parent=50635"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/categories?post=50635"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.cqdx.ru\/ham\/wp-json\/wp\/v2\/tags?post=50635"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}