Generative AI on NVIDIA Jetson Orin, Jetpack 6 SDK to support multiple OSes

Jetson Orin Generative AI

NVIDIA has had several announcements at ROSCon 2023 related to robotics & embedded with highlights including generative AI on the NVIDIA Jetson Orin module and the Jetpack 6 SDK will be released next month (November 2023) with supports for Ubuntu as usual, but also other operating systems and platforms such as Debian, Yocto, Wind River, Redhawk RTOS, and Balena. Generative AI on NVIDIA Jetson Orin There’s been a lot of hype in the last year about generative AI thanks to services such as ChatGPT, Google Bard, or Microsoft Bing Chat. But those rely on closed-source software that runs on powerful servers in the cloud. As we noted in our article about the “AI in a box” offline LLM solution there are some open-source projects such as Whisper speech-to-text model and Llama2 language models that could be run on embedded hardware at the edge, but as noted by some readers platforms […]

Bluetooth NLC (Networked Lighting Control) fully standardizes Bluetooth light bulbs

Bluetooth NLC

Bluetooth NLC (Networked Lighting Control) is a full-stack standard for wireless lighting control from the Bluetooth SIG that will enable multi-vendor interoperability, improve ease of deployment, and offer greater scalability. Bluetooth light bulbs have been around for many years, at first using Bluetooth LE (Radio Layer) and then adding Bluetooth Mesh (Network Layer) to the mix, but there were always some proprietary bits to the software stack, and Bluetooth NLC removes all those with a complete standard for lighting control that further adds Device Profiles specific to his use case. Bluetooth NLC still relies on Bluetooth Low Energy and Bluetooth Mesh, but adds the following NLC Device Profiles at the Device Layer defining the requirements for a range of devices/features: Ambient Light Sensor Basic Lightness Controller Basic Scene Selector Dimming Control Energy Monitor Occupancy Sensor You’ll find the specifications for each profile on the Bluetooth website. While the announcement was […]

Cadence Neo NPU IP scales from 8 GOPS to 80 TOPS

Cadence Neo NPU

Cadence Neo NPU (Neural Processing Unit) IP delivers 8 GOPS to 80 TOPS in single core configuration and can be scaled to multicore configuration for hundreds of TOPS. The company says the Neo NPUs deliver high AI performance and energy efficiency for optimal PPA (Power, Performance, Area) and cost points for next-generation AI SoCs for intelligent sensors, IoT, audio/vision, hearables/wearables, mobile vision/voice AI, AR/VR and ADAS. Some highlights of the new Neo NPU IP include: Scalability – Single-core solution is scalable from 8 GOPS to 80 TOPS, with further extension to hundreds of TOPS with multicore Supports 256 to 32K MACs per cycle to allow SoC architects to meet power, performance, and area (PPA) tradeoffs Works with DSPs, general-purpose microcontrollers, and application processors Support for Int4, Int8, Int16, and FP16 data types for CNN, RNN and transformer-based networks. Up to 20x higher performance than the first-generation Cadence AI IP, with […]

LuckFox Pico Rockchip RV1103 Cortex-A7/RISC-V camera board comes with an optional Ethernet port

LuckFox Pico Plus Camera Board

LuckFox Pico is a small Linux camera board based on the Rockchip RV1103 Cortex-A7 and RISC-V AI camera SoC and offered with an Ethernet port in a longer version of the PCB called LuckFox Pico Plus. Both models come with 64MB RAM (apparently embedded in RV1103), a microSD card slot for storage, a MIPI CSI camera connector, a USB Type-C port for power, and a few through holes for expansion through GPIO, I2C, UART, and so on. LuckFox Pico and Pico Plus specifications: SoC – Rockchip RV1103 with Arm Cortex-A7 processor @ 1.2GHz, RISC-V core, 64MB DDR2, 0.8 TOPS NPU, 4M @ 30 fps USP Storage MicroSD card slot LuckFox Plus only – 1Gbit (128MB) SPI flash (W25N01GV) Camera – 2-lane MIPI CSI connector Networking (LuckFox Pico Plus only) – 10/100M Ethernet RJ45 port USB – USB 2.0 Host/Device Type-C port Expansion – 2x 20-pin headers with up to 24x […]

Firefly AIO-1684XQ motherboard features BM1684X AI SoC with up to 32 TOPS for video analytics, computer vision

Firefly AIO-1684XQ motherboard

Firefly AIO-1684XQ is a motherboard based on SOPHGO SOPHON BM1684X octa-core Cortex-A53 AI SoC delivering up to 32TOPS for AI inference, and designed for computer vision applications and video analytics. The headless machine vision board is equipped with 16GB RAM, 64GB eMMC flash, and 128MB SPI flash, and comes with a SATA 3.0 port, dual Gigabit Ethernet, optional 4G LTE or 5G modules, four USB 3.0 ports, and a terminal block with two RS485 interface, two relay outputs, and a few GPIOs. Firefly AIO-1684XQ specifications: SoC – SOPHGO SOPHON BM1684X CPU – Octa-core Arm Cortex-A53 processor @ up to 2.3 GHz TPU – Up to 32TOPS (INT8), 16 TFLOPS (FP16/BF16), 2 TFLOPS (FP32) VPU Up to 32-channel H.265/H.264 1080p25 video decoding Up to 32-channel 1080p25 HD video processing (decoding + AI analysis) Up to 12-channel H.265/H.264 1080p25fps video encoding System Memory – 16GB LPDDR4x Storage 64GB eMMC flash 128MB SPI […]

e-con systems See3CAM_24CUG USB 3.1 global shutter camera review

See3CAM_24CUG USB 3.1 camera review

e-con Systems See3CAM_24CUG a full HD color global shutter USB 3.1 Gen 1 camera based on an Onsemi AR0234CS CMOS image sensor capable of capturing moving scenes at up to 120 fps. This global shutter camera is especially useful for robotics and other applications that may require a high frame rate such as Automatic Number Plate Recognition (ANPR), Autonomous Mobile Robots (AMR), gesture recognition, drones, barcode scanners, factory automation, conveyor monitoring cameras, and traffic monitoring systems. e-con Systems sent a See3CAM_24CUG USB global shutter camera sample to CNX Software for review. I’ll go through an unboxing before testing in Ubuntu with both an AMD Ryzen 7 2700U laptop and a Raspberry Pi 4 single board computer. It happens to be based on the same sensor as the e-CAM20_CURB camera for Raspberry Pi 4 that we reviewed last year. See3CAM_24CUG specifications ON Semiconductor AR0234CS CMOS sensor with 1/2.6″ optical form-factor Global […]

WeAct launches $6 ESP32-C6 development board, ESP-IDF 5.1 framework released

WeAct ESP32-C6 development board

As expected, Espressif has just released the ESP-IDF 5.1 framework with ESP32-C6 and ESP32-H2 support, so more ESP32-C6 boards should become available, and after Olimex ESP32-C6-EVB launched earlier this week, we’ve noticed WeAct had introduced a low-cost ESP32-C6 development board that sells for just $6.43 plus shipping a few weeks ago. WeAct ESP32-C6 board The WeAct board offers 2.4 GHz WiFi 6, Bluetooth LE 5.0., and Zigbee/Thread connectivity through the ESP32-C6-WROOM-1 module, two USB-C ports, two 16-pin headers for GPIOs, and if it looks familiar, it’s because it closely follows the design of the official ESP32-C6-DevKitC-1 development kit, albeit with some small modifications. WeAct ESP32-C6 board specifications: Wireless module  – ESP32-C6-WROOM-1 with ESP32-C6 single-core 32-bit RISC-V clocked up to 160 MHz, with 320KB ROM, 512KB SRAM, low-power RISC-V core @ up to 20 MHz Wireless – 2.4 GHz WiFi 6, Bluetooth 5.0 LE, 802.15.4 radio for Zigbee 3.0 and Thread. […]

Firefly’s Rockchip RK3588 SBCs are now available with 32GB RAM

ROC-RK3588-PC 32GB RAM

The Rockchip RK3588 datasheet clearly states the processor supports up to 32 GB RAM, and many vendors claimed their board supports up to 32GB RAM at launch, but none were to be found once you accessed a shop, and the maximum was 16GB RAM so far, likely due to availability and the high price of of the two 16GB RAM chips needed to get 32GB of RAM. But Firefly has now discreetly started to sell boards with 32GB RAM including the ROC-RK3588-PC, ROC-RK3588S-PC, and ITX-3358J mini-ITX motherboard. I’ve just noticed I never covered the former, so I’ll have a closer look at it today. Firefly ROC-RK3588S-PC specifications: SoM – Core-3588J system-on-module SoC – Rockchip RK3588 octa-core processor with 4x Cortex-A76 cores @ up to 2.4 GHz, four Cortex-A55 cores, Arm Mali-G610 MP4 quad-core GPU with OpenGL ES3.2 / OpenCL 2.2 / Vulkan 1.1 support, 6 TOPS NPU, and an 8Kp60 […]

EDATEC Raspberry Pi 5 fanless case