tensorflow

Posted on by Debashis Das - No Comments on Waveshare ESP32 robotic arm kit with 5+1 DoF supports ROS2, LeRobot, and Jetson Orin NX integration

Waveshare ESP32 robotic arm kit with 5+1 DoF supports ROS2, LeRobot, and Jetson Orin NX integration

RoArm M3 Pro and RoArm M3 S High Torque Serial Bus Servo Robotic Arm Kit

Waveshare has recently released the RoArm-M3-Pro and RoArm-M3-S, a 5+1 DOF high-torque ESP32 robotic arm kit. The main difference between the two is that the RoArm-M3-Pro features all-metal ST3235 bus servos for durability and longevity, on the other hand, the RoArm-M3-S uses standard servo motors which are less durable for long-term use. These robotic arms feature a lightweight structure, a 360° omnidirectional base, and five flexible joints, which together create a 1m workspace with a 200 grams @ 0.5m payload. A 2-DOF wrist joint enables multi-dimensional clamping and precise force control. It integrates an ESP32 MCU, supporting multiple wireless control modes via a web app, it also supports inverse kinematics for accurate positioning, curve velocity control for smooth motion, and adaptive force control. The design is open source and with ROS2 compatibility, it allows secondary development via JSON commands and ESP-NOW for multi-device communication. Compatible with the LeRobot AI framework, […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 14 Comments on Orange Pi AIPro (8T) SBC features a 8 TOPS Huawei Ascend AI SoC, runs Ubuntu or openEuler

Orange Pi AIPro (8T) SBC features a 8 TOPS Huawei Ascend AI SoC, runs Ubuntu or openEuler

Orange Pi AIPro (8T)

Orange Pi AIPro (8T) is a new single board computer for AI applications that features an unnamed Huawei Ascend AI quad-core 64-bit processor delivering up to 8 TOPS (INT8) of AI inference performance, although there’s also a 20 TOPS (INT8) variant of the SoC. The SBC comes with up to 16GB LPDDR4X and a 32MB SPI flash but also supports other storage options such as a microSD card, an eMMC flash module, and/or an M.2 NVMe or SATA SSD. The board also features two HDMI 2.0 ports, one MIPI DSI connector, a 3.5mm audio jack, two MIPI CSI camera interfaces, Gigabit Ethernet and WiFi 5 connectivity, a few USB ports, and a 40-pin GPIO header for expansion. Orange Pi AIPro specifications: SoC – Huawei Ascend quad-core 64-bit processor delivering up to 8 TOPS (INT8) AI performance and equipped with an unnamed 3D GPU; Likely Ascend 310B with Arm Cortex-A76 equivalent […]

Posted on by Debashis Das - 1 Comment on Seeed Studio introduces ESP32-C3-based Modbus Vision RS485 and SenseCAP A1102 LoRaWAN outdoor Edge AI cameras

Seeed Studio introduces ESP32-C3-based Modbus Vision RS485 and SenseCAP A1102 LoRaWAN outdoor Edge AI cameras

Seeed Studio's Modbus Vision RS485 and SenseCAP A1102 outdoor Edge AI cameras

Seeed Studio has recently released the Modbus Vision RS485 and SenseCAP A1102 (LoRaWAN) outdoor Edge AI cameras based on ESP32-C3 SoC through the XIAO-ESP32C3 module for WiFi and the Himax WiseEye2 processor for vision AI. Both are IP66-rated AI vision cameras designed for home and industrial applications. The RS485 camera is designed for industrial systems and features a Modbus interface, making it suitable for factory automation and smart buildings. The SenseCAP A1102 uses LoRaWAN for long-range, low-power monitoring in remote locations. Both offer advanced AI for tasks like object detection and facial recognition. Besides its built-in RS485 interface, the Modbus Vision RS485 also supports LoRaWAN and 4G LTE connectivity via external Data Transfer Units (DTUs). With over 300 pre-trained AI models, the camera can do object detection and classification tasks making it suitable for industrial automation, smart agriculture, environmental monitoring, and other AI-driven applications requiring high performance. The SenseCAP A1102 […]

Posted on by Debashis Das - No Comments on Firefly’s CSB1-N10 series AI cluster servers can deliver up to 1000 TOPS of AI power with Rockchip or NVIDIA Jetson Modules

Firefly’s CSB1-N10 series AI cluster servers can deliver up to 1000 TOPS of AI power with Rockchip or NVIDIA Jetson Modules

CSB1 N10 series AI cluster servers

Firefly has recently introduced the CSB1-N10 series AI cluster servers designed for applications such as natural language processing, robotics, and image generation. These 1U rack-mounted servers are ideal for data centers, private servers, and edge deployments. The servers have multiple computing nodes, featuring either energy-efficient processors (Rockchip RK3588, RK3576, or SOPHON BM1688) or high-performance NVIDIA Jetson modules (Orin Nano, Orin NX). With 60 to 1000 TOPS AI power, the CSB1-N10 servers can handle the demands of large AI models, including language models like Gemma-2B and Llama3, as well as visual models like EfficientVIT and Stable Diffusion. CSB1-N10 series specifications All CSB1-N10 AI servers have the same interfaces, and the only differences are the CPU, memory, storage, multimedia, AI capabilities, and related software support. So it’s likely Firefly has made Rockchip system-on-modules compatible with NVIDIA Jetson SO-DIMM form factor, and indeed we previously noted that Firefly designed Core-1688JD4, Core-3576JD4, or Core-3588JD4 […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 3 Comments on Getting Started with Raspberry Pi AI HAT+ (26 TOPS) and Raspberry Pi AI camera

Getting Started with Raspberry Pi AI HAT+ (26 TOPS) and Raspberry Pi AI camera

Raspberry Pi AI HAT+ and AI camera review

Raspberry Pi recently launched several AI products including the Raspberry Pi AI HAT+ for the Pi 5 with 13 TOPS or 26 TOPS of performance and the less powerful Raspberry Pi AI camera suitable for all Raspberry Pi SBC with a MIPI CSI connector. The company sent me samples of the AI HAT+ (26 TOPS) and the AI camera for review, as well as other accessories such as the Raspberry Pi Touch Display 2 and Raspberry Pi Bumper, so I’ll report my experience getting started mostly following the documentation for the AI HAT+ and AI camera. Hardware used for testing In this tutorial/review, I’ll use a Raspberry Pi 5 with the AI HAT+ and a Raspberry Pi Camera Module 3, while I’ll connect the AI camera to a Raspberry Pi 4. I also plan to use one of the boards with the new Touch Display 2. Let’s go through a […]

Posted on by Kumpee Teeravech - 5 Comments on BeagleY-AI SBC review with Debian 12, TensorFlow Lite, other AI demos

BeagleY-AI SBC review with Debian 12, TensorFlow Lite, other AI demos

BeagleY-AI review

Today I’ll be reviewing the BeagleY-AI open-source single-board computer (SBC) developed by BeagleBoard.org for artificial intelligence applications. It is powered by a Texas Instruments AM67A quad-core Cortex-A53 processor running at 1.4 GHz along with an ARM Cortex-R5F processor running at 800 MHz for handling general tasks and low-latency I/O operations. The SoC is also equipped with two C7x DSP units and a Matrix Multiply Accelerator (MMA) to enhance AI performance and accelerate deep learning tasks. Each C7x DSP delivers 2 TOPS, offering a total of up to 4 TOPS. Additionally, it includes an Imagination BXS-4-64 graphics accelerator that provides 50 GFlops of performance for multimedia tasks such as video encoding and decoding. For more information, refer to our previous article on CNX Software or visit the manufacturer’s website. BeagleY-AI unboxing The BeagleY-AI board was shipped from India in a glossy-coated, printed corrugated cardboard box. Inside, the board is protected by […]

Posted on by Debashis Das - 2 Comments on Firefly introduces Rockchip RK3576 SoM and All-in-One carrier board compatible with NVIDIA Jetson Orin Nano and Orin NX modules

Firefly introduces Rockchip RK3576 SoM and All-in-One carrier board compatible with NVIDIA Jetson Orin Nano and Orin NX modules

AIO 3576JD4 Mainboard or devboard

Firefly has released a Rockchip RK3576 SoM and development board called the Core-3576JD4 Core Board with a SO-DIMM edge connector and the AIO-3576JD4 carrier board respectively. The core board or the SoM is built around an octa-core 64-bit processor with a Mali G52 MC3 GPU and a 6 TOPS NPU, so it can handle demanding AI tasks while maintaining low power consumption. The AIO-3576JD4 is a full-fledged carrier board with a wide range of on-board interfaces, like dual Gigabit Ethernet ports, MIPI-CSI, HDMI 2.1, USB 3.0, USB 2.0, USB Type-C, a Phoenix connector for serial, dual-row pin headers (SPI, I2C, Line in, and Line out), an M.2 socket for 5G, a mini PCIe for 4G LTE, an M.2 socket for WiFi 6/BT 5.2, and a third M.2 socket for SATA/PCIe NVMe SSD expansion. RK3576 AI SoM and dev board specification Core-3576JD4 specifications SoC – Rockchip RK3576 CPU – Octa-core  CPU […]

Posted on by Debashis Das - No Comments on NXP i.MX RT700 dual-core Cortex-M33 AI Crossover MCU includes eIQ Neutron NPU and DSPs

NXP i.MX RT700 dual-core Cortex-M33 AI Crossover MCU includes eIQ Neutron NPU and DSPs

NXP i.MX RT700 AI crossover MCU block diagram

NXP has recently announced the release of  NXP i.MX RT700 RT700 AI crossover MCU following the NXP i.MX RT600 series release in 2018 and the i.MX RT500 series introduction in 2021. The new i.MX RT700 Crossover MCU features two Cortex-M33 cores, a main core clocked at 325 MHz with a Tensilica HiFi 4 DSP and a secondary 250 MHz core with a low-power Tensilica HiFi 1 DSP for always-on sensing tasks. Additionally, it integrates a powerful eIQ Neutron NPU with an upgraded 7.5 MB of SRAM and a 2D GPU with a JPEG/PNG decoder. These features make this device suitable for applications including AR glasses, hearables, smartwatches, wristbands, and more. NXP i.MX RT700 specifications: Compute subsystems Main Compute Subsystem Cortex-M33 @ up to 325 MHz with Arm TrustZone, built-in Memory Protection Unit (MPU), a floating-point unit (FPU),  a HiFi 4 DSP and supported by NVIC for interrupt handling and SWD […]

EmbeddedTS embedded systems design