#rk3588 System on Module

[forlinx]

Forlinx FET3588-C SoM Facilitating the Intelligent Development of Infrared Thermal Imaging

According to Maxtech International data, the global civil infrared market size will exceed 7.6 billion US dollars in 2023, and in the past four years, the infrared industry has maintained a growth rate of over 11%. Moreover, according to data from Huajing Industrial Research Institute, the market size of China's infrared thermal imaging industry reached 65.534 billion yuan in 2021.

With the development of non-cooled infrared thermal imaging technology, infrared thermal imagers have been widely used in civil applications. This statement is attributed to Huajing Industrial Research Institute.

Against this backdrop, manufacturers and institutions that specialize in the research and production of infrared thermal imaging products have begun to lay out strategies for the civilian infrared thermal imaging market, which is a blue ocean market. The breast surgery research team from Peking Union Medical College Hospital in Beijing has applied their independently developed artificial intelligence-based infrared thermal imaging system (AI-IRT) to pre-screening for breast cancer.

The team has also developed a portable AI-IRT system, which includes an infrared miniature camera connected to a smartphone, AI software, and a real-time updated infrared thermal imaging database.

When using this system for pre-screening of breast cancer, the real-time captured infrared thermal images of the breasts are uploaded to the artificial intelligence software, which then provides a risk assessment rating. The system is non-invasive, radiation-free and easy to use, and can be used in families and community health service centers for screening.

Infrared thermal imaging can be used as an electrical equipment monitoring system, which is installed around the transformer, etc. Through optical fiber transmission, the monitoring of equipment can be completed in the monitoring room. 24 hours, all-weather, full coverage of all substation power equipment for real-time monitoring of thermal distribution field, real-time grasp of equipment operation status, found abnormal temperature rise immediately alarm.

In addition to equipment monitoring, it is also widely used in substation inspection, distribution inspection, transmission and distribution cable inspection industry, so that inspectors can grasp the temperature while helping the power industry inspection work become more efficient and easier.

In order to adapt to the development of infrared thermal imaging industry, Forlinx Embedded recommends FET3588-C System on Module(SoM) as the main control of highly integrated infrared thermal imager.

FET3588-C has 8K video codec + 8K display supporting 8K @ 60fps H.265 and VP9 decoders, 8K @ 30fps H.264 decoders and 4K @ 60fps AV1 decoders, supporting 8K @ 30fps H.264 and H.265 encoders. High quality JPEG encoder/decoder.

Optimization of 12V power supply can reduce losses, while PMIC dynamic frequency scaling can improve stability.

Powerful: Quad-core Cortex-A76 + Quad-core Cortex-A55, main frequency height of 2.4 GHZ, NPU with 6 TOPS

Support multi-channel video access and display output

Complete functional interfaces such as mipi-csi, mipi-dsi, USB, SATA, UART, CAN and Gigabit Ethernet

Originally published at www.forlinx.net.

[anywaychina]

High-Performance AI Edge Computing Box with RK3588 | 8K Output, Multi-Screen Support, and AI Algorithms

Features: - Advanced AI Processing: Equipped with RK3588 (6TOPS) NPU for AI edge computing, supporting object recognition, facial recognition, and more. - 8K Video Output: Supports 8K@60FPS H.265/H.264/VP9 video encoding and decoding with six HDMI 2.0 outputs for high-definition display. - Multi-Screen Support: Allows up to six screens for seamless video wall or multi-display setups, perfect for retail, security, or industrial applications. - Rich Connectivity: Includes HDMI IN/OUT, dual gigabit Ethernet, Wi-Fi 6, USB 3.0, and more, ensuring robust connection options for diverse use cases. - AI Algorithm Compatibility: Supports popular AI frameworks such as OpenCV, TensorFlow, PyTorch, Caffe, and YOLO, with extensive SDK and API for easy integration. Specifications: - CPU: 8-core 64-bit architecture (4x Cortex-A76 + 4x Cortex-A55) - GPU: Mali-G610 MC4, supports OpenGL ES 1.1/2.0/3.2, OpenCL 2.0, Vulkan 1.1 - NPU: Neon and FPU, up to 6TOPs - Memory: DDR4 4GB (default) - Storage: EMMC 32GB, expandable via USB - Video Decode: 8K60FPS, H.265/H.264/VP9 codecs - Video Output: 6x HDMI 2.0 (7680x4320 resolution) - Audio: HDMI audio, 1x microphone input, 1x speaker output - Ports: 1x USB 3.0 host, 1x USB 3.0 OTG, 4x USB 2.0 - Network: 2x 10/100/1000M adaptive Ethernet ports, optional 3G/4G module - Wi-Fi: 2.4GHz/5GHz support - Bluetooth: 4.0 (supports BLE) - Operating System: Android 12 - Software: Visualized multimedia display system for Android

Read the full article

[mdshariful]

Today we are reviewing the compact system on module based on the versatile Rockchip RK3588 Octa Core SoC, the MIXTILE CORE 3588E. you may also like Mixtile Blade 3 Best New PICO-ITX and Stackable Single-Board MIXTILE CORE 3588E Module Mixtile launches this new high-performance AI board (6 TOPS), with a small form factor (69.6 x 45 mm) with a 260-pin edge connector. It can be used on carrier boards that are compatible with NVIDIA Jetson TX2 NX developer boards. This system-on-module has enough power to run high-resolution video encoding/decoding, graphics processing, and artificial intelligence applications. It is basically a computing module, so all inputs and outputs on the board are made through 260-pin connectors, communicating through four PCIe 3.0 x4 lanes and one PCIe 2.1 lane. The operating systems supported by MIXTILE CORE 3588E are Debian 11, Android 11, Ubuntu 22.04 and Armbian 23.07. Specification of MIXTILE CORE 3588E Module Feature Details Brand Mixtile Model CORE 3588E Processor Rockchip RK3588 (8nm) CPU 4 x ARM Cortex-A76 cores (Up to 2.4 GHz) 4 x ARM Cortex-A55 cores (Up to 1.8 GHz) GPU ARM Mali-G610MC4 RAM Options: 4/16/32 GB LPDDR4 Storage Options: 32/128/256 GB eMMC 5.1 Form Factor Compact System-on-Module (69.6 x 45 mm) AI Performance 6 TOPS Edge Connector 260-pin PCIe Lanes - Four PCIe 3.0 x4 lanes - One PCIe 2.1 lane Operating Systems Debian 11, Android 11, Ubuntu 22.04, Armbian 23.07 Video Outputs - DisplayPort 1.2a (Up to 8K resolutions) - HDMI 2.1 (Up to 8K resolutions) Camera Interfaces - 3 x 4-lane or 5 x 2-lane MIPI CSI @ 2.5 Gbps/lane - 48MP ISP Network Connector 10/100/1000 BASE-T USB Ports - 1 x USB 3.0 (Gen1) - 3 x USB 2.0 Other Connectors - UART DEBUG x1 - UART flow control x2 - SPI x2 - I2C x4 - CAN x1 - I2S x4 - SD 4.0, SDHOST 4.0, and SDIO 3.0 - PWM x3, GPIO x15 The MIXTILE CORE 3588E system-on-module is powered by the Rockchip RK3588 8nm processor. A chip that integrates 4 ARM Cortex-A76 cores at 2.4 GHz and another 4 ARM Cortex-A55 CPUs capable of reaching 1.8 GHz. In the graphics department we have a powerful ARM Mali-G610MC4 GPU. Thank you for completing the Mixtile Core 3568M/3588E Concept Survey! Pre-orders for the Mixtile Core 3568M/3588E system-on-module are now available! You can purchase it at the Mixtile store: https://t.co/YiEPk5b6n1 pic.twitter.com/OBlE21wUaW — Mixtile (@Mixtile) September 1, 2022 For RAM, we have options for all needs, including 4/16/32 GB LPDDR4 versions. For storage, we also have the option of 32/128/256 GB eMMc 5.1. You Can also like  Mixtile Blade 3 Mixtile Cluster Box Mixtile Blade 3 Case Mixtile Edge 2 Mixtile Edge 2 Kit Mixtile Core 3588E Mixtile Core 3568 Mixtile Core 3568M Mixtile Core 3568J Mixtile Core 3399E Mixtile Hub Mixtile Telematics Gateway 3 With this board we can use different types of ports such as DisplayPort 1.2a and HDMI 2.1 video output up to 8K resolution. We control up to 3x 4-lane or 5x 2-lane MIPI CSI interfaces with 2.5 Gbps/lane cameras and a 48 MP ISP. We have access to a 10/100/1000 BASE-T network connector, a USB 3.0 (Gen1) and 3 USB 2.0 ports. Price and availability The MIXTILE CORE 3588E SoM can be purchased from the official Mixtile store starting at $109 with shipping at the end of January. Optionally we can add a specific Heatsik for this board with dynamic speed adjustment between 0 and 5000 RPM. The board supports customization, please contact Mixtile for more information.

[ozrobotics]

[forlinx]

Introduction to RK3588

What is RK3588?

RK3588 is a universal SoC with ARM architecture, which integrates quad-core Cortex-A76 (large core) and quad-core Cortex-A55(small core). Equipped with G610 MP4 GPU, which can run complex graphics processing smoothly. Embedded 3D GPU makes RK3588 fully compatible with OpenGLES 1.1, 2.0 and 3.2, OpenCL up to 2.2 and Vulkan1.2. A special 2D hardware engine with MMU will maximize display performance and provide smooth operation. And a 6 TOPs NPU empowers various AI scenarios, providing possibilities for local offline AI computing in complex scenarios, complex video stream analysis, and other applications. Built-in a variety of powerful embedded hardware engines, support 8K@60fps H.265 and VP9 decoders, 8K@30fps H.264 decoders and 4K@60fps AV1 decoders; support 8K@30fps H.264 and H.265 encoder, high-quality JPEG encoder/decoder, dedicated image pre-processor and post-processor.

RK3588 also introduces a new generation of fully hardware-based ISP (Image Signal Processor) with a maximum of 48 million pixels, implementing many algorithm accelerators, such as HDR, 3A, LSC, 3DNR, 2DNR, sharpening, dehaze, fisheye correction, gamma Correction, etc., have a wide range of applications in graphics post-processing. RK3588 integrates Rockchip's new generation NPU, which can support INT4/INT8/INT16/FP16 hybrid computing. Its strong compatibility can easily convert network models based on a series of frameworks such as TensorFlow / MXNet / PyTorch / Caffe. RK3588 has a high-performance 4-channel external memory interface (LPDDR4/LPDDR4X/LPDDR5), capable of supporting demanding memory bandwidth.

RK3588 Block Diagram

Advantages of RK3588?

Computing: RK3588 integrates quad-core Cortex-A76 and quad-core Cortex-A55, G610 MP4 graphics processor, and a separate NEON coprocessor. Integrating the third-generation NPU self-developed by Rockchip, computing power 6TOPS, which can meet the computing power requirements of most artificial intelligence models.

Vision: support multi-camera input, ISP3.0, high-quality audio;

Display: support multi-screen display, 8K high-quality, 3D display, etc.;

Video processing: support 8k video and multiple 4k codecs;

Communication: support multiple high-speed interfaces such as PCIe2.0 and PCIe3.0, USB3.0, and Gigabit Ethernet;

Operating system: Android 12 is supported. Linux and Ubuntu will be developed in succession;

FET3588-C SoM based on Rockchip RK3588

Forlinx FET3588-C SoM inherits all advantages of RK3588. The following introduces it from structure and hardware design.

1. Structure:

The SoM size is 50mm x 68mm, smaller than most RK3588 SoMs on market;

100pin ultra-thin connector is used to connect SoM and carrier board. The combined height of connectors is 1.5mm, which greatly reduces the thickness of SoM; four mounting holes with a diameter of 2.2mm are reserved at the four corners of SoM. The product is used in a vibration environment can install fixing screws to improve the reliability of product connections.

2. Hardware Design:

FET3568-C SoM uses 12V power supply. A higher power supply voltage can increase the upper limit of power supply and reduce line loss. Ensure that the Forlinx’s SoM can run stably for a long time at full load. The power supply adopts RK single PMIC solution, which supports dynamic frequency modulation.

FET3568-C SoM uses 4 pieces of 100pin connectors, with a total of 400 pins; all the functions that can be extracted from processor are all extracted, and ground loop pins of high-speed signal are sufficient, and power supply and loop pins are sufficient to ensure signal integrity and power integrity.

The default memory configuration of FET3568-C SoM supports 4GB/8GB (up to 32GB) LPDDR4/LPDDR4X-4266; default storage configuration supports 32GB/64GB (larger storage is optional) eMMC; Each interface signal and power supply of SoM and carrier board have been strictly tested to ensure that the signal quality is good and the power wave is within specified range.

PCB layout: Forlinx uses top layer-GND-POWER-bottom layer to ensure the continuity and stability of signals.

RK3588 SoM hardware design Guide

FET3588-C SoM has integrated power supply and storage circuit in a small module. The required external circuit is very simple. A minimal system only needs power supply and startup configuration to run, as shown in the figure below:

The minimum system includes SoM power supply, system flashing circuit, and debugging serial port circuit. The minimum system schematic diagram can be found in "OK3588-C_Hardware Manual". However, in general, it is recommended to connect some external devices, such as debugging serial port, otherwise user cannot judge whether system is started. After completing these, on this basis, add the functions required by user according to default interface definition of RK3588 SoM provided by Forlinx.

RK3588 Carrier Board Hardware Design Guide

The interface resources derived from Forlinx embedded OK3588-C development board are very rich, which provides great convenience for customers' development and testing. Moreover, OK3588-C development board has passed rigorous tests and can provide stable performance support for customers' high-end applications.

In order to facilitate user's secondary development, Forlinx provides RK3588 hardware design guidelines to annotate the problems that may be encountered during design process of RK3588. We want to help users make the research and development process simpler and more efficient, and make customers' products smarter and more stable. Due to the large amount of content, only a few guidelines for interface design are listed here. For details, you can contact us online to obtain "OK3588-C_Hardware Manual" (Click to Inquiry)

[forlinx]

Advantages of FET3588J-C SoM in UAV Hyperspectral Imager Application

Product Background

With the rapid development and widespread application of drone technology, drone-mounted hyperspectral imaging systems that integrate drone platforms with high-precision spectral imaging technology are gradually gaining attention. The drone-mounted hyperspectral imaging system can measure spectral information of plants, water bodies, soil, etc., in real-time and generate spectral images. By analyzing these images, it is possible to establish relationships with the physicochemical properties of plants and use the data for research on plant classification and growth conditions. Additionally, it has applications in geological and mineral resource exploration, forest pest and disease monitoring, meteorological studies, and other industry fields.

Product Features

Hyperspectral resolution: Capable of capturing hundreds of continuous and narrow spectral bands, enabling detailed spectral characterization of surface materials.

High spatial resolution: Combined with the flexibility and stability of the drone platform, this enables high-resolution imaging of ground targets.

Intelligent data processing: Integrates advanced image processing algorithms and spectral analysis software, supporting rapid processing and interpretation of data.

Portability and ease of use: The equipment is lightweight and portable, making it easy to mount on drone platforms, while the user interface is user-friendly, simplifying operation for users.

Broader application scenarios: Suitable for environmental monitoring, agricultural surveys, geological exploration and other fields, meeting the needs of different users.

Product Requirements:

1. Compact carrier board design: Considering the weight and space constraints of the drone, the accompanying imaging device needs to be designed as compactly as possible. The carrier board design should be compact, effectively utilizing every inch of space while ensuring that all key components can be securely installed.

The size of the SoM should also be strictly controlled to fit the compact carrier board layout, without sacrificing its performance.

2. High compression ratio image compression algorithm: The product should incorporate a proprietary high compression ratio image compression algorithm to optimize the storage and transmission efficiency of image data. The algorithm needs to fully leverage the computational power of the SoM to ensure that excessive performance loss does not occur during image compression. The compression algorithm should minimize file size while maintaining image quality to accommodate the limited data transmission bandwidth and storage space of drones.

3. High-quality product stability: Given the complexity of the product application environment, such as extreme weather and mechanical vibrations, the requirements for product quality and stability are extremely high. All components and materials shall be of industrial grade or higher quality to ensure proper operation in a variety of harsh environments. Products shall be subjected to rigorous tests for shock, impact and weather resistance to verify their reliability in complex application environments.

Based on the product characteristics, Forlinx Embedded recommends using the FET3588J-C system on module(SoM) as the hardware design solution for the product.

Solution Features:

1. Strong performance support

High-performance processor: FET3588-C is based on Rockchip's new flagship RK3588 processor, which adopts an 8nm manufacturing process and integrates a quad-core Cortex-A76+quad-core Cortex-A55 architecture with a clock speed up to 2.4GHz, ensuring strong data processing capabilities for drones during hyperspectral imaging.

Powerful computing power: The built-in NPU provides 6 TOPS computing power, which makes it possible for artificial intelligence to be applied in UAV hyperspectral imaging, such as automatic target recognition, real-time analysis, etc.

2. Excellent image processing capabilities

Next-generation ISP 3.0: The FET3588-C introduces a 48-megapixel ISP 3.0, which supports various image optimization functions such as lens shading correction and 2D/3D noise reduction. This is crucial for enhancing the quality and clarity of hyperspectral imaging.

3. Highly integrated and scalable

Abundant high-speed data communication interfaces: FET3588-C is equipped with high-speed data communication interfaces, which can ensure the rapid transmission and processing of hyperspectral imaging data and improve the operation efficiency.

4. Wide application adaptability

Temperature range upgrade: The temperature range of the commercial-grade FET3588-C SoM is increased from 0 ℃ ~ + 80 ℃ to -20 ℃ ~ + 85 ℃, enabling the UAV to perform hyperspectral imaging operations in a wider range of environmental conditions.

Support for multiple operating systems: Adapt to multiple operating systems, provide flexibility for different users and development environments, and facilitate the integration and development of hyperspectral imaging systems.

In short, the FET3588-C SoM offers strong performance, great image processing, flexible display setup, high integration and scalability, and wide adaptability for use in unmanned aerial vehicle hyperspectral imaging equipment. These advantages make FET3588-C an ideal choice for UAV hyperspectral imaging.

Originally published at www.forlinx.net.

[forlinx]

Presenting the OK3588-C Development Board Featuring the Rockchip RK3588

Introduction:

In March of this year, I attended the Embedded World Exhibition, which focuses on embedded systems. During my visit, I explored the Forlinx booth. Forlinx is renowned for developing System on Modules (SoMs) and Evaluation Boards for industrial PCs. I previously acquired an evaluation board from Forlinx last year. This year, I am excited to present the new Forlinx OK3588-C board in this video.

Presenting the OK3588-C Development Board (featuring a Rockchip RK3588)

Today, we will explore the Forlinx OK3588-C board. Allow me to switch off the camera and transition to the desktop view.

Here, I have the hardware manual for the OK3588 board. If you require this hardware manual or the necessary SDKs to develop software for this board, please contact Forlinx, and they will provide you with the required resources.

SoM Appearance Diagram:

The evaluation board comprises two primary components. Firstly, this is the physical appearance. Here, we have the System on Module (SoM) mounted on a carrier board, which connects all peripherals to the SoM.

Let's begin by examining the System on Module. This module includes the Rockchip RK3588 main processor, two DRAM ICs, and eMMC storage for non-volatile data. Various components on the module generate the required voltages for the chip's operation. The Rockchip RK3588 is a robust processor.

RK3588 Description:

Displayed here is a block diagram of the RK3588. It features a dual-cluster core configuration. One cluster consists of a quad-core Cortex-A76 processor clocked at 2.6 GHz, and the second cluster includes a quad-core Cortex-A55 processor, clocked at either 1.5 or 1.8 GHz. This setup allows for power-saving capabilities by disabling the A76 cores when full performance is not required.

Another notable feature is the high-performance Neural Processing Unit (NPU), which is advantageous for tasks related to artificial intelligence and machine learning. In the future, I hope to demonstrate the NPU's capabilities.

The chip also includes a multimedia processor supporting various video decoders, even up to 8K resolution, and an embedded Mali-G GPU. For external memory interfaces, it has two eMMC controllers and support for LPDDR4 and LPDDR5. Additionally, it includes standard system peripherals, such as USB OTG 3.1, PCIe interfaces, Gigabit Ethernet, GPIO, SPI, and I²C.

Development Board Interface Description:

The carrier board includes numerous peripherals. There is a 12V power supply, a power switch, a reset switch, up to five camera connectors, microphone and speaker connectors, USB 2.0 host, and two USB 3.1 OTG ports. These USB ports can function as either hosts or devices. It also features two HDMI ports (one input and one output), a real-time clock with a battery, eDP ports, ADC connectors, an SD card slot, a fan connector, and M.2 slots for Wi-Fi and cellular cards.

The board also includes two full-size PCIe connectors, user buttons, CAN interfaces, an RS485 interface, a USB-to-serial adapter, and two Gigabit Ethernet ports. The overall setup is impressive.

Operation:

Let's power on the board. I have also connected a PCIe card to a free slot. Before proceeding, let's open the serial terminal to monitor the output.

The board is booting, and the kernel is starting successfully. Currently, we are running a minimal BusyBox root file system. In a future video, I will demonstrate how to build a custom Linux for this board. For now, this setup is sufficient.

We are running kernel version 5.10.66, built for ARM64 architecture. The board has eight processors, consisting of different Cortex-A cores. The available memory is 3.6 GB, with 155 MB currently in use. Background processes and the Mali GPU likely consume some memory.

We have eight I²C buses available, with one connected to the display connector for Display Data Channel (DDC) management.

The eMMC storage has multiple partitions. The board features seven GPIO chips and eight I²C connectors.

Lastly, I have connected a PCIe card, and the system detects it successfully. The card operates at PCIe Gen 1 speed with a link width of x1. Higher-end cards could achieve link speeds up to 8 GT/s and wider link widths.

This concludes the initial demonstration of the OK3588 board. In future videos, I will compile software for this board. Thank you for watching.

Originally published at www.forlinx.net.

[forlinx]

Application of Forlinx RK3588 SoM in Drone Delivery Service

Amazon recently announced its plan to use drones to deliver packages in the UK by the end of 2024. Amazon has been investing in drone technology for a decade now, but currently, its drone delivery services are limited to a few regions and primarily cover the delivery of non-pharmacy products such as home goods, office supplies, and beauty products. To drive business growth, Amazon has decided to expand its drone delivery services to the pharmaceutical industry.

After purchasing medication from Amazon Pharmacy, users will be able to receive fast delivery within 60 minutes through drone services. This initiative aims to meet consumer demand for rapid medication delivery, which is particularly important in emergency situations. To drive business growth, Amazon has decided to expand its medication delivery services to the pharmaceutical industry.

The launch of drone delivery services will bring new growth opportunities to the e-commerce industry and foster further advancements in technology innovation and the drone industry, opening up new possibilities for future delivery methods.

Absolutely, in addition to that, we can also expect to see more drones playing a role in other industries, such as agriculture, mapping, and more. Indeed, the development of drone technology undoubtedly brings forth more possibilities for both our personal lives and work environments.

However, drone product design faces certain challenges. For the purpose of targeted application in various scenarios, many drones adopt a modular design, which means incorporating additional expansion modules beyond the basic flight control system to achieve different functionalities.

While this design approach offers flexibility, it increases the overall weight of the drone to some extent. As a result, the size of the drone is limited. If the size is too small, it may not be able to accommodate the necessary expansion modules.

On the other hand, if the size is too large, it can increase power consumption and reduce battery life, affecting the overall flight endurance of the drone. Debugging and adaptation can also be a complex process.

For drone product design and development, using a highly integrated processor with more advanced features as the drone's main controller is a more suitable choice. This allows for the integration of required functionalities directly into the drone, tailored to meet the specific needs of different fields.

In this way, it is possible to better control the size of the drone, while balancing performance, size, and endurance. Forlinx Embedded recommends using the FET3588-C SoM as the main controller for a highly integrated drone.

Forlinx Embedded's FET3588-C SoM is developed and designed based on Rockchip's RK3588 processor. It integrates a quad-core Cortex-A76 and quad-core Cortex-A55 architecture. The A76 cores have a clock speed of up to 2.4GHz, while the A55 cores have a clock speed of up to 1.8GHz, providing powerful performance support. The FET3588-C SoM has also undergone rigorous testing to ensure stability and reliability for customers' high-end applications.

In terms of the most fundamental shooting functions of drones, the Forlinx Embedded FET3588-C SoM is also highly capable. It introduces the new generation 48 million pixel ISP3.0, which allows for lens shading correction, 2D/3D noise reduction, sharpening and fog removal, fisheye correction, gamma correction, and wide dynamic contrast enhancement effects. These features significantly enhance the image quality and are suitable for customers with special image requirements.

RK3588 has undergone significant improvements in integer operations, floating-point operations, memory, overall performance, power consumption, and core area. It also features a wide range of high-speed data communication interfaces, meeting the diverse needs of various industries.

Additionally, it is equipped with Rockchip's self-developed tri-core NPU, which can work in collaboration or independently, allowing for flexible allocation of computational power and avoiding redundancy. The integrated NPU can deliver up to 6 TOPS of computing power, empowering artificial intelligence applications and providing more possibilities for expanding the application scenarios of drones.

Drones have penetrated into numerous industries, and the increasingly fierce competition has driven drones to develop and improve in the directions of intelligence, miniaturization, and systematization. In the selection of drone controllers, there will also be a greater preference for more versatile, all-encompassing, and powerful platform.

The above is the drone controller selection scheme recommended by Forlinx Embedded, based on the FET3588-C SoM. We hope this can be helpful to all engineers.

Originally published at www.forlinx.net.

[forlinx]

Introduction to Forlinx's Hot-sale SoMs Based on Rockchip

In this article, we will introduce the SoMs of the Rockchip.

Rockchip x Forlinx

Since 2020, Forlinx Embedded has launched three SoM products based on Rockchip RK3399, RK3568, and RK3588 processors and got affirmation and recognition from thousands of enterprise users.

01 RK3588 Series

The FET3588J-C SoM is developed and designed based on the Rockchip new generation flagship RK3588J processor, which adopts an advanced 8nm process and integrates quad-core Cortex-A76 + quad-core Cortex-A55, with A76 cores frequency up to 1.6GHz and A55 cores frequency up to 1.3GHz, providing powerful performance support. It supports an 8K ultra-high-definition display and a four-screen heterodyne display, and it is equipped with a wealth of high-speed data communication interfaces to meet the diverse needs of users.

After rigorous test, it can operate stably for a long time under -40~+85℃.

02 RK3568 Series

FET3568J-C SoM is developed and designed based on Rockchip RK3568J processor, which integrates quad-core 64-bit Cortex-A55 architecture, with frequency up to 1.8GHz and built-in NPU. It is a high-performance, low-power, feature-rich application processor built by Rockchip for the AIoT and industrial markets.

The FET3568J-C SoM has been subjected to industrial-grade standard ambient temperature tests, pressure tests, and long-term stability operation tests to ensure its stable and reliable operation.

03 RK3399 Series

FET3399-C SoM is the first product jointly launched by Forlinx Embedded and Rockchip. It is based on Rockchip's RK3399 processor design and has two ARM Cortex-A72 cores at 1.8GHz and four ARM Cortex-A53 cores at 1.4GHz; the GPU adopts Mali-T864 and supports OpenGL ES1.1/2.0/3.0/3.1, OpenVG1.1, OpenCL, DX11; 2GB LPDDR3 RAM on board (4GB optional), 16GB eMMC ROM.

With its powerful performance configuration, this SoM has been widely used in cutting-edge technology fields such as intelligent self-service terminals, edge computing, 5G intelligent terminals, visual recognition, etc.

Originally published at www.forlinx.net.