1.1.1 USX51 Compute Flight Controller
Product Description
The USX51 Compute Flight Controller combines the mature Pixhawk 6X flight controller architecture with the D-Robotics X5 AI chip, integrating stable flight control with edge intelligence in an onboard flight control platform. Based on PX4/ArduPilot firmware, it achieves highly reliable flight management. With the X5 chip's BPU AI computing power of 10 TOPS, it can run various neural network algorithms locally in real-time, including image recognition, object detection, semantic segmentation, human detection, object counting, spatial perception, reinforcement learning, and more. The CPU general computing power reaches 21.6 DMIPS/MHz, which can run VIO visual odometry, LIO LiDAR odometry, SLAM mapping and localization, Navigation2 navigation, path planning, and other algorithms without relying on cloud computing, completing the perception, planning, and action loop independently. The module is compatible with RTK, UWB, optical flow, ADS-B and other peripherals, supporting multi-sensor data fusion and intelligent mission planning, balancing flight safety, positioning accuracy, and operational autonomy. Widely applicable to industrial inspection, research and development, autonomous operations, and other drone scenarios with dual demands for flight stability and edge intelligence.
Specifications
Onboard Computer (OBC)
| Parameter | Specification |
|---|---|
| Chip Model | D-Robotics X5 SIP |
| CPU | 8x A55@1.5GHz |
| BPU | 10 TOPS |
| GPU | 32 Gflops |
| RAM | 8GB LPDDR4 |
| Storage | 32GB eMMC |
| OS | Ubuntu 22.04 |
| Input | 5V/5A |
RDK X5 Module
The RDK X5 Module is equipped with the Sunrise 5 intelligent computing chip, providing up to 10 TOPS of computing power. It is a comprehensive development kit for intelligent computing and robotics applications, with rich interfaces and extreme ease of use, supporting Transformer, RWKV, Occupancy, Stereo Perception, and other complex models and latest algorithms, accelerating the rapid implementation of intelligent applications.
Algorithm Support
- Object Detection: FCOS, YOLO, FasterRCNN, Efficientdet, Mobilenet_ssd
- Image Classification: Mobilenet
- Semantic Segmentation: Unet
- Application Algorithms: Human detection and tracking, gesture recognition, hand keypoint detection, monocular depth estimation network, monocular 3D detection, speech processing
For more software algorithm applications, please refer to D-Robotics Community Official Documentation
CSI Camera Support
| No. | Sensor | Resolution |
|---|---|---|
| 1 | IMX219 | 800W |
| 2 | OV5647 | 500W |
| 3 | IMX477 | 1230W |
For easy plugging and unplugging, USX51 changed this interface to Micro-HDMI type.
Flight Controller (FMU)
| Parameter | Specification |
|---|---|
| FMU Processor | STM32H753 – Arm® Cortex®-M7 480MHz, 2MB memory, 1MB SRAM |
| IO Processor | STM32F103 – Arm® Cortex®-M3 72MHz, 64KB SRAM |
| Accelerometer/Gyroscope | ICM-45686 × 3 |
| Compass | BMM150 |
| Barometer | BMP388 + ICP20100 |
| Input | 5V / 5A |
| Operating Temperature | -20 ~ 70°C |
| Dimensions | 122 × 58 × 28mm |
| Weight | 170g |
| Power Consumption | 8.7W |
Interface Definition
| Interface Name | Function Description | Interface Type |
|---|---|---|
| FC PWR1 | Flight controller power input1, with I2C | MOLEX-6P |
| FC PWR2 | Flight controller backup power input2, with I2C | MOLEX-6P |
| AI PWR | AI power input | XT30 |
| CAN1 | Flight controller CAN1 bus | GH1.25-4P |
| CAN2 | Flight controller CAN2 bus | GH1.25-4P |
| I2C | Flight controller I2C bus | GH1.25-4P |
| TELEM1 | Flight controller serial port | GH1.25-6P |
| TELEM3 | Flight controller serial port | GH1.25-6P |
| SPI | Flight controller SPI port | GH1.25-11P |
| UART&I2C | Flight controller serial and I2C port | GH1.25-7P |
| GPS1 | GPS module interface | GH1.25-10P |
| GPS2 | GPS module interface | GH1.25-6P |
| ADC | Analog to digital signal input | GH1.25-4P |
| DSM | DSM receiver interface | GH1.25-3P |
| RSSI | Signal strength output | 2.54 DIP-3P |
| RC IN | S-BUS/PPM signal input | 2.54 DIP-3P |
| FC PWM1~8 | Flight controller PWM output | 2.54 DIP-3P × 8 |
| I/O PWM1~8 | Coprocessor PWM output | 2.54 DIP-3P × 8 |
| FC ETH | Flight controller network port | GH1.25-4P |
| FC USB | Flight controller USB interface | Type-C |
| AI ETH | AI module network port, default static IP: 192.168.127.10 | GH1.25-8P |
| AI CAN | AI module CAN port | GH1.25-4P |
| AI UART0/1 | AI module serial port | GH1.25-8P |
| AI USB2.0 | AI module USB2.0 port, USB Device mode, for connecting host for ADB, Fastboot, system flashing | Type-C |
| AI USB3.0 | AI module USB3.0 port, USB Host mode, for connecting USB 3.0 peripherals | Type-C |
| AI REC | AI module upgrade button | - |
| HDMI | AI video output, supports up to 1080P resolution | miniHDMI |
| CAMERA1 | CSI camera1 interface | microHDMI |
| CAMERA2 | CSI camera2 interface | microHDMI |
| FC Debug | Flight controller debug port | SH1.0-10P |
| IO Debug | Flight controller coprocessor debug port | SH1.0-10P |
Status LEDs
| LED | Description |
|---|---|
| FC LINK | Flight controller network port LED |
| FC ACT | Flight controller working LED |
| FC B/E | Flight controller BOOT/ERR LED |
| FC PWR | Flight controller power LED |
| AI LINK | AI network port LED |
| AI ACT | AI working LED |
| AI SYS | AI system LED |
| AI PWR | AI power LED |