DJI Manifold

DJI Manifold

Powerful Computing on the Fly
Advanced Image Processing in the Sky
Powered by Ubuntu
Supports DJI Onboard SDK
Low Power Consumption
Compatible with the Matrice 100 and Matrice 600
Comprehensive Connectivity

Powerful Processing. Limitless Possibilities. 
The Manifold is a high-performance embedded computer specially designed for the DJI Onboard SDK. It enables developers to transform aerial platforms into truly intelligent flying robots that can perform complex computing tasks and advanced image processing literally on the fly.

Powerful Computing on the Fly 
With the NVIDIA Tegra K1's 4-Plus-1 Quad-core ARM Cortex-A15 Processor, the NVIDIA Kepler GPU that contains 192 CUDA cores in each SMX, and clock speeds of up to 2.2 GHz, the Manifold allows you to take-off with the world's most advanced mobile processors. The GPU cores provide powerful image processing abilities, efficient parallel computing, and a blazing fast throughput of 326 GFLOPS. Now you can design more intelligent applications that unlock the full potential of your aerial platforms in whole new ways.

Advanced Image Processing in the Sky 
The Manifold packs the processing power of a PC graphics card and supports DirectX 11 and OpenGL 4.4, enabling your aerial platform to process complex images in real time. The Manifold also supports NVIDIA CUDA, which can be used to develop the most advanced GPU-accelerated applications and boost the performance of a program. It can be deployed for use in artificial intelligence applications such as computer vision and deep learning. This means your aerial platforms will not only be able to sense the surrounding environment, but also identify objects and respond almost instantly. 

Convenient Development Environment 
Designed for developers, the Manifold's built-in Ubuntu operating system supports Linux, CUDA, OpenCV, and ROS. It is ideal for research and development of professional applications. The Manifold can natively run the DJI Onboard SDK, access flight data and perform intelligent control and data analysis. With CUDA, the Manifold can be used to accelerate your applications to achieve unprecedented levels of performance. 

Low Power Consumption 
The Manifold is optimized for power efficiency with a peak power consumption of approximately 15 W, or one fourth of that of a typical laptop. The Manifold's Tegra K1 CPU uses four A15 cores for heavy computing tasks, and a single battery-saver core when performing simple calculations. The number of active cores can be dynamically adjusted to decrease power consumption, and the extra core is automatically activated when needed.

Versatile Compatibility 
Limited space on aerial platforms is no longer a limit to developing powerful applications. With a size of only 11 cm x 11 cm x 2.6 cm, a weight of less than 200 g, and built-in customized ports, the Manifold is optimized for DJI developer platforms. It can be easily mounted to the expansion bay of the Matrice 100 and Matrice 600, and is also compatible with the A3 and N3 flight controller.

Comprehensive Connectivity  
Equipped with USB, Ethernet, Mini-PCIe, HDMI, UART, SPI, and I2C ports, the Manifold allows you to connect to a wide array of sensors, monitors and other peripheral devices. The Manifold also provides customized ports to connect to the Matrice 100 and Matrice 600, so the images captured by the camera mounted to the platform can be processed. This opens up more possibilities for developers to create extraordinary applications.