A modern drone can not only simply obey the pilot's commands, but also independently analyze and "understand" the surrounding situation during flight with the help of AI: recognize targets, bypass obstacles, make decisions autonomously. Cloud processing is not suitable for this due to significant delays and dependence on communication, which can be jammed by electronic warfare. That is why neural networks are increasingly being run directly on board, using compact and energy-efficient modules such as NVIDIA Jetson.
NVIDIA Jetson for autonomous vision on a drone
The Jetson lineup includes module variants of different power levels that can be selected for a wide variety of tasks. All versions of the boards run on the basis of a single JetPack system. It combines three main tools for AI:
Thanks to this, optimized neural networks (for example, YOLO) can detect objects directly on board the copter via cameras, track them, and analyze the environment directly during flight. Accordingly, NVIDIA microcomputers for drones become an ideal solution if you need to set up autonomous navigation of UAVs. The main advantage of using this particular module on board is its minimal weight and ultra-high computing capability.
How to choose a Jetson board model for a UAV
First, determine the drone's use case. Four defining characteristics of the board will depend on this:
Consultation on choosing a specific version of the module can be obtained at the specialized electronics store Zelen Store. Specialists will also, if necessary, help select other compatible components for your UAV.