A New Concept of GPU-Accelerated On-Board Visual System for Aerial Vehicles

Abstract

As technology advances, the intellectual ability and autonomy of the electronic-mechanical control system in modern aircrafts and spacecrafts continue to increase, which helps to reduce the crew load and accident rate. But these helpful controlling systems are not perfect. Under some unfavorable circumstances, they get stuck or start to function unpredictably when faced with a much more complicated real situation than the developers expected, even leading to crashes sometimes. The concept of visual multichannel processing support of aircraft/spacecraft launch and landing as an additional element of automatic control loop for flight safety and reliability improvement is proposed, and its advantages, feasibility, and expediency are discussed and evaluated. Visual analyzers are highly typical for the overwhelming majority of highly organized organisms (humans, animals, and insects) as the most informative source for controlling movement parameters. As a result, they have the potential to significantly enhance the reliability of the entire embedded vehicle control system. Moreover, their principal structure, implementation, and further functioning are very similar and universal across the actual flight operations of different vehicles. This opens up considerable prospects for their application in engineering, leveraging modern revolutionary advances in methodology and computational technologies for pattern recognition. In particular, it was shown that the required accuracy and productivity for real-world vehicle applications can be reached by developing the visual multichannel system as an additional source of flight state information. On the base of NVIDIA Jetson embedded portable low-power consuming Graphics Processing Unit (GPU)-accelerated massively parallel computational platform, providing Compute-Unified-Device-Architecture (CUDA) and Artificial Intelligence data processing in real-time mode.