Neural Networks for Unmanned Aerial Vehicles and Air Traffic Management

JP2023538588A5Active Publication Date: 2025-10-31DROBOTICS LLC
0 Cites 0 Cited by

Patent Information

Application Number
JP2023512046
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2020-08-21
Filing Date
2021-07-27
Publication Date
2025-10-31
Estimated Expiration
2041-07-27

AI Technical Summary

Technical Problem

Drones are unable to adapt to unplanned changes in flight paths, such as avoiding obstacles or unexpected conditions, due to limitations in GPS drift correction and lack of real-time data processing capabilities, leading to inefficiencies and potential safety hazards during asset surveys.

Method used

Implementing neural networks, both on high-altitude pseudolite platforms (HAPSNN) and low-altitude survey drones (DINN), to process real-time data from onboard sensors and air traffic management systems, enabling adaptive flight paths and collision avoidance.

Benefits of technology

Ensures safe and efficient drone operations by accurately navigating around obstacles, correcting for GPS drift, and optimizing flight paths in real-time, enhancing mission performance and data collection accuracy.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Unmanned aerial vehicles (UAVs) or "drones" run neural networks to support reconnaissance, reconnaissance, reporting, and other missions. The drone reconnaissance neural network may monitor data streams from multiple onboard sensors in real time while navigating to an asset along a pre-programmed flight path and / or during its mission (e.g., when scanning and surveying an asset). A HAPS platform may run a neural network ("HAPSNN") while monitoring air traffic. The neural network enables it to classify, predict, and analyze events within its airspace of coverage in real time, and to learn from new events not previously seen or detected.
Need to check novelty before this filing date? Find Prior Art