Autonomous Aircraft Guidance for Prohibited-Zone Imaging Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing guidance methods for autonomous aircraft fail to anticipate headings towards objects of interest and are inefficient in navigating overflight prohibited zones, leading to high deployment costs, energy consumption, and degraded image quality due to vibrations.
Innovation Solution
A guidance method and device using a neural network to determine optimal actions for autonomous aircraft, incorporating a learning phase with fictitious flights to optimize control instructions, ensuring the aircraft avoids prohibited zones and captures objects of interest while maintaining a safe corridor.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multi-rotor drone is used for aerial photography, then the aircraft can be positioned according to a precise angle to photograph objects of interest, but the vibrations from motors significantly degrade image quality and shorten flight time
Solution Approach 1:
The patent replaces the mechanical multi-rotor drone system with a fixed-wing aircraft system. This substitution eliminates the high-vibration motor operations characteristic of multi-rotors while maintaining the ability to achieve precise positioning through aerodynamic control surfaces and guidance systems, thereby resolving the contradiction between positioning precision and vibration-induced image degradation
Solution Approach 2:
The patent changes the fundamental operational parameters of the aircraft system by transitioning from vertical takeoff and hover-capable multi-rotor operation to fixed-wing aerodynamic flight. This parameter change includes adopting continuous forward motion, wing-based lift generation, and reduced vibration characteristics, which collectively eliminate the harmful vibrations while preserving positioning capabilities through flight control systems
2Productivity
If existing guidance laws are used to navigate autonomous aircraft, then the aircraft can pass by a given number of objects of interest, but the guidance laws do not make it possible to anticipate the heading taken by the aircraft to be situated within the field of the object of interest
Solution Approach 1:
The patent implements preliminary action by using a neural network to pre-calculate and anticipate the optimal heading and trajectory of the aircraft before reaching the objects of interest. The system processes geographic information, object locations, and aircraft state in advance to determine the anticipated heading that will position the aircraft correctly within the field of view of each object, eliminating the reactive nature of traditional guidance laws
Solution Approach 2:
The patent introduces a neural network as an intermediary between the traditional guidance law and the aircraft control system. This neural network intermediary processes the relationship between aircraft position, heading, and object locations, generating anticipated heading information that bridges the gap between simple waypoint navigation and precise object-oriented positioning, thereby enabling both high productivity and accurate heading anticipation
3Area of stationary object
If autonomous aircraft navigate through overflight prohibited zones, then coverage of objects of interest is improved, but deployment costs and energy consumption increase significantly
Solution Approach 1:
The patent applies dynamics by implementing a flexible, adaptive route planning system that dynamically adjusts the aircraft's flight path based on real-time constraints and objectives. The neural network continuously optimizes the trajectory to find energy-efficient routes that achieve complete coverage of objects of interest without unnecessarily entering prohibited zones, allowing the system to adapt its coverage strategy to minimize energy consumption while maintaining comprehensive area coverage
Data Source
AI summary
A method for guiding an autonomous aircraft, the aircraft includes an automatic pilot, a plurality of sensors and an imaging unit, the aircraft being configured to fly over a geographic zone comprising overflight prohibited zones, the guidance method can advantageously comprise a phase of real flight of the autonomous aircraft by using a given guidance law, comprising the following steps: determining a current state of the autonomous aircraft; determining an optimum action to be executed by using a neural network receiving the current state; determining a plurality of control instructions compatible with the guidance law based on the optimum action to be executed; transmitting to the automatic pilot the plurality of control instructions, which provides a new state of the autonomous aircraft.