Aircraft Navigation Calibration Using Vision-Based State Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for determining the navigational state and accuracy of aircraft are unreliable, prone to interference, and require expensive maintenance, making them unsuitable for autonomous and semi-autonomous flight operations.
Innovation Solution
A method that uses a state recognition model to analyze images from an aerial vehicle's environment, determining its navigational state and uncertainty, and compares these to a reconstructed image to assess accuracy, with a protection model determining a protection level for navigation actions based on the uncertainty, allowing the aircraft to perform safe navigation actions when the level is below a threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional GPS-based navigation systems are used, then navigation coverage is extensive, but measurement precision and reliability deteriorate due to interference and drift
Solution Approach 1:
The patent introduces computer vision systems as an intermediary to verify and cross-check GPS-based navigational measurements. The vision system independently determines aircraft state through image analysis of the environment, providing a mediator that can detect GPS errors and interference, thereby improving both measurement precision and reliability without sacrificing extensive navigation coverage.
Solution Approach 2:
The system implements feedback by continuously comparing GPS-derived navigational states with vision-based estimates. When discrepancies exceed threshold values, the system generates alerts and can switch to vision-based navigation, creating a closed-loop feedback mechanism that maintains high reliability and precision while utilizing the extensive coverage capability of GPS.
2Measurement precision
If expensive calibration apparatuses are installed, then measurement precision improves, but device complexity and maintenance costs increase
Solution Approach 1:
Instead of installing expensive physical calibration apparatuses, the patent uses computer vision to create virtual models and estimates of the aircraft's navigational state. The vision system captures images of the environment and generates virtual representations of aircraft position and orientation, providing accurate measurement without complex physical hardware, thereby reducing device complexity and maintenance requirements while maintaining high precision.
Solution Approach 2:
The patent replaces mechanical calibration apparatuses with computational image processing systems. Rather than using physical devices to measure and verify aircraft state, the system uses cameras and algorithms to extract navigational information from visual data, substituting mechanical systems with optical and computational approaches that reduce complexity and maintenance burden.
3Productivity
If autonomous navigation systems are implemented, then productivity increases, but reliability decreases due to lack of human oversight
Solution Approach 1:
The autonomous navigation system incorporates continuous feedback loops where computer vision independently verifies GPS-based navigational decisions. The system compares vision-derived state estimates with planned autonomous actions, and when discrepancies are detected, it can alert operators or switch to manual control, maintaining high productivity through automation while preserving reliability through multiple layers of verification.
Solution Approach 2:
The system performs preliminary verification of navigational decisions using computer vision before executing autonomous actions. By pre-checking the accuracy and reliability of GPS-based state estimates against vision-based estimates, the system ensures safe autonomous operation, allowing high productivity while maintaining reliability through advance verification rather than relying solely on human oversight.
Data Source
AI summary
A system having components coupled to an aircraft that measure the navigational state and state uncertainty of an aircraft. To do so, the aircraft captures an image of its surrounding environment including an object of interest and applies one or more machine vision models to the image. One or more of the models determine if the image is acceptable, in that it determines if an object of interest is represented in the image. One or more of the models determine a calibrated uncertainty based on information extracted previously labelled images and current measurements of navigational state and uncertainty. One or more of the models determine a protection level for the aircraft and determines an operational system of the aircraft is available to perform a navigational action based on the protection level (e.g., by comparing protection level to an alert level).