UAV Backup Navigation with Visual Feature Matching After GPS Failure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned aerial vehicles (UAVs) face navigation failures due to primary navigation system failures or malicious attacks, leading to potential crashes or loss of control, as current backup navigation systems are inadequate for real-time navigation and are vulnerable to position errors and complexity issues.
Innovation Solution
A backup navigation system that uses real-time image data to generate and update a map of the UAV's flight path, transitioning from a feature localization mode to a UAV localization mode to navigate the UAV to a safe landing zone by identifying visual features and determining its location using triangulation and feature matching algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a backup navigation system is implemented to replace primary navigation functionality upon failure, then navigation reliability is improved, but device complexity increases due to additional image capture devices, processing algorithms, and dual-mode operation systems
Solution Approach 1:
The navigation system is segmented into two independent modes: feature localization mode (using pre-stored localized visual features) and UAV localization mode (using real-time image capture and matching). This segmentation allows the system to switch between modes based on primary navigation system status, improving reliability while managing complexity through modular operation
Solution Approach 2:
Visual features are localized and stored in a database before the UAV flight begins. This preliminary action creates a ready-to-use reference system that enables rapid switching to backup mode without requiring complex real-time processing during critical failure scenarios, thus improving reliability while minimizing the complexity increase during operation
2Measurement precision
If real-time image data is used to generate and update flight path maps, then navigation accuracy is improved, but use of energy increases due to continuous image capture, processing, and analysis requirements
Solution Approach 1:
The system dynamically adjusts its operation between two modes: feature localization mode (lower energy consumption, using pre-processed visual features) and UAV localization mode (higher energy consumption, using real-time image capture and processing). This dynamic switching allows the system to maintain measurement precision when needed while managing energy consumption during normal operation
Solution Approach 2:
Instead of continuously processing raw image data, the system creates and stores localized visual features as simplified representations (copies) of the environment. These feature copies are much less computationally intensive to process while maintaining the essential information needed for accurate location determination, thus reducing energy consumption while preserving measurement precision
3Ease of operation
If visual feature localization and matching algorithms are implemented for backup navigation, then ease of operation is improved through autonomous operation, but device complexity increases due to algorithm complexity and processing requirements
Solution Approach 1:
The complex visual feature localization and matching algorithms are extracted as separate, dedicated processing functions within the backup navigation system. By isolating these complex algorithms into specific modules that operate only when needed (in backup mode), the system achieves autonomous navigation capability without requiring the entire system to constantly manage the complexity of these algorithms
Solution Approach 2:
Localized visual features serve as an intermediary representation between the raw environment and the UAV's navigation system. These pre-processed feature descriptors mediate the complex image processing requirements, allowing the system to achieve autonomous operation by matching simplified feature representations rather than processing complete images in real-time
Data Source
AI summary
Described is a method that involves operating an unmanned aerial vehicle (UAV) to begin a flight, where the UAV relies on a navigation system to navigate to a destination. During the flight, the method involves operating a camera to capture images of the UAV's environment, and analyzing the images to detect features in the environment. The method also involves establishing a correlation between features detected in different images, and using location information from the navigation system to localize a feature detected in different images. Further, the method involves generating a flight log that includes the localized feature. Also, the method involves detecting a failure involving the navigation system, and responsively operating the camera to capture a post-failure image. The method also involves identifying one or more features in the post-failure image, and determining a location of the UAV based on a relationship between an identified feature and a localized feature.