UAV Urban Navigation via GPS-Tagged Image Mosaics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned aerial vehicles (UAVs) face navigation challenges in urban environments due to GPS signal interference from the 'urban canyon' effect, which causes multipath errors and position/velocity errors, and existing image-aided navigation methods lack temporal and spatial proximity for effective navigation.
Innovation Solution
A system that captures GPS-tagged images during an initial fly-over at a higher altitude, stitches them into an image mosaic, and matches image features from subsequent lower-altitude flights to calculate the UAV's current position relative to the GPS-aided positions, using inertial sensors and image matching algorithms for accurate navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS signals are used for navigation in urban environments, then navigation accuracy is improved, but signal reception is blocked by urban canyon effects causing multipath errors
Solution Approach 1:
The patent introduces image mosaics as an intermediary reference system between the UAV and GPS satellites. Instead of directly relying on blocked GPS signals, the system captures images, creates mosaics with GPS tags, and uses these mosaics as intermediate references for position calculation when GPS signals are unavailable in urban canyons
Solution Approach 2:
The system performs preliminary actions by capturing images and creating GPS-tagged image mosaics during an initial fly-over before the actual navigation mission. This pre-established mosaic serves as a reference map that enables subsequent navigation without real-time GPS signals
2Ease of operation
If satellite images are used for image-aided navigation, then navigation capability is provided, but temporal and spatial proximity is insufficient for effective navigation in urban canyons
Solution Approach 1:
The system performs preliminary image capture and mosaic creation during an initial fly-over mission, establishing a current and relevant reference map before the navigation phase. This ensures the reference images are temporally and spatially proximate to the actual navigation environment
Solution Approach 2:
The system dynamically adapts the reference mosaic to match the specific temporal and spatial conditions of the urban environment. By capturing images during an initial fly-over and updating the mosaic accordingly, the system ensures the reference material remains current and relevant for subsequent navigation
3Reliability
If image mosaics are created from initial fly-over images, then navigation reference is established, but image matching difficulty increases due to lighting and view angle differences
Solution Approach 1:
The system changes image parameters by capturing mosaics at higher altitudes during the initial fly-over, which provides more consistent lighting conditions and reduces view angle variations. This parameter adjustment (altitude) makes subsequent image matching easier while maintaining navigation reference reliability
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
A method and system for navigation of an unmanned aerial vehicle (UAV) (110) in an urban environment (120) are provided. The method comprises capturing a first set of Global Positioning System (GPS)-tagged images in an initial fly-over of the urban environment at a first altitude (A), with each of the GPS-tagged images being related to respective GPS-aided positions. The captured GPS-tagged images are stitched together into an image mosaic using the GPS-aided positions. A second set of images is captured in a subsequent fly-over of the urban environment at a second altitude that is lower than the first altitude. Image features from the second set of images are matched with image features from the image mosaic during the subsequent fly-over. A current position of the UAV relative to the GPS-aided positions is calculated based on the matched image features from the second set of images and the image mosaic.