Optical Measurement System for Aerial Vehicle Landing Vector
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aerial vehicles face challenges in maneuvering towards platforms located below them due to limited visual or sensor-based observations, which can be occluded or lagging in real-time data.
Innovation Solution
An optical measurement and cuing system that uses image data from a camera to detect a point-of-interest, such as a helipad, and processes this data to determine a vector between the aerial vehicle and the platform, providing a cue for the pilot or autonomy system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If visual or sensor-based observation is used to detect the platform location, then the aerial vehicle can identify the landing target, but the observation may be occluded or lagging resulting in inaccurate or delayed position information
Solution Approach 1:
The system transitions from 2D image data to 3D spatial understanding by calculating a three-dimensional position vector (x, y, z coordinates) representing the platform's location relative to the aerial vehicle. This dimensional transformation enables accurate platform localization even when visual observation is partially occluded, as the system computes the third dimension (vertical distance) based on image frame analysis and sensor fusion.
Solution Approach 2:
The system introduces an intermediary computational model that processes image data and sensor inputs to generate a reliable platform position estimate. This intermediary layer (the position calculation algorithm) mediates between raw sensor data and the final landing control decisions, filtering out occlusion effects and temporal lag to provide consistent position information.
2Loss of information
If the aerial vehicle extends flight time to re-approach the obscured platform, then it can obtain better observation data, but the condition may deteriorate further during the extended time
Solution Approach 1:
The system performs preliminary action by calculating the platform's three-dimensional position in advance using current image data and sensor inputs, before attempting visual re-approach. This preliminary position estimation enables the aerial vehicle to navigate directly toward the computed platform location without needing to extend flight time for additional observation, thereby preventing condition deterioration during extended exposure.
Solution Approach 2:
The system implements feedback by continuously updating the platform position vector based on real-time image frame analysis and sensor data. This feedback loop allows the aerial vehicle to maintain accurate platform location information without extending flight time, as the system adapts to changing conditions and recalculates position dynamically rather than relying on extended observation periods.
3Loss of information
If a camera system is used to capture image frames of the platform, then the platform location can be identified, but the system complexity increases due to image processing requirements
Solution Approach 1:
The system extracts only the essential information needed for platform localization from the image frames, specifically identifying the platform's position in the image coordinate system. Rather than processing complete image data, the system extracts minimal necessary features (platform location coordinates) and combines them with sensor inputs to compute the three-dimensional position vector, thereby reducing computational complexity while maintaining information quality.
Solution Approach 2:
The camera system serves multiple functions: it captures image frames for platform identification, provides spatial reference information for position calculation, and works in conjunction with other sensors to generate the final three-dimensional position estimate. This multi-functionality reduces the need for separate dedicated components, thereby managing system complexity while achieving comprehensive platform location information.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Aerial navigation is disclosed. A system can receive, via a camera coupled to the aerial vehicle, image frames of a platform. The system can generate, via a first model trained with machine learning on reference patterns, a feature map that identifies a predetermined pattern. The system can input, responsive to recognition of the predetermined pattern, a feature map generated by the first model into a second model trained with machine learning on slope-intercept functions. The system can determine, based on an offset of the zone in the image frame and the orientation of the aerial vehicle relative to the zone, a vector between the aerial vehicle and the zone. The system can provide for display, via a display device communicatively coupled to the computing system, an indication of the vector overlayed on a digital representation of the image frame.