Monocular Aircraft Position Refinement for Autonomous Aerial Refueling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aerial refueling currently relies on human operators, which is costly and requires additional expensive components like stereoscopic vision and LIDAR, and there is a need for automated systems that can accurately estimate the position and orientation of aircraft fuel receptacles using a single camera.
Innovation Solution
The system receives a video stream from a single camera, determines an initial position estimate for the aircraft, refines it using a deep learning neural network or optimization techniques, and controls an aerial refueling boom to engage the fuel receptacle, enabling autonomous or assisted refueling operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single camera is used for aerial refueling, then device complexity and cost are reduced, but measurement precision of aircraft position is insufficient
Solution Approach 1:
The system performs preliminary action by using an estimate refiner to generate refined position estimates from initial estimates before final boom control. This preliminary refinement step improves measurement precision without adding complex hardware, as the refiner processes data computationally to enhance accuracy.
Solution Approach 2:
The patent replaces mechanical/stereoscopic vision systems with a computational approach using a single camera. Instead of using dual cameras for stereoscopic vision or LIDAR for range measurements, the system substitutes these with algorithmic refinement of position estimates from monocular video, reducing device complexity while maintaining or improving precision.
2Reliability
If human operators are used for aerial refueling, then operational reliability is maintained, but device complexity and cost increase
Solution Approach 1:
The system implements self-service by enabling autonomous boom control that operates without human operators. The automated system uses video processing and estimate refinement to independently determine aircraft position and control the refueling boom, eliminating the need for operator accommodation while maintaining operational reliability through automated decision-making.
Solution Approach 2:
The patent substitutes the human operator's visual and manual control system with an automated computer vision and control system. The single camera combined with estimate refinement algorithms replaces the operator's stereoscopic vision and judgment, while the automated control system replaces manual boom manipulation, reducing device complexity by eliminating operator accommodation.
3Measurement precision
If stereoscopic vision or LIDAR is used, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent substitutes stereoscopic vision systems (dual cameras) or LIDAR range-finding systems with a single camera combined with computational estimate refinement. Instead of using multiple sensors to achieve precision, the system uses algorithmic processing to refine position estimates from monocular video, replacing complex sensor systems with a simpler computational approach.
Solution Approach 2:
The system creates a refined computational copy of the aircraft position through the estimate refiner, which generates improved position estimates from initial estimates. This computational copying and refinement process achieves measurement precision without requiring additional physical sensors, as the refined estimates serve as a enhanced representation of the true position.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Examples of the disclosure provide fuel receptacle position estimation for aerial refueling (derived from aircraft position estimation). A video stream comprising a plurality of video frames each showing an aircraft to be refueled, is received from a single camera. An initial position estimate is determined for the aircraft for the plurality of video frames, generating an estimated flight history for the aircraft. The estimated flight history for the aircraft is used to determine a temporally consistent refined position estimate, based on known aircraft flight path trajectories in an aerial refueling setting. The position of a fuel receptacle on the aircraft is determined, based on the refined position estimate for the aircraft, and an aerial refueling boom may be controlled to engage the fuel receptacle. Examples may use a deep learning neural network (NN) or optimization (e.g., bundle adjustment) to determine the refined position estimate from the estimated flight history.