Aircraft-Relative Robot Positioning Using 3D Geometric Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial robots face challenges in automating aircraft maintenance tasks, such as distinguishing between aircraft and other objects in a hangar and navigating to a specific aircraft without prior knowledge of its location, due to the dynamic nature of aircraft movement and varying environments.
Innovation Solution
A robot equipped with odometry systems and 3D vision sensors, utilizing neural networks to generate and process point cloud data for identifying target aircraft by comparing geometric features with reference models, allowing it to autonomously locate and position itself for tasks like fastener installation, removal, and replacement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional object detection methods are used, then the robot can detect objects in the hangar, but it cannot distinguish the target aircraft from other objects without prior knowledge
Solution Approach 1:
The system performs preliminary scanning of the hangar environment to generate a point cloud representation before aircraft arrival. This pre-established spatial framework allows the robot to quickly identify and track the target aircraft when it enters, eliminating the need for prior knowledge of aircraft location while maintaining high identification accuracy.
Solution Approach 2:
The patent replaces conventional mechanical object detection methods with a point cloud-based vision system. By using 3D spatial data and geometric feature matching, the system achieves precise aircraft identification without relying on pre-programmed location information or traditional sensor arrays.
2Adaptability or versatility
If the robot navigates to the target aircraft without prior knowledge, then it can adapt to dynamic aircraft movement, but it increases the complexity of navigation and positioning
Solution Approach 1:
The robot performs self-localization by continuously matching observed geometric features of the aircraft with its internal point cloud model. This self-service positioning approach eliminates the need for complex external guidance systems or pre-configured navigation paths, allowing the robot to adapt to dynamic aircraft movement while maintaining manageable system complexity.
Solution Approach 2:
The system transitions from 2D image processing to 3D point cloud analysis, adding spatial depth information. This dimensional enhancement provides more robust geometric features for aircraft identification and navigation, enabling the robot to handle dynamic environments more effectively without proportionally increasing system complexity.
3Measurement precision
If the robot uses 3D vision sensors and neural networks to identify aircraft, then it can accurately locate the target aircraft, but it increases the computational requirements and processing time
Solution Approach 1:
The system extracts and focuses on key geometric features from the complete point cloud data, such as wing shapes, fuselage contours, and tail configurations. By processing only these discriminative features rather than the entire point cloud, the system maintains high location accuracy while significantly reducing computational burden and processing time.
Solution Approach 2:
The neural network performs partial processing by initially identifying coarse aircraft features and then progressively refining the location estimate. This staged approach processes less data in each step compared to exhaustive analysis, achieving accurate aircraft localization with reduced overall processing time and computational resources.
Data Source
AI summary
Techniques for auto-locating and positioning relative to an aircraft are disclosed. An example method can include a robot receiving a multi-dimensional representation of an enclosure that includes a candidate target aircraft. The robot can extract a geometric feature from the multi-dimensional representation associated with the candidate target aircraft. The robot can compare the geometric feature of the candidate target aircraft with a second geometric feature from a reference model of a target aircraft. The robot can determine whether the candidate target aircraft is the target aircraft based on the comparison. The robot can calculate a path from a location of the robot to the target aircraft based on the determination. The robot can traverse the path from the location to the target aircraft based on the calculation.