Aircraft-Maintenance Robot Localization Using 3D Point Clouds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial robots face challenges in automating aircraft maintenance tasks, such as distinguishing aircraft from other objects and determining their position without prior knowledge, due to dynamic environments and varying aircraft configurations.
Innovation Solution
A robot equipped with odometry systems and 3D vision sensors, utilizing neural networks to generate and compare point cloud data to identify target aircraft, navigate, and perform tasks like fastener removal or installation, by distinguishing geometric features and updating its path in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional object detection methods are used, then the robot can detect objects in the enclosure, but the robot cannot distinguish the target aircraft from other objects without prior knowledge
Solution Approach 1:
The patent transitions from 2D image processing to 3D point cloud analysis using LiDAR data. By utilizing three-dimensional spatial information, the system can distinguish the target aircraft from other objects based on geometric features and spatial relationships, achieving accurate identification without prior knowledge of aircraft location or orientation.
Solution Approach 2:
The system changes the parameters used for object detection by incorporating multiple geometric features (distance, orientation, shape characteristics) from point cloud data. This multi-parameter approach enables the robot to identify the target aircraft by comparing observed geometric parameters against stored reference models, resolving the contradiction between detection capability and lack of prior information.
2Extent of automation
If the robot navigates to the target aircraft without prior knowledge of its position, then the robot can operate autonomously, but the navigation time and complexity increase
Solution Approach 1:
The system performs preliminary actions by pre-storing reference models of target aircraft with their geometric features and characteristics in a database. Before actual operation, these reference models are prepared and available for rapid comparison. This preliminary preparation enables the robot to quickly identify the target aircraft during autonomous navigation, reducing the time required to locate and reach the target.
Solution Approach 2:
The system implements feedback mechanisms where the robot continuously compares observed point cloud data against reference models during navigation. This real-time feedback allows the robot to adjust its search strategy and navigate more efficiently toward the target aircraft, balancing autonomous operation with reduced location time.
3Measurement precision
If the robot uses 3D vision sensors and neural networks to identify the target aircraft, then the robot can distinguish the target from other objects, but the computational complexity and processing time increase
Solution Approach 1:
The patent segments the complex identification task into distinct processing stages: point cloud acquisition, feature extraction, reference model comparison, and target identification. By dividing the computational workload into manageable segments, the system achieves high identification accuracy while managing computational complexity through structured processing pipelines.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables robots to autonomously locate and position themselves relative to aircraft in dynamic environments, improving efficiency and safety in maintenance operations by accurately identifying and interacting with specific aircraft despite changing conditions.
Implementation Method 1
a light detection and ranging (LiDAR) sensor configured to collect data representing the enclosure
Data Source
AI summary
Techniques for auto-locating and autonomous operation data storage are disclosed. An example method can include storing a representation of an aircraft in a data storage of the computing system. The representation and instructions for performing a first operation on the aircraft can be transmitted to a first robot. The first robot can be configured to identify the aircraft based on a first feature of the representation. The method can further include receiving sensor data. The method can further include transmitting the sensor data to an analysis service to identify a state of a part of the aircraft. The method can further include storing the analysis in the data storage. The method can further include generating second instructions for performing a second operation on the aircraft based on the analysis and the representation stored in the data storage.