Inspection Device 3D Mapping for GPS-Denied Structural Faults
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing inspection methods for buildings and structures, such as those in the nuclear, oil, and gas industries, face challenges in accurately determining the location of faults within structures without external GPS signals, particularly in underground or occluded environments, leading to inefficiencies and safety risks for manual inspections.
Innovation Solution
A method utilizing an inspection device equipped with depth sensors and a Simultaneous Localization and Mapping (SLAM) algorithm, combined with a Normal Distribution Transform (NDT) scan matching algorithm, to create a 3D map of the surroundings and determine the device's position, allowing for precise geo-tagging of inspection data without relying on external GPS.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS signals are used to monitor drone position, then the drone's location can be tracked, but GPS signals are unavailable in underground or occluded environments
Solution Approach 1:
The patent introduces depth sensors as an intermediary to capture 3D spatial data of the environment, which then serves as the basis for determining position through SLAM algorithms, replacing the direct GPS-based positioning method that fails in occluded environments
Solution Approach 2:
The patent replaces the GPS satellite-based electromagnetic signal system with a local 3D mapping and localization system using depth sensors and SLAM algorithms, enabling positioning through environmental feature recognition rather than external signal reception
2Reliability
If manual inspection with scaffolding is used, then personnel can directly observe structural flaws, but it is costly, time-consuming, and exposes workers to injury risk
Solution Approach 1:
The inspection device performs self-positioning and self-mapping using its onboard depth sensors and SLAM algorithms, automatically determining its location and creating 3D maps without requiring external positioning infrastructure or manual intervention for location tracking
Solution Approach 2:
The patent replaces manual visual inspection with an automated drone-based inspection system that uses depth sensors, 3D mapping, and image processing to detect structural flaws, eliminating the need for personnel to physically access hazardous areas
3Area of stationary object
If a large number of images are collected by the drone, then comprehensive coverage is achieved, but it becomes difficult to determine which part of the structure each image corresponds to
Solution Approach 1:
The patent implements a feedback mechanism where the SLAM algorithm continuously updates the drone's position estimate based on newly captured 3D data, and this position information is then used to geotag images with their corresponding locations in the 3D map, creating a closed-loop system that maintains spatial context throughout the inspection
Solution Approach 2:
The patent discards the reliance on GPS coordinate systems in favor of a local 3D map-based coordinate system, recovering spatial context information through environmental feature matching and 3D point cloud registration instead of external satellite positioning
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 accurate and efficient identification of structural faults within buildings and structures, reducing the need for manual inspections and enhancing safety by providing precise location data of defects in real-time, even in GPS-denied environments.
Implementation Method 1
one or more depth sensors for capturing sets of 3D data of the device's surroundings at respective points in time, each set of 3D data comprising information indicating a distance of the device from one or more surfaces
Data Source
AI summary
A method for processing data captured by an inspection device during inspection of a building or structure, the method comprising:receiving sets of inspection data captured by one or more inspection sensors onboard the inspection device, each set of inspection data being captured from a different region of the building or structure and being suitable for evaluating the condition of the building or structure in the respective region, each set of inspection data being captured at a respective point in time as the inspection device maneuvers relative to the building or structure;receiving sets of 3D data of the inspection device's surroundings, each set of 3D data being captured by one or more depth sensors onboard the inspection device at a respective point in time, wherein each set of 3D data comprises information indicating a distance of the device from one or more surfaces of the building or structure at the time of capture of the set of 3D data;combining the sets of 3D data to obtain a 3D map of the device's surroundings when carrying out the inspection; andoutputting data indicating, for each set of inspection data, a position of the device in the 3D map at which the set of inspection data was captured.