Aerial vehicle inspection path planning
AssigneeKespry Inc.
InventorRobert Parker Clark
Life of this patent
Estimating the term…
Abstract
Structure inspections are performed with a high resolution by first performing a modeling flight path at a relatively high altitude over the structure. Images are gathered during the modeling flight path and are used to generate a three dimensional model of the structure. From the three dimensional model a lower altitude closer inspection flight path is defined and executed.
Claims24
A method of gathering data with a single unmanned aerial vehicle comprising:
- executing first travel instructions with the single unmanned aerial vehicle to perform a first flight path of a first serpentine shape over a pre-defined geographic area containing at least one feature of interest, wherein at least a portion of the first flight path is at a first altitude;
- acquiring images of the at least one feature of interest with the single unmanned aerial vehicle while performing the first flight path;
- while the single unmanned aerial vehicle is in flight, creating a three dimensional model of the at least one feature of interest based on the images acquired by the single unmanned aerial vehicle while performing the first flight path;
- based at least in part on the three dimensional model, generating second travel instructions that define a second flight path of a second serpentine shape over at least a portion of the pre-defined geographic area by:
- determining heights of the at least one feature of interest in at least the portion of the pre-defined geographic area based on the three dimensional model;
- and
- determining respective second altitudes of the second flight path over at least the portion of the pre-defined geographic area, wherein at points along the second flight path, the respective second altitudes are lower than the first altitude and are higher than the heights of the at least one feature of interest;
- executing the second travel instructions with the single unmanned aerial vehicle to perform the second flight path;
- and
- acquiring additional images of the at least one feature of interest while performing the second flight path.
A system for gathering data regarding at least one feature of interest, the system comprising:
- a single unmanned aerial vehicle comprising an image acquisition device, one or more processors, memory circuitry, and one or more wireless transceivers;
- a base station comprising one or more processors, memory circuitry, and one or more wireless transceivers for communicating wirelessly to the single unmanned aerial vehicle during flight;
- a computing device comprising one or more processors, memory, and a user interface configured to receive input from a user of the system to define a two dimensional geographic area containing the at least one feature of interest for unmanned aerial vehicle operation;
- image processing software resident in the memory of one or more of the single unmanned aerial vehicle, base station, and computing device configured to receive images acquired during unmanned aerial vehicle operation and to generate a three dimensional model of the at least one feature of interest based on the images acquired as the single unmanned aerial vehicle performs a first flight path;
- travel instruction generation software resident in the memory of one or more of the single unmanned aerial vehicle, base station, and computing device configured to generate first travel instructions defining the first flight path of a first serpentine shape over the defined two dimensional area and to generate second travel instructions defining a second flight path of a second serpentine shape over at least a portion of the defined two dimensional area based at least in part on the generated three dimensional model, wherein the image acquisition device is configured to acquire additional images of the at least one feature of interest as the single unmanned aerial vehicle performs the second flight path, wherein generating the second travel instructions comprises:
- determining heights of the at least one feature of interest in at least the portion of the two dimensional area based on the three dimensional model;
- and
- determining respective second altitudes of the second flight path over at least the portion of the two dimensional area, wherein at points along the second flight path, the respective second altitudes are lower than the first altitude and are higher than the heights of the at least one feature of interest.
A method of inspecting a feature of interest with a single unmanned aerial vehicle, the method comprising:
- defining a two dimensional geographic area containing the feature of interest;
- defining a modeling flight path of a first serpentine shape within the defined geographic area, wherein the modeling flight path lies above the feature of interest at a first altitude;
- performing the defined modeling flight path with the single unmanned aerial vehicle and acquiring images of the feature of interest while performing the defined modeling flight path;
- responsive to the completion of the modeling flight path, creating a three dimensional model of the feature of interest based on the acquired images from the modeling flight path performed by the single unmanned aerial vehicle;
- responsive to the completion of the creation of the three dimensional model, defining an inspection flight path of a second serpentine shape based at least in part on the created three dimensional model by:
- determining heights of the feature of interest within the defined geographic area based on the three dimensional model;
- and
- determining respective second altitudes of the inspection flight path over the feature of interest, wherein at points along the inspection flight path, the respective second altitudes are lower than the first altitude and are higher than the heights of the feature of interest;
- and
- responsive to the completion of defining the inspection flight path, performing the inspection flight path with the single unmanned aerial vehicle and acquiring additional images of the feature of interest.
Dependencies are inferred from the claim text.