AUTOMATIC FLIGHT CONTROL FOR UAV BASED SOLID MODELING

• US 20130317667A1
• Filed: 09/30/2010
• Published: 11/28/2013
• Est. Priority Date: 09/30/2010
• Status: Active Grant

• Current Assignee: Fury Technologies LLC (IP Edge LLC)
• Original Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Inventors: Kruglick, Ezekiel
• Granted Patent: US 8,965,598 B2
• Time in Patent Office: Days
• US Class Current: 701/2
• CPC Class Codes: B64C 19/00 Aircraft control not otherwise provided for
• CPC Class Codes: B64U 2101/30 for imaging, photography or videography
• CPC Class Codes: B64U 2201/10 autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS]
• CPC Class Codes: B64U 2201/20 Remote controls
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0094 involving pointing a payload, e.g. camera, weapon, sensor, towards a fixed or moving target
• CPC Class Codes: G05D 1/101 specially adapted for aircraft
• CPC Class Codes: G06T 17/05 Geographic models
• CPC Class Codes: G06T 17/10 Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
• CPC Class Codes: G06T 2210/21 Collision detection, intersection
• CPC Class Codes: G06T 2210/61 Scene description

Abstract

Technologies are generally described for controlling a flight path of a UAV based image capture system for solid modeling. Upon determining an initial movement path based on an estimate of a structure to be modeled, images of the structure to be modeled may be captured and surface hypotheses formed for unobserved surfaces based on the captured images. A normal vector and a viewing cone may be computed for each hypothesized surface. A set of desired locations may be determined based on the viewing cones for the entire structure to be modeled and a least impact path for the UAV determined based on the desired locations and desired flight parameters.

Claims

1. An automatic unmanned aerial vehicle (UAV) flight control system for solid modeling, the system comprising:

a UAV with an onboard camera;

a controller capable of communicating with a flight control module of the UAV, the controller configured to;

determine an initial movement path based on an estimate of a structure to be modeled;

capture images of the structure to be modeled;

form surface hypotheses for unobserved surfaces based on the captured images;

determine missing surface information from the surface hypotheses; and

determine a least impact path for the UAV based on the missing surface information and desired flight parameters.

2. The system according to claim 1, wherein the initial movement path is determined based on one of user definition and automatic estimation of an outline of the structure to be modeled.

3. The system according to claim 1, wherein the controller is further configured to determine a normal vector and a viewing cone for each surface with missing surface information.

4. The system according to claim 3, wherein the controller is further configured to determine a set of desired locations based on the viewing cones for the entire structure to be modeled.

5. The system according to claim 4, wherein the controller is further configured to determine a confidence interval associated with each viewing cone, the confidence interval defining one of a priority and/or a value of the UAV visiting the viewing cone.

6. The system according to claim 4, wherein the controller is further configured to determine the desired locations based on hypothesized surfaces for portions of the structure to be modeled that have not been captured yet.

7. The system according to claim 6, wherein the hypothesized surfaces are computed employing a Random Sample Consensus Surface Extraction (RANSAC) algorithm.

8. The system according to claim 1, wherein the desired flight parameters include one or more of a total flight time, available UAV power, a noise limitation, and/or a user defined restriction.

9. The system according to claim 1, wherein the controller is part of a remote computing device and is further configured to communicate with the flight control module of the UAV via wireless means.

10. A method for controlling a flight path of an unmanned aerial vehicle (UAV) based image capture system for solid modeling, the method comprising:

determining an initial movement path based on an estimate of a structure to be modeled;

capturing images of the structure to be modeled;

forming surface hypotheses for unobserved surfaces based on the captured images;

computing a normal vector and a viewing cone for each hypothesized surface;

determining a set of desired locations based on the viewing cones for the entire structure to be modeled; and

determining a least impact path for the UAV based on the desired locations and desired flight parameters.

11. The method according to claim 10, further comprising:

computing the viewing cone for each hypothesized surface using the normal vector and a view angle.

12. The method according to claim 11, wherein the view angle is dynamically determined as a goodness gradient based on the onboard camera'"'"'s optical capabilities, the UAV'"'"'s distance to the surface, and lighting conditions such that a goodness parameter for the flight path is optimized.

13. The method according to claim 12, wherein the goodness parameter is derived from a quality of data associated with unobserved surfaces of the structure to be modeled 102.

14. The method according to claim 12, further comprising:

optimizing the goodness parameter employing a multi-dimensional optimization of values algorithm on the goodness gradient and a cost function representing one or more of a total flight time, available UAV power, a noise limitation, and/or a user defined restriction for the UAV.

15. The method according to claim 14, wherein the optimization of values algorithm is one of a lazy optimization algorithm and a simulated annealing optimization algorithm.

16. The method according to claim 12, wherein the goodness gradient is computed once per travel path for each portion of the structure to be modeled.

17. A computer-readable storage medium having instructions stored thereon for controlling a flight path of an unmanned aerial vehicle (UAV) based image capture system for solid modeling, the instructions comprising:

determining an initial movement path based on an estimate of a structure to be modeled;

capturing images of the structure to be modeled;

guiding the flight path by;

forming surface hypotheses for unobserved surfaces based on the captured images;

computing a normal vector and a viewing cone for each hypothesized surface;

determining a set of desired locations based on the viewing cones for the entire structure to be modeled; and

determining a least impact path for the UAV based on the desired locations and one or more of a total flight time, available UAV power, a noise limitation, and/or a user defined restriction for the UAV.

18. The computer-readable storage medium according to claim 17, wherein the instructions further comprise:

dynamically computing a view angle for each viewing cone as a goodness gradient based on an onboard camera'"'"'s optical capabilities, the UAV'"'"'s distance to the surface, and lighting conditions such that a goodness parameter for the flight path representing a quality of captured images of the structure to be modeled is optimized.

19. The computer-readable storage medium according to claim 17, wherein the normal vector is determined using an average normal from lowest quality data gathered from the captured images.

20. The computer-readable storage medium according to claim 17, wherein the normal vector is determined for non-planar surfaces by breaking down surfaces that are previously identified as low quality from a single score into a Voronoi tessellation and assigning each region a similar score.

21. The computer-readable storage medium according to claim 20, wherein the instructions further comprise:

employing a largest area in a resulting Voronoi diagram with a score below a predefined threshold as the surface for normal vector generation; and

extending the determined normal vector to define the viewing cone based on an onboard camera'"'"'s optical capabilities, the UAV'"'"'s distance to the surface, and lighting conditions.