Unmanned vehicle navigation, and associated methods, systems, and computer-readable medium

Patent metadata

Field	Value
Publication number	US-2022383541-A1
Application number	US-202017755878-A
Country	US
Kind code	A1
Filing date	Nov 13, 2020
Priority date	Nov 13, 2019
Publication date	Dec 1, 2022
Grant date	—

Abstract

Various embodiments relate to unmanned vehicle navigation. A navigation system may include one or more processors configured to communicatively couple with an unmanned vehicle. The one or more processors may be configured to receive an image from the unmanned vehicle and detect a feature within the image. The one or more processors may be further be configured to determine a location of the unmanned vehicle based on the feature and convey one or more commands to the unmanned vehicle based on the location of the unmanned vehicle. Associated methods and computer-readable medium are also disclosed.

First claim

1 . A navigation system, comprising:
one or more processors configured to communicatively couple with an unmanned vehicle positioned within or proximate to an environment, the one or more processors further configured to: receive an image from the unmanned vehicle; detect one or more features of a number of features inserted into the environment and depicted within the image; determine a location of the unmanned vehicle based on the one or more features; and convey one or more commands to the unmanned vehicle based on the location of the unmanned vehicle.

2 . The navigation system of claim 1 , further comprising a first module including at least one processor of the one or more processors, the first module configured to:
receive the image from the unmanned vehicle; detect the one or more features within the image; generate a bounding box around at least one feature of the one or more features; and decode information stored in the at least one feature.

3 . The navigation system of claim 2 , wherein the first module includes at least one of a deep learning module and a machine learning module configured to receive the image, identify the one or more features, and generate the bounding box around the at least one feature.

4 . The navigation system of claim 2 , wherein the one or more processors are further configured to crop and/or resize the bounding box in response to dimensions of the image exceeding a predetermined maximum size.

5 . The navigation system of claim 2 , where in the one or more processors are further configured to filter the image.

6 . The navigation system of claim 2 , further comprising a second module including at least one processor of the one or more processors, the second module configured to:
receive the at least one feature including the bounding box; and determine the location of the unmanned vehicle relative to the at least one feature based on a view of the at least one feature.

7 . The navigation system of claim 6 , wherein the second module is further configured to determine a number of view angles and a relative distance between the unmanned vehicle and known location of the one or more features to determine the location of the unmanned vehicle.

8 . The navigation system of claim 6 , further comprising a third module including at least one processor of the one or more processors, the third module configured to:
receive the location of the unmanned vehicle; and generate the one or more commands to be conveyed to the unmanned vehicle based on a difference between the location of the unmanned vehicle and a desired location of the unmanned vehicle.

9 . The navigation system of claim 1 , wherein each feature of the number of features comprise either a quick response (QR) code or a bar code.

10 . The navigation system of claim 1 , further comprising the unmanned vehicle including a camera configured to capture the image.

11 . A method, comprising:
positioning a number of features within an environment; receiving an image from a vehicle positioned in or proximate to the environment; detecting at least one feature of the number of features within the image; determining a location of the vehicle based on the at least one feature; and conveying one or more commands to the vehicle based on the location of the vehicle.

12 . The method of claim 11 , further comprising decoding the at least one feature to determine a location of the at least one feature.

13 . The method of claim 12 , wherein determining the location of the vehicle comprises determining the location of the vehicle relative to the location of the at least one feature.

14 . The method of claim 11 , wherein determining the location of the vehicle comprises determining one or more angles between the vehicle and the at least one feature within the image and a relative distance between the vehicle and the location of the at least one feature to determine the location of the vehicle.

15 . The method of claim 11 , further comprising generating a bounding box around the at least one feature in response to detecting the at least one feature.

16 . The method of claim 11 , wherein determining the location comprises determining the location based on two or more features in the image.

17 . The method of claim 11 , wherein determining the location of the vehicle based on the at least one feature comprises comparing known dimensions and a shape of a feature to the at least one feature within the image.

18 . The method of claim 11 , wherein conveying the one or more commands comprises conveying one or more of a roll input, a pitch input, a yaw input, and a throttle input to the vehicle based on the location of the vehicle.

19 . The method of claim 11 , wherein detecting the at least one feature within the image comprises detecting the at least one feature via at least one of a brightness, a shape, a size, and an orientation of the at least one feature.

20 . The method of claim 11 , further comprising controlling the vehicle via one or more navigation techniques selected from the group consisting of one or more of:
simultaneous localization and mapping (SLAM), target tracking, and global positioning.

21 . A non-transitory computer-readable medium including computer-executable instructions that, when executed, perform acts comprising:
detecting at least one feature within an image captured via a vehicle; decoding information stored in the at least one feature; determining a location of the vehicle relative to the at least one feature; and conveying one or more control signals to the vehicle based on the location of the vehicle and the information stored in the at least one feature.

22 . The non-transitory computer-readable medium of claim 21 , wherein detecting the at least one feature comprises detecting the at least one feature via at least one artificial neural network.

23 . The non-transitory computer-readable medium of claim 21 , wherein determining the location of the vehicle relative to the at least one feature comprises measuring a distortion of the at least one feature within the image to determine one or more rotations of the at least one feature relative to the vehicle and a relative distance between the vehicle and the location of the at least one feature.

24 . The non-transitory computer-readable medium of claim 21 , wherein detecting the at least one feature within the image comprises:
applying a binary threshold to a number of pixels of the image; filtering the image, via a number of filters, to generate a set of images; detecting shapes in each image of the set of images; identifying regions of interests in each image of the set of images; generating a heatmap based on regions of interests in each image of the set of images; applying a threshold to the heatmap to create a binary image including potential feature areas; and detecting the at least one feature based on the binary image.

25 . The non-transitory computer-readable medium of claim 21 , wherein conveying the one or more control signals comprises conveying the one or more controls signal to control at least one of a roll motion, a pitch motion, a yaw motion, and a thrust of the vehicle in a number of directions based on the location of the vehicle and the information stored in the at least one feature.

Assignees

• Battelle Energy Alliance Llc

Inventors

• Al Rashdan Ahmad Y
• Wheeler Michael L
• Lew Roger
• Roberson Dakota
• Griffel Lloyd M
• Boza Roger
• Thompson Michael W

Classifications

• G06T7/50

  Depth or shape recovery · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06K7/1417

  2D bar codes · CPC title

• G06T2207/30204

  Marker · CPC title

• G06T2207/10032

  Satellite or aerial image; Remote sensing · CPC title