Granted Patent B2

US 12,386,068 · App. 17/991,695 · Granted Aug 12, 2025

Inventors: Geoffrey Michael Douglass (West Palm Beach, FL); John Rogers Houston (Weston, MA); Allen Edward Flick (Pittsburgh, PA); Damon Allen Wolfe (Hartwell, GA)

Assignee: Mythos AI Inc

G01S15/8902B63B79/40G01C13/00G01S7/52003G05D1/0206B63B2211/02

Abstract

Claims (57)

1. An apparatus for artificial intelligence (AI) bathymetry, the apparatus comprising:

at least a computing device, wherein the at least a computing device is configured to:

create a map comprising a plurality of bathymetric survey areas, wherein creating the map comprises receiving at least a bathymetric image from an image processing module communicatively connected to a sonic unit;

select a bathymetric survey area from the plurality of bathymetric survey areas as a function of at least a frequency of mapping;

generate a path datum as a function of the selected bathymetric survey area and a survey resolution, wherein determining the path datum further comprises detecting one or more gaps in the at least a bathymetric image, wherein detecting the one or more gaps comprises:

receiving training data, wherein the training data correlates portions of bathymetric images with identifications of gaps; and

training a neural network using the training data, wherein the neural network comprises an input layer of nodes, one or more intermediate layers of nodes and an output layer of nodes, and wherein training the neural network comprises:

creating connections between the nodes by applying elements of the training data to the input layer of nodes; and

using a training algorithm to adjust the connections and weights between nodes in adjacent layers of the neural network to produce outputs at the output layer of nodes;

transmit the path datum to an autonomous navigation module installed on a boat; and

control navigation of the boat, using the autonomous navigation module, by determining a heading for the boat as a function of the path datum.

2. The apparatus of claim 1 , wherein the at least a computing device is further configured to determine the survey resolution as a function of an average depth of an area to be traversed.

3. The apparatus of claim 1 , wherein the at least a computing device is further configured to:

receive a plurality of bathymetric data from the at least a communication module; and

determine the survey resolution as a function of survey criteria, wherein the survey criteria comprise at least an error rate of the plurality of bathymetric data.

4. The apparatus of claim 3 , wherein the at least a computing device is further configured to determine the survey resolution, wherein determining the survey resolution comprises:

training a machine-learning model using training data, wherein the training data comprises past survey criteria correlated to past selections for survey resolution; and

determining the survey resolution using the machine-learning model, wherein the machine-learning model is configured to receive survey criteria as input and output the survey resolution.

5. The apparatus of claim 1 , wherein generating the path datum comprises determining a traversal path as a function of a desired traversal direction.

6. The apparatus of claim 5 , wherein:

determining the traversal path comprises determining the traversal path as a function of the one or more gaps, wherein the traversal path traverses at least a portion of the one or more gaps.

7. The apparatus of claim 6 , wherein detecting the one or more gaps comprises detecting the one or more gaps using a fast Fourier transform.

8. The apparatus of claim 1 , wherein the at least a computing device is further configured to:

select a survey map corresponding to the bathymetric survey area; and

transmit the survey map to the autonomous navigation module.

9. The apparatus of claim 1 , wherein the at least a computing device is further configured to determine the frequency of mapping as a function of historical data of a shipping channel.

10. The apparatus of claim 1 , wherein the at least a computing device is further configured to:

receive an identified underwater landmark from the at least a communication module; and

register the bathymetric image to a map location as a function of the underwater landmark.

11. A method for artificial intelligence (AI) bathymetry, the method comprising:

creating, by at least a computing device, a map comprising a plurality of bathymetric survey areas, wherein creating the map comprises receiving at least a bathymetric image from an image processing module communicatively connected to a sonic unit;

selecting, by the at least a computing device, a bathymetric survey area from the plurality of bathymetric survey areas as a function of at least a frequency of mapping;

generating, by the at least a computing device, a path datum as a function of the selected bathymetric survey area and a survey resolution, wherein determining the path datum further comprises detecting one or more gaps in the at least a bathymetric image, wherein detecting the one or more gaps comprises:

receiving training data, wherein the training data correlates portions of bathymetric images with identifications of gaps; and

training a neural network using the training data, wherein the neural network comprises an input layer of nodes, one or more intermediate layers of nodes and an output layer of nodes, and wherein training the neural network comprises:

creating connections between the nodes by applying elements of the training data to the input layer of nodes; and

using a training algorithm to adjust the connections and weights between nodes in adjacent layers of the neural network to produce outputs at the output layer of nodes;

transmitting, by the at least a computing device, the path datum to an autonomous navigation module installed on a boat; and

controlling, by the autonomous navigation module, navigation of the boat by determining a heading for the boat as a function of the path datum.

12. The method of claim 11 , further comprising determining, by the at least a computing device, the survey resolution as a function of an average depth of an area to be traversed.

13. The method of claim 11 , further comprising:

receiving, by the at least a computing device, a plurality of bathymetric data from the at least a communication module; and

determining, by the at least a computing device, the survey resolution as a function of survey criteria, wherein the survey criteria comprise at least an error rate of the plurality of bathymetric data.

14. The method of claim 13 , further comprising determining, by the at least a computing device, the survey resolution, wherein determining the survey resolution comprises:

training a machine-learning model using training data, wherein the training data comprises past survey criteria correlated to past selections for survey resolution; and

determining the survey resolution using the machine-learning model, wherein the machine-learning model is configured to receive survey criteria as input and output the survey resolution.

15. The method of claim 11 , wherein generating the path datum comprises determining a traversal path as a function of a desired traversal direction.

16. The method of claim 15 , wherein:

determining the traversal path comprises determining the traversal path as a function of the one or more gaps, wherein the traversal path traverses at least a portion of the one or more gaps.

17. The method of claim 16 , wherein detecting the one or more gaps comprises detecting the one or more gaps using a fast Fourier transform.

18. The method of claim 11 , further comprising:

selecting, by the at least a computing device, a map corresponding to the bathymetric survey area; and

transmitting, by the at least a computing device, the map to the autonomous navigation module.

19. The method of claim 11 , further comprising determining, by the at least a computing device, the frequency of mapping as a function of historical data of a shipping channel.

20. The method of claim 11 , further comprising:

receiving, by the at least a computing device, an identified underwater landmark from the at least a communication module; and

registering, by the at least a computing device, the bathymetric image to a map location as a function of the underwater landmark.

Assignments (1)

Continuity (2)

References Cited (20)