IP Library Granted Patent US 12,597,180
Granted Patent B2
US 12,597,180 · App. 18/645,254 · Granted Apr 7, 2026

Artificial intelligence augmentation of geographic data layers

Inventors: Mohammed Ismaeel Babur (Temple City, CA); Yury Sokolov (La Mesa, CA); Dihan Yang (Alhambra, CA)
Assignee: DP WORLD LOGISTICS US HOLDINGS, INC.
G06T11/203G06T7/13G06T11/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,597,180
App. No.
18/645,254
Granted
Apr 7, 2026
Kind
B2
Abstract

A method for gap filling geographic information service data includes determining a bounding region at or near an initial alignment. The method also includes determining the initial alignment within the bounding region. A corridor buffer is generated at or near the initial alignment, and within the bounding region. Cost layer data is processed. Incompleteness of a number of polygon-bounded areas is determined based on the cost layer data. Partial completeness of the polygon-bounded areas and completeness of the polygon-bounded areas are also determined based on the cost layer data. A synthetic completeness of the number of polygon-bounded areas is generated based on the incompleteness, the partial completeness, synthetic completeness, and completeness of the polygon-based areas. A rasterized cost map including the completeness and the synthetic completeness of the polygon-bounded areas is stored at the processor(s) and in memory(ies).

Claims (58)

1 . A method for gap filling of geographic information service (“GIS”) data, the method comprising:

determining, at at least one processor, a bounding region at or near an initial alignment;

determining, at the at least one processor, the initial alignment within the bounding region;

generating, at the at least one processor, a corridor buffer at or near the initial alignment and within the bounding region;

processing, at the at least one processor, cost layer data;

determining, at the at least one processor and based on the cost layer data, incompleteness of a plurality of polygon-bounded areas;

determining, at the at least one processor and based on the cost layer data, partial completeness of the plurality of polygon-bounded areas;

determining, at the at least one processor and based on the cost layer data, completeness of the plurality of polygon-bounded areas;

generating, at the at least one processor and based on the incompleteness, the partial completeness, synthetic completeness, and the completeness of the plurality of polygon-based areas, the synthetic completeness of the plurality of polygon-bounded areas; and

storing, at the at least one processor and in at least one memory, a rasterized cost map including the completeness and the synthetic completeness of the plurality of polygon-bounded areas.

2 . The method of claim 1 , in which the generating of the synthetic completeness is based on the completeness of the plurality of polygon-bounded areas, the synthetic completeness of the plurality of polygon-bounded areas, the partial completeness of the plurality of polygon-bounded areas, or a combination thereof.

3 . The method of claim 1 , further comprising communicating, at the at least one processor and from the at least one memory, the rasterized cost map to a one dimensional (1-D) optimizer, the 1-D optimizer being configured to optimize a profile of the initial alignment based on the completeness and synthetic completeness of the plurality of polygon-bounded areas.

4 . The method of claim 1 , in which the generating the corridor buffer is based on a point distribution.

5 . The method of claim 1 , in which the rasterized cost map comprises a two dimensional (2-D) plurality of values associated with costs to traverse.

6 . An apparatus for gap filling of geographic information service (“GIS”) data, the apparatus comprising:

at least one memory; and

at least one processor coupled to the at least one memory, the at least one processor configured:

to determine a bounding region at or near an initial alignment;

to determine the initial alignment within the bounding region;

to generate a corridor buffer at or near the initial alignment and within the bounding region;

to process cost layer data;

to determine based on the cost layer data, incompleteness of a plurality of polygon-bounded areas;

to determine, based on the cost layer data, partial completeness of the plurality of polygon-bounded areas;

to determine, based on the cost layer data, completeness of the plurality of polygon-bounded areas;

to generate, based on the incompleteness, the partial completeness, synthetic completeness, and the completeness of the plurality of polygon-based areas, the synthetic completeness of the plurality of polygon-bounded areas; and

to store in the at least one memory, a rasterized cost map, the rasterized cost map including the completeness and the synthetic completeness of the plurality of polygon-bounded areas.

7 . The apparatus of claim 6 , in which the at least one processor is further configured to generate the synthetic completeness based on the completeness of the plurality of polygon-bounded areas, the synthetic completeness of the plurality of polygon-bounded areas, the partial completeness of the plurality of polygon-bounded areas, or a combination thereof.

8 . The apparatus of claim 6 , in which the at least one processor is further configured to communicate, from the at least one memory, the rasterized cost map to a one dimensional (1-D) optimizer, the 1-D optimizer being configured to optimize a profile of the initial alignment based on the completeness and synthetic completeness of the plurality of polygon-bounded areas.

9 . The apparatus of claim 6 , in which the at least one processor is further configured to generate the corridor buffer is based on a point distribution.

10 . The apparatus of claim 6 , in which the rasterized cost map comprises a two dimensional (2-D) plurality of values associated with costs to traverse.

11 . A non-transitory computer-readable medium having program code recorded thereon, the program code executed by at least one processor and comprising:

program code to determine a bounding region, the bounding region being at or near an initial alignment;

program code to determine the initial alignment, the initial alignment being within the bounding region;

program code to generate a corridor buffer, the corridor buffer being at or near the initial alignment, the corridor buffer further being within the bounding region;

program code to process cost layer data;

program code to determine based on the cost layer data, incompleteness of a plurality of polygon-bounded areas;

program code to determine based on the cost layer data, partial completeness of the plurality of polygon-bounded areas;

program code to determine based on the cost layer data, completeness of the plurality of polygon-bounded areas;

program code to generate based on the incompleteness, the partial completeness, synthetic completeness, and the completeness of the plurality of polygon-based areas, the synthetic completeness of the plurality of polygon-bounded areas; and

program code to store, at the at least one processor and in at least one memory, a rasterized cost map, the rasterized cost map including the completeness and the synthetic completeness of the plurality of polygon-bounded areas.

12 . The non-transitory computer-readable medium of claim 11 , in which the program code comprises program code to generate the synthetic completeness based on the completeness of the plurality of polygon-bounded areas, the synthetic completeness of the plurality of polygon-bounded areas, the partial completeness of the plurality of polygon-bounded areas, or a combination thereof.

13 . The non-transitory computer-readable medium of claim 11 , in which the program code comprises program code to communicate, at the at least one processor and from the at least one memory, the rasterized cost map to a 1-D optimizer, the 1-D optimizer being configured to optimize a profile of the initial alignment based on the completeness and synthetic completeness of the plurality of polygon-bounded areas.

14 . The non-transitory computer-readable medium of claim 11 , in which the program code to generate the corridor buffer is based on a point distribution.

15 . The non-transitory computer-readable medium of claim 11 , in which the rasterized cost map comprises a two dimensional (2-D) plurality of values associated with costs to traverse.

16 . An apparatus for gap filling of geographic information service (“GIS”) data, comprising:

means for determining, at at least one processor, a bounding region at or near an initial alignment;

means for determining, at the at least one processor, the initial alignment within the bounding region;

means for generating, at the at least one processor, a corridor buffer at or near the initial alignment and within the bounding region;

means for processing, at the at least one processor, cost layer data;

means for determining, at the at least one processor and based on the cost layer data, incompleteness of a plurality of polygon-bounded areas;

means for determining, at the at least one processor and based on the cost layer data, partial completeness of the plurality of polygon-bounded areas;

means for determining, at the at least one processor and based on the cost layer data, completeness of the plurality of polygon-bounded areas;

means for generating, at the at least one processor and based on the incompleteness, the partial completeness, synthetic completeness, and the completeness of the plurality of polygon-based areas, the synthetic completeness of the plurality of polygon-bounded areas; and

means for storing, at the at least one processor and in at least one memory, a rasterized cost map, the rasterized cost map including the completeness and the synthetic completeness of the plurality of polygon-bounded areas.

17 . The apparatus of claim 16 , further comprising means for generating the synthetic completeness, at the at least one processor, based on the completeness of the plurality of polygon-bounded areas, the synthetic completeness of the plurality of polygon-bounded areas, the partial completeness of the plurality of polygon-bounded areas, or a combination thereof.

18 . The apparatus of claim 16 , further comprising means for communicating, at the at least one processor and from the at least one memory, the rasterized cost map to a one dimensional (1-D) optimizer, the 1-D optimizer being configured to optimize a profile of the initial alignment based on the completeness and synthetic completeness of the plurality of polygon-bounded areas.

19 . The apparatus of claim 16 , in which the means for generating the corridor buffer is based on a point distribution.

20 . The apparatus of claim 16 , in which the rasterized cost map comprises a two dimensional (2-D) plurality of values associated with costs to traverse.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 19, 2025
From: BABUR, MOHAMMED ISMAEEL; SOKOLOV, YURY; YANG, DIHAN
To: HYPERLOOP TECHNOLOGIES, INC.
Reel/Frame 072963/0764 →
CHANGE OF NAME Recorded Aug 29, 2025
From: HYPERLOOP TECHNOLOGIES, INC.
To: DP WORLD LOGISTICS US HOLDINGS, INC.
Reel/Frame 072757/0363 →
Continuity (2)
Provisional Application 63462925 · Apr 28, 2023
Related Publication 20240362836A1 · Oct 31, 2024
References Cited (21)
US 9411898B1 · Ward · 2016 [cited by applicant]
US 10593074B1 · Friedman · 2020 [cited by examiner]
US 12229712B1 · Merchan et al. · 2025 [cited by applicant]
US 20060242108A1 · Cuspard et al. · 2006 [cited by applicant]
US 20120274642A1 · Ofek et al. · 2012 [cited by applicant]
US 20120320089A1 · Kreft · 2012 [cited by examiner]
US 20150154323A1 · Koch et al. · 2015 [cited by applicant]
US 20170329875A1 · Detwiler et al. · 2017 [cited by applicant]
US 20190164313A1 · Ma et al. · 2019 [cited by applicant]
US 20220341752A1 · Broadway et al. · 2022 [cited by applicant]
US 20230154316A1 · Najar-Robles et al. · 2023 [cited by applicant]
US 20240362374A1 · Babur et al. · 2024 [cited by applicant]
US 20240362375A1 · Babur et al. · 2024 [cited by applicant]
US 20240362837A1 · Babur et al. · 2024 [cited by applicant]
US 20240362841A1 · Babur et al. · 2024 [cited by applicant]
Wenwen Li et al., GeoAI for Large Scale Image Analysis and Machine Vision: Recent Progress of Artificial Intelligence in Geography, ISPRS International Journal of Geo-Information, 2022, 11(7), 385, Jul. 2022, pp. 1-44. [cited by examiner]
ArcGISPro_2.6, “Edit elevation pixels” and “Pixelate a confidential region,” 2020 (Year: 2020). [cited by applicant]
Climate Data Tools, 2019 https://iri.columbia.edu/-rijaf/CDTUserGuide/index.html, IRI International Research Institute for Climate and Society (Year: 2019). [cited by applicant]
Grass Gis, “Grass Gis manual: r.fill.gaps”, 2017 (Year: 2017). [cited by applicant]
Q. Tang and W. Dou, “A fast shortest path method based on multi-resolution raster model,” 2020 19th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES), pp. 25… [cited by applicant]
Yonetani et al. “Path Planning using Neural A* Search”, Proceedings of the 38 th International Conference on Machine Learning, PMLR 139, 2021 (Year: 2021). [cited by applicant]