IP Library › Granted Patent US 12,613,534
Granted Patent B2
US 12,613,534 · App. 18/525,514 · Granted Apr 28, 2026

Methods and systems for jobsite creation

Inventors: Nicholas Hanauer (Washington, IL); Chad Brickner (Dunlap, IL); Manaswini Nama (Dunlap, IL); Bradley Bomer (Perkin, IL); Rajesh Ramamoorthy (Tamil Nadu, IN); Gowtham Krishnan (Tamil Nadu, IN); Mugesh Ganesh (Tamil Nadu, IN)
Assignee: Caterpillar Inc.
G05D1/648G05D2101/15G05D2107/70
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 12,613,534
App. No.
18/525,514
Granted
Apr 28, 2026
Kind
B2
Abstract

A technique is directed to methods and systems for creating digital representations jobsites. The jobsite creation system can collect machine data, such as location data, from machines in a worksite and determine the role, such as loading, hauling, drilling, etc. of each machine in the worksite. The machines are grouped together and organized based on which machines operate in a geographic region together. The jobsite creation system generates a digital representation of a jobsite with a site boundary based on the machine groupings. A user can view the jobsite on a user interface to monitor the operation of the machines and track productivity and utilization data for the machines in the jobsite.

Claims (65)

1 . A computing system comprising:

at least one processor; and

at least one memory storing instructions that, when executed by the at least one processor, cause the computing system to perform a process for generating digital representations of jobsites, the process comprising:

receiving location data from one or more devices associated with a plurality of machines operating in a jobsite;

identifying locations of the plurality of machines operating in the jobsite based upon the location data;

organizing at least two machines of the plurality of machines into at least one group of machines;

determining a centroid of the jobsite based on the locations of the plurality of machines and the at least one group of machines;

determining a dynamic boundary of the jobsite based on the locations of the plurality of machines relative to the centroid, wherein the dynamic boundary of the jobsite changes as the locations of the plurality of machines move during operations;

generating, using a machine learning module, a digital representation of the jobsite that illustrates the locations of the plurality of machines in real-time within the dynamic boundary and the at least one group of machines; and

displaying, via a user interface, the digital representation of the jobsite.

2 . The computing system of claim 1 , wherein the process further comprises:

receiving machine data from devices mounted on the plurality of machines; and

determining the locations of the plurality of machines based on the machine data.

3 . The computing system of claim 1 , wherein the process further comprises:

determining at least one movement pattern of at least one machine of the plurality of machines based on the locations;

determining a role assignment of the at least one machine based on the at least one movement pattern; and

tagging the at least one machine with the role assignment.

4 . The computing system of claim 1 , wherein the process further comprises:

organizing the at least two machines into the at least one group of machines based on machine type, location, or role assignment of the at least two machines.

5 . The computing system of claim 1 , wherein the process further comprises:

displaying the digital representation of the jobsite in a user interface; and

receiving, via the user interface, one or more edits to the digital representation of the jobsite.

6 . The computing system of claim 1 , wherein the digital representation of the jobsite is generated by at least one machine-learning algorithm, wherein the at least one machine-learning algorithm is trained based on at least one dataset associated with previously generated digital representations of jobsites.

7 . A method for generating digital representations of jobsites, the method comprising:

receiving location data from one or more devices associated with a plurality of machines operating in a jobsite;

identifying locations of the plurality of machines operating in the jobsite based upon the location data;

organizing at least two machines of the plurality of machines into at least one group of machines;

determining a centroid of the jobsite based on the locations of the plurality of machines and the at least one group of machines;

determining a dynamic boundary of the jobsite based on the locations of the plurality of machines relative to the centroid, wherein the dynamic boundary of the jobsite changes as the locations of the plurality of machines move during operations;

generating, using a machine learning module, a digital representation of the jobsite that illustrates the locations of the plurality of machines in real-time within the dynamic boundary and the at least one group of machines; and

displaying via a user interface, the digital representation of the jobsite.

8 . The method of claim 7 , further comprising:

receiving machine data from devices mounted on the plurality of machines; and

determining the locations of the plurality of machines based on the machine data.

9 . The method of claim 7 , further comprising:

determining at least one movement pattern of at least one machine of the plurality of machines based on the locations;

determining a role assignment of the at least one machine based on the at least one movement pattern; and

tagging the at least one machine with the role assignment.

10 . The method of claim 7 , further comprising:

organizing the at least two machines into the at least one group of machines based on machine type, location, or role assignment of the at least two machines.

11 . The method of claim 7 , further comprising:

displaying the digital representation of the jobsite in a user interface; and

receiving, via the user interface, one or more edits to the digital representation of the jobsite.

12 . The method of claim 7 , wherein the digital representation of the jobsite is generated by at least one machine-learning algorithm, wherein the at least one machine-learning algorithm is trained based on at least one dataset associated with previously generated digital representations of jobsites.

13 . A non-transitory computer-readable storage medium comprising: a set of instructions that, when executed by at least one processor, causes the at least one processor to perform operations for generating digital representations of jobsites, the operations comprising:

receiving location data from one or more devices associated with a plurality of machines operating in a jobsite;

identifying locations of the plurality of machines operating in the jobsite based upon the location data;

organizing at least two machines of the plurality of machines into at least one group of machines;

determining a centroid of the jobsite based on the locations of the plurality of machines and the at least one group of machines;

determining a dynamic boundary of the jobsite based on the locations of the plurality of machines relative to the centroid, wherein the dynamic boundary of the jobsite changes as the locations of the plurality of machines move during operations;

generating, using a machine learning module, a digital representation of the jobsite that illustrates the locations of the plurality of machines in real-time within the dynamic boundary and the at least one group of machines; and

displaying, via a user interface, the digital representation of the jobsite.

14 . The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprise:

receiving machine data from devices mounted on the plurality of machines; and

determining the locations of the plurality of machines based on the machine data.

15 . The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprise:

determining at least one movement pattern of at least one machine of the plurality of machines based on the locations;

determining a role assignment of the at least one machine based on the at least one movement pattern; and

tagging the at least one machine with the role assignment.

16 . The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprise:

organizing the at least two machines into the at least one group of machines based on machine type, location, or role assignment of the at least two machines.

17 . The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprise:

displaying the digital representation of the jobsite in a user interface; and

receiving, via the user interface, one or more edits to the digital representation of the jobsite.

18 . The non-transitory computer-readable storage medium of claim 13 , wherein the digital representation of the jobsite is generated by at least one machine-learning algorithm, wherein the at least one machine-learning algorithm is trained based on at least one dataset associated with previously generated digital representations of jobsites.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 30, 2023
From: HANAUER, NICHOLAS; BRICKNER, CHAD; NAMA, MANASWINI; BOMER, BRADLEY; RAMAMOORTHY, RAJESH; KRISHNAN, GOWTHAM; GANESH, MUGESH
To: CATERPILLAR INC.
Reel/Frame 065724/0001 →
Continuity (1)
Related Publication 20250181077A1 · Jun 5, 2025
References Cited (13)
US 7921000B2 · Ohkura et al. · 2011 [cited by applicant]
US 10872302B2 · Selvaraj et al. · 2020 [cited by applicant]
US 20020059320A1 · Tamaru · 2002 [cited by applicant]
US 20080084332A1 · Ritter et al. · 2008 [cited by applicant]
US 20170314232A1 · Chi · 2017 [cited by examiner]
US 20200117201A1 · Oetken et al. · 2020 [cited by applicant]
US 20210097462A1 · Brickner et al. · 2021 [cited by applicant]
US 20210216889A1 · Spurgeon · 2021 [cited by examiner]
US 20210318666A1 · Brockhurst · 2021 [cited by examiner]
US 20220187823A1 · Ramasamy et al. · 2022 [cited by applicant]
EP 2587419A2 · 2013 [cited by applicant]
KR 102026268B1 · 2019 [cited by applicant]
WO 2021101241A1 · 2021 [cited by applicant]