IP Library Granted Patent US 12,639,655
Granted Patent B2
US 12,639,655 · App. 18/060,162 · Granted May 26, 2026

Control system for container terminal and related methods

Inventors: Mark D. Mills (Land O Lakes, FL); Artem Davtyan (New Port Richey, FL); Matthew Michael McDermott (Odessa, FL); Jorge A. Perez Rincon (Tampa, FL); Christopher Alexander (Tarpon Springs, FL)
Assignee: All Terminal Services, LLC
G06Q10/083
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 12,639,655
App. No.
18/060,162
Granted
May 26, 2026
Kind
B2
Abstract

A control system is for a container terminal with containers. The control system includes a server, and a terminal tractor operable within the container terminal. The terminal tractor comprises onboard tractor sensors configured to generate sensor data of at least some of the containers, a geolocation device configured to generate a geolocation value for the terminal tractor, a wireless transceiver, and a controller coupled to the onboard tractor sensors, the geolocation device, and the wireless transceiver. The controller is configured to transmit the sensor data and the geolocation value for the terminal tractor to the server. The server is in communication with the terminal tractor and is configured to generate a database associated with the sensor data, the database comprising, for each container, a container type value, a container logo image, and a vehicle classification value.

Claims (81)

1 . A control system for one or more terminal tractors operable within a container terminal with one or more containers therein, the control system comprising:

one or more servers;

one or more onboard tractor sensors for the one or more terminal tractors operable within the container terminal, the one or more onboard tractor sensors configured to generate sensor data of the one or more containers, wherein the one or more onboard tractor sensors comprises one or more image sensors configured to generate container image data of the one or more containers;

one or more geolocation devices configured to generate one or more geolocation values for the one or more terminal tractors;

one or more wireless transceivers; and

one or more controllers coupled to the one or more onboard tractor sensors, the one or more geolocation devices, and the one or more wireless transceivers, the one or more controllers configured to transmit the container image data and the one or more geolocation values for the one or more terminal tractors to the one or more servers via the one or more wireless transceivers; and

the one or more servers in communication with the one or more wireless transceivers, wherein the one or more servers are configured to:

perform machine learning on the container image data including executing at least one of:

a first machine learning model comprising a neural network trained to predict a location of text sequences in the container image data; or

a second machine learning model comprising a neural network trained to scan the text sequences in the container image data and predict a sequence of missing characters in the container image data; or

a combination thereof, and

generate a database associated with the container image data, the database comprising, for each container, at least one of a container type value, a container logo image, a vehicle classification value, or a container slot location or a parking spot location, or a combination of two or more thereof,

wherein the one or more servers are further configured to perform machine learning on the container image data including executing a machine learning model comprising a neural network trained to predict at least one of a container slot location or a parking spot location of the one or more containers of the plurality of containers,

wherein the one or more servers are further configured to perform machine learning on the container image data including executing a machine learning model comprising a neural network trained to determine at least one of:

an occupancy status of one or more container slot locations or parking spot locations of the container terminal, or

one or more occupancy details of the one or more container slot locations or parking spot locations of the container terminal, or

a combination thereof.

2 . The control system of claim 1 , wherein the plurality of onboard tractor sensors comprises one or more proximity sensors configured to detect a presence of the one or more containers.

3 . The control system of claim 1 , wherein the one or more servers are configured to weight detected objects in the container terminal based upon a number of frames in the container image data including the detected objects.

4 . The control system of claim 1 , wherein the one or more servers are configured to identify each container based upon the container image data.

5 . The control system of claim 1 , wherein the one or more servers are configured to perform optical character recognition (OCR) on the container image data.

6 . The control system of claim 1 , wherein the one or more onboard tractor sensors comprises a plurality of image sensors configured to generate a plurality of container image data streams; and

wherein the server is configured to merge the plurality of container image data streams.

7 . The control system of claim 1 , wherein the first machine learning model comprises a convolutional neural network (CNN) trained to predict the location of text sequences in the container image data, and

wherein the second machine learning model comprises a recurrent neural network (RNN) for scanning the text sequences in the container image data and predicting the sequence of missing characters.

8 . The control system of claim 1 , wherein each container comprises one of a railcar container, a trailer, a chassis, a boxcar, a cargobeamer car, a coil car, a combine car, a flatcar, a schnable car, a gondola car, a Presflo and Prestwin car, a bulk cement wagon car, a roll-block car, a slate wagon car, a stock car, a tank car, a milk car, a transporter wagon car, and a well car.

9 . The control system of claim 1 , wherein the predicted container slot location or parking spot location is a closest container slot location or parking spot location to the one or more geolocation values.

10 . The control system of claim 1 , wherein the one or more geolocation values comprises at least one of a latitude value, a longitude value, or an angle value, or a combination of two or more thereof.

11 . The control system of claim 1 , wherein the one or more geolocation values comprises a coordinate and a direction.

12 . The controlsystem of claim 1 , wherein the one or more servers are configured to perform machine learning on the one or more geolocation values including executing a machine learning model comprising a neural network trained to determine a course of a terminal tractor of the one or more terminal tractors.

13 . The control system of claim 1 , wherein the one or more servers are configured to identify the one or more containers based upon the container image data.

14 . The control system of claim 1 , wherein the one or more servers are configured to transmit one or more operational values to a terminal tractor of the one or more terminal tractors to position a container of the one or more containers at a predetermined location within the container terminal.

15 . A server for a control system for one or more terminal tractors operable within a container terminal with one or more containers therein,

the control system comprising:

one or more onboard tractor sensors for the one or more terminal tractors operable within the container terminal, the one or more onboard tractor sensors configured to generate sensor data of the one or more containers, wherein the one or more onboard tractor sensors comprises one or more image sensors configured to generate container image data of the one or more containers;

one or more geolocation devices configured to generate one or more geolocation values for the one or more terminal tractors;

one or more wireless transceivers; and

one or more controllers coupled to the one or more onboard tractor sensors, the one or more geolocation devices, and the one or more wireless transceivers, the one or more controllers configured to transmit the container image data and the one or more geolocation values for the one or more terminal tractors to the server via the one or more wireless transceivers;

the server comprising:

one or more processors and one or more non-transitory computer-readable storage mediums cooperating therewith and in communication with the one or more wireless transceivers, the one or more non-transitory computer-readable storage mediums storing instructions comprising one or more algorithms configured for execution by the one or more processors, the one or more processors configured to:

receive the container image sensor data and the one or more geolocation values for the one or more terminal tractors from the one or more wireless transceivers-terminal tractors;

perform machine learning on the container image data including executing at least one of:

a first machine learning model comprising a neural network trained to predict a location of text sequences in the container image data; or

a second machine learning model comprising a neural network trained to scan the text sequences in the container image data and predict a sequence of missing characters in the container image data; or

a combination thereof, and

generate a database associated with the sensor data, the database comprising, for each container, at least one of a container type value, a container logo image, a vehicle classification value, or a container slot location or a parking spot location, or a combination of two or more thereof,

wherein the server is further configured to perform machine learning on the container image data including executing a machine learning model comprising a neural network trained to predict a container slot location or a parking spot location of the one or more containers of the plurality of containers,

wherein the server is further configured to perform machine learning on the container image data including executing a machine learning model comprising a neural network trained to determine at least one of:

an occupancy status of one or more container slot locations or parking spot locations of the container terminal, or

one or more occupancy details of the one or more container slot locations or parking spot locations of the container terminal, or

a combination thereof.

16 . The server of claim 15 , wherein the plurality of onboard tractor sensors comprises one or more proximity sensors configured to detect a presence of the one or more containers.

17 . The server of claim 15 , wherein the one or more servers are configured to weight detected objects in the container terminal based upon a number of frames in the container image data including the detected objects.

18 . The server of claim 15 , wherein the one or more servers are configured to identify each container based upon the container image data.

19 . The server of claim 15 , wherein the one or more servers are configured to perform optical character recognition (OCR) on the container image data.

20 . The server of claim 15 , wherein the one or more onboard tractor sensors comprises a plurality of image sensors configured to generate a plurality of container image data streams; and

wherein the server is configured to merge the plurality of container image data streams.

21 . The server of claim 15 , wherein the first machine learning model comprises a convolutional neural network (CNN) trained to predict the location of text sequences in the container image data; and wherein the second machine learning model comprises a recurrent neural network (RNN) for scanning the text sequences in the container image data and predicting a sequence of missing characters.

22 . The server of claim 15 , wherein each wherein each container comprises one of a railcar container, a trailer, a chassis, a boxcar, a cargobeamer car, a coil car, a combine car, a flatcar, a schnable car, a gondola car, a Presflo and Prestwin car, a bulk cement wagon car, a roll-block car, a slate wagon car, a stock car, a tank car, a milk car, a transporter wagon car, and a well car.

23 . A method of operating one or more servers in a control system for one or more terminal tractors operable within a container terminal with one or more containers therein,

the control system comprising:

one or more onboard tractor sensors for the one or more terminal tractors operable within the container terminal, the one or more onboard tractor sensors configured to generate sensor data of at least one container of the one or more containers, wherein the one or more onboard tractor sensors comprises one or more image sensors configured to generate container image data of the one or more containers;

one or more geolocation devices configured to generate one or more geolocation values for the one or more terminal tractors;

one or more wireless transceivers; and

one or more controllers coupled to the one or more onboard tractor sensors, the one or more geolocation devices, and the one or more wireless transceivers, the one or more controllers configured to transmit the container image data and the one or more geolocation values for the one or more terminal tractors to the one or more servers via the one or more wireless transceivers;

the method comprising:

operating the one or more servers in communication with the one or more wireless transceivers to:

receive the container image data and the one or more geolocation values for the one or more terminal tractors from the one or more wireless transceivers;

perform machine learning on the container image data including executing at least one of;

a first machine learning model comprising a neural network trained to predict a location of text sequences in the container image data; or

a second machine learning model comprising a neural network trained to scan the text sequences in the container image data and predict a sequence of missing characters in the container image data; or

a combination thereof; and

generate a database associated with the container image sensor data, the database comprising, for each container, at least one of a container type value, a container logo image, a vehicle classification value, or a container slot location or parking spot location, or a combination of two or more thereof,

wherein the method further comprises operating the one or more servers to perform machine learning on the container image data including executing a machine learning model comprising a neural network trained to predict a container slot location or parking spot location of the one or more containers of the plurality of containers,

wherein the method further comprises operating the one or more servers to perform machine learning on the container image data including executing a machine learning model comprising a neural network trained to determine at least one of:

an occupancy status of one or more container slot locations or parking spot locations of the container terminal, or

one or more occupancy details of the one or more container slot locations or parking spot locations of the container terminal, or

a combination thereof.

24 . The method of claim 23 , wherein the plurality of onboard tractor sensors comprises one or more proximity sensors configured to detect a presence of the one or more containers.

25 . The method of claim 23 , further comprising weighting detected objects in the container terminal based upon a number of frames including the detected objects.

26 . The method of claim 23 , wherein each container comprises one of a railcar container, a trailer, a chassis, a boxcar, a cargobeamer car, a coil car, a combine car, a flatcar, a schnable car, a gondola car, a Presflo and Prestwin car, a bulk cement wagon car, a roll-block car, a slate wagon car, a stock car, a tank car, a milk car, a transporter wagon car, and a well car.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 24, 2024
From: ITS TECHNOLOGIES & LOGISTICS, LLC (D/B/A CONGLOBAL)
To: ALL TERMINAL SERVICES, LLC (D/B/A CONGLOBAL TECHNOLOGIES)
Reel/Frame 068064/0346 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 18, 2023
From: COMMUNICATION CONCEPTS INTEGRATION INC.
To: ITS TECHNOLOGIES & LOGISTICS, LLC
Reel/Frame 064302/0521 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 8, 2022
From: MILLS, MARK D.; DAVTYAN, ARTEM; MCDERMOTT, MATTHEW MICHAEL; PEREZ RINCON, JORGE A.; ALEXANDER, CHRISTOPHER
To: COMMUNICATION CONCEPTS INTEGRATION INC.
Reel/Frame 062022/0108 →
Continuity (4)
Continuation In Part 16951015 · Nov 18, 2020
Provisional Application 63284071 · Nov 30, 2021
Provisional Application 62936715 · Nov 18, 2019
Related Publication 20240354687A1 · Oct 24, 2024
References Cited (71)
US 2853968A · Mclean · 1958 [cited by applicant]
US 6637703B2 · Matheson et al. · 2003 [cited by applicant]
US 7813846B2 · Wills et al. · 2010 [cited by applicant]
US 8180590B2 · Szwilski et al. · 2012 [cited by applicant]
US 8280567B2 · Brand et al. · 2012 [cited by applicant]
US 8532842B2 · Smith et al. · 2013 [cited by applicant]
US 8942426B2 · Bar-Am · 2015 [cited by applicant]
US 10029708B2 · Viviani · 2018 [cited by applicant]
US 10597053B2 · Mian et al. · 2020 [cited by applicant]
US 11958529B2 · Mandlekar et al. · 2024 [cited by applicant]
US 12020148B1 · Mills et al. · 2024 [cited by applicant]
US 20020188593A1 · Moser et al. · 2002 [cited by applicant]
US 20050125113A1 · Wheeler et al. · 2005 [cited by applicant]
US 20080086393A1 · Naghshiineh et al. · 2008 [cited by applicant]
US 20090015400A1 · Breed · 2009 [cited by applicant]
US 20100063734A1 · Kumar · 2010 [cited by applicant]
US 20120051643A1 · Ha et al. · 2012 [cited by applicant]
US 20120130562A1 · Brand · 2012 [cited by examiner]
US 20150201165A1 · Bocionek et al. · 2015 [cited by applicant]
US 20150331931A1 · Burke et al. · 2015 [cited by applicant]
US 20160104098A1 · Matula et al. · 2016 [cited by applicant]
US 20160239790A1 · Burch et al. · 2016 [cited by applicant]
US 20170001653A1 · Ferencz, Jr. · 2017 [cited by examiner]
US 20170032316A1 · Benedict · 2017 [cited by applicant]
US 20170154347A1 · Bateman · 2017 [cited by applicant]
US 20180215545A1 · High et al. · 2018 [cited by applicant]
US 20180374039A1 · Walden et al. · 2018 [cited by applicant]
US 20190311625A1 · Anvari · 2019 [cited by applicant]
US 20190392231A1 · Dean et al. · 2019 [cited by applicant]
US 20200125877A1 · Phan et al. · 2020 [cited by applicant]
US 20200193507A1 · Glaser et al. · 2020 [cited by applicant]
US 20200265377A1 · Al Dhaheri · 2020 [cited by examiner]
US 20200320231A1 · Santarone et al. · 2020 [cited by applicant]
US 20210056497A1 · Engedal et al. · 2021 [cited by applicant]
US 20240029092A1 · Simpson · 2024 [cited by applicant]
US 20240354690A1 · Mills et al. · 2024 [cited by applicant]
US 20240386269A1 · Mills et al. · 2024 [cited by applicant]
US 20240386270A1 · Mills et al. · 2024 [cited by applicant]
CN 107364434A · 2017 [cited by applicant]
CN 110457420A · 2019 [cited by examiner]
EP 3275764A1 · 2018 [cited by examiner]
RU 2630859C1 · 2017 [cited by applicant]
WO 2016191711 · 2016 [cited by applicant]
WO 2019060767A1 · 2019 [cited by applicant]
Lakshmanan, Barath. A Parking Garage Management System. Oklahoma State University ProQuest Dissertations & Theses, 2016. (Year: 2016). [cited by examiner]
Wang, Zhihuan et al. Extracting Global Shipping Networks from Massive Historical Automation Identification System Sensor Data: A Bottom-Up Approach. Sensors, 2019. (Year: 2019). [cited by examiner]
Jung et al., “Real-time car tracking system based on surveillance videos,” EURASIP Journal on Image and Video Processing, 2018; 2018(1): pp. 1-13. [cited by applicant]
U.S. Appl. No. 18/731,207, dated Sep. 20, 2024, Office Action issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 18/731,207, dated Nov. 18, 2024, Notice of Allowance issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 18/744,198, dated Oct. 18, 2024, Office Action issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 18/748,961, dated Oct. 8, 2024, Office Action issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 16/951,015, filed Nov. 18, 2020, Mark D. Mills et al. [cited by applicant]
U.S. Appl. No. 18/731,207, filed May 31, 2024, Mark D. Mills et al. [cited by applicant]
U.S. Appl. No. 18/744,198, filed Jun. 14, 2024, Mark D. Mills et al. [cited by applicant]
U.S. Appl. No. 18/748,961, filed Jun. 20, 2024, Mark D. Mills et al. [cited by applicant]
U.S. Appl. No. 62/936,715, filed Nov. 18, 2019, Mills, Mark. [cited by applicant]
U.S. Appl. No. 63/284,071, filed Nov. 30, 2021, Mark D. Mills et al. [cited by applicant]
U.S. Appl. No. 63/557,470, filed Feb. 23, 2024, Mark D. Mills et al. [cited by applicant]
U.S. Appl. No. 63/557,472, filed Feb. 23, 2024, Mark D. Mills et al. [cited by applicant]
U.S. Appl. No. 16/951,015, dated Dec. 5, 2023, Office Action issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 16/951,015, dated Apr. 29, 2024, Notice of Allowance issued by the U.S. Patent and Trademark Office. [cited by applicant]
International Search Report and Written Opinion issued in PCT/US2025/017089, mailed Apr. 30, 2025. [cited by applicant]
U.S. Appl. No. 18/744,198, dated Feb. 11, 2025, Final Office Action issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 19/061,932, dated Apr. 15, 2025, Notice of Allowance issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 18/748,961, dated Jan. 31, 2025, Notice of Allowance issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 19/061,932, dated Jun. 4, 2025, Corrected Notice of Allowance issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 19/224,521, dated Aug. 19, 2025, Office Action issued by the U.S. Patent and Trademark Office. [cited by applicant]
Unknown, “IEEE Guide for Collecting and Managing Transmission Line Inspection and Maintenance Data,” in IEEE Std 1808-2011, 2011: pp. 1-50. [cited by applicant]
[cited by applicant]
U.S. Appl. No. 18/744,198, dated Oct. 22, 2025, Office Action issued by the U.S. Patent and Trademark Office. [cited by applicant]
U.S. Appl. No. 19/224,521, dated Dec. 12, 2025, Final Office Action issued by the U.S. Patent and Trademark Office. [cited by applicant]