IP Library Granted Patent US 12,639,492
Granted Patent B2
US 12,639,492 · App. 17/466,545 · Granted May 26, 2026

Apparatuses, computer-implemented methods, and computer program products for real-time environment digital twin simulating

Inventors: Mayank Pathak (Pittsburgh, PA); Thomas Henry Evans (Morgantown, WV); Jagtar Singh (Pittsburgh, PA)
Assignee: INTELLIGRATED HEADQUARTERS, LLC
G06F30/27G06N20/00G06Q10/06375G06Q10/0639
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 12,639,492
App. No.
17/466,545
Granted
May 26, 2026
Kind
B2
Abstract

Embodiments of the present disclosure provide for improved real-world environment simulation and processing thereof. Some embodiments enable real-time simulating of a real-world environment, and/or visualization of portion(s) of the corresponding simulated environment. Some embodiments enable accurate testing of alteration(s) to a real-world environment utilizing simulated environment(s) to determine the effects of such alteration(s), and apply alteration(s) that are determined from said simulations to improve operation of the real-world environment. Such alteration(s) may be applied automatically to enable a self-optimizing environment based on such simulation(s).

Claims (88)

1 . An apparatus comprising at least one processor and at least one memory, the at least one memory having computer-coded instructions stored thereon that, in execution with the at least one processor causes the apparatus to:

retrieve a trained model corresponding to a real-world environment;

receive, via a communications network, a real-time data set associated with the real-world environment;

updating the trained model based on the real-time data to generate an updated trained model;

generate an updated simulated environment based on the real-time data set associated with the real-world environment; and

initiate at least one process based on the updated simulated environment, wherein to initiate the at least one process based on the updated simulated environment, the apparatus is caused to:

apply the trained model and the updated trained model to at least a portion of the updated simulated environment;

determine at least first simulated operational metric value associated with the updated simulated environment based on a simulated operation of at least one simulated computing device in the updated simulated environment utilizing the trained model;

determine at least second simulated operational metric value associated with the updated simulated environment based on the simulated operation of the at least one simulated computing device in the updated simulated environment utilizing the updated trained model;

identify a first accuracy data associated with the updated trained model and a second accuracy data associated with the trained model, wherein the first accuracy data is determined by comparing the at least first simulated operational metric value associated with the trained model and at least one real-time operational metric value, wherein the second accuracy data is determined by comparing the at least second simulated operational metric value associated with the updated trained model and the at least one real-time operational metric value;

determine a difference between the first accuracy data and the second accuracy data; and

compare the difference with an improvement threshold value, wherein the apparatus applies the updated trained model to the at least portion of the updated simulated environment if the difference is equal or greater than the improvement threshold value.

2 . The apparatus according to claim 1 , wherein to initiate the at least one process based on the updated simulated environment, the apparatus is caused to:

cause rendering of a user interface representing the at least portion of the updated simulated environment.

3 . The apparatus according to claim 1 , wherein to initiate the at least one process based on the updated simulated environment the apparatus is caused to:

identify the at least one real-time operational metric value associated with the updated simulated environment, the at least one real-time operational metric value corresponding to at least one operational metric;

retrieve at least one historical operational metric value associated with the real-world environment, the at least one historical operational metric value corresponding to the at least one operational metric; and

cause rendering of a dashboard interface comprising data representing a trend of the at least one operational metric based on the at least one real-time operational metric value and the at least one historical operational metric value.

4 . The apparatus according to claim 1 , wherein to initiate the at least one process based on the updated simulated environment, the apparatus is caused to:

cause rendering of an augmented reality interface representing the at least portion of the updated simulated environment.

5 . The apparatus according to claim 1 , the apparatus further caused to:

cause rendering of a dashboard interface comprising at least the at least second simulated operational metric value associated with the updated simulated environment.

6 . The apparatus according to claim 1 , the apparatus further caused to:

receive the at least one real-time operational metric value associated with the simulated operation of the real-world environment, the at least one real-time operational metric value corresponding to at least one operational metric;

determine the first accuracy data by comparing the at least one real-time operational metric value associated with the simulated operation of the real-world environment with the at least first simulated operational metric value associated with the trained model;

determine the second accuracy data by comparing the at least one real-time operational metric value associated with the simulated operation of the real-world environment with the at least second simulated operational metric value associated with the updated trained model; and

in response to determining the difference between the first accuracy data and the second accuracy data, compare the at least first simulated operational metric value associated with the trained model and the at least second simulated operational metric value associated with the updated trained model:

automatically configure at least one computing device in the real-world environment utilizing the updated trained model.

7 . The apparatus according to claim 1 , the apparatus further caused to:

identify the first accuracy data associated with the updated trained model and the second accuracy data associated with the trained model;

determine the difference between the first accuracy data and the second accuracy data; and

compare the difference with the improvement threshold value, wherein if the difference is smaller than the improvement threshold value, continue to update the trained model without applying the trained model to the portion of the updated simulated environment.

8 . The apparatus according to claim 1 , wherein to initiate the at least one process based on the updated simulated environment, the apparatus is caused to:

reconfigure the at least portion of the updated simulated environment;

determine the at least second simulated operational metric value associated with the updated simulated environment based on the simulated operation of the updated simulated environment after reconfiguration;

receive the at least one real-time operational metric value associated with the simulated operation of the real-world environment;

determine comparison results by comparing the at least one real-time operational metric value associated with operation of the real-world environment with the at least second simulated operational metric value associated with the updated simulated environment after a reconfiguration; and

in response to determining the comparison results indicate the at least second simulated operational metric value improves the at least one operational metric compared to the at least one real-time operational metric value associated with the simulated operation of the real-world environment:

automatically configure at least one computing device in the real-world environment in accordance with the reconfiguration of the updated simulated environment.

9 . The apparatus according to claim 1 , wherein to initiate the at least one process based on the updated simulated environment, the apparatus is caused to:

apply the trained model to at least one simulated data-controlled robot of the updated simulated environment;

detect at least one simulated error data object associated with simulated operation of the at least one simulated data-controlled robot; and

in response to detecting the at least one simulated error data object, continue to update the trained model without applying the trained model to the portion of the updated simulated environment.

10 . The apparatus according to claim 1 , the apparatus further caused to:

apply the trained model to at least one simulated data-controlled robot of the updated simulated environment;

generate simulated data associated with the simulated operation of the at least one simulated data-controlled robot of the updated simulated environment; and

update the trained model based on the simulated data associated with the simulated operation of the at least one simulated data-controlled robot.

11 . The apparatus according to claim 1 , wherein to initiate the at least one process based on the updated simulated environment, the apparatus is caused to:

apply the trained model to the at least portion of a first instance of the updated simulated environment;

determine the at least first simulated operational metric value associated with the first instance of the updated simulated environment based on a simulated operation of a first the at least one simulated computing device in the first instance of the updated simulated environment utilizing the trained model, the at least first simulated operational metric value corresponding to at least one operational metric;

apply the updated trained model to the at least portion of a second instance of the updated simulated environment;

determine the at least second simulated operational metric value associated with the second instance of the updated simulated environment based on the simulated operation of a second the at least one simulated computing device in the second instance of the updated simulated environment utilizing the updated trained model, the at least second simulated operational metric value corresponding to the at least one operational metric; and

determine a preferred model of the trained model and the updated trained model based on the at least first simulated operational metric value and the at least second simulated operational metric value.

12 . The apparatus according to claim 1 , the apparatus further caused to:

store the real-time data set, the real-time data set retrieved during generation of a second updated environment.

13 . The apparatus according to claim 1 , wherein the real-time data set comprises a plurality of sensor data types, the plurality of sensor data types comprising LiDAR data, distance data, pressure sensor data, temperature data, and/or image data.

14 . The apparatus according to claim 1 , wherein the real-time data set comprises data-controlled robot movement data, the at least one real-time operational metric value, and real-time sensor data.

15 . The apparatus according to claim 1 , the apparatus further caused to:

derive at least the one real-time operational metric value corresponding to at least one operational metric, the at least one real-time operational metric value derived based on real-time sensor data of the real-time data set.

16 . The apparatus according to claim 1 , wherein to initiate the at least one process based on the updated simulated environment, the apparatus is caused to:

cause rendering of a user interface representing the at least portion of the updated simulated environment, the user interface dynamically updating as new real-time data is received; and

simultaneously while causing rendering of the user interface:

apply the trained model to the at least portion of the updated simulated environment; and

determine the at least second simulated operational metric value associated with the updated simulated environment based on a simulated operation of the at least one simulated computing device in the updated simulated environment utilizing the trained model.

17 . A computer-implemented method comprising:

retrieving a trained model corresponding to a real-world environment;

receiving, via a communications network, real-time data set associated with the real-world environment;

updating the trained model based on the real-time data to generate an updated trained model;

generating an updated simulated environment based on the real-time data set associated with the real-world environment; and

initiating at least one process based on the updated simulated environment, wherein, to initiate the at least one process based on the updated simulated environment, the computer-implemented method further comprises:

applying the trained model and the updated trained model to at least a portion of the updated simulated environment;

determining at least first simulated operational metric value associated with the updated simulated environment based on a simulated operation of at least one simulated computing device in the updated simulated environment utilizing the trained model;

determining at least second simulated operational metric value associated with the updated simulated environment based on the simulated operation of the at least one simulated computing device in the updated simulated environment utilizing the updated trained model;

identifying a first accuracy data associated with the updated trained model and a second accuracy data associated with the trained model, wherein the first accuracy data is determined by comparing the at least first simulated operational metric value associated with the trained model and at least one real-time operational metric value, wherein the second accuracy data is determined by comparing the at least second simulated operational metric value associated with the updated trained model and the at least one real-time operational metric value;

determining a difference between the first accuracy data and the second accuracy data; and

comparing the difference with an improvement threshold value and apply the updated trained model to the at least portion of the updated simulated environment if the difference is equal or greater than the improvement threshold value.

18 . A computer program product comprising at least one non-transitory computer-readable storage medium having computer program code stored thereon that, in execution with at least one processor, configures the computer program product for:

retrieving a trained model corresponding to a real-world environment;

receiving, via a communications network, a real-time data set associated with the real-world environment;

updating the trained model based on the real-time data to generate an updated trained model;

generating an updated simulated environment based on the real-time data set associated with the real-world environment; and

initiating at least one process based on the updated simulated environment, wherein to initiate the at least one process based on the updated simulated environment, the processor further configures the computer program product to:

apply the trained model and the updated trained model to at least a portion of the updated simulated environment;

determine at least first simulated operational metric value associated with the updated simulated environment based on a simulated operation of at least one simulated computing device in the updated simulated environment utilizing the trained model;

determine at least second simulated operational metric value associated with the updated simulated environment based on the simulated operation of the at least one simulated computing device in the updated simulated environment utilizing the updated trained model;

identify a first accuracy data associated with the updated trained model and a second accuracy data associated with the trained model, wherein the first accuracy data is determined by comparing the at least first simulated operational metric value associated with the trained model and at least one real-time operational metric value, wherein the second accuracy data is determined by comparing the at least second simulated operational metric value associated with the updated trained model and the at least one real-time operational metric value;

determine a difference between the first accuracy data and the second accuracy data; and

compare the difference with an improvement threshold value, wherein the at least one processor applies the updated trained model to the at least portion of the updated simulated environment if the difference is equal or greater than the improvement threshold value.

Assignments (2)
SECURITY AGREEMENT Recorded Jul 29, 2026
From: INTELLIGRATED HEADQUARTERS, LLC; TRANSNORM SYSTEM INC.; HILMOT, LLC; TREW, LLC; UNITED SORTATION SOLUTIONS LLC; TECH KING OPERATIONS, LLC
To: ALLY BANK, AS COLLATERAL AGENT
Reel/Frame 076077/0385 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 3, 2021
From: PATHAK, MAYANK; EVANS, THOMAS HENRY; SINGH, JAGTAR
To: INTELLIGRATED HEADQUARTERS, LLC
Reel/Frame 057384/0161 →
Continuity (1)
Related Publication 20230076433A1 · Mar 9, 2023
References Cited (8)
US 20120191630A1 · Breckenridge · 2012 [cited by examiner]
US 20220134537A1 · Chadalavada Vijay Kumar · 2022 [cited by examiner]
He F, Ong SK, Nee AY. An integrated mobile augmented reality digital twin monitoring system. Computers. Aug. 12, 2021;10(8):99. (Year: 2021). [cited by examiner]
Liu S, Lu S, Li J, Sun X, Lu Y, Bao J. Machining process-oriented monitoring method based on digital twin via augmented reality. The International Journal of Advanced Manufacturing Technology. Apr. 2021;113:3491-508. (Y… [cited by examiner]
J. C. Jones, A. Panken and J. A. Lopez, “Surrogate-Based Optimization for Radar Surveillance Requirements to Support RWC and CA for Unmanned Aircraft,” 2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC), Lon… [cited by examiner]
Raschka S. Model evaluation, model selection, and algorithm selection in machine learning. arXiv preprint arXiv:1811.12808. Nov. 13, 2018. (Year: 2018). [cited by examiner]
López, Carlos Eduardo Belman. “Real-time event-based platform for the development of digital twin applications.” The International Journal of Advanced Manufacturing Technology 116, No. 3 (2021): 835-845. (Year: 2021). [cited by examiner]
Yang Z, Al-Dahidi S, Baraldi P, Zio E, Montelatici L. A novel concept drift detection method for incremental learning in nonstationary environments. IEEE transactions on neural networks and learning systems. Mar. 26, 20… [cited by examiner]