IP Library › Granted Patent US 12,411,212
Granted Patent B1
US 12,411,212 · App. 17/307,542 · Granted Sep 9, 2025

Mobile safety systems

Inventors: Sandeep Pandya (Irvine, CA); Sundeep Ahluwalia (San Diego, CA); Changsoo Jeong (Rancho Palos Verdes, CA); Michael Korkin (Glendale, CA); Kyungsuk Lee (Rancho Palos Verdes, CA); Christopher Ro (Aliso Viejo, CA); Yong Wu (Signal Hill, CA)
Assignee: Everguard, Inc.
G01S7/4802G01S7/4915G01S17/42G01S17/894G06N20/00
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 12,411,212
App. No.
17/307,542
Granted
Sep 9, 2025
Kind
B1
Abstract

A mobile system is provided for managing safety in a dynamic environment. The system comprises: a computer vision component for generating a computer vision output data; a real-time locating component for generating location data about an object within the industrial environment; a LIDAR component for generating 3D point cloud data of the industrial environment; and one or more processors coupled to the computer vision component, the real-time locating component and the LIDAR component and configured to: (i) process the data stream with aid of a machine learning algorithm trained model to generate a safety related result and feedback data, and (ii) deliver the feedback data to the object via the mobile tag device, and a mobile platform configured to move the mobile system in the environment.

Claims (44)

1. A mobile system for managing safety in an environment, comprising:

a mobile platform configured to move the mobile system in the environment;

a computer vision component for generating computer vision output data of the environment;

a real-time locating component for generating location data about an object within the environment, the location data including identity of the object and location of the object within the environment, wherein the location of the object is determined based on location tracking performed by a mobile tag device carried by the object, further wherein the mobile tag identifies the object;

a light detection and ranging (LIDAR) component for generating 3D point cloud data of the environment; and

an edge computing device coupled to the computer vision component, the real-time locating component and the LIDAR component and configured to:

(i) receive a data stream including the computer vision output data, the location data and the 3D point cloud data to generate an input feature dataset, wherein the generation of the input feature dataset includes use of complementary information in the location data, the computer vision data, and the 3D point cloud for multimodal sensor fusion, further wherein:

the identity of the object depicted within the computer vision output data is determined based on the identity of the object and location of the object included in the location data; and

the 3D point cloud and the location data are registered to a 3D scene map of the environment, the 3D scene map of the environment generated based on the computer vision output data; and

(ii) process the input feature dataset using a machine learning algorithm trained model to generate a safety related result, wherein the safety related result indicates a detected or predicted adverse event involving the object and one or more other objects within the environment.

2. The mobile system of claim 1 , further comprising a gateway device for establishing a connection with a cloud to download an updated machine learning algorithm trained model.

3. The mobile system of claim 1 , further comprising a power source to power the computer vision component, the real-time locating component, the LIDAR component and the edge computing device.

4. The mobile system of claim 1 , further comprising a detector for detecting an unauthorized removal of a component of the mobile platform.

5. The mobile system of claim 1 , wherein:

the mobile tag device carried by the object further detects orientation, speed, or acceleration of the object;

the location data further includes the orientation, the speed, or the acceleration of the object; and

the input feature dataset is generated further based on the orientation, the speed, or the acceleration of the object.

6. The mobile system of claim 5 , wherein the mobile tag device comprises a motion sensor.

7. The mobile system of claim 2 , wherein the machine learning algorithm trained model is run on the edge computing device to locally generate the safety related result while the machine learning algorithm trained model is trained and updated on the cloud.

8. The mobile system of claim 1 , wherein the machine learning algorithm trained model further generates a feedback data that is delivered to the object.

9. The mobile system of claim 8 , wherein the safety related result includes a detection of an action of the object that does not comply with a safety protocol and the feedback data comprises an alert indicative of the detection delivered to the object via the mobile tag device.

10. The mobile system of claim 8 , wherein the feedback data comprises a control signal to effect an operation of the object.

11. The mobile system of claim 1 , wherein the computer vision output data comprises a description of the environment.

12. A method for managing safety in an environment using a mobile system, comprising:

generating, using a computer vision component of the mobile system,

computer vision output data of the environment;

generating, using a real-time locating component of the mobile system, location data about an object within the environment, the location data including identity of the object and location of the object within the environment, wherein the location of the object is determined based on location tracking performed by a mobile tag device carried by the object, further wherein the mobile tag identifies the object;

generating, using a light detection and ranging (LIDAR) component of the mobile system, 3D point cloud data of the environment;

receiving, at an edge computing device located at the mobile system, a data stream including the computer vision output data, the location data and the 3D point cloud data to generate an input feature dataset, wherein the generation of the input feature dataset includes use of complementary information in the location data, the computer vision data, and the 3D point cloud for multimodal sensor fusion, further wherein:

the identity of the object depicted within the computer vision output data is determined based on the identity of the object and location of the object included in the location data; and

the 3D point cloud and the location data are registered to a 3D scene map of the environment, the 3D scene map of the environment generated based on the computer vision output data;

processing, by the edge computing device, the input feature dataset using a machine learning algorithm trained model to generate a safety related result, wherein the safety related result indicates a detected or predicted adverse event involving the object and one or more other objects within the environment; and

providing a mobile platform for moving the mobile system in the environment.

13. The method of claim 12 , further comprising establishing, via a gateway device of the mobile system, a connection with a cloud to download an updated machine learning algorithm trained model.

14. The method of claim 12 , further comprising detecting, with aid of a detector, an unauthorized removal of a component of the mobile platform.

15. The method of claim 12 , wherein:

the mobile tag device carried by the object further detects orientation, speed, or acceleration of the object;

the location data further includes the orientation, the speed, or the acceleration of the object; and

the input feature dataset is generated further based on the orientation, the speed, or the acceleration of the object.

16. The method of claim 15 , wherein the mobile tag device comprises a motion sensor.

17. The method of claim 12 , further comprising generating a feedback data, by the machine learning algorithm trained model, to be delivered to the object.

18. The method of claim 17 , wherein the safety related result includes a detection of an action of the object that does not comply with a safety protocol and the feedback data comprises an alert indicative of the detection delivered to the object via the mobile tag device.

19. The method of claim 17 , wherein the feedback data comprises a control signal to effect an operation of the object.

20. The method of claim 12 , wherein the computer vision output data comprises a description of the environment.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 4, 2022
From: PANDYA, SANDEEP; AHLUWALIA, SUNDEEP; JEONG, CHANGSOO; KORKIN, MICHAEL; LEE, KYUNGSUK; RO, CHRISTOPHER; WU, YONG
To: EVERGUARD, INC.
Reel/Frame 059174/0765 →
Continuity (1)
Provisional Application 63022964 · May 11, 2020
References Cited (46)
US 11675878B1 · Pandya · 2023 [cited by examiner]
US 11803955B1 · Pandya · 2023 [cited by examiner]
US 20030193398A1 · Geber · 2003 [cited by examiner]
US 20150332463A1 · Galera · 2015 [cited by applicant]
US 20180082244A1 · Brazeau · 2018 [cited by applicant]
US 20180276841A1 · Krishnaswamy · 2018 [cited by applicant]
US 20190209022A1 · Sobol et al. · 2019 [cited by applicant]
US 20190236370A1 · Man · 2019 [cited by applicant]
US 20190258251A1 · Ditty et al. · 2019 [cited by applicant]
US 20190258878A1 · Koivisto · 2019 [cited by applicant]
US 20190291723A1 · Srivatsa · 2019 [cited by applicant]
US 20190303759A1 · Farabet et al. · 2019 [cited by applicant]
US 20190324145A1 · Buehring · 2019 [cited by examiner]
US 20200034620A1 · Lutterodt · 2020 [cited by applicant]
US 20200089942A1 · Man · 2020 [cited by applicant]
US 20200202208A1 · Li · 2020 [cited by applicant]
US 20200202472A1 · Barak · 2020 [cited by examiner]
US 20210309460A1 · Kim · 2021 [cited by examiner]
US 20220187847A1 · Cella · 2022 [cited by examiner]
US 20240078656A1 · Pandya · 2024 [cited by applicant]
CN 104376348 · 2015 [cited by applicant]
CN 107742141 · 2018 [cited by applicant]
KR 101907964 · 2018 [cited by applicant]
WO WO2019216975A1 · 2019 [cited by examiner]
WO WO2020088739A1 · 2020 [cited by examiner]
Mandeljc et al., “Tracking by Identification Using Computer Vision and Radio”, Sensors 2013, 13, 241-273 (Year: 2012). [cited by examiner]
“AI Insights for a Safer, Healthier and Productive Workforce.” WearHealth, wearhealth.com/. Accessed on Apr. 22, 2020. [cited by applicant]
“AI-Powered Workplace Safety.” Intenseye, http://www.intenseye.com/.Accessed on Apr. 22, 2020. [cited by applicant]
Cheng et al. Automated task-level activity analysis through fusion of real time location sensors and worker's thoracic posture data; Automation in Construction 29 (2013) 24-39. [cited by applicant]
“Connected Safety.” Home-HIS, safety.honeywell.com/en-us/software-and-services/connected-safety. Accessed on Apr. 22, 2020. [cited by applicant]
“Connected Worker Solutions.” Intel, http://www.intel.com/content/www/us/en/connected-worker/overview.html. Accessed on Apr. 22, 2020. [cited by applicant]
Co-pending U.S. Appl. No. 17/241,737, inventors Pandya; Sandeep et al., filed on Apr. 27, 2021. [cited by applicant]
“DeepCanopy.” DeepCanopy, http://www.deepcanopy.com/. Accessed on Apr. 22, 2020. [cited by applicant]
“Guardhat.” Guardhat, http://www.guardhat.com/. Accessed on Apr. 22, 2020. [cited by applicant]
“Hitachi Solutions IoT Service Hub for Worker Safety.” Hitachi Solutions, us.hitachi-solutions.com/products/hitachi-solutions-iot-service-hub-for-worker-safety/. Accessed on Apr. 22, 2020. [cited by applicant]
“Home: Safety First.” Safetyfirst, margad.wixsite.com/safetyfirst.Accessed on Apr. 22, 2020. [cited by applicant]
Mandeljc et al. Tracking by identification using computer vision and radio; Sensors 13:241-273 (2013). [cited by applicant]
Smartvid.io, Inc. “Minimize Risk across Projects with the Smartvid.io Platform.” Minimize Risk across Projects with the Smartvid.io Platform, http://www.smartvid.io/our-platform. Accessed on Apr. 22, 2020. [cited by applicant]
“Video Analytics Partner.” EasyFlow, easyflow.biz/. Accessed on Apr. 22, 2020. [cited by applicant]
“Worker Insights.” Worker Insights | IBM Watson IoT, http://www.ibm.com/internet-of-things/solutions/enterprise-asset-management/worker-insights. Accessed on Apr. 22, 2020. [cited by applicant]
“Worker Safety.” HCL Technologies, http://www.hcltech.com/Internet-of-Things-IoT/our-solutions/worker-safety#an-introduction. Accessed on Apr. 22, 2020. [cited by applicant]
Zhang et al. A framework of on-site construction safety management using computer vision and real-time location system. International Conference on Smart Infrastructure and Construction 2019 (ICSIC); pp. 327-333; availa… [cited by applicant]
“Guardhat.” Guardhat, http://www.guardhat.com/. Accessed on Apr. 22, 2020. (2 pages). [cited by applicant]
“Video Analytics Partner.” EasyFlow, easyflow.biz/. Accessed on Apr. 22, 2020. (10 pages). [cited by applicant]
AI Insights for a Safer, Healthier and Productive Workforce. WearHealth, wearhealth.com/.Accessed on Apr. 22, 2020 (5 pages). [cited by applicant]
Smartvid.io, Inc. “Minimize Risk across Projects with the Smartvid.io Platform.” Minimize Risk across Projects with the Smartvid.io Platform, http://www.smartvid.io/our-platform. Accessed on Apr. 22, 2020. (4 pages). [cited by applicant]