IP Library Granted Patent US 12,501,014
Granted Patent B2
US 12,501,014 · App. 18/801,089 · Granted Dec 16, 2025

Automatically determining extrinsic parameters of modular edge computing devices

Inventors: Elliott Grant (Woodside, CA); Sergey Yaroshenko (Newark, CA); Gabriella Levine (San Francisco, CA)
Assignee: Deere & Company
H04N13/239A01B63/02A01B76/00A01B79/005G06T7/73G06T7/85H04N13/246H04N13/296G06T2207/30188G06T2207/30204
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 12,501,014
App. No.
18/801,089
Granted
Dec 16, 2025
Kind
B2
Abstract

Implementations are disclosed for automatic commissioning, configuring, calibrating, and/or coordinating sensor-equipped modular edge computing devices that are mountable on agricultural vehicles. In various implementations, neighbor modular edge computing device(s) that are mounted on a vehicle nearest a given modular edge computing device may be detected based on sensor signal(s) generated by contactless sensor(s) of the given modular edge computing device. Based on the detected neighbor modular edge computing device(s), an ordinal position of the given modular edge computing device may be determined relative to a plurality of modular edge computing devices mounted on the agricultural vehicle. Based on the sensor signal(s), distance(s) to the neighbor modular edge computing device(s) may be determined. Extrinsic parameters of the given modular edge computing device may be determined based on the ordinal position of the given modular edge computing device and the distance(s).

Claims (51)

1 . A method for automatically determining extrinsic parameters of a first edge computing device of a plurality of edge computing devices in an agricultural environment, the method comprising:

detecting, using signals by generated by one or more sensors of the first edge computing device, a second edge computing device of the plurality of edge computing devices near the first edge computing device;

determining, based on the detected second edge computing device, an ordinal position of the first edge computing device relative to the second edge computing device;

determining, based on visual signals generated by a visual sensor of the first edge computing device, a distance to the second edge computing device; and

determining the extrinsic parameters of the first edge computing device based on the ordinal position of the first edge computing device and the distance to the second edge computing device.

2 . The method of claim 1 , wherein detecting the second edge computing device further comprises:

receiving, from the second edge computing device, a wireless communication comprising position and distance information.

3 . The method of claim 2 , wherein determining the ordinal position of the first edge computing device is additionally based on the wirelessly received position and distance information.

4 . The method of claim 2 , wherein determining the distance to the second edge computing device based on visual signals generated by the visual sensor of the first edge computing device is additionally based on the wirelessly received position and distance information.

5 . The method of claim 1 , further comprising:

receiving, from a server computing system, an agricultural inference about the agricultural environment; and

wherein automatically determining the extrinsic parameters of the first edge computing device occurs on a local system in response to receiving the agricultural inference.

6 . The method of claim 1 , wherein determining the distance to the second edge computing device based on visual signals generated by the visual sensor of the first edge computing device comprises:

identifying at least one visual features detected in a first region of a first image captured by the visual sensor of the first edge computing device that is the same as one or more visual features detected in a second region of a second image captured by a visual sensor of the second edge computing device; and

determining the distance to the second edge computing device based on the at least one visual feature that is the same between the first image and the second image.

7 . The method of claim 1 , wherein determining the ordinal position of the first edge computing device comprises:

identifying a visual feature detected in a first image captured by the visual sensor of the first edge computing device representing the second edge computing device; and

determining the ordinal position of first edge computing device based on the identified visual feature.

8 . The method of claim 1 , wherein the first edge computing device is mounted to an agricultural robot operating in the agricultural environment.

9 . The method of claim 1 , wherein the second edge computing device is mounted to an agricultural vehicle operating in the agricultural environment.

10 . The method of claim 9 , wherein the second edge computing device is removably couplable from the agricultural vehicle.

11 . A non-transitory computer-readable storage medium storing computer program instructions for automatically determining extrinsic parameters of a first edge computing device of a plurality of edge computing devices in an agricultural environment, the computer program instructions, when executed by one or more processors, causing the one or more processors to:

detect, using signals by generated by one sensors of the first edge computing device, a second edge computing device of the plurality of edge computing devices near the first edge computing device;

determine, based on the detected second edge computing device, an ordinal position of the first edge computing device relative to the second edge computing device;

determine, based on visual signals generated by a visual sensor of the first edge computing device, a distance to the second edge computing device; and

determine the extrinsic parameters of the first edge computing device based on the ordinal position of the first edge computing device and the distance to the second edge computing device.

12 . The non-transitory computer-readable storage medium of claim 11 , wherein detecting the second edge computing device causes the one or more processors to:

receive, from the second edge computing device, a wireless communication comprising position and distance information.

13 . The non-transitory computer-readable storage medium of claim 12 , wherein determining the ordinal position of the first edge computing device is additionally based on the wirelessly received position and distance information.

14 . The non-transitory computer-readable storage medium of claim 12 , wherein determining the distance to the second edge computing device based on visual signals generated by the visual sensor of the first edge computing device is additionally based on the wirelessly received position and distance information.

15 . The non-transitory computer-readable storage medium of claim 11 , wherein executing the computer program instructions further cause the one or more processors to:

receive, from a server computing system, an agricultural inference about the agricultural environment; and

wherein automatically determining the extrinsic parameters of the first edge computing device occurs on a local system in response to receiving the agricultural inference.

16 . The non-transitory computer-readable storage medium of claim 11 , wherein determining the distance to the second edge computing device based on visual signals generated by the visual sensor of the first edge computing device causes the one or more processors to:

identify at least one visual features detected in a first region of a first image captured by the visual sensor of the first edge computing device that is the same as one or more visual features detected in a second region of a second image captured by a visual sensor of the second edge computing device; and

determine the distance to the second edge computing device based on the at least one visual feature that is the same between the first image and the second image.

17 . The non-transitory computer-readable storage medium of claim 11 , wherein determining the ordinal position of the first edge computing device causes the one or more processors to:

identify a visual feature detected in a first image captured by the visual sensor of the first edge computing device representing the second edge computing device; and

determine the ordinal position of the first edge computing device based on the identified visual feature.

18 . The non-transitory computer-readable storage medium of claim 11 , wherein the first edge computing device is mounted to an agricultural robot operating in the agricultural environment.

19 . The non-transitory computer-readable storage medium of claim 11 , wherein the second edge computing device is mounted to an agricultural vehicle operating in the agricultural environment.

20 . An agriculture robot comprising:

one or more sensors configured to generate signals representing position and location information in an agricultural environment;

a visual sensor configured to capture images of the agricultural environment;

a first edge computing device of a plurality of edge computing devices in the agricultural environment;

one or more processors; and

a non-transitory computer-readable storing medium storing computer program instructions for automatically determining extrinsic parameters of the first edge computing device of a plurality of edge computing devices, the computer program instructions, when executed by the one or more processors, causing the one or more processors to:

detect, using signals by generated by the one sensors, a second edge computing device near the first edge computing device;

determine, based on the detected second edge computing device, an ordinal position of the first edge computing device relative to the second edge computing device;

determine, based on visual signals generated by a visual sensor of the first edge computing device, a distance to the second edge computing device; and

determine the extrinsic parameters of the first edge computing device based on the ordinal position of the first edge computing device and the distance to the second edge computing device.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 31, 2025
From: GRANT, ELLIOTT; YAROSHENKO, SERGEY; LEVINE, GABRIELLA
To: X DEVELOPMENT LLC
Reel/Frame 070069/0494 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 31, 2025
From: X DEVELOPMENT LLC
To: MINERAL EARTH SCIENCES LLC
Reel/Frame 070069/0510 →
MERGER Recorded Jan 31, 2025
From: MINERAL EARTH SCIENCES LLC
To: DEERE & COMPANY
Reel/Frame 070070/0656 →
Continuity (3)
Continuation 18223859 · Jul 19, 2023
Continuation 17505058 · Oct 19, 2021
Related Publication 20250168312A1 · May 22, 2025
References Cited (22)
US 8922626B2 · Aoki · 2014 [cited by applicant]
US 9325917B2 · Macmillan et al. · 2016 [cited by applicant]
US 10255670B1 · Wu et al. · 2019 [cited by applicant]
US 10499037B1 · Wilcox · 2019 [cited by applicant]
US 11315258B1 · Anagnostopoulos · 2022 [cited by applicant]
US 20130229497A1 · Delacoux · 2013 [cited by applicant]
US 20200357138A1 · Xiang et al. · 2020 [cited by applicant]
US 20210185886A1 · Sibley et al. · 2021 [cited by applicant]
US 20210283642A1 · Smith · 2021 [cited by applicant]
US 20230047045A1 · Wieckhorst · 2023 [cited by examiner]
US 20230120944A1 · Grant et al. · 2023 [cited by applicant]
Cerfontaine et al., “Automatic Multi-Camera Setup Optimization for Optical Tracking” IEEE Virtual Reality. Mar. 2006. pp. 25-29. [cited by applicant]
Knorr et al., “Online Extrinsic Multi-Camera Calibration Using Ground Plane Induced Homographies” IEEE Intelligent Vehicles Symposium. Gold Coast, Australia. Dated Jun. 2013. pp. 236-241. [cited by applicant]
Lin et al., “Infrastructure-based Multi-Camera Calibration using Radial Projections” arXiv:2007.15330v2 [cs.CV] Dated Sep. 16, 2020. 17 pages. [cited by applicant]
Luck et al., “Potential for Pesticide and Nutrient Savings Via Map-Based Automatic Boom Section Control of Spray Nozzles” Computers and Electronics in Agriculture 70 (2010). pp. 19-26. [cited by applicant]
Mark Deutsch, “Impact of Boom Height Sensor Placement and Quantity on Boom Height Error” Iowa State University Digital Repository. Graduate Theses and Dissertations. 2020. 28 pages. [cited by applicant]
Thessler et al., “Geosensors to Support Crop Production: Current Applications and User Requirements” Sensors 2011, 11, 6656-6684; doi:10.3390/s110706656. ISSN 1424-8220. 29 pages. [cited by applicant]
Truong et al., “Automatic Multi-Camera Extrinsic Parameter Calibration Based on Pedestrian Torsors” Sensors 2019, 19. 4989; doi:10.3390/s19224989. www.mdpi.com/joumal/sensors. Nov. 15, 2019. 26 pages. [cited by applicant]
Vellidis et al., “How Wireless Will Change Agriculture” Stafford, J.V. (Ed.), Precision Agriculture '07. Proceedings of the Sixth European Conference on Precision Agriculture (6ECPA), Skiathos, Greece, pp. 57-67. [cited by applicant]
Wei et al, “Extrinsic Parameters Calibration of Multi-Camera with Non-Overlapping Fields of View Using Laser Scanning” https://doi.org/10.1364/OE.27.016719. Dated May 31, 2019. 19 pages. [cited by applicant]
Yao et al., “Multi-Camera Positioning for Automated Tracking Systems in Dynamic Environments” International Journal of Information Acquisition. vol. 7, No. 3 (2010) 225-242. doi:10.1142/S0219878910002208. 19 pages. [cited by applicant]
United States Office Action, U.S. Appl. No. 17/505,058, Dec. 14, 2022, 20 pages. [cited by applicant]