IP Library Granted Patent US 12,249,097
Granted Patent B2
US 12,249,097 · App. 17/667,438 · Granted Mar 11, 2025

Object collection system and method

Inventors: Brent Ronald Frei (Bellevue, WA); Dwight Galen McMaster (Burien, WA); Michael Racine (Bellevue, WA); Jacobus du Preez (Snoqualmie, WA); William David Dimmit (Seattle, WA); Isabelle Butterfield (Bellevue, WA); Clifford Holmgren (Spanaway, WA); Dafydd Daniel Rhys-Jones (Tacoma, WA); Thayne Kollmorgen (Eugene, OR); Vivek Ullal Nayak (Seattle, WA)
Assignee: TerraClear Inc.
G06T7/74A01B43/00A01B59/042A01B69/001G05D1/0038G05D1/101G06F18/211G06F18/214G06F18/2163G06F18/217G06F18/285G06N3/045G06N3/08G06T3/00G06T7/0002G06T7/13G06T7/60G06T7/62G06T7/70G06T7/73G06V10/255G06V20/10G06V20/188G06V20/38G08G5/0034G08G5/0069B64U10/13B64U2101/30B64U2101/60B64U2201/20G06T2207/10032G06T2207/20081G06T2207/20084G06T2207/20104G06T2207/30188G06T2207/30244
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 12,249,097
App. No.
17/667,438
Granted
Mar 11, 2025
Kind
B2
Abstract

An object-collection system is disclosed. The system including a vehicle connected to a bucket, a camera connected to the vehicle, and an object picking assembly configured to pick up objects off of ground. The system further includes a processor that obtains object information for identified objects, guides the object-collection system over a target geographical area toward the identified objects based on the object information, captures images of the ground relative to the object picker as the object-collection system is guided towards the identified objects, identifies a target object in the images, tracks movement of the target object across the images as the object-collection system is guided towards the identified objects, and employs the tracked movement of the target object to instruct the object picker to pick up the target object.

Claims (56)

1. An object collection system, the system including:

a vehicle connected to a bucket;

multiple cameras connected to the vehicle;

an object picking assembly configured to pick up objects off of ground, the object picking assembly disposed at a front-end of the bucket, the object picking assembly including one or more paddle components with one or more moving belts and a hinge on at least one of the one or more paddle components;

a sensor array associated with the system;

a processor; and

a memory that stores computer instructions that, when executed by the processor, cause the processor to:

scan a region that includes a catcher swath to identify one or more objects;

guide the object collection system over a target geographical area toward the one or more identified objects based on object information;

capture, via the multiple cameras, a plurality of images of the ground relative to an object picker as the object collection system is guided towards the one or more identified objects, the object picker having the catcher swath to pick up the one or more identified objects;

identify a target object on the ground from among the one or more identified objects in the plurality of images based on a dataset of known object features;

track movement of the ground relative to the moving vehicle across the plurality of images as the object collection system is guided towards the one or more identified objects; and

employ the tracked movement of the ground to instruct the object picker to move the one or more paddles from a storage height to a pick-up height to pick up the target object using the hinge on the at least one of the one or more paddle components to pinch the target object to be picked up from the ground using the one or more paddles while the object-collection system is in movement; and

picking up the target object from the ground while the object-collection system is in movement and moving the one or more paddles from the pick-up height to the storage height after the target object has been picked.

2. The system of claim 1 , wherein the object picking assembly includes two or more paddle components with one or more moving belts on each of the two or more paddle components.

3. The system of claim 2 , wherein the one or more moving belts on each of the two or more paddle components of the object picking assembly move to pull the one or more identified objects in between the two or more paddle components.

4. The system of claim 2 , wherein the two or more paddle components of the object picking assembly include multiple joints which enable repositioning of an object of the one or more identified objects after the object of the one or more identified objects has been picked up.

5. The system of claim 2 , wherein the two or more paddle components of the object picking assembly include three paddle components, and wherein at least one of the three paddle components includes a hinge that enables an object of the one or more identified objects to be pinched.

6. The system of claim 2 , wherein the two or more paddle components of the object picking assembly include three paddle components, wherein a first two of the paddle components are fixed in position with respect to each other, and a third paddle component is spaced apart from the first two of the paddle components, and wherein the third paddle component includes a hinge that enables an object of the one or more identified objects to be pinched.

7. The system of claim 1 , wherein the sensor array determines whether or not the object picking assembly successfully picks up an object.

8. The system of claim 1 , wherein the sensor array includes one or more altitude sensors that determine the distance between the ground and at least one of the object picking assembly and the bucket.

9. The system of claim 1 , wherein the plurality of images taken by the multiple cameras identify and tag false negatives, wherein a false negative is an object that was not included in the one or more identified objects in obtained object information, and wherein tagging the false negative includes dropping virtual pins at locations of the false negatives in stored mapping data.

10. The system of claim 1 , wherein, when the movement of the target object is tracked across the plurality of images, the object collection system applies a parallax correction to pick up the target object at a correct location.

11. The system of claim 1 , wherein if an object of the one or more identified objects is unable to be picked up by the object picking assembly, the object collection system leaves the object and tags the unpicked object of the one or more identified objects by dropping a virtual pin at a location of the unpicked object of the one or more identified objects in stored mapping data.

12. The system of claim 1 , wherein the bucket has a width dimension, and wherein the object picking assembly is movably connected to the bucket, enabling the object picking assembly slide to laterally along the width of the bucket to assist in positioning for picking up the objects.

13. The system of claim 1 , wherein the bucket is positioned a height distance above the ground, and wherein the object picking assembly is movably connected to the bucket, enabling the object picking assembly to move towards the ground with respect to the bucket in picking up the objects, wherein a time that it takes the object picking assembly to move from an initial position to contact with the object to be picked is called sting time.

14. The system of claim 1 , wherein the object picking assembly is operatively associated with the bucket, and wherein the system includes one or more picker arms for manipulating the object picking assembly with respect to an object of the one or more identified objects to be picked.

15. The system of claim 1 , wherein the system includes a picker arm for manipulating the object picking assembly with respect to an object of the one or more identified objects to be picked, and wherein the picker arm has one or more degrees of freedom.

16. The system of claim 1 , wherein the system includes one or more picker arms for manipulating the object picking assembly with respect to an object of the one or more identified objects to be picked, and wherein the one or more picker arms are extendable, enabling the object picking assembly to move away from the bucket and towards the object of the one or more identified objects to be picked on the ground, and wherein the one or more picker arms are retractable, enabling the object picking assembly to move towards the bucket and away from the ground after the object of the one or more identified objects has been picked.

17. The system of claim 1 , wherein the system includes one or more picker arms for manipulating the object picking assembly with respect to an object of the one or more identified objects to be picked, and wherein the one or more picker arms are extendable and retractable by one segment of one or more picker arms telescoping within another segment of the one or more picker arms.

18. The system of claim 1 , wherein the bucket is rotatably associated with the vehicle, enabling the bucket to rotate and dump picked objects that have been placed in the bucket.

19. The system of claim 1 , wherein the bucket and the object picking assembly are positioned on a front side of the vehicle.

20. The system of claim 1 , wherein the bucket and the object picking assembly are pulled behind the vehicle.

21. The system of claim 1 , wherein the object collection system includes a plurality of buckets and a plurality of object picking assemblies.

22. The system of claim 1 , further comprising: an in-cab display screen that presents a visual representation of the one or more identified objects approaching the vehicle.

23. The system of claim 1 , wherein the vehicle is driven autonomously along a determined path to pick up the one or more identified objects.

24. The system of claim 1 , wherein object picking success is confirmed using load sensors associated with the bucket.

25. The system of claim 1 , wherein object picking success is confirmed using a three dimensional camera system and volumetric estimates.

26. The system of claim 1 , further including a rear facing camera to identify object that failed to be picked up by the object collection system.

27. A method for an object collection system, the object collection system including a vehicle connected to a bucket, the multiple cameras connected to the vehicle, an object picking assembly configured to pick up objects off of ground, the object picking assembly disposed at a front-end of the bucket, a sensor array disposed on the bucket, a memory that stores computer instructions, and a processor that executes the stored computer instructions, the method comprising:

scanning a region that includes a catcher swath to identify one or more objects;

guiding the object collection system over the target geographical area toward the one or more identified objects based on object information;

capturing, via the multiple cameras, a plurality of images of the ground relative to an object picker as the object collection system is guided towards the one or more identified objects, the object picker having the catcher swath to pick up the one or more objects;

identifying a target object on the ground from among the one or more identified objects in the plurality of images based on a dataset of known object features;

tracking movement of the ground relative to the moving vehicle across the plurality of images as the object collection system is guided towards the one or more identified objects; and

employing the tracked movement of the ground to instruct the object picker to pick up the target object.

28. An object-collection system, the system including:

an object picking assembly configured to pick up objects off of ground, the object picking assembly positioned at a front-end of a bucket;

a processor; and

a memory that stores computer instructions that, when executed by the processor, cause the processor to:

scan a region that includes a catcher swath to identify one or more objects;

guide the object-collection system over a target geographical area toward the one or more identified objects based on object information;

receive a plurality of images of the ground relative to an object picker as the object-collection system is guided towards the one or more identified objects, the object picker having the catcher swath to pick up the one or more objects;

identify a target object on the ground from among the one or more identified objects in the plurality of images based on a dataset of known object features;

track movement of the ground relative to the moving vehicle across the plurality of images as the object-collection system is guided towards the one or more identified objects; and

employ the tracked movement of the ground to instruct the object picker to pick up the target object.

Continuity (3)
Continuation 16510776 · Jul 12, 2019
Provisional Application 62697057 · Jul 12, 2018
Related Publication 20220164941A1 · May 26, 2022
References Cited (72)
US 6456991B1 · Srinivasa et al. · 2002 [cited by applicant]
US 6792147B1 · Saka et al. · 2004 [cited by applicant]
US 8903177B2 · Livet et al. · 2014 [cited by applicant]
US 9514389B1 · Erhan et al. · 2016 [cited by applicant]
US 9607220B1 · Smith et al. · 2017 [cited by applicant]
US 9811082B2 · Tillmann · 2017 [cited by applicant]
US 9830706B2 · Barajas Hernandez et al. · 2017 [cited by applicant]
US 10189568B2 · O'Connor et al. · 2019 [cited by applicant]
US 10303172B2 · Hwang et al. · 2019 [cited by applicant]
US 10796275B1 · Wilkins · 2020 [cited by applicant]
US 10861184B1 · Kalakrishnan et al. · 2020 [cited by applicant]
US 11017518B2 · Frei et al. · 2021 [cited by applicant]
US 11074680B2 · Frei et al. · 2021 [cited by applicant]
US 11138712B2 · Frei et al. · 2021 [cited by applicant]
US 20030165258A1 · Kubota et al. · 2003 [cited by applicant]
US 20080159622A1 · Agnihotri et al. · 2008 [cited by applicant]
US 20090038186A1 · Osswald et al. · 2009 [cited by applicant]
US 20100250024A1 · Macedo Ribeiro et al. · 2010 [cited by applicant]
US 20110053642A1 · Lee · 2011 [cited by applicant]
US 20110305445A1 · Yasuda et al. · 2011 [cited by applicant]
US 20120124037A1 · Lee et al. · 2012 [cited by applicant]
US 20120201469A1 · Livet et al. · 2012 [cited by applicant]
US 20120290152A1 · Cheung et al. · 2012 [cited by applicant]
US 20140007730A1 · DeLouis · 2014 [cited by applicant]
US 20140211987A1 · Fan et al. · 2014 [cited by applicant]
US 20140343955A1 · Raman · 2014 [cited by applicant]
US 20160063420A1 · Tomii et al. · 2016 [cited by applicant]
US 20160070265A1 · Liu et al. · 2016 [cited by applicant]
US 20160202227A1 · Mathur et al. · 2016 [cited by applicant]
US 20160309650A1 · Jens et al. · 2016 [cited by applicant]
US 20160340120A1 · Curotto et al. · 2016 [cited by applicant]
US 20160378109A1 · Raffa et al. · 2016 [cited by applicant]
US 20170154273A1 · Guttman · 2017 [cited by applicant]
US 20170300514A1 · Yan et al. · 2017 [cited by applicant]
US 20170351933A1 · Bleiweiss · 2017 [cited by applicant]
US 20180109767A1 · Li et al. · 2018 [cited by applicant]
US 20180150718A1 · Omari et al. · 2018 [cited by applicant]
US 20180189971A1 · Hildreth · 2018 [cited by applicant]
US 20180319396A1 · Foster et al. · 2018 [cited by applicant]
US 20180335779A1 · Fisher et al. · 2018 [cited by applicant]
US 20190028676A1 · Koga et al. · 2019 [cited by applicant]
US 20190049968A1 · Dean · 2019 [cited by examiner]
US 20190050685A1 · Kaminski et al. · 2019 [cited by applicant]
US 20190166765A1 · Maor · 2019 [cited by applicant]
US 20190294914A1 · Fevold et al. · 2019 [cited by applicant]
US 20190318636A1 · Gu · 2019 [cited by applicant]
US 20200015401A1 · Frei et al. · 2020 [cited by applicant]
US 20200019752A1 · Frei et al. · 2020 [cited by applicant]
US 20200019778A1 · Frei et al. · 2020 [cited by applicant]
US 20200019825A1 · Frei et al. · 2020 [cited by applicant]
US 20200020093A1 · Frei et al. · 2020 [cited by applicant]
US 20210272264A1 · Frei et al. · 2021 [cited by applicant]
US 20210358104A1 · Frei et al. · 2021 [cited by applicant]
US 20220028048A1 · Frei et al. · 2022 [cited by applicant]
BE 1024513B1 · 2018 [cited by applicant]
CA 2359237A1 · 2000 [cited by applicant]
CA 3034059A1 · 2018 [cited by applicant]
CA 3024573C · 2021 [cited by examiner]
KR 20170065337A · 2017 [cited by applicant]
WO 2008048700A2 · 2008 [cited by applicant]
WO 2013097252A1 · 2013 [cited by applicant]
WO 2016123656A1 · 2016 [cited by applicant]
WO 2017077543A1 · 2017 [cited by applicant]
WO 2017144291A1 · 2017 [cited by applicant]
WO 2017170651A1 · 2017 [cited by applicant]
WO 2017199088A1 · 2017 [cited by applicant]
WO 2018033922A1 · 2018 [cited by applicant]
WO 2018087546A1 · 2018 [cited by applicant]
WO 2018201180A1 · 2018 [cited by applicant]
Shi et al., “Ship Classification Based on Multifeature Ensemble with Convolutional Neural Network,” [cited by applicant]
Wen et al., “Ensemble of Deep Neural Networks with Probability-Based Fusion for Facial Expression Recognition,” [cited by applicant]
Lehnert et al., “Autonomous Sweet Pepper Harvesting for Protected Cropping Systems,” [cited by applicant]