IP Library Granted Patent US 12,567,048
Granted Patent B2
US 12,567,048 · App. 17/477,723 · Granted Mar 3, 2026

Hardware system for identifying grab- and-go transactions in a cashierless store

Inventors: Davi Geiger (Old Greenwich, CT); Carlos Henrique Cavalcanti Corrêa (Rio de Janeiro, BR)
Assignee: Kooick Inc.
G06Q20/203G06Q20/202G06Q20/206G06V20/13G06F2218/16
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 12,567,048
App. No.
17/477,723
Granted
Mar 3, 2026
Kind
B2
Abstract

A method and system for detecting a commercial transaction through physical interactions with products, the system comprising a frame that is placed within a product display unit. The frame includes a shelf, at least one camera, a weight sensor, and display screens. The system further comprises a computing device communicatively connected to the frame. The computing device is configured to detect physical interactions with items that are placed on the shelf based on data that is received from the at least one camera and the weight sensor. The computing device is further configured to determine a commercial transaction associated with physical interactions and transmit item and price data to the display screens based on machine learning of the physical interactions with items.

Claims (64)

1 . A system for detecting a commercial transaction through physical interactions with one or more items in a pod, the pod comprising at least one shelf, the at least one shelf comprising a plurality of lanes along a width of the at least one shelf from a left side to a right side of the at least one shelf having items up to height A arranged along a depth D of the at least one shelf from a front of the at least one shelf towards a rear of the at least one shelf, the system comprising:

at least one camera positioned within the pod between two lanes of the plurality of lanes to capture photos of items from the two lanes of the plurality of lanes on the at least one shelf, and wherein the at least one camera and the at least one shelf are inclined with respect to each other an inclination of an angle θ sufficient to allow the at least one camera to see items on or towards the rear of the at least one shelf without being completely occluded by items towards the front of the at least one shelf, the at least one camera and at least one shelf having an adjustment mechanism for adjusting the inclination of the at least one camera and at least one shelf; and

a computing device communicatively connected to the at least one camera and at least one shelf, the computing device configured to:

recognize physical interactions with items on the at least one shelf based on data that is received from the at least one camera during a pod use session, the data including one or more image frames taken by the at least one camera;

determine, using artificial intelligence, a commercial transaction representing one or more items removed from or added to the at least one shelf associated with the physical interactions,

transmit item and price data based on the determined commercial transaction;

determine an adjusted angle θ of inclination to cover the depth D for items up to the height A in the two lanes while preventing occlusions following removal or addition of the one more items from the at least one shelf; and

control the adjustment mechanism to change the inclination of the at least one camera or at least one shelf to the adjusted angle θ.

2 . The system of claim 1 wherein the pod includes at least one front camera and/or at least one rear camera.

3 . The system of claim 1 wherein the pod includes at least a motor that is configured to move the at least one camera along the width of the at least one shelf.

4 . The system of claim 1 wherein the pod further comprises display screens configured to simulate price tags for the items.

5 . The system of claim 1 wherein the computing device is further configured to interact with consumers via a real time voice recognition system.

6 . The system of claim 1 wherein the at least one camera is configured at a height h above the at least one shelf, the at least one camera including an angle view Φ and being configured according to the angle θ for covering the depth D of items of height up to A to be seen.

7 . The system of claim 6 wherein the angle θ includes an angle the at least one camera makes with the at least one shelf to cover a first item at a distance d.

8 . The system of claim 7 wherein

θ

=

π

2

-

Φ

2

-

tan

-

1

d

h

.

9 . The system of claim 7 wherein depth

D

=

h

-

A

tan

(

π

2

-

Φ

-

tan

-

1

d

h

)

,

the maximum depth that the at least one camera can cover.

10 . The system of claim 1 wherein the adjustment mechanism is configured to adjust angle and direction of the at least one camera.

11 . The system of claim 1 further comprising a jig including a plurality of mechanisms including a plurality of cameras, the plurality of mechanisms configured to simultaneously adjust angle and direction of the plurality of cameras.

12 . The system of claim 11 wherein the jig further comprises a motor mechanism configured to move the at least one camera along a width of the at least one shelf.

13 . The system of claim 1 further comprising video cameras coupled to the computing device, the video cameras configured to monitor activities outside of the pod to check items leaving and returning to the pod.

14 . The system of claim 1 wherein the pod further comprises display screens, the display screens including information indicating item availability and item characteristics, wherein the information is programmable via the computing device.

15 . The system of claim 1 wherein the pod further comprises display screens and wherein the computing device is further configured to transmit promotions from a list of predefined promotions to the display screens.

16 . The system of claim 1 wherein the pod further comprises display screens and wherein the computing device is further configured to transmit dynamic pricing to the display screens.

17 . The system of claim 1 wherein the pod further comprises display screens and wherein the computing device is further configured to transmit price updates and promotions to the display screens based on machine learning of objectives set by a vendor.

18 . The system of claim 1 further comprising a hub executing a power up sequence of the at least one shelf and transmitting a command to the at least one shelf to power up the at least one camera.

19 . The system of claim 1 further comprising a tiered USB hub and controller configuration.

20 . The system of claim 1 , wherein the pod further comprises at least one weight sensor.

Continuity (2)
Provisional Application 63079623 · Sep 17, 2020
Related Publication 20220084005A1 · Mar 17, 2022
References Cited (34)
US 9330474B1 · Shekar · 2016 [cited by examiner]
US 9996818B1 · Ren · 2018 [cited by examiner]
US 10064502B1 · Gyori · 2018 [cited by applicant]
US 10121121B1 · De Bonet · 2018 [cited by applicant]
US 10140820B1 · Zalewski · 2018 [cited by applicant]
US 11636740B2 · Zalewski · 2023 [cited by applicant]
US 11741447B1 · Matheson · 2023 [cited by applicant]
US 11879213B2 · Pereira Maia · 2024 [cited by applicant]
US 11893534B2 · Hines · 2024 [cited by applicant]
US 20120004769A1 · Hallenbeck · 2012 [cited by examiner]
US 20130039543A1 · Fuhr · 2013 [cited by applicant]
US 20140039951A1 · Appel · 2014 [cited by applicant]
US 20150019391A1 · Kumar · 2015 [cited by applicant]
US 20160364686A1 · Wolfe · 2016 [cited by examiner]
US 20170228686A1 · Bermudez Rodriguez · 2017 [cited by applicant]
US 20190088096A1 · King · 2019 [cited by applicant]
US 20200118400A1 · Zalewski · 2020 [cited by applicant]
US 20200184230A1 · Liu · 2020 [cited by applicant]
US 20200184442A1 · Gu · 2020 [cited by applicant]
US 20200184444A1 · Gu · 2020 [cited by applicant]
US 20200184447A1 · Gu · 2020 [cited by applicant]
US 20210342805A1 · Geiger · 2021 [cited by applicant]
US 20210406813A1 · Liu · 2021 [cited by examiner]
US 20220067689A1 · Guack · 2022 [cited by examiner]
WO WO2021150406A1 · 2021 [cited by examiner]
Milella, Annalisa, Towards Intelligent Retail: Automated On-Shelf Availability Estimation Using a Depth Camera, 2021 23rd International Conference on Control Systems and Computer Science, pp. 243-248. (Year: 2020). [cited by examiner]
R.S.C. Broadband Supply Co., Lenses for Video Motion Detection, 2006 (Year: 2006). [cited by examiner]
CCTVCAD Software, CCTV Design Lens Calculator (Year: 2019). [cited by examiner]
Annalisa Milella, Towards Intelligent Retail: Automated On-Shelf Availability Estimation Using a Depth Camera, Jan. 30, 2020, IEEEAccess, Institute of Intelligent Industrial Systems and Technologies for Advanced Manufac… [cited by examiner]
PCT International Search Report and Written Opinion for International Application No. PCT/US2021/036300, Sep. 21, 2021 (11 pages). [cited by applicant]
Douglas et al. “Amazon Go, the cashierless retail store of the future, has some new competition.” Nov. 12, 2019 (Nov. 12, 2019) Retrieved on Aug. 10, 2021 (Aug. 10, 2021) from <https://www.cnbc.com/2019/11 /12/amazon-go… [cited by applicant]
Ives et al. “Amazon Go: Disrupting retail?” Journal of Information Technology Teaching Cases 9.1 (2019): 2-12. Mar. 26, 2019 (Mar. 26, 2019) Retrieved on Aug. 10, 2021 (Aug. 10, 2021) from <https://journals.sagepub.com/… [cited by applicant]
Schmidt et al. “Ubiquitous interaction-using surfaces in everyday environments as pointing devices.” ERCIM Workshop on User Interfaces for All. Springer, Berlin, Heidelberg, 2002. Mar. 14, 2003 (Mar. 14, 2003) Retrieved… [cited by applicant]
EPO Search Report for Application No. 21796707.4, Oct. 5, 2023 (9 pages). [cited by applicant]