Delivery system

Patent metadata

Field	Value
Publication number	US-11087160-B2
Application number	US-202117204088-A
Country	US
Kind code	B2
Filing date	Mar 17, 2021
Priority date	Feb 25, 2019
Publication date	Aug 10, 2021
Grant date	Aug 10, 2021

Abstract

A delivery system generates a pick sheet containing a plurality of SKUs based upon an order. A loaded pallet is imaged to identify the SKUs on the loaded pallet, which are compared to the order prior to the loaded pallet leaving the distribution center. The loaded pallet may be imaged while being wrapped with stretch wrap. At the point of delivery, the loaded pallet may be imaged again and analyzed to compare with the pick sheet.

First claim

What is claimed is:

1. A delivery system comprising:
at least one computer programmed to perform the steps of:
a) receiving a pick sheet for a plurality of SKUs, wherein each SKU has an associated package type and an associated brand, and wherein not all brands are available in all package types;
b) receiving at least one image of a plurality of items stacked together;
c) analyzing the at least one image to identify a package type of one of the plurality of items;
d) based upon the identified package type from said step c) identifying a subset of possible brands of the one of the plurality of items;
e) determining a brand of the one of the plurality of items based upon the identified subset of brands from said step d);
f) identifying the SKU of the one of the plurality of items based upon said steps d) and e);
g) repeating steps c) to f) for each of the plurality of items;
h) comparing the SKUs identified in step f) to the SKUs on the pick sheet; and
i) indicating whether the SKUs identified in step f) match the SKUs on the pick sheet based upon the comparison in step h).

2. The system of claim 1 wherein the at least one computer includes a machine learning model trained with images of cases of beverage containers.

3. The system of claim 2 wherein the machine learning model is trained to identify a plurality of available package types including reusable beverage crate, tray with translucent wrap, and fully enclosed box, wherein the at least one computer is programmed to perform said step c) using the machine learning model.

4. The system of claim 1 wherein in said step b), the plurality of items in the at least one image are stacked on a platform.

5. The system of claim 4 wherein the platform is a pallet.

6. The system of claim 5 wherein the at least one computer is further programmed to perform the step of indicating that a SKU from the pick sheet is missing on the pallet.

7. The system of claim 5 wherein the plurality of items are containers of beverage containers.

8. The system of claim 5 further including at least one camera for generating the at least one image.

9. The system of claim 8 wherein the at least one camera is a depth camera.

10. The system of claim 8 wherein the at least one camera is mounted to a wrapper configured to wrap the plurality of items stacked on the pallet.

11. A validation system comprising:
a camera configured to generate at least one image of a plurality of items each having an associated SKU; and
at least one computer programmed to:
a) analyze the at least one image to identify a package type of one of the plurality of items;
b) determine a brand of the one of the plurality of items;
c) identify the associated SKU of the one of the plurality of items based upon said steps a) and b);
d) perform steps a) to c) for each of the plurality of items;
e) comparing the SKUs identified in step c) to SKUs on a pick sheet.

12. The system of claim 11 wherein the at least one computer is programmed to determine the brand of the one of the plurality of items in step b) by analyzing the at least one image.

13. The validation system of claim 12 wherein at least one computer is programmed to perform said step a) while the plurality of items are on a pallet and wherein the plurality of items are containers of beverage containers.

14. The validation system of claim 11 wherein said step a) is performed before said step b).

15. The validation system of claim 14 further including the step of: c) based upon the identified package type from said step a) identifying a subset of possible brands of the one of the plurality of items; and wherein said step b) includes determining the brand of the one of the plurality of items based upon the identified subset of brands from said step c).

16. The validation system of claim 15 further including a turntable for receiving and rotating the plurality of items while the camera generates the at least one image, wherein the at least one image is a plurality of images.

17. The validation system of claim 16 wherein the plurality of items are on a platform.

18. The validation system of claim 17 further including an RFID reader for reading an RFID tag on the platform when it is on the turntable.

19. The validation system of claim 11 wherein the at least one computer includes at least one machine learning model trained on images of cases of beverage containers of a plurality of available package types including the package types of the plurality of items and of a plurality of available brands including the brands of the plurality of items.

20. The validation system of claim 19 wherein the at least one computer is programmed to perform said steps a) and b) using the at least one machine learning model.

21. The validation system of claim 20 wherein the at least one machine learning model is trained on images of containers of beverage containers on a pallet.

22. A method for delivery validation including the steps of:
a) bringing to a store a plurality of items on a pallet in response to an order, wherein the items are containers of beverage containers;
b) imaging the plurality of items on the pallet after step a) to generate at least one store image;
c) analyzing the at least one store image to determine SKUs of the plurality of items;
d) comparing the SKUs determined in step c) to the order; and
e) indicating whether the SKUs of the plurality of items match the order.

23. The method of claim 22 wherein step b) includes imaging multiple sides of the plurality of items and wherein the at least one store image is a plurality of store images; and wherein step c) includes determining the SKUs of the items visible in each of the plurality of store images and removing duplicate items that appear in more than one of the plurality of images.

24. The method of claim 23 wherein said step c) is performed by at least one computer including a machine learning model trained with images of cases of beverage containers.

25. The method of claim 23 wherein said step c) includes the step of determining layers of the plurality of items on the pallet in each of the plurality of store images.

26. The method of claim 25 further including the step of removing a wrap around the plurality of items prior to step b).

27. A delivery system comprising:
at least one computer programmed to perform the steps of:
a) receiving a pick sheet for a plurality of SKUs, wherein each SKU has an associated package type and an associated brand;
b) receiving a plurality of images of a plurality of items stacked together, wherein the plurality of images are taken from a plurality of sides of a stack of the plurality of items;
c) determining that a first item of the plurality of items is visible in a first image of the plurality of images and in a second image of the plurality of images;
d) analyzing the first image to determine a first SKU of the first item at a first confidence level;
e) analyzing the second image to determine a second SKU of the first item at a second confidence level;
f) determining the SKU of the first item based upon a higher of the first confidence level or the second confidence level; and
g) repeating steps c) to f) for each of a subset of the plurality of items.

28. The system of claim 27 wherein the at least one computer is further programed to perform the steps of:
h) comparin

Assignees

• Rehrig Pacific Co

Inventors

• Martin Jr Robert Lee
• Mahesh Kalpana
• Herstad Rachel
• John Georgey
• Tatineni Hari Durga
• Agarwal Rahul
• Miller Jason Crawford
• Raghunathan Ravi
• Melendez Joseph
• Petrochilos Deanna
• Burden Charles

Classifications

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06V10/147 Primary

  Details of sensors, e.g. sensor lenses (fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19) · CPC title

• G06Q10/087 Primary

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

• B65G1/1378

  the orders being assembled on fixed commissioning areas remote from the storage areas · CPC title