Methods and apparatuses for automatically palletizing and depallitizing items

Patent metadata

Field	Value
Publication number	US-12229713-B2
Application number	US-202117379316-A
Country	US
Kind code	B2
Filing date	Jul 19, 2021
Priority date	Jul 19, 2021
Publication date	Feb 18, 2025
Grant date	Feb 18, 2025

Abstract

Method, apparatuses, and computer program products for automatically determining a placement location or removal location for one or more items is disclosed. An example method comprising generating a plurality of three-dimensional pallet cells for a pallet; generating one or more three-dimensional item cells for each item of a plurality of items; determining a placement location comprising one or more three-dimensional pallet cells for one or more items of the plurality of items; and causing one or more indications describing the placement location for the one or more items of the plurality of items.

First claim

That which is claimed:

1. A computer-implemented method for determining one or more placement locations on a pallet for one or more items of a plurality of items, the computer-implemented method comprising:
generating, using one or more processors, a plurality of three-dimensional pallet cells for the pallet having a pallet volume, wherein the plurality of three-dimensional pallet cells is arranged to segment said pallet volume such that each three-dimensional cell is associated with a cell volume that is at least a portion of the pallet volume;
generating, using the one or more processors, one or more three-dimensional item cells for each item of the plurality of items, wherein each item has a corresponding item volume, and wherein the one or more three-dimensional item cells for each item contain the corresponding item volume;
training, using the one or more processors, a predictive machine learning model to select from the one or more placement locations each comprising one or more three-dimensional pallet cells for the one or more three-dimensional item cells corresponding to each item by utilizing at least one location score for at least one placement location for the one or more three-dimensional item cells, wherein the at least one location score is determined based on overall volume occupancy data of the pallet, wherein the overall volume occupancy data is determined based on a number of three-dimensional pallet cells that are associated with an occupied state, and wherein the at least one location score is increased when one of the plurality of items is placed in a placement location associated with a high occupancy of an adjacent three-dimensional item cell; and
causing, using the one or more processors, one or more prediction-based actions to be performed by a robotic arm on the one or more items based at least in part on the one or more placement locations.

2. The computer-implemented method of claim 1 further comprising:
updating, using the one or more processors, an occupancy state associated with each of the one or more three-dimensional pallet cells based at least in part on the one or more placement locations determined for the one or more three-dimensional pallet cells corresponding to the one or more items.

3. The computer-implemented method of claim 2 , wherein updating the occupancy state of the one or more three-dimensional pallet cells further comprises:
receiving, from one or more computing devices, an item characteristic data object for the one or more items of the plurality of items, wherein the item characteristic data object describes one or more item characteristics pertaining to the one or more items; and
determining, using the one or more processors, a portion of the cell volume that is occupied for each three-dimensional cell associated with the occupied state based at least in part on the item characteristic data object for the one or more items and the one or more placement locations for the one or more items.

4. The computer-implemented method of claim 1 , wherein the predictive machine learning model is trained using reinforcement learning techniques; and selecting the one or more placement locations further comprises:
assigning a corresponding placement location comprising the one or more three-dimensional pallet cells for the one or more three-dimensional item cells corresponding to an item.

5. The computer-implemented method of claim 4 , wherein one or more location scores for the one or more placement locations are based further on an occupancy state for at least one three-dimensional pallet cell that is adjacent to the one or more three-dimensional pallet cells associated with the corresponding placement location.

6. The computer-implemented method of claim 1 , wherein each three-dimensional cell of the plurality of three-dimensional pallet cells is associated with an occupancy state.

7. The computer-implemented method of claim 1 , wherein each three-dimensional cell corresponds to a particular location on the pallet.

8. The computer-implemented method of claim 1 , further comprising:
receiving, from one or more computing devices, an item characteristic data object for the one or more items of the plurality of items, wherein the item characteristic data object describes one or more item characteristics pertaining to the one or more items; and
wherein selecting the one or more placement locations is further based at least in part on the one or more item characteristics associated with each item of the plurality of items.

9. The computer-implemented method of claim 1 , further comprising:
receiving, from one or more computing devices, an item characteristic data object for the one or more items of the plurality of items, wherein the item characteristic data object describes one or more item characteristics pertaining to the one or more items; and
wherein generating the plurality of three-dimensional pallet cells for the pallet is based at least in part on the item characteristic data object.

10. The computer-implemented method of claim 1 , wherein the cell volume for each three-dimensional pallet cell is equivalent and wherein the cell volume is based at least in part on an item associated with a smallest item volume.

11. The computer-implemented method of claim 1 , wherein causing the one or more prediction-based actions further comprises:
causing, using the one or more processors, one or more indications to be provided to one or more associated computing devices such that the one or more associated computing devices may place the one or more items on the pallet based at least in part on the one or more placement locations.

12. The computer-implemented method of claim 11 , further comprising:
updating, using the one or more processors, an occupancy state associated with each of the one or more three-dimensional pallet cells based at least in part on one or more removal locations determined for the one or more three-dimensional pallet cells corresponding to the one or more items.

13. The computer-implemented method of claim 12 , wherein updating the occupancy state of the one or more three-dimensional pallet cells further comprises:
receiving, from one or more computing devices, an item characteristic data object for the one or more items of the plurality of items, wherein the item characteristic data object describes one or more characteristics pertaining to the one or more items; and
determining, using the one or more processors, a portion of the cell volume that is occupied for each three-dimensional cell associated with the occupied state based at least in part on the item characteristic data object for the one or more items and a removal location for each item.

14. The computer-implemented method of claim 11 , wherein the predictive machine learning model is trained using reinforcement learning techniques; and the computer-implemented method further comprises:
assigning a removal location comprising the one or more three-dimensional pallet cells for the one or more three-dimensional item cells corresponding to an item; and
determining a location score for the removal location for the one or more three-dimensional item cells corresponding to the item.

15. The computer-implemented method of claim 14 , wherein the location score for the removal location is based at least in part on an occupancy state for at least one three-dimensional pallet cell that is adjacent to the one or more three-dimensional pallet cells associated with the removal location.

16. The computer-implemented method of claim 11 , wherein each three-dimensional cell of th

Assignees

• Intelligrated Headquarters Llc

Inventors

• Pepley David Frederick
• Pathak Mayank

Classifications

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q10/087 Primary

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