Automated guided vehicle control and organizing inventory items using predictive models for slow item types

Patent metadata

Field	Value
Publication number	US-11030573-B2
Application number	US-201816044210-A
Country	US
Kind code	B2
Filing date	Jul 24, 2018
Priority date	Jul 24, 2018
Publication date	Jun 8, 2021
Grant date	Jun 8, 2021

Abstract

In an example embodiment, a method determines a container containing one or more items associated with one or more item types, the container located at a current position in a storage facility; determines one or more order likelihoods of the one or more item types contained in the container; determines a container utilization likelihood of the container based on the one or more order likelihoods of the one or more item types contained in the container; determines an optimal position for the container in the storage facility based on the container utilization likelihood of the container, the optimal position being different from the current position of the container; and instructing an automated guided vehicle (AGV) to transport the container from the current position of the container to the optimal position of the container in the storage facility.

First claim

What is claimed is:

1. A method comprising:
determining a container containing one or more items associated with one or more item types, the container located at a current position in a storage facility;
determining one or more order likelihoods of the one or more item types contained in the container;
determining a container utilization likelihood of the container in one or more time windows based on the one or more order likelihoods of the one or more item types contained in the container;
determining an optimal position for the container in the storage facility based on the container utilization likelihood of the container, the optimal position being different from the current position of the container, wherein determining the optimal position for the container in the storage facility includes:
determining that the optimal position of the container is associated with a storage aisle in the storage facility,
determining other containers associated with the storage aisle,
determining a rank for the container based on the container utilization likelihood of the container in the one or more time windows relative to other container utilization likelihoods of the other containers in the one or more time windows, and
determining the optimal position for the container in the storage aisle based on the rank of the container; and

instructing an automated guided vehicle (AGV) to transport the container from the current position of the container to the optimal position of the container in the storage facility.

2. The method of claim 1 , wherein determining the one or more order likelihoods of the one or more item types contained in the container includes:
determining, using a trained predictive model associated with a window duration, the one or more order likelihoods of the one or more item types in the one or more time windows, the one or more time windows specified by the window duration and a current timestamp.

3. The method of claim 1 , wherein determining the container utilization likelihood of the container includes:
estimating the container utilization likelihood of the container in the one or more time windows to be a maximal order likelihood among the one or more order likelihoods of the one or more item types contained in the container in the one or more time windows.

4. The method of claim 1 , wherein determining the optimal position for the container in the storage aisle based on the rank of the container includes:
determining the optimal position in the storage aisle that has a distance to a pick-to-carton area of the storage facility proportional to the rank of the container.

5. The method of claim 1 , wherein:
determining the container utilization likelihood of the container includes determining the container utilization likelihood of the container in the one or more time windows; and
determining the optimal position for the container in the storage facility includes:
determining that the container utilization likelihood of the container in the one or more time windows satisfies a predefined container utilization likelihood threshold; and
responsive to determining that the container utilization likelihood of the container in the one or more time windows satisfies the predefined container utilization likelihood threshold, determining the optimal position for the container to be in a temporary storage area of the storage facility.

6. The method of claim 1 , wherein:
determining the container utilization likelihood of the container includes determining the container utilization likelihood of the container in the one or more time windows; and
determining the optimal position for the container in the storage facility includes:
determining that the current position of the container associated with a picking station of the storage facility;
determining that the container utilization likelihood of the container in the one or more time windows satisfies a predefined container utilization likelihood threshold; and
responsive to determining that the container utilization likelihood of the container in the one or more time windows satisfies the predefined container utilization likelihood threshold, determining the optimal position for the container to be in the picking station of the storage facility.

7. The method of claim 1 , further comprising:
receiving a customer order requesting a first item type;
determining a first order likelihood of the first item type in the one or more time windows;
determining that the first order likelihood of the first item type in the one or more time windows satisfies a predefined order likelihood threshold; and
responsive to determining that the first order likelihood of the first item type in the one or more time windows satisfies the predefined order likelihood threshold, postponing a fulfillment of the customer order.

8. The method of claim 1 , further comprising:
receiving a customer order requesting a first item type among the one or more item types contained in the container; and
responsive to instructing the AGV to transport the container to the optimal position of the container in the storage facility, assigning the customer order to a picking station in the storage facility to fulfill the customer order at the storage facility.

9. The method of claim 1 , further comprising:
determining one or more first order likelihoods of one or more first item types in the one or more time windows;
determining, from the one or more first item types, one or more likely-ordered item types, the one or more first order likelihoods of the one or more likely-ordered item types in the one or more time windows satisfying a predefined order likelihood threshold;
aggregating the one or more likely-ordered item types into one or more groups of likely-ordered item types based on item velocity of the one or more likely-ordered item types, the one or more groups of likely-ordered item types including a first group of likely-ordered item types and a second group of likely-ordered item types;
assigning the first group of likely-ordered item types to a first storage aisle and assigning the second group of likely-ordered item types to a second storage aisle;
determining a first container containing a first item type in the first group of likely-ordered item types;
determining a first optimal position for the first container containing the first item type in the first storage aisle;
determining a second container containing a second item type in the second group of likely-ordered item types; and
determining a second optimal position for the second container containing the second item type in the second storage aisle.

10. The method of claim 9 , wherein:
a number of groups of likely-ordered item types equals to a number of storage aisles in the storage facility;
a number of likely-ordered item types in the first group of likely-ordered item types substantially equals to a number of likely-ordered item types in the second group of likely-ordered item types; and
a total item velocity of the likely-ordered item types in the first group of likely-ordered item types substantially equals to a total item velocity of the likely-ordered item types in the second group of likely-ordered item types.

11. A system comprising:
one or more processors; and
one or more memories storing instructions that, when executed by the one or more processors, cause the system to:
determine a container containing one or more items associated with one or more item types, the container located at a current position in a storage facility;
determine one or more order likelihoods of the one or more item types contained in the container;
determine a container utili

Assignees

• Staples Inc

Inventors

• Sikka Sandeep
• Verma Nitin
• Bhaskaran Michael

Classifications

• G06Q10/087 Primary

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

• G06N20/00

  Machine learning · CPC title

• B65G1/137

  with arrangements or automatic control means for selecting which articles are to be removed · CPC title

• B65G1/0492

  with cars adapted to travel in storage aisles · CPC title

• G06Q30/0202 Primary

  Market predictions or forecasting for commercial activities · CPC title