Method for deploying a robotic system to scan inventory within a store based on local wireless connectivity

Patent metadata

Field	Value
Publication number	US-11897148-B2
Application number	US-202117169327-A
Country	US
Kind code	B2
Filing date	Feb 5, 2021
Priority date	Feb 5, 2020
Publication date	Feb 13, 2024
Grant date	Feb 13, 2024

Abstract

One variation of a method for deploying a mobile robotic system to scan inventory structures within a store includes: dispatching the mobile robotic system to navigate along inventory structures within the store during a setup cycle; at the mobile robotic system, while navigating along the inventory structures during the setup cycle, capturing a set of wireless connectivity metrics representing connectivity to a first wireless network; assembling the set of wireless connectivity metrics into a wireless connectivity map of the store; estimating a processing duration from start of the scan cycle to transformation of images of the inventory structures, captured by the mobile robotic system, into a stock condition of the store; and dispatching the mobile robotic system to autonomously capture images of the inventory structures within the store during a scan cycle preceding a scheduled restocking period in the store based on the processing duration.

First claim

I claim:

1. A method for deploying a mobile robotic system to scan inventory within a store, the method comprising:
dispatching the mobile robotic system to navigate along a set of inventory structures within the store during a mapping cycle;
at the mobile robotic system, while navigating along the set of inventory structures during the mapping cycle, capturing a set of wireless connectivity metrics representing connectivity to a first wireless network;
assembling the set of wireless connectivity metrics into a wireless connectivity map of the store;
for a first inventory structure in the set of inventory structures:
estimating a first traversal duration for the mobile robotic system to traverse the first inventory structure and capture a first set of images that depict product units occupying the first inventory structure within a target resolution range;
estimating a first data size of the first set of images; and
estimating a first upload duration for the mobile robotic system to upload the first set of images to a remote computer system via the first wireless network based on the first data size and the wireless connectivity map;

for a second inventory structure in the set of inventory structures:
estimating a second traversal duration for the mobile robotic system to traverse the second inventory structure and capture a second set of images that depict product units occupying the second inventory structure within the target resolution range;
estimating a second data size of the second set of images; and
estimating a second upload duration for the mobile robotic system to upload the second set of images to the remote computer system via the first wireless network based on the second data size and the wireless connectivity map;

dispatching the mobile robotic system to autonomously capture images of the set of inventory structures within the store during a scan cycle succeeding the mapping cycle; and
in response to the first upload duration exceeding the first traversal duration and in response to the second traversal duration exceeding the second upload duration, scheduling upload of a subset of the first set of images from the mobile robotic system to the remote computer system during traversal of the second inventory structure by the mobile robotic system during the scan cycle.

2. The method of claim 1 , further comprising, in response to the first upload duration exceeding the first traversal duration and in response to the second traversal duration exceeding the second upload duration, scheduling traversal and imaging of the first inventory structure by the mobile robotic computer system prior to traversal and imaging of the second inventory structure by the mobile robotic computer system during the scan cycle.

3. The method of claim 1 , further comprising, in response to the first upload duration exceeding the first traversal duration and in response to the second traversal duration exceeding the second upload duration:
scheduling upload of a second subset of the first set of images from the mobile robotic system to the remote computer system during traversal and imaging of the first inventory structure by the mobile robotic system during the scan cycle;
scheduling local interpretation, by the mobile robotic system, of stock conditions of a third subset of slots in the first inventory structure from a third subset of the first set of images during traversal and imaging of the first inventory structure by the mobile robotic system during the scan cycle; and
specifying upload of stock conditions of the third subset of slots in the first inventory structure, interpreted by the mobile robotic system, to the remote computer system in place of the third subset of the first set of images during the scan cycle.

4. The method of claim 3 , further comprising, at the mobile robotic system during the scan cycle:
capturing an image, in the third subset of images, of the first inventory structure;
detecting a first slot boundary, of a first slot in the first inventory structure, in a first region of the image;
extracting a first set of color features, geometry features, and textual features from within the first slot boundary in the image;
identifying a first product type assigned to the first slot;
retrieving a first set of representative features of the first product type;
detecting an out-of-stock condition at the first slot in response to deviation of the first set of color features, geometry features, and textual features from the first set of representative features; and
returning the out-of-stock condition at the first slot to the remote computer system in place of the image.

5. The method of claim 4 , further comprising, at the remote computer system:
receiving a second image, in the second subset of images of the first inventory structure, captured by the mobile robotic system during the scan cycle;
detecting a second slot boundary, of a second slot in the first inventory structure, in a second region of the image;
extracting a second set of color features, geometry features, and textual features from within the second slot boundary in the image;
identifying a second product type assigned to the second slot;
retrieving a second set of representative features of the second product type;
detecting a second stock condition at the second slot based on correspondence between the second set of color features, geometry features, and textual features and the second set of representative features; and
compiling the out-of-stock condition at the first slot and the second stock condition at the second slot into a global stock condition of the store.

6. The method of claim 1 , further comprising, at the remote computer system:
receiving an image, of the first inventory structure, captured by the mobile robotic system during the scan cycle;
detecting a first slot boundary, of a first slot in the first inventory structure, in a first region of the image;
extracting a first set of color features, geometry features, and textual features from within the first slot boundary in the image;
identifying a first product type assigned to the first slot;
retrieving a first set of representative features of the first product type;
detecting an out-of-stock condition at the first slot in response to deviation of the first set of color features, geometry features, and textual features from the first set of representative features; and
in response to detecting the out-of-stock condition, generating a prompt to restock the first slot with product units of the first product type.

7. The method of claim 1 :
wherein estimating the first traversal duration, the first upload duration, the second traversal duration, and the second upload duration comprise, for each inventory structure in the set of inventory structures:
estimating a traversal duration, in a set of traversal durations, for the mobile robotic system to traverse the inventory structure and capture a set of images that depict product units occupying the inventory structure within the target resolution range;
estimating a data size of the set of images; and
estimating an upload duration, in a set of upload durations, for the mobile robotic system to upload the set of images to the remote computer system via the first wireless network based on the data size and the wireless connectivity map; and

further comprising estimating a processing duration from start of the scan cycle to transformation of images of inventory structures in the store, captured by the mobile robotic system during the scan cycle, into a stock condition of the store based on the set of upload durations.

8. The method of claim 7 :
wherein estimating the upload duration for each inventory structure in t

Assignees

• Simbe Robotics Inc

Inventors

• Shah Mirza Akbar
• Ersoz Cem
• Safi Jariullah
• Bogolea Bradley

Classifications

• B25J9/1697 Primary

  Vision controlled systems · CPC title

• B25J9/1674

  characterised by safety, monitoring, diagnostic · CPC title

• B25J9/1679

  characterised by the tasks executed · CPC title

• B25J13/006

  by means of a wireless system for controlling one or several manipulators · CPC title

• G06Q10/087

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