System to validate load cell data

• US 10,520,352 B1
• Filed: 12/22/2016
• Issued: 12/31/2019
• Est. Priority Date: 12/22/2016
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Shi, Qicai, O'Neill, Nathan Pius
• Primary Examiner(s): Gibson, Randy W
• Application Number:
  US15/388,528
• Time in Patent Office: 1,104 Days
• CPC Class Codes: A47F 10/02 for self-service type systems, e.g. supermarkets A47F10/06 takes precedence; hand-carts B62B; baskets B65D
• CPC Class Codes: A47F 2010/025 using stock management systems
• CPC Class Codes: A47F 3/00 Show cases or show cabinets
• CPC Class Codes: A47F 3/001 Devices for lighting, humidifying, heating, ventilation
• CPC Class Codes: A47F 3/0426 Details
• CPC Class Codes: F25D 23/12 Arrangements of compartments additional to cooling compartments; Combinations of refrigerators with other equipment, e.g. stove
• CPC Class Codes: F25D 25/02 by shelves
• CPC Class Codes: F25D 2500/06 Stock management
• CPC Class Codes: F25D 2700/06 Sensors detecting the presence of a product
• CPC Class Codes: F25D 29/00 Arrangement or mounting of control or safety devices
• CPC Class Codes: F25D 29/005 Mounting of control devices
• CPC Class Codes: G01G 19/4144 for controlling weight of goods in commercial establishments, e.g. supermarket, P.O.S. systems
• CPC Class Codes: G01G 19/42 for counting by weighing G01G19/387 takes precedence
• CPC Class Codes: G01G 21/23 Support or suspension of weighing platforms G01G21/24 takes precedence
• CPC Class Codes: G01G 21/28 Frames, Housings
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders

Abstract

Shelves or other fixtures may be used to hold items at a facility. Load cells at the shelf may be used to acquire weight data indicative of changes as items are added or removed from the shelf. The shelves may be part of a fixture that includes a door that results in air movement with respect to the shelves when opened or closed. This air movement may produce weight data that is erroneously indicative of an event, such as a pick or place, even when no actual event has taken place. Weight data from load cells of a shelf may be analyzed to determine a trajectory associated with changes in the weight data over time. A portion of the space may be designated as being associated with invalid weight data. If the trajectory avoids this portion of the space, the weight data may be deemed valid.

Claims

1. A system comprising:

a fixture comprising;

an insulated enclosure;

a shelf within the insulated enclosure;

a set of load cells configured to measure weight of a load on the shelf and generate weight data;

a door configured to provide access to the shelf within the insulated enclosure; and

a refrigeration unit configured to cool an interior of the insulated enclosure; and

a computing device comprising;

a memory storing first computer-executable instructions; and

a hardware processor to execute the first computer-executable instructions to;

determine a change in the weight data that occurs during a time interval;

determine, using the weight data, an estimated location;

access data indicative of a physical boundary of the shelf; and

determine validity data indicative of validity of the weight data based on the estimated location as compared to the data indicative of the physical boundary.

2. The system of claim 1, wherein the estimated location is indicative of one or more of:

a location of center of mass of the shelf, or

a location of a weight change at the shelf.

3. The system of claim 1, further comprising:

the memory storing second computer-executable instructions; and

the hardware processor to execute the second computer-executable instructions to;

generate door status data indicative of a change in configuration of the door based on the estimated location as compared to the data indicative of the physical boundary of the shelf.

4. A system comprising:

a fixture comprising;

a first shelf; and

a first set of load cells configured to measure weight of a load on the first shelf and generate first weight data; and

a computing device comprising;

a memory storing first computer-executable instructions; and

a hardware processor to execute the first computer-executable instructions to;

access the first weight data;

determine trajectory data using the first weight data, wherein the trajectory data is indicative of at least one location with respect to a space corresponding to the first shelf;

access data indicative of a region within the space corresponding to the first shelf; and

determine validity data indicative of validity of at least a portion of the first weight data based on the trajectory data as compared to the data indicative of the region within the space corresponding to the first shelf.

5. The system of claim 4, wherein the first set of load cells comprises a plurality of load cells arranged at three or more corners of the first shelf.

6. The system of claim 4, wherein:

the at least one location in the trajectory data is representative of a center-of-mass location with respect to the space corresponding to the first shelf; and

the region within the space corresponding the first shelf is representative of a physical boundary of the first shelf.

7. The system of claim 6, wherein the at least one location is indicative of one or more of:

a location of center of mass of the first shelf, or

a location of a weight change at the first shelf.

8. The system of claim 4, wherein the trajectory data comprises information indicative of a time associated with the at least one location;

and

the first computer-executable instructions to determine the validity data further comprising instructions to;

designate as invalid weight data the first weight data associated with a first time during which the at least one location is located outside the region within the space corresponding to the first shelf; and

designate as valid weight data the first weight data associated with a second time during which the at least one location is located inside the region within the space corresponding to the first shelf.

9. The system of claim 8, the computing device further comprising:

the memory storing second computer-executable instructions; and

the hardware processor to execute the second computer-executable instructions to;

access data indicative of a weight of a type of item stowed at the first shelf;

determine, using the valid weight data, a change in weight of the load on the first shelf; and

determine a quantity of the type of item stowed at the first shelf using the valid weight data.

10. The system of claim 4, the fixture further comprising a door;

and

the computing device further comprising;

the memory storing second computer-executable instructions; and

the hardware processor to execute the second computer-executable instructions to;

generate door status data indicative of a change in configuration of the door.

11. The system of claim 4, the fixture further comprising:

an enclosure with the first shelf located therein; and

further comprising one or more of;

one or more heating devices to heat an interior of the fixture, or

a refrigeration unit configured to cool an interior of the enclosure.

12. A system comprising:

a fixture comprising;

a first shelf; and

a first set of load cells configured to measure weight of a load on the first shelf and generate first weight data; and

a computing device comprising;

a memory storing first computer-executable instructions; and

a hardware processor to execute the first computer-executable instructions to;

access the first weight data acquired during a time interval;

determine, using the first weight data, first trajectory data indicative of a trajectory of an estimated location of a center of mass for the first shelf; and

determine validity data indicative of validity of the first weight data based on the first trajectory data.

13. The system of claim 12, wherein the first set of load cells comprises a plurality of load cells arranged at three or more corners of the first shelf.

14. The system of claim 12, the computing device further comprising:

the memory storing second computer-executable instructions; and

the hardware processor to execute the second computer-executable instructions to;

determine the first trajectory data in a two-dimensional space;

determine, using the first weight data, second trajectory data in a three-dimensional space that is based on the first weight data; and

the first computer-executable instructions to determine the validity data further comprising instructions to determine the validity data based on the second trajectory data.

15. The system of claim 14, the first computer-executable instructions to determine the first trajectory data further comprising instructions to:

calculate the first trajectory data by using expressions;

x=Weight_LC2+Weight_LC3−

Weight_LC1

y=Weight_LC4−

Weight_LC1

where x is a first axis in the two-dimensional space, y is a second axis in the two-dimensional space that is orthogonal to the first axis, and LC_i indicates weight data from an i^th load cell of the first set of load cells.

16. The system of claim 14, the second computer-executable instructions to determine the second trajectory data further comprising instructions to:

calculate the second trajectory data by using expressions;

x=Weight_LC2−

Weight_LC1

y=Weight_LC3−

Weight_LC1

z=Weight_LC4−

Weight_LC1

where x is a first axis in the three-dimensional space, y is a second axis in the three-dimensional space, z is a third axis in the three-dimensional space, the first axis, second axis, and third axis are mutually orthogonal, and LC_i indicates weight data from an i^th load cell of the first set of load cells.

17. The system of claim 12, the computing device further comprising:

the memory storing second computer-executable instructions; and

the hardware processor to execute the second computer-executable instructions to;

access data indicative of a first region in a space;

determine the first trajectory data is indicative of the trajectory having one or more points that intersect at least a portion of the first region; and

designate the first weight data as invalid.

18. The system of claim 12, the fixture further comprising a door;

and

the computing device further comprising;

the memory storing second computer-executable instructions; and

the hardware processor to execute the second computer-executable instructions to;

access door status data indicative of a change in configuration of the door associated with the time interval; and

train a machine learning module using the first trajectory data and the door status data to define a first region of space as being associated with valid weight data and a second region of space as being associated with invalid weight data.

19. The system of claim 12, the fixture further comprising:

an enclosure with the first shelf located therein; and

further comprising one or more of;

one or more heating devices to heat an interior of the fixture, or

a refrigeration unit configured to cool an interior of the enclosure.

20. The system of claim 12, the fixture further comprising:

a second shelf; and

a second set of load cells configured to measure weight of a load on the second shelf and generate second weight data; and

the computing device further comprising;

the memory storing second computer-executable instructions; and

the hardware processor to execute the second computer-executable instructions to;

access the first weight data that is associated with a first time interval;

access the second weight data associated with the first time interval;

determine a correlation value indicative of a degree of correlation between the first weight data and the second weight data during at least a portion of the first time interval; and

wherein the validity data is further determined based on the correlation value.