Granted Patent B2

US 12,330,832 · App. 18/825,078 · Granted Jun 17, 2025

Inventors: Ashutosh Prasad (Dallas, TX); Vivek Prasad (Bengaluru, IN)

Assignee: KoiReader Technologies, Inc.

B65B57/14B65B5/06B65B57/18

Abstract

Claims (91)

1. A system comprising:

a first image device to capture first image data associated with a packing event occurring in a packing area, the packing event including a first item and two or more containers;

one or more processors;

one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

determining, based at least in part on the first image data, segmented and classified image data, the segmented and classified image data including data representing a class associated with the first item and data associated with the two or more containers;

generating, based at least in part the data associated with the two or more container, a pixel mapping representing the packing area, the pixel mapping including a first pixel region associated with a first container of the two or more containers and a second pixel region associated with a second container of the two or more containers;

determining, based at least in part on the class, the first container of the two or more containers to receive the item;

determining, based at least in part on the pixel mapping and the segmented and classified image data, an area location associated with the pixel mapping and a placement of the first item; and

responsive to determining, based at least in part on the area and the first pixel region, that the first item was placed in the first container by an agent, sending an alert to the agent notifying the agent to proceed with a next item.

2. The system of claim 1 , further comprising a second image device to capture second image data associated with the packing event occurring in the packing area and wherein determining the class of the first item is based at least in part on the second image data.

3. The system of claim 1 , wherein:

the first item is one of a plurality of items;

the operations further comprise:

determining based at least in part on the first image data, a class for each of the plurality of items; and

determining a quantity metric of each class of items;

determining a corresponding container of the one or more containers associated with each item; and

determining a counter metric for each class of item representative of a number of items of each class placed in the corresponding container.

4. The system of claim 3 , wherein the operations further comprise:

determining a final counter metric for each container of the two or more containers for each class of items; and

determining that the final counter metric equals an expected number for each container of the one or more containers.

5. The system of claim 4 , wherein the operations further comprise:

for a first container of the one or more containers and responsive to determining that the final counter metric equals the expected number for the first container, sending a notification to an agent that the first container is ready to ship.

6. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving image data of a packing event occurring in a packing area, the packing event including a plurality of items and a first container;

determining, based at least in part on the image data, segmented and classified image data, the segmented and classified image data including data representing a class associated with a first item of the plurality of items and data associated with the first container;

generating, based at least in part the data associated with the first container, a pixel mapping representing the packing area, the pixel mapping including a first pixel region associated with the first container;

determining, based at least in part on the class of the first item, the first container to receive the first item;

determining, based at least in part on the pixel mapping and the segmented and classified image data, an area associated with a placement of the first item;

determining, based at least in part on the pixel mapping and the area, that the first item was placed in the first container by an agent; and

responsive to determining that the first item was placed in the first container by an agent:

determining a counter metric for the first container, the counter metric indicating a number of items of the class placed in the container; and

sending an alert to the agent notifying the agent to proceed with a next item of the plurality of items.

7. The one or more non-transitory computer-readable media of claim 6 , wherein the operations further comprise:

determining, based at least in part on the image data, a value of the counter metric for the first container equals an expected number of items of the class; and

sending a notification to an agent that the first container is ready to ship.

8. The one or more non-transitory computer-readable media of claim 6 , wherein the operations further comprise:

determining, based at least in part on the image data, a value of the counter metric for the first container is less than an expected number of items of the class; and

sending a notification to an agent that the first container is not ready to ship.

9. The one or more non-transitory computer-readable media of claim 6 , wherein the operations further comprise:

determining, based at least in part on the image data, a value of the counter metric for the first container is greater than an expected number of items of the class; and

sending a notification to an agent that the first container is not ready to ship.

10. The one or more non-transitory computer-readable media of claim 6 , wherein the operations further comprise:

causing an image to be presented on a display associated with the packing area, the image including:

a visual representation of the first container and a value of the counter metric; and

a visual representing each of the items placed in the first container.

11. The one or more non-transitory computer-readable media of claim 6 , wherein the operations further comprise:

causing an image to be presented on a display associated with the packing area, the image including:

a visual representation of a status of the agent; and

a visual representation of a status of a current item being packed by the agent.

12. A system comprising:

an image device to capture first image data associated with a packing event occurring in a packing area, the packing event including a first item and one or more containers;

a display within the packing area;

one or more processors;

one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving, from the image device, the first image data of the packing event, the packing event including a first container and a second container;

determining, based at least in part on the first image data, segmented and classified image data, the segmented and classified image data including data representing a class associated with the first item and data associated with the two or more containers;

generating, based at least in part the data associated with the two or more container, a pixel mapping representing the packing area, the pixel mapping including a first pixel region associated with a first container of the two or more containers and a second pixel region associated with a second container of the two or more containers;

determining, based at least in part on the pixel mapping and the segmented and classified image data, an area location associated with the pixel mapping and a placement of the first item;

determining, based at least in part on the area and the pixel mapping, that the first item was not placed in the first container by an agent;

sending a first alert to the display, the first alert notifying an agent to repack the first item;

receiving, from the image device, second image data of the packing event occurring in the packing area;

determining, based at least in part on the second image data, that the first item was repacked in the first container by the agent; and

sending a second alert to the display, the second alert notifying the agent to proceed with a next item.

13. The system of claim 12 , the operations further comprising:

receiving, from the image device, third image data of the packing event occurring in the packing area, the third image data including a second item;

determining, based at least in part on the third image data, that the second item was not placed in the first container by the agent;

sending a third alert to the display, the third alert notifying the agent to repack the second item;

receiving, from the image device, fourth image data of the packing event occurring in the packing area;

determining, based at least in part on the fourth image data, that the second item was not retrieved and placed in the first container by the agent;

sending a fourth alert to the display, the fourth alert re-notifying the agent to repack the second item;

receiving, from the image device, fifth image data of the packing event occurring in the packing area; and

determining, based at least in part on the fifth image data, that the second item was retrieved and placed in the first container by the agent; and

sending a fifth alert to the display, the fifth alert notifying the agent to proceed with a next item.

14. The system of claim 12 , wherein:

determining that the first item was not placed in the first container by the agent further comprises inputting the first image data into one or more first machine learning models and receiving as an output of the one or more first machine learning models an indication that the first item was not placed in the first container, the one or more first machine learning models trained on first image training data of various items being placed in containers by various agents; and

determining that the first item was repacked in the first container by the agent further comprises inputting the second image data into one or more second machine learning models and receiving as an output of the one or more second machine learning models an indication that the first item was placed in the first container, the one or more second machine learning models trained on second image training data of various items being placed in containers by various agents.

15. The system of claim 14 , wherein the one or more first machine learning models includes:

one or more machine learning models to segment the first image data and generate segmented image data;

one or more machine learning models to classify the segmented image data and generate the segmented and classified image data; and

one or more machine learning models to determine the area based at least in part on the segmented and classified image data.

16. The system of claim 12 , wherein the first alert includes an indication of the second container that the first item was placed in.

17. The system of claim 12 , wherein the display is associated with the packing area and the first alert provides a visual indication on the display that the first item was not placed in the first container.

18. The system of claim 17 , further comprising

responsive to sending the first alert, causing a visual representation of the first container, a visual representation each of the items placed in the first container, and a visual representation of a status of the agent to be concurrently presented on the display.

19. The system of claim 12 , wherein:

the agent is an autonomous system;

sending the first alert includes sending a first control signal to cause the autonomous system to perform an action associated with the first item, the action including causing the autonomous system to repack the first item in the first container; and

sending the second alert includes sending a second control signal to cause the autonomous system to perform an action associated with another item.

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

determining, based at least in part on the first image data, a class associated with the first item; and

determining, based at least in part on the class of the first item, that the first item belongs in the first container.

Assignments (1)

Continuity (2)

References Cited (14)