Processing systems and methods for providing processing of a variety of objects

Patent metadata

Field	Value
Publication number	US-12440987-B2
Application number	US-202418761968-A
Country	US
Kind code	B2
Filing date	Jul 2, 2024
Priority date	Nov 13, 2015
Publication date	Oct 14, 2025
Grant date	Oct 14, 2025

Abstract

A sortation system is disclosed that includes a programmable motion device including an end effector, a perception system for recognizing any of the identity, location, and orientation of an object presented in a plurality of objects, a grasp selection system for selecting a grasp location on the object, the grasp location being chosen to provide a secure grasp of the object by the end effector to permit the object to be moved from the plurality of objects to one of a plurality of destination locations, and a motion planning system for providing a motion path for the transport of the object when grasped by the end effector from the plurality of objects to the one of the plurality of destination locations, wherein the motion path is chosen to provide a path from the plurality of objects to the one of the plurality of destination locations.

First claim

What is claimed is:

1. An object processing system comprising:
a programmable motion device including an end-effector;
a perception unit for capturing real-time image data of the plurality of objects at an input area;
an interactive display system including a touch screen input display for displaying the real-time image data and through which machine learning grasp input data regarding a plurality of objects is received; and
a control system accessing the machine learning grasp input data and for providing object grasp information regarding a grasp location for grasping the object responsive to the machine learning grasp input data regarding a plurality of objects.

2. The object processing system of claim 1 , wherein the machine learning grasp input data is received off-line not during object processing.

3. The object processing system of claim 1 , wherein the object grasp information is further responsive to information regarding at least one property of a suction cup of the end -effector.

4. The object processing system of claim 1 , wherein the object grasp information is further responsive to appearance-based features of the object.

5. The object processing system of claim 1 , wherein the machine learning grasp input data is received in real-time during object processing.

6. The object processing system of claim 5 , wherein the machine learning grasp input data is recorded with each grasp attempt.

7. The object processing system of claim 1 , wherein the object grasp information includes a grasp direction at the grasp location for grasping the object.

8. The object processing system of claim 7 , wherein the grasp direction is a direction that is normal to a surface of the object at the grasp location.

9. The object processing system of claim 8 , wherein the surface of the object at the grasp location is curved.

10. An object processing system comprising:
a programmable motion device including an end-effector;
a perception unit for capturing real-time image data of the plurality of objects at an input area;
an interactive display that includes a touch screen input display for displaying the real -time image data; and
a control system for providing object grasp information regarding a plurality of grasp locations for grasping the object with the end-effector, the plurality of object grasp locations being derived from a plurality of machine learning grasp input data regarding a plurality of objects, the machine learning grasp input data including data received via the interactive display system that includes the touch screen input display.

11. The object processing system of claim 10 , wherein the machine learning grasp input data is received off-line not during object processing.

12. The object processing system of claim 10 , wherein the object grasp information is further responsive to information regarding at least one property of a suction cup of the end -effector.

13. The object processing system of claim 10 , wherein the object grasp information is further responsive to appearance-based features of the object.

14. The object processing system of claim 10 , wherein the machine learning grasp input data is received in real-time during object processing.

15. The object processing system of claim 14 , wherein the machine learning grasp input data is recorded with each grasp attempt.

16. The object processing system of claim 10 , wherein the object grasp information includes a grasp direction at a selected grasp location of the plurality of grasp locations for grasping the object.

17. The object processing system of claim 16 , wherein the grasp direction is a direction that is normal to a surface of the object at the selected grasp location.

18. The object processing system of claim 17 , wherein the surface of the object at the selected grasp location is curved.

19. A method of processing objects received at an input area, said method comprising:
providing a programmable motion device with an end-effector. obtaining first grasp input information for a selected object of a plurality of objects in a container at an input area responsive to machine learning grasp input data;
using the end effector to move the selected object of the plurality of objects in the container at the input area without grasping the object; and
obtaining second grasp input information for the selected object of the plurality of objects in the container at the input area responsive to machine learning grasp input data.

20. The method of claim 19 , wherein the machine learning grasp input data is received in real-time during object processing.

21. The method of claim 19 , wherein the machine learning grasp input data is recorded with each grasp attempt.

22. The method of claim 19 , wherein the machine learning grasp input data is received off-line not during object processing.

23. The method of claim 19 , wherein the second grasp input information is further responsive to information regarding at least one property of a suction cup of the end-effector.

24. The method of claim 19 , wherein the second grasp input information is further responsive to appearance-based features of the object.

25. The method of claim 19 , wherein the second grasp input information includes a grasp direction at a selected grasp location of the plurality of grasp locations for grasping the object.

26. The method of claim 25 , wherein the grasp direction is a direction that is normal to a surface of the object at the selected grasp location.

27. The method of claim 26 , wherein the surface of the object at the selected grasp location is curved.

Assignees

• Berkshire Grey Operating Company Inc

Inventors

• Wagner Thomas
• Ahearn Kevin
• Cohen Benjamin
• DAWSON-HAGGERTY Michael
• GEYER Christopher
• Koletschka Thomas
• MARONEY Kyle
• Mason Matthew T
• Price Gene Temple
• Romano Joseph
• Smith Daniel Carlton
• SRINIVASA Siddhartha
• Velagapudi Prasanna
• Allen Thomas

Classifications

• G05B2219/39295

  Learn position correction values to be added to reference values · CPC title

• B25J19/04

  Viewing devices · CPC title

• B25J9/1664

  characterised by motion, path, trajectory planning · CPC title

• B25J9/1612 Primary

  characterised by the hand, wrist, grip control · CPC title

• B07C5/36

  Sorting apparatus characterised by the means used for distribution {(sorting according to destination B07C3/003, B07C3/02)} · CPC title