System and method for adaptive bin picking for manufacturing

Patent metadata

Field	Value
Publication number	US-11040447-B2
Application number	US-201716317876-A
Country	US
Kind code	B2
Filing date	Jul 17, 2017
Priority date	Jul 15, 2016
Publication date	Jun 22, 2021
Grant date	Jun 22, 2021

Abstract

A system and method for automatically moving one or more parts between a bin at a source location and a destination using a robot is provided. The system includes a first vision system to identify a part within the bin and to determine the pick location and pick orientation of the part. A second vision system determines the location and orientation of a destination inside or outside of the bin, which may or may not be in a fixed location. A controller plans the best path for the robot to follow in moving the part between the pick location and the destination. An end effector is attached to the robot for picking the part from the bin, holding the part as the robot moves it, and placing the part at the destination. The system may also check the part for quality by one or both of the vision systems.

First claim

What is claimed is:

1. A system for automatically moving one or more parts comprising:
a first vision system configured to identify and to determine a pick location and pick orientation of a part having a non-fixed location and orientation within a bin at a source location;
a second vision system configured to determine a location and orientation of a destination;
a robot having an end effector configured to pick the part from the bin and to move the part to the destination; and
a controller programmed to simulate a plurality of possible paths between the pick location and the destination incorporating geometrical information of the robot and the pick location and the pick orientation and the target location and the target orientation; and
wherein the controller is further programmed to determine, from the plurality of possible paths, a best path for the robot to follow in moving the part between the pick location and the destination.

2. The system as set forth in claim 1 , wherein the part having a non-fixed location and orientation within the bin has a random location and orientation within the bin.

3. The system as set forth in claim 1 , wherein the destination is within the bin at the source location.

4. The system as set forth in claim 1 , wherein the destination is outside of the bin at the source location.

5. The system as set forth in claim 1 , wherein the first vision system includes two or more cameras.

6. The system as set forth in claim 1 , wherein the second vision system includes two or more cameras.

7. The system as set forth in claim 1 , wherein at least one of the first vision system or the second vision system is a 2.5D system.

8. The system as set forth in claim 1 , wherein at least one of the first vision system or the second vision system is a 3D system.

9. The system as set forth in claim 1 , wherein at least one of the first vision system or the second vision system is a 2D system.

10. The system as set forth in claim 1 , wherein the end effector comprises a grasp.

11. The system as set forth in claim 1 , wherein the end effector comprises a suction device.

12. A method for automatically moving one or more parts between a bin at a source location and a destination comprising:
identifying a part having a non-fixed location and orientation within the bin using a first vision system;
determining the pick location and pick orientation of the part within the bin using the first vision system;
determining the location and orientation of a destination using a second vision system;
simulating a plurality of possible paths between the pick location and the destination incorporating geometrical information of the robot and the pick location and the pick orientation and the target location and the target orientation;
determining a best path between the pick location and the destination from the plurality of possible paths;
picking the part from the pick location by an end effector on a robot;
moving the part along the best path by the robot; and
placing the part at the destination by the end effector on the robot.

13. The method as set forth in claim 12 , wherein identifying a part having a non-fixed location and orientation within the bin using a first vision system further includes identifying a part having a random location and orientation within the bin.

14. The method as set forth in claim 12 , wherein identifying a part having a non-fixed location and orientation within the bin using the first vision system further includes comparing an image of the part with one or more reference images.

15. The method as set forth in claim 12 , wherein determining the pick location and pick orientation of the part within the bin using the first vision system further includes comparing an image of the part with one or more reference images.

16. The method as set forth in claim 12 , further comprising:
checking the item for quality by one of the first vision system or the second vision system.

17. The method as set forth in claim 16 , further comprising:
checking the item for quality by both of the first vision system and the second vision system.

Assignees

• Magna Int Inc
• Zak Alexander
• Perovski Dusko

Inventors

• Zak Alexander
• Perovski Dusko

Classifications

• H04N23/90

  Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums · CPC title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• B25J9/1697 Primary

  Vision controlled systems · CPC title

• G06T2207/30241

  Trajectory · CPC title

• G06T7/0004

  Industrial image inspection · CPC title