Material handling system and method

• US 10,417,521 B2
• Filed: 09/12/2014
• Issued: 09/17/2019
• Est. Priority Date: 09/13/2013
• Status: Active Grant

• Current Assignee: JCS-Echigo Pte, Ltd. (JCS Group), JSC-Echigo Pte., Ltd.
• Original Assignee: JCS-Echigo Pte, Ltd. (JCS Group)
• Inventors: Dong, Junfeng
• Primary Examiner(s): Randazzo, Thomas
• Application Number:
  US14/485,420
• Publication Number:
  US 20150081090A1
• Time in Patent Office: 1,831 Days
• CPC Class Codes: B07C 5/00 Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches sorting by hand only B07C7/00; separating solids from solids by sieving, screening, or sifting or by using gas currents or other separating by dry methods applicable to bulk material B07B
• CPC Class Codes: B07C 5/3422 using video scanning devices, e.g. TV-cameras
• CPC Class Codes: B25J 13/08 by means of sensing devices, e.g. viewing or touching devices
• CPC Class Codes: B25J 15/065 provided with separating means for releasing the gripped object after suction
• CPC Class Codes: B65G 43/08 Control devices operated by article or material being fed, conveyed or discharged and controlling the discharging devices B65G47/42
• CPC Class Codes: B65G 47/91 incorporating pneumatic, e.g. suction, grippers
• CPC Class Codes: G05B 2219/40036 Transport plates or sheets between two locations without motion inversion
• CPC Class Codes: G05B 2219/45047 Sorting
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06T 19/20 Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
• CPC Class Codes: G06T 2207/20224 Image subtraction

Abstract

A system and method for material handling are disclosed. The system includes a platform for receiving a plurality of articles, a plurality of sorting bins that each correspond to an article type, an object recognition system for identifying the article on the platform and categorizing the article by a specific article type, and an article engagement assembly. The object recognition system includes a 3D detector for detecting the article and a database containing data on characteristics of article types. The 3D detector is arranged to capture at least one two-dimensional image, and at least one depth image of the article. The article engagement assembly engages and delivers the article to the corresponding sorting bin. The object recognition system is arranged to identify the article based upon the data within the database and instructs the article engagement assembly to engage and place the article in the sorting bin.

Claims

1. A material handling system comprising:

a platform for receiving a plurality of articles;

a plurality of sorting bins, each bin in corresponding to an article type;

an object recognition system for identifying the article on the platform and categorizing said article by specific article type;

said object recognition system including a 3D detector for detecting said article and a database containing data on characteristics of article types;

said 3D detector arranged to capture at least one two-dimensional image, and at least one depth image of said article; and

an article engagement assembly for engaging and delivering said article to said corresponding sorting bin;

wherein the object recognition system is arranged to;

digitally remove background from said captured depth image, and identify the article based upon the data within said database, and instruct the article engagement assembly to engage and place the article in said sorting bin, wherein said data includes a range of images of the article taken from different perspectives,

wherein the article engagement assembly includes an end-effector for engaging the article, said end-effector mounted to a robotic arm, said robotic arm arranged to move said end-effector from the platform to said sorting bins;

wherein said robotic arm including a plurality of branches each having at least one end effector mounted thereto, and

wherein the article engagement assembly and the 3D detector are arranged to be separate from each other such that the depth image of said article also includes said end-effector in the depth image.

2. The system according to claim 1, wherein said 3D detector is a 3D camera and the data contained by said database includes image data, said object recognition system arranged to compare said captured two-dimensional image with images from said database.

3. The system according to claim 1, wherein said end-effector includes suction cups for engaging said article.

4. The system according to claim 1, wherein the robotic arm includes a plurality of branches each having two end effectors mounted thereto.

5. The system according to claim 1, wherein the material handling system is a conveyor system, with the platform part of a conveyor of said conveyor system.

6. The system according to claim 5, wherein the platform is delivered by a conveyor to a designated location for handling of said articles.

7. The system according to claim 1, wherein each sorting bin includes a container on a sliding base and enmeshed in a security fence.

8. The system according to claim 7, wherein the security fence is arranged to be locked by electro-magnet lock controlled by system digital I/O output.

9. The system according to claim 7, wherein each sorting bin is mounted with manual push button and proximity sensors to detect the loads of placed articles.

10. The system according to claim 9, wherein the system is arranged such that on activating the push buttons or the proximity sensor signals that on a sorting bin being full, no further articles are placed into the respective bin.

11. A method for identifying and sorting an article, said method comprising the steps of:

detecting the presence of the article by a 3D detector, said detector arranged to obtain at least one two-dimensional image, and at least one depth image of said article;

digitally removing background from said captured depth image;

comparing captured two-dimensional image of said detected article with images contained on a database, wherein said data includes a range of images of the article taken from different perspectives;

locating the position and orientation of the article from the two-dimensional and depth images and transform such information into a motion profile for at least one robotic arm;

categorizing said article as a specific article type based upon said comparison;

engaging the article based upon said location information, with at least one end effector located on one of a plurality of branches of a robotic arm; and

delivering the article to a sorting bin corresponding to the categorized article type,

wherein the robotic arm and the 3D detector are arranged to be separate from each other such that the depth image of said article also includes said end-effector in the depth image.

12. The method according to claim 11 wherein said database is pre-established using sample articles of finite different types;

each type in the database corresponding to any one or a combination of;

shape, size and 3D point cloud of particular type of article.

13. The method according to claim 11, wherein said background includes everything the camera detects except the articles so that the articles can be extracted and localized from the image to provide location information of said articles;

the location information includes identified type of each article by matching with said database, the 3D position of each article and 3D orientation of each article.

14. The method according to claim 11, wherein the removing step includes:

capturing the image with a 3 dimensional camera so as to detect depth in said image;

distinguishing the article from the background in said captured image, and;

digitally removing the background so as to leave the article image only.