SHAPE DETECTION SYSTEM

• US 20100324737A1
• Filed: 06/18/2010
• Published: 12/23/2010
• Est. Priority Date: 06/19/2009
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Yaskawa Denki
• Original Assignee: Kabushiki Kaisha Yaskawa Denki
• Inventors: ICHIMARU, Yuji, HANDA, Hiroyuki, ARIE, Takeshi
• Granted Patent: US 8,660,697 B2
• Time in Patent Office: Days
• US Class Current: 700/259
• CPC Class Codes: G06F 18/24765 Rule-based classification
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/765 using rules for classification or partitioning the feature space

Abstract

A shape detection system includes a distance image sensor that detects an image of a plurality of detection objects and distances to the detection objects, the detection objects being randomly arranged in a container, a sensor controller that detects a position and an orientation of each of the detection objects in the container on the basis of the result of the detection performed by the distance image sensor and a preset algorithm, and a user controller that selects the algorithm to be used by the sensor controller and sets the algorithm for the sensor controller.

Claims

1. A shape detection system comprising:

a distance image sensor that detects an image of a plurality of detection objects and distances to the detection objects, the detection objects being randomly arranged in a container;

a sensor controller that detects a position and an orientation of each of the detection objects in the container on the basis of the result of the detection performed by the distance image sensor and a preset algorithm; and

a user controller that selects the algorithm to be used by the sensor controller and sets the algorithm for the sensor controller.

2. The shape detection system according to claim 1,

wherein the user controller includes

an algorithm database in which pre-registered shape patterns of the detection objects and detection algorithms corresponding to the shape patterns are stored in association with each other,

selecting means for selecting the shape pattern of a desired one of the detection objects,

specification input means for inputting a specification of the shape pattern selected by the selecting means, and

algorithm setting means for correcting one of the detection algorithms in the algorithm database on the basis of the shape pattern selected by the selecting means and the specification input by the specification input means and setting the corrected detection algorithm as the algorithm for the sensor controller.

3. The shape detection system according to claim 2,

wherein the user controller includes

a script database that stores a plurality of scripts that serve as parts of the detection algorithms stored in the algorithm database,

script selecting means for selecting desired scripts and the order of execution of the desired scripts, the desired scripts being selected from the scripts stored in the script database, and

algorithm creating means for creating a new algorithm on the basis of the combination of the scripts selected by the script selecting means and the order of execution of the selected scripts and registering the created algorithm in the algorithm database.

4. The shape detection system according to claim 3,

wherein the user controller includes

algorithm execution display means for transmitting, when the algorithm created by the algorithm creating means is executed, the scripts included in the created algorithm to the sensor controller one step at a time or a plurality of steps at a time, receiving a result of execution of the scripts from the sensor controller, and displaying the result of execution of the scripts.

5. The shape detection system according to claim 2,

wherein pre-scan algorithms for detecting the position and the orientation of each of the detection objects on the basis of shape characteristics of the detection objects are registered in the algorithm database, the shape characteristics of the detection objects being stored in advance, and

wherein the sensor controller measures a three-dimensional shape of each of the detection objects on the basis of the result of the detection performed by the distance image sensor and outputs the three-dimensional shape to the user controller.

6. The shape detection system according to claim 1, further comprising:

a robot that performs an operation for the detection objects arranged in the container; and

a robot controller that controls a movement of the robot on the basis of the result of the detection performed by the sensor controller.

7. The shape detection system according to claim 6,

wherein the robot successively holds the detection objects that are randomly arranged in the container and causes the detection objects to be conveyed to a section where the next process is performed.

8. The shape detection system according to claim 2, further comprising:

a robot that performs an operation for the detection objects arranged in the container; and

a robot controller that controls a movement of the robot on the basis of the result of the detection performed by the sensor controller.

9. The shape detection system according to claim 3, further comprising:

a robot that performs an operation for the detection objects arranged in the container; and

a robot controller that controls a movement of the robot on the basis of the result of the detection performed by the sensor controller.

10. The shape detection system according to claim 4, further comprising:

a robot that performs an operation for the detection objects arranged in the container; and

a robot controller that controls a movement of the robot on the basis of the result of the detection performed by the sensor controller.

11. A shape detection system comprising:

distance-image detection means for detecting an image of a plurality of detection objects and distances to the detection objects, the detection objects being randomly arranged in a container;

position-and-orientation detection means for detecting a position and an orientation of each of the detection objects in the container on the basis of the result of the detection performed by the distance-image detection means and a preset algorithm; and

means for selecting the algorithm to be used by the position-and-orientation detection means and sets the algorithm for the position-and-orientation detection means.