KR-102961906-B1 - Stacker crane teaching device using 3D vision

KR102961906B1KR 102961906 B1KR102961906 B1KR 102961906B1KR-102961906-B1

Abstract

The present invention relates to a stacker crane teaching device using 3D vision that enables accurate control of the position of a stacker crane using 3D vision without a reference object, comprising: a projector that projects a structured pattern onto a target object; an image sensor that captures the pattern of the target object to acquire an image of the target object with the pattern applied; an object depth calculation unit that calculates the depth of the object from the image of the target object with the pattern applied captured by the image sensor; a 3D shape generation unit that generates an image of a 3D shape using the object depth calculated by the object depth calculation unit and the image of the target object captured by the image sensor; a teaching control unit that recognizes a rack shape based on the 3D image generated by the 3D shape generation unit, extracts rack position information from a rack information storage unit based on the recognized rack shape, generates and outputs teaching information for the stacker crane; and a crane position movement unit that moves the position of the stacker crane based on the teaching information generated from the teaching control unit.

Inventors

정상민
임장수
우윤제
김건희
성효상
박정현
김기훈

Assignees

주식회사 에이텍오토

Dates

Publication Date: 20260507
Application Date: 20231207

Claims (6)

A projector that projects a structured pattern onto an object; An image sensor that captures the pattern of the above-mentioned object to acquire an image of the object with the pattern applied; An object depth calculation unit that calculates the depth of an object from an image of a patterned object captured by the image sensor; A 3D shape generation unit that generates a 3D shape image using the object depth calculated by the object depth calculation unit and the image of the target object captured by the image sensor; A teaching control unit that recognizes a rack shape based on a 3D image generated by the above 3D shape generation unit, extracts rack position information from a rack information storage unit based on the recognized rack shape, and generates and outputs teaching information for a stacker crane; and A stacker crane teaching device using 3D vision, characterized by including a crane position moving unit that moves the position of the stacker crane based on teaching information generated from the teaching control unit.
In claim 1, the projector, A stacker crane teaching device using 3D vision, characterized by projecting a pattern of a specific color onto an object using an LED, or projecting an image of a characteristic color onto the object using DLP (Digital Light Processing).
In claim 1, the image sensor is, A stacker crane teaching device using 3D vision, characterized by being a camera that captures the pattern of the object and acquires an image of the object with the pattern applied.
In claim 1, the object depth calculation unit, A stacker crane teaching device using 3D vision characterized by calculating the depth of an object by calculating the distance of each point from an image of an object with a captured pattern applied using a triangulation method.
In claim 1, the rack information storage unit, A stacker crane teaching device using 3D vision characterized by storing rack 3D images and reference points in advance.
In claim 1, the teaching control unit, A stacker crane teaching device using 3D vision, characterized by superimposing a 3D image generated by the 3D shape generation unit with a 3D image stored in the rack information storage unit, and generating a position control value of the stacker crane by calculating the X, Y, and theta values of the generated 3D image based on a reference point.

Description

Stacker crane teaching device using 3D vision The present invention relates to a stacker crane teaching device using 3D vision, and in particular, to a stacker crane teaching device using 3D vision that enables accurate control of the position of a stacker crane using 3D vision without a reference object. Automated logistics warehouse systems (hereinafter referred to as "automated warehouse systems") are widely used. In an automated warehouse system, incoming goods are automatically loaded onto shelves (racks) at designated locations, and upon a request for shipment, the corresponding goods are automatically retrieved from the shelves at the loaded locations and shipped out. Here, the device that automatically loads and retrieves goods is called a stacker; specifically, a system in which shelves are arranged in multiple tiers vertically and the stacker also functions as a lifter to raise and lower goods to load or retrieve them from the desired tier is called a stacker crane. Here, automated warehouse systems are applied in various fields, such as logistics warehouses, automated factory warehouses, display return warehouses, and semiconductor return warehouses. In this automated warehouse system, a control device (sequence and computer) is provided to control the positional movement of the stacker crane. The control device controls the position and movement of the stacker crane by using a sensor to acquire position and distance information, or by using an image-based camera to acquire marker and position values from an image. When controlling the position and movement of a stacker crane based on sensors, the position reference (reference object) is scanned using sensors, a distance value is acquired, and the relative deviation with respect to the current position is calculated to control the position and movement of the stacker crane. While this sensor method has the advantage of being usable for teaching and calibration of stacker cranes, it has the disadvantages of requiring additional components, such as reflectors, to acquire distance values across the entire target area, and is time-consuming. When controlling the position and movement of a stacker crane using a camera-based vision method, markers (reference objects) and position values are obtained from images acquired through the camera to control the position and movement of the stacker crane. While this vision method has the advantage of being usable for teaching and correcting stacker cranes, it has limitations in precise control of stacker cranes because it is impossible to reflect relative deviations from the current position. Therefore, there is a need for technology that can precisely control the position and movement of a stacker crane based simply on the installation, without the need for a reference object. FIG. 1 is a block diagram of a stacker crane teaching device using 3D vision according to the present invention, and FIG. 2 is a concept of structured light applied to the present invention, and FIG. 3 is an example of reading an object using structured light in the present invention, and FIG. 4 is an explanatory diagram for calculating object depth from an object image with a pattern applied in the present invention, and FIG. 5 is an example illustrating software that captures an object and generates 3D shape reproduction and teaching control information based on it in the present invention. A stacker crane teaching device using 3D vision according to a preferred embodiment of the present invention will be described in detail below with reference to the attached drawings. The terms or words used in the present invention described below should not be interpreted as being limited to their ordinary or dictionary meanings, but should be interpreted in a meaning and concept consistent with the technical spirit of the present invention, based on the principle that the inventor can appropriately define the concept of the terms to best describe his invention. Therefore, the embodiments described in this specification and the configurations illustrated in the drawings are merely preferred embodiments of the present invention and do not represent all technical concepts of the present invention; thus, it should be understood that various equivalents and modifications that can replace them may exist at the time of filing this application. FIG. 1 is a block diagram of a stacker crane teaching device (100) using 3D vision according to a preferred embodiment of the present invention, and may include a projector (101), an image sensor (102), an object depth calculation unit (103), a 3D shape generation unit (104), a teaching control unit (105), a rack information storage unit (107), and a crane position movement unit (106). The projector (101) serves to project a structured pattern onto an object. This projector (101) can project a pattern of a specific color (e.g., white, blue) onto the object using an LED, or project an image of a characteristic colo