CN115122341A - Automatic boxing method and boxing robot - Google Patents
Automatic boxing method and boxing robot Download PDFInfo
- Publication number
- CN115122341A CN115122341A CN202211050191.3A CN202211050191A CN115122341A CN 115122341 A CN115122341 A CN 115122341A CN 202211050191 A CN202211050191 A CN 202211050191A CN 115122341 A CN115122341 A CN 115122341A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- boxing
- laser
- robot
- dimensional model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/021—Optical sensing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/04—Viewing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
Abstract
The invention discloses an automatic boxing method and a boxing robot, wherein images are collected at a plurality of visual angles of a packaging box through a plurality of cameras, and a three-dimensional model is generated by the obtained images; measuring the contour distance of the packing box by laser to obtain a three-dimensional coordinate; combining the three-dimensional model with the three-dimensional coordinates to obtain a three-dimensional model with data parameters; and the boxing robot generates a manipulator operation path according to the obtained three-dimensional model with the data parameters, so that the boxing robot is controlled to automatically box. The automatic packaging robot has the advantages that the accurate position of the packaging box can be automatically identified without a fixed position, the articles needing to be packaged are put in the accurate position, the standard positioning mechanism of the packaging box is not needed, the packaging box only needs to be placed in the visual range of the robot to achieve automatic packaging, and due to the fact that a conveying belt does not need to be arranged, the robot can be applied to various environments, can be moved and changed in position at any time, is convenient to use, and has popularization and application values.
Description
Technical Field
The invention relates to the technical field of packaging boxes, in particular to an automatic boxing method and a boxing robot.
Background
The automatic box filler is a machine for completing transportation and packaging, filling packaged finished products into boxes in a certain arrangement and quantity, and closing or sealing the opening parts of the boxes. In an automatic packaging line, a box filling machine is the core of the operation of a whole line system, and although a packaging machine is not a direct product production machine, the packaging machine is necessary for realizing production automation. Among the prior art, automatic case packer adopts conveyer belt or other transfer apparatus mostly to transmit the packing box to the feed position of manipulator with the standard position, though this kind of subassembly can realize the automation, but need guarantee the position accurate positioning of packing box to the feed position, otherwise can cause the damage, and except the manipulator, just need the transmission equipment of one set of accurate positioning just can realize, so increased equipment cost, and use the rigidity, can not remove defects such as at any time, consequently, need an automatic positioning's vanning robot.
Disclosure of Invention
The invention aims to provide an automatic boxing method and a boxing robot.
In order to achieve the purpose, the invention is implemented according to the following technical scheme:
the automatic boxing method comprises the following steps:
s1: acquiring images at a plurality of viewing angles of the packing box through a plurality of cameras, and generating a three-dimensional model from the acquired images;
s2: measuring the profile distance of the packing box by laser to obtain a three-dimensional coordinate;
s3: combining the three-dimensional model of step S1 with the three-dimensional coordinates of step S2 to obtain a three-dimensional model with data parameters;
s4: and the boxing robot generates a manipulator operation path according to the obtained three-dimensional model with the data parameters, so that the boxing robot is controlled to automatically box.
The invention provides an automatic boxing robot, which comprises a control module loaded with a programmable processor, wherein the programmable processor is written with a program, and the automatic boxing method can be realized when the program is executed.
The invention has the beneficial effects that:
the invention relates to an automatic boxing method and a boxing robot, compared with the prior art, the automatic boxing method and the boxing robot are applied to the boxing robot, images are collected through a camera, a three-dimensional model is generated by the images, the outline distance of a packaging box is further measured through laser, and distance measurement is combined with the model, so that the boxing robot plans a path according to the model and distance measurement data, the accurate position of the packaging box can be automatically identified and objects to be packaged can be put in the packaging box without a fixed position, a standard positioning mechanism of the packaging box is not needed, the automatic boxing can be realized only by placing the packaging box in a visible range of the robot, and the robot can be applied to various environments without arranging a conveying belt, can move and change the position at any time, is convenient to use, and has popularization and application values.
Drawings
Fig. 1 is a schematic diagram of the laser ranging principle of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and specific embodiments, which are illustrative of the invention and are not to be construed as limiting the invention.
The automatic boxing method comprises the following steps:
s1: acquiring images at a plurality of viewing angles of the packing box through a plurality of cameras, and generating a three-dimensional model from the acquired images; the projection process to generate the three-dimensional model may be represented as:
𝐯̅ 𝑖 =𝑃(𝑋,𝑌,𝑍)=𝐊 𝑖 (𝐑 𝑖 𝐕+𝐓 𝑖 )（1）
wherein𝐯̅ 𝑖 Is the homogeneous coordinate of the projected pixel point in the image;𝑖representing the view angles of different cameras, the three-dimensional coordinates of the key points being𝐕；𝐕={𝑋,𝑌,𝑍}；𝐊𝑖Is a 3 x 3 matrix of the matrix,𝐑𝑖is a 3 x 3 rotation matrix and,𝐓𝑖is a 3 x 1 vector; p is a component of the model; each two-dimensional pixel point position is obtained by the following formula:
𝑥 𝑖 ,𝑦 𝑖 representing the pixel position in two dimensions, z representing the pixel pointA global position at a certain perspective; calculating Global coordinates X, Y from the above equation A parametric equation containing Z as follows𝐟 𝑥 (𝑍)；𝐟 𝑦 (𝑍)：
𝑋=𝐟 𝑥 (𝑍)=𝑎 𝑥 𝑍+d 𝑥 （3）
𝑌=𝐟 𝑦 (𝑍)=𝑎 𝑦 𝑍+d 𝑦 （4）
Wherein𝑎𝑥,𝑎𝑦,d𝑥,d𝑦Representing projection parameters, the projection parameters passing through pixel locations𝑥 𝑖 ,𝑦 𝑖 And camera external parameter matrix𝐊𝑖Calculating to obtain;
the three-dimensional point X, Y, Z is projected on the second place by the formula (1) and the formula (2)𝑖Pixel point in image under individual visual angle𝑥 𝑖 ,𝑦 𝑖 Then, the pixel points are processed by the formulas (3) and (4)𝑥 𝑖 ,𝑦 𝑖 Back-projection to spatial three-dimensional coordinates𝑋,𝑌,𝑍Thereby generating a three-dimensional model.
The projection principle of the three-dimensional model is as follows:
let the first two lines of the projection have three end points 1, 2, 3, which define a base plane. Taking the shape of a cylindrical box as an example, the first line 1, 2 determines the diameter of the bottom surface of the cylinder, the end point 3 of the second line is on the bottom surface circle, and the circular sparse three-dimensional point determining the bottom surface of the cylinder is projected in the two-dimensional image to assist in calculating the depth values of the three end points 1, 2, 3 in the image coordinate system, however, usually, none of the three-dimensional points can completely correspond to some specified two-dimensional end points. Therefore, the depth value 3 of the end point 3 needs to be calculated through the geometric constraint relation of the two sides 1, 2 and 2, 3 in three dimensions, namely, the triangle enclosed by the three end points 1, 2, 3 is a right-angled triangle. The depth values of the three-dimensional coordinates 1 and 2 are represented by 1 and 2, respectively, the three-dimensional coordinates of each point can be obtained according to the formula (3), the depth value represents f (), f (), and the right triangle constraint relationship can obtain the following formula:
𝑒1𝑒2 ∙ 𝑒2𝑒3 = (f𝑋(𝑍3) - f𝑋(𝑍1)) ∗ (f𝑋(𝑍3) - f𝑋(𝑍1)) + (f𝑌(𝑍3) - f𝑌(𝑍1)) ∗ (f𝑌(𝑍3) - f𝑌(𝑍1)) + (𝑍3 - 𝑍1) ∗ (𝑍2 - 𝑍1) = 0
the above equation is a quadratic equation about the parameter 3, and the sparse point cloud closest to 1 is selected in the local coordinate at the view angle and assigned to 1 as the initial value, and it is assumed that the initial value of 2 is the same as 1, that is, after the first line is measured, a perfect circle at the view angle is obtained, and the diameter of the circle is 12. The initial value of 3 is obtained by the above equation. Obtaining an initial value of three endpoints to obtain a three-dimensional circular base surface, optimizing the initial circular base surface to ensure that the surface is maximally matched with the input point cloud, namely in a three-dimensional space, the distance from the point cloud near the base surface to the base surface is the minimum, and obtaining the final cylindrical base surface after optimization.
S2: measuring the profile distance of the packing box by laser to obtain a three-dimensional coordinate; laser ranging can be mainly classified into three categories according to the ranging principle: pulse method, phase method and trigonometry. The distance information is solved by calculating the laser time, the pulse method is long in measuring distance, the required transmitting power is large, and the phase method is more suitable for long-distance measurement. The triangle rule solves the distance by calculating the geometric relation of the triangle, is suitable for being applied to the scene with shorter distance measurement, and has the advantages of small calculated amount and convenient data processing. The laser is mainly emitted to an object through laser rays, and a lens receives the returned rays to form a triangular relation so as to solve distance information. The laser measurement of the profile distance of the packing box specifically comprises the following steps:
as shown in fig. 1: the laser emits a laser beam at a certain angle beta, and the distance along the laser direction isdThe object receiving the laser light has a long lens focal length offThe perpendicular distance of the object from the plane isqThe distance between the laser and the focal point isS，q，dTriangle heel composed of betax，fThe triangles formed are similar triangles, so that:
according to the triangle principle, the following steps are carried out:
the laser measurement distance is as follows:
s3: combining the three-dimensional model of step S1 with the three-dimensional coordinates of step S2 to obtain a three-dimensional model with data parameters;
s4: and the boxing robot generates a manipulator operation path according to the obtained three-dimensional model with the data parameters, so that the boxing robot is controlled to automatically perform boxing.
The invention provides an automatic boxing robot, which comprises a control module loaded with a programmable processor, wherein the programmable processor is written with a program, and the automatic boxing method can be realized when the program is executed.
The technical solution of the present invention is not limited to the limitations of the above specific embodiments, and all technical modifications made according to the technical solution of the present invention fall within the protection scope of the present invention.
Claims (4)
1. An automatic boxing method is characterized by comprising the following steps:
s1: collecting images at a plurality of visual angles of the packing box through a plurality of cameras, and generating a three-dimensional model from the obtained images;
s2: measuring the profile distance of the packing box by laser to obtain a three-dimensional coordinate;
s3: combining the three-dimensional model of the step S1 with the three-dimensional coordinates of the step S2 to obtain a three-dimensional model with data parameters;
s4: and the boxing robot generates a manipulator operation path according to the obtained three-dimensional model with the data parameters, so that the boxing robot is controlled to automatically perform boxing.
2. The automated binning method of claim 1, wherein: the projection process for generating the three-dimensional model in step S1 can be represented as:
𝐯̅ 𝑖 =𝑃(𝑋,𝑌,𝑍)=𝐊 𝑖 (𝐑 𝑖 𝐕+𝐓 𝑖 )（1）
wherein𝐯̅ 𝑖 Is the homogeneous coordinate of the projected pixel point in the image;𝑖representing the view angle of different cameras, the three-dimensional coordinates of the key points are𝐕；𝐕={𝑋,𝑌,𝑍}；𝐊𝑖Is a 3 x 3 matrix of the matrix,𝐑𝑖is a 3 x 3 rotation matrix and,𝐓𝑖is a 3 x 1 vector; p is a component of the model; each two-dimensional pixel point position is obtained by the following formula:
𝑥 𝑖 ,𝑦 𝑖 representing a two-dimensional pixel position, wherein z represents the global position of the pixel point under a certain visual angle; calculating Global coordinates X, Y from the above equation A parametric equation containing Z as follows𝐟 𝑥 (𝑍)；𝐟 𝑦 (𝑍)：
𝑋=𝐟 𝑥 (𝑍)=𝑎 𝑥 𝑍+d 𝑥 （3）
𝑌=𝐟 𝑦 (𝑍)=𝑎 𝑦 𝑍+d 𝑦 （4）
Wherein𝑎𝑥,𝑎𝑦,d𝑥,d𝑦Representing projection parameters, the projection parameters passing through pixel locations𝑥 𝑖 ,𝑦 𝑖 And camera extrinsic parameter matrix𝐊𝑖Calculating to obtain;
the three-dimensional point X, Y, Z is projected on the second place by the formula (1) and the formula (2)𝑖Pixel point in image under individual visual angle𝑥 𝑖 ,𝑦 𝑖 Then, the pixel points are processed by the formulas (3) and (4)𝑥 𝑖 ,𝑦 𝑖 Back-projection to spatial three-dimensional coordinates𝑋,𝑌,𝑍Thereby generating a three-dimensional model.
3. The automated binning method of claim 1, wherein: the step S2 of measuring the profile distance of the packaging box by laser specifically includes:
laser emits a beam of laser at a certain angle beta, an object with a distance of d along the laser direction reflects the laser, the focal length of a long lens receiving the laser is f, the vertical distance between the object and a plane is q, the distance between the laser and a focus is S, q, d, the triangle formed by the beta and the triangle formed by the x and the f are similar triangles, so that the method has the following steps:
according to the triangle principle, the method comprises the following steps:
the laser measurement distance is as follows:
4. the utility model provides an automatic change vanning robot which characterized in that: the automated boxing method according to any one of claims 1 to 3, which includes a control module having a programmable processor in which a program is written, and which is executed to implement the automated boxing method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211050191.3A CN115122341A (en) | 2022-08-31 | 2022-08-31 | Automatic boxing method and boxing robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211050191.3A CN115122341A (en) | 2022-08-31 | 2022-08-31 | Automatic boxing method and boxing robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115122341A true CN115122341A (en) | 2022-09-30 |
Family
ID=83386961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211050191.3A Pending CN115122341A (en) | 2022-08-31 | 2022-08-31 | Automatic boxing method and boxing robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115122341A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107745207A (en) * | 2017-10-17 | 2018-03-02 | 桂林电子科技大学 | A kind of three-dimensional welding robot mixing control method |
| CN109954613A (en) * | 2017-12-25 | 2019-07-02 | 广州智信科技有限公司 | Spraying method |
| CN110815213A (en) * | 2019-10-21 | 2020-02-21 | 华中科技大学 | Part identification and assembly method and device based on multi-dimensional feature fusion |
| CN113012236A (en) * | 2021-03-31 | 2021-06-22 | 武汉理工大学 | Intelligent robot polishing method based on crossed binocular vision guidance |
-
2022
- 2022-08-31 CN CN202211050191.3A patent/CN115122341A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107745207A (en) * | 2017-10-17 | 2018-03-02 | 桂林电子科技大学 | A kind of three-dimensional welding robot mixing control method |
| CN109954613A (en) * | 2017-12-25 | 2019-07-02 | 广州智信科技有限公司 | Spraying method |
| CN110815213A (en) * | 2019-10-21 | 2020-02-21 | 华中科技大学 | Part identification and assembly method and device based on multi-dimensional feature fusion |
| CN113012236A (en) * | 2021-03-31 | 2021-06-22 | 武汉理工大学 | Intelligent robot polishing method based on crossed binocular vision guidance |
Non-Patent Citations (1)
| Title |
|---|
| 李明原: "《三维模型的重建及优化处理》", 《中国博士学位论文全文数据库 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103115613B (en) | Three-dimensional space positioning method | |
| JP2014028415A (en) | Device for unloading bulk loaded commodities with robot | |
| CN111028340B (en) | Three-dimensional reconstruction method, device, equipment and system in precise assembly | |
| US20020169586A1 (en) | Automated CAD guided sensor planning process | |
| WO2018201677A1 (en) | Bundle adjustment-based calibration method and device for telecentric lens-containing three-dimensional imaging system | |
| Bellandi et al. | Roboscan: a combined 2D and 3D vision system for improved speed and flexibility in pick-and-place operation | |
| CN111640156A (en) | Three-dimensional reconstruction method, equipment and storage equipment for outdoor weak texture target | |
| Kumar et al. | 3D scanner integration with product development | |
| CN114543787B (en) | Millimeter-scale indoor map positioning method based on fringe projection profilometry | |
| CN113226668A (en) | Method and device for production line simulation | |
| CN113281777A (en) | Dynamic measuring method and device for cargo volume | |
| CN116958146A (en) | Acquisition method and device of 3D point cloud and electronic device | |
| Hosseininaveh et al. | A low-cost and portable system for 3D reconstruction of texture-less objects | |
| US11443418B2 (en) | Machine vision system with a computer generated virtual reference object | |
| Zong et al. | A high-efficiency and high-precision automatic 3D scanning system for industrial parts based on a scanning path planning algorithm | |
| Bergström et al. | Automatic in-line inspection of shape based on photogrammetry | |
| CN115122341A (en) | Automatic boxing method and boxing robot | |
| Borangiu et al. | Robot arms with 3D vision capabilities | |
| Seçil et al. | 3-d visualization system for geometric parts using a laser profile sensor and an industrial robot | |
| CN105157562A (en) | On-line dynamic visual measuring system and on-line dynamic visual measuring method for geometrical dimension of complex and precise workpiece in small space | |
| CN105528788B (en) | Scaling method, device and the device for determining 3D shape of relative pose parameter | |
| Malhan et al. | Fast, accurate, and automated 3d reconstruction using a depth camera mounted on an industrial robot | |
| CN203857963U (en) | Binocular measuring device based on variable-vision-field target search | |
| Gothandaraman et al. | Robot-assisted 3D digital reconstruction of heritage artifacts: area similarity approach | |
| Irgenfried et al. | Image formation simulation for computer-aided inspection planning of machine vision systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220930 |
|
| RJ01 | Rejection of invention patent application after publication |