CN114373012A - Method for generating special-shaped plane spraying operation track - Google Patents
Method for generating special-shaped plane spraying operation track Download PDFInfo
- Publication number
- CN114373012A CN114373012A CN202111570167.8A CN202111570167A CN114373012A CN 114373012 A CN114373012 A CN 114373012A CN 202111570167 A CN202111570167 A CN 202111570167A CN 114373012 A CN114373012 A CN 114373012A
- Authority
- CN
- China
- Prior art keywords
- point
- track
- trajectory
- sliding window
- pose
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000005507 spraying Methods 0.000 title claims abstract description 13
- 238000005070 sampling Methods 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 14
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 238000004026 adhesive bonding Methods 0.000 abstract description 6
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 239000003292 glue Substances 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 239000011248 coating agent Substances 0.000 description 4
- 238000000576 coating method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003754 machining Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Abstract
A method for generating a special-shaped plane spraying operation track for automatic sole spraying and gluing is characterized in that the height change of a plane contour is obtained by acquiring a three-dimensional point cloud of an operation plane and extracting the highest point on the contour of a positioning plane, and an optimized track which is adaptive to different plane edge fluctuation and matched with the tail end posture of a robot is generated by further combining the tail end posture of the robot. The method can generate self-adaptive operation tracks aiming at different special-shaped planes, and the self-adaptive operation tracks are matched with the current terminal pose of the robot to obtain continuous tracks in the pose.
Description
Technical Field
The invention relates to the field of robot control, in particular to a method for generating self-adaptive operation tracks aiming at different working planes in similar applications such as robot shoe bottom coating glue spraying and the like.
Background
Automation technology is being applied to more and more processing and manufacturing works, such as shoe manufacturing enterprises, and since hundreds of shoe types can be simultaneously produced on the production line of the enterprise of the type, the automation production line applying the robot technology is required to have certain flexibility, wherein a sole glue coating and spraying process is an important step in the production process, but the sole glue coating and spraying cannot be completed by a set of ready-made operation tracks due to different shapes of the sole.
Disclosure of Invention
The invention provides an operation track generation method for automatic shoe sole glue coating and spraying and other similar special-shaped plane machining operations, which can realize self-adaptation to the fluctuation of edges of different shoe types and generate a better track.
The method for generating the special-shaped plane spraying operation track comprises the following steps:
acquiring a three-dimensional point cloud of a working plane, and constructing a three-dimensional point cloud coordinate system of the working plane based on a principal component analysis method;
performing sliding window scanning along two side edges of a working plane in a first main direction of the three-dimensional point cloud coordinate system, and extracting the highest point in each sliding window in a third main direction to obtain an initial track;
performing sliding window mean filtering on the initial track;
and constructing the gesture of each 3-dimensional track point in the track obtained after the sliding window mean filtering based on the current terminal pose of the robot to obtain a track containing the pose with 6 degrees of freedom, namely the required track.
Preferably, the method for obtaining the initial trajectory comprises the following steps:
solving the maximum value and the minimum value of the three-dimensional point cloud in three main directions, and subtracting the two values to obtain the length, width and height l of the operation planec，wc，hc；
Setting the number of sampling points of one operation track of the operation plane as N, and respectively setting the size of a sampling frame in three main directions of the three-dimensional point cloud coordinate system as 2lc/N、wc/2、h c2, the sampling frame starts from the negative direction extreme point of the first main direction from the second main direction side and starts with 2lcthe/N is a moving interval, the sampling is carried out to the positive direction extreme point of the first main direction, and the sampling mode is that the point cloud in the sampling frame is sampled in the positive direction of the third main directionExtracting the extreme point to obtain Pn(n∈[0，N/2))；
Sampling from the positive pole point to the negative pole point along the first main direction to obtain another point set Pn(n∈[N/2，N))；
Pn(N ∈ [0, N)) is the initial track obtained by sampling.
Preferably, the method for performing sliding window mean filtering on the initial trajectory comprises the following steps:
let the width of the sliding window be NfFor each point Pn in the initial trajectory, take the set of points in the sliding window as
Point set { P }n，iMean of P'nI.e. is pair PnAnd filtering the points to obtain the points.
Preferably, based on the current terminal pose of the robot, the pose of each 3-dimensional track point in the track obtained by the sliding window mean filtering is constructed, and the method specifically comprises the following steps:
let track point P 'obtained after filtering'n(n∈[0，N))，
Line P'nIs directed to P'n+1Has a unit vector of Vn，x；
Let the current robot end attitude be { Vt，x，Vt，y，Vt，zGet its component V in z directiont，zAs P'nReference vector V of pointsn，z′；
Get Vn，y＝Vn，z′×Vn，x，Vn，z＝Vn，x×Vn，yI.e. construct P'nAttitude of point { Vn，x，Vn，y，Vn，z}。
Preferably, the obtained final track is expressed by the space pose of each point
T′n(N ∈ [0, N)) is the trajectory sought.
According to the method for generating the spraying operation track for the special-shaped planes such as the soles, the height change of the contour is obtained by obtaining the three-dimensional point cloud of the operation plane and extracting and positioning the highest point on the contour of the operation track, and the optimized track which is suitable for the edge fluctuation of different special-shaped planes and is matched with the terminal attitude of the robot is obtained by further combining the terminal attitude of the robot.
Compared with the prior art, the beneficial effect of this disclosure is: firstly, generating self-adaptive tracks aiming at the fluctuation of different operation planes; and secondly, matching the pose of the current tail end of the robot to obtain a continuous track on the pose.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be apparent from the following more particular descriptions of exemplary embodiments of the disclosure as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the disclosure.
FIG. 1 shows an exemplary robot sole glue application work scenario and associated coordinate system;
FIG. 2 shows a set of shoe sole three-dimensional point cloud data according to an exemplary embodiment;
FIG. 3 shows three orthogonal principal directions of a three-dimensional point cloud of a sole, according to an exemplary embodiment;
FIG. 4 shows the process of sliding window scanning along the two sides of the sole and the resulting initial set of trajectory points;
FIG. 5 shows a schematic diagram of a unit vector between adjacent trace points;
FIG. 6 illustrates the introduction of robot tip poses at various trajectory points;
FIG. 7 shows the relationship between the pose components at a locus point.
Detailed Description
Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Fig. 1 shows an exemplary working scenario with robot gluing of shoe soles and associated coordinate system.
According to the special-shaped plane spraying operation track generation method disclosed by the disclosure, the track generation for sole gluing comprises the following steps:
1. shooting the sole by using a depth camera to obtain a sole three-dimensional point cloud data set { P }cAs shown in the attached figure 2, the three-dimensional point cloud of the sole can be obtained by other feasible means.
2. Applying principal component analysis method to sole point cloud to obtain three orthogonal principal directions { V }1，V2，V3As shown in FIG. 3, averaging all the point clouds to obtain a point cloud center point (x)c，yc，zc) The orthogonal base formed by the main direction and the point cloud center are combined to form the pose expression of the sole point cloud
3. The maximum value and the minimum value of the sole point cloud in three main directions are obtained, and the length, the width and the height l of the sole are obtained by subtracting the maximum value and the minimum valuec，wc，hc；
Assuming that the number of sampling points of all the tracks of the sole is N, the number of half points can be N/2, and the sizes of the sampling frames in three main directions are respectively 2lc/N、wc/2、h c2, starting from the negative extreme point of the second main direction side along the first main direction, by 2lcand/N is a moving interval, sampling is carried out towards the positive direction extreme point, as shown in figure 4, the sampling mode is that the point cloud in the sampling frame is extracted in the positive direction extreme point of the third main direction, and P is obtainedn(n∈[0，N/2))；
Sampling from the positive pole point to the negative pole point in the first main direction to obtain another point set P on the negative side of the second main directionn(n∈[N/2，N))；
Then P isn(N ∈ [0, N)) is the initial trajectory of the sample.
4. For { PnConducting sliding window mean value filtering on the track points, and enabling the width of a sliding window to be NfFor each point PnTaking a set of points in the sliding window as
Point set { P }n，iMean of P'nI.e. is PnAnd (4) point-filtering the points.
5. For track point P'n(N ∈ [0, N)), and let P'nIs directed to P'n+1Has a unit vector of Vn，xAs shown in fig. 5.
6. In order to enable the gluing track to be matched with the current terminal pose of the robot as much as possible so as to obtain a continuous track on the pose, the terminal pose of the robot needs to be referred to in the track generation process, and the pose is recorded as Vt，x，Vt，y，Vt，z}. Taking a z-direction component V of the tail end attitude of the robott，zAs P'nReference vector V of pointsn，z′As shown in fig. 6.
7. Let Vn，y＝Vn，z′×Vn，x，Vn，z＝Vn，x×Vn，yThus, construct out P 'based on the reference vector'nAttitude of point { Vn，x，Vn，y，Vn，zAs shown in fig. 7.
To sum up, P 'is obtained'nCorresponding spatial pose expresses T'n：
Then T'n(N ∈ [0, N)) is the result of the trajectory obtained.
Therefore, according to the gluing track generation method of the exemplary embodiment, the height change of the sole profile is obtained by obtaining the three-dimensional point cloud of the sole and extracting and positioning the highest point on the sole profile, and the optimized track which is suitable for the edge fluctuation of different shoe types and is matched with the tail end pose of the robot is generated by further combining the tail end pose of the robot. Compared with the prior art, the beneficial effect of this disclosure is: firstly, generating self-adaptive tracks aiming at different shoe types; and secondly, matching the pose of the current tail end of the robot to obtain a continuous track on the pose.
The track generation method disclosed by the disclosure can also be applied to robot machining operation similar to sole spraying and gluing.
The foregoing is illustrative of the present invention and various modifications and changes in form or detail will readily occur to those skilled in the art based upon the teachings herein and the application of the principles and principles disclosed herein, which are to be regarded as illustrative rather than restrictive on the broad principles of the present invention.
Claims (5)
1. A method for generating a special-shaped plane spraying operation track comprises the following steps:
acquiring a three-dimensional point cloud of a working plane, and constructing a three-dimensional point cloud coordinate system based on a principal component analysis method;
performing sliding window scanning along two side edges of the operation plane in a first main direction of the three-dimensional point cloud coordinate system, and extracting the highest point in each sliding window in a third main direction to obtain an initial track;
performing sliding window mean filtering on the initial track;
and constructing the gesture of each 3-dimensional track point in the track obtained after the sliding window mean filtering based on the current terminal pose of the robot to obtain a track containing the pose with 6 degrees of freedom, namely the required track.
2. The trajectory generation method according to claim 1, wherein the method of obtaining the initial trajectory comprises the steps of:
solving the maximum value and the minimum value of the three-dimensional point cloud in three main directions, and subtracting the two values to obtain the length, width and height l of the operation planec，wc，hc；
Setting the number of sampling points of one operation track on the operation plane as N, and respectively setting the size of a sampling frame in three main directions of the three-dimensional point cloud coordinate system as 2lc/N、wc/2、hc2, the sampling frame starts from the negative direction extreme point of the first main direction from the second main direction side and starts with 2lcthe/N is a moving interval, the sampling is carried out to the positive direction extreme point of the first main direction, the sampling mode is that the extreme point of the point cloud in the sampling frame in the positive direction of the third main direction is extracted, and P is obtainedn(n∈[0，N/2))；
Sampling from the positive pole point to the negative pole point along the first main direction to obtain another point set Pn(n∈[N/2，N))；
Pn(N ∈ [0, N)) is the initial track obtained by sampling.
3. The trajectory generation method of claim 1, the method of sliding window mean filtering the initial trajectory comprising the steps of:
let the width of the sliding window be NfFor each point P in the initial trajectorynTaking a set of points in the sliding window as
Point set { P }n，iMean of P'nI.e. is pair PnAnd filtering the points to obtain the points.
4. The trajectory generation method according to claim 1, wherein the method for constructing the pose of each 3-dimensional trajectory point in the trajectory obtained by the sliding window mean filtering based on the current end pose of the robot specifically comprises the following steps:
let track point P 'obtained after filtering'n(n∈[0，N))，
Line P'nIs directed to P'n+1Has a unit vector of Vn，x；
Let the current robot end attitude be { Vt，x，Vt，y，Vt，zGet its component V in z directiont，zAs P'nReference vector V of pointsn，z′；
Get Vn，y＝Vn，z′×Vn，x，Vn，z＝Vn，x×Vn，yI.e. construct P'nAttitude of point { Vn，x，Vn，y，Vn，z}。
5. The trajectory generation method according to claim 4, wherein the obtained final trajectory each point space pose is expressed as
T′n(N ∈ [0, N)) is the obtained final trajectory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111570167.8A CN114373012A (en) | 2021-12-21 | 2021-12-21 | Method for generating special-shaped plane spraying operation track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111570167.8A CN114373012A (en) | 2021-12-21 | 2021-12-21 | Method for generating special-shaped plane spraying operation track |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114373012A true CN114373012A (en) | 2022-04-19 |
Family
ID=81140988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111570167.8A Pending CN114373012A (en) | 2021-12-21 | 2021-12-21 | Method for generating special-shaped plane spraying operation track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114373012A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9460557B1 (en) * | 2016-03-07 | 2016-10-04 | Bao Tran | Systems and methods for footwear fitting |
| CN109454642A (en) * | 2018-12-27 | 2019-03-12 | 南京埃克里得视觉技术有限公司 | Robot coating track automatic manufacturing method based on 3D vision |
| CN110181516A (en) * | 2019-06-18 | 2019-08-30 | 苏州大学 | A kind of paths planning method of spray robot, device, system and storage medium |
| CN110226806A (en) * | 2019-05-07 | 2019-09-13 | 深圳市皕像科技有限公司 | A kind of sole gluing track generation method and device |
| CN112862704A (en) * | 2021-01-22 | 2021-05-28 | 北京科技大学 | Glue spraying and glue spraying quality detection system based on 3D vision |
-
2021
- 2021-12-21 CN CN202111570167.8A patent/CN114373012A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9460557B1 (en) * | 2016-03-07 | 2016-10-04 | Bao Tran | Systems and methods for footwear fitting |
| CN109454642A (en) * | 2018-12-27 | 2019-03-12 | 南京埃克里得视觉技术有限公司 | Robot coating track automatic manufacturing method based on 3D vision |
| WO2020133873A1 (en) * | 2018-12-27 | 2020-07-02 | 南京埃克里得视觉技术有限公司 | Three-dimensional vision-based production method by automatically calculating robot glue coating trajectory |
| CN110226806A (en) * | 2019-05-07 | 2019-09-13 | 深圳市皕像科技有限公司 | A kind of sole gluing track generation method and device |
| CN110181516A (en) * | 2019-06-18 | 2019-08-30 | 苏州大学 | A kind of paths planning method of spray robot, device, system and storage medium |
| CN112862704A (en) * | 2021-01-22 | 2021-05-28 | 北京科技大学 | Glue spraying and glue spraying quality detection system based on 3D vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107901041B (en) | Robot vision servo control method based on image mixing moment | |
| Bateux et al. | Training deep neural networks for visual servoing | |
| CN106737692B (en) | Mechanical gripper grabbing planning method based on depth projection and control device | |
| Torsello et al. | Multiview registration via graph diffusion of dual quaternions | |
| Ückermann et al. | Real-time 3D segmentation of cluttered scenes for robot grasping | |
| CN109100731B (en) | Mobile robot positioning method based on laser radar scanning matching algorithm | |
| CN114571153B (en) | Weld joint identification and robot weld joint tracking method based on 3D point cloud | |
| Bateux et al. | Visual servoing from deep neural networks | |
| CN108876852B (en) | Online real-time object identification and positioning method based on 3D vision | |
| CN110909644A (en) | Method and system for adjusting grabbing posture of mechanical arm end effector based on reinforcement learning | |
| CN111283686A (en) | Grasping posture calculation method for live working robot in grasping branch line scene | |
| CN114260908B (en) | Robot teaching method, apparatus, computer device and computer program product | |
| CN106595601B (en) | Accurate repositioning method for camera pose with six degrees of freedom without hand-eye calibration | |
| CN113191243B (en) | Human hand three-dimensional attitude estimation model establishment method based on camera distance and application thereof | |
| CN114373012A (en) | Method for generating special-shaped plane spraying operation track | |
| Song et al. | Distortion-free robotic surface-drawing using conformal mapping | |
| CN111709095B (en) | Method for constructing 6D virtual clamp for complex curved surface | |
| CN110470298B (en) | Robot vision servo pose estimation method based on rolling time domain | |
| Xu et al. | OD-SLAM: Real-time localization and mapping in dynamic environment through multi-sensor fusion | |
| Seo et al. | 3D Hole center and surface normal estimation in robot vision systems | |
| Nammoto et al. | Model-based compliant motion control scheme for assembly tasks using vision and force information | |
| Kim et al. | Contact-based pose estimation of workpieces for robotic setups | |
| CN106934831B (en) | Method for identifying position and posture of space object based on point cloud VFH descriptor | |
| Peng | K-means based RANSAC algorithm for ICP registration of 3D point cloud with dense outliers | |
| Liu et al. | Set space visual servoing of a 6-dof manipulator |
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 |