CN109822576B - Method for generating virtual fixture for robot machining - Google Patents
Method for generating virtual fixture for robot machining Download PDFInfo
- Publication number
- CN109822576B CN109822576B CN201910247278.1A CN201910247278A CN109822576B CN 109822576 B CN109822576 B CN 109822576B CN 201910247278 A CN201910247278 A CN 201910247278A CN 109822576 B CN109822576 B CN 109822576B
- Authority
- CN
- China
- Prior art keywords
- virtual
- manifold
- teaching
- data set
- robot
- 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.)
- Active
Links
Images
Landscapes
- Numerical Control (AREA)
Abstract
The invention belongs to the technical field related to intelligent robots, and discloses a method for generating a virtual fixture for robot machining, which comprises the following steps: performing robot kinesthesis teaching on a part to be processed, and collecting a robot kinesthesis teaching data set; generating a curved surface manifold of the surface of the part to be processed according to the acquired teaching data set; and generating a virtual clamp required by the task according to the obtained curved manifold. The invention also discloses a corresponding process method for machining the complex curved surface by the robot. Compared with the prior art, the method and the device can generate the required complex curved surface processing virtual fixture with higher efficiency and higher precision, can fully utilize the generalization characteristic of the curved surface manifold to construct the virtual fixture on similar parts, and have the advantages of convenience in operation and control, good stability, strong adaptability and the like, thereby obviously improving the processing quality of the finally obtained robot workpiece.
Description
Technical Field
The invention belongs to the technical field of intelligent robots, and particularly relates to a method for generating a virtual fixture for robot machining, which is particularly suitable for application occasions of processing workpieces such as complex curved surfaces by using a robot.
Background
With the continuous improvement of the industrial level, the complex curved surface is more and more widely applied to the aspects of aerospace engine blades, wind power blades, high-speed rail white bodies and the like. The robot has the characteristics of low cost, good flexibility, high efficiency and the like, and is widely applied to the complex curved surface grinding and polishing work and the like. At present, the manual teaching mode is mainly adopted for the hard programming part of a complex curved surface, such as a damping table. Robot teaching is a process in which a robot is simulated by an artificial teaching robot and then specified to execute an operation to be completed, that is, a series of tasks are completed using the teaching operation.
However, in the manual teaching process, the accuracy of completing the task is low only depending on the control of the operator on the terminal. To address this problem and ensure that the operator can perform the task more accurately, researchers have developed a concept of a virtual clamp. In the industry, the virtual clamp adopts a group of general guide modes to limit the robot to move to certain areas, and loads sensing information of the virtual, additional vision, force sense, auditory sense and the like of a local end in the process so as to improve the perception of an operator to the environment, so as to assist a human-computer cooperation system to accurately complete tasks.
As can be seen from further retrieval and analysis, on one hand, the generation of the virtual fixture in the prior art is often dependent on the existing geometric model, and the construction of the virtual fixture needs to depend on stronger expert experience, so that the design period is longer; on the other hand, the generated virtual fixture is often only suitable for the current parts and cannot be applied to similar parts, and the generalization capability is poor. Accordingly, there is a need in the art for further improvements to better meet the higher demands of intelligent industrial robot machining processes.
Disclosure of Invention
Aiming at the above defects and improvement requirements of the prior art, the invention provides a method for generating a virtual fixture for robot machining, wherein a Manifold of a part to be machined is obtained by introducing a Manifold Learning (modified Learning) algorithm, and a corresponding virtual fixture is generated and part machining is executed based on the Manifold.
To achieve the above object, according to one aspect of the present invention, there is provided a method for generating a robot machining virtual jig, comprising the steps of:
(S1) teaching data acquisition step of part to be processed
Aiming at a complex curved surface serving as a part to be processed, teaching learning is performed on the surface of the complex curved surface in a kinesthesia teaching mode, and a corresponding teaching data set { x is collectedi}i＝0:N(ii) a Wherein x isiRepresenting the ith data point sequentially numbered in the teaching data set, wherein N is the total number of samples of the teaching data set;
(S2) curved surface manifold learning step of the part to be machined
Processing the teaching data set acquired in the step (S1) by using a manifold learning algorithm, thereby completing the curved manifold learning of the part to be processed;
(S3) virtual jig guide trajectory generation step
And (S2) obtaining corresponding discrete data points on the curved manifold by using the curved manifold learning result of the step (S2), and carrying out interpolation processing according to the discrete data points to obtain a track curve so as to generate a guide track of the virtual clamp meeting the requirement of the part to be processed, thereby completing the generation process of the whole robot processing virtual clamp.
As a further preference, in the step (S2), the curved manifold learning process of the part to be machined may preferably specifically include the following sub-steps:
(S201) for each data point x in the teaching data setiFinding a plurality of adjacent points closest to the Euclidean distance based on the Euclidean distance, and calculating at each data point x by adopting the following expressions (one) and (two)iCentral estimate of the directional derivative of (a)i,j：
Wherein x isjIs representative of the distance from said data point xiOne of the nearest plurality of neighboring points and itself also belonging to said teach data set;
representing the simultaneous proximity of these two data points xi、xjA center point of (a); h (x) represents a curved manifold characterization function constructed for the part to be machined,i,jrepresents the data point xi、xjSlight variations in local cut space, which need to be followedContinuing to estimate;
(S202) a plurality of center estimated values Delta calculated based on the abovei,jContinuing to construct an objective function of the curved manifold characterization function H (x) of the part to be machined, wherein the objective function is shown in the following expression (three):
wherein the content of the first and second substances,
the expression (III) is calculated by taking the minimum value; i | · | purple wind2Calculating by taking a two-norm; λ represents a preset weight coefficient;
expressing Frobenius norm; j' denotes the data point xiSubscript number of the nearest neighbor;
then two data points x are representedi、xj′A center point of (a);
(S203) performing a linear parameterization on the surface manifold characterization function h (x) using the following expression (four), and describing each data point x by using the following expressions (five) and (six)iThe characteristics of (A):
H(x)＝[θ1f(x) … θDf(x)]T(IV)
f(x)＝[f1(x) … fp(x)]T(V)
fi(x)＝exp(-||x-μj||2/2σ2) (VI)
Wherein, in the expression (IV), θkAnother parameter which needs to be estimated subsequently is shown, and is numbered as k being 1,2, …, D in sequence, and D shows the total number of the parameters theta which need to be estimated in the expression; in expressions (five) and (six), fi(x) Representing the ith radial basis function of the defined p radial basis functions(ii) a x represents the parametric variable of the radial basis function, passing the data point x in this expression (six)iSubstituting; mu.sjRepresents the jth center point of the p center points obtained by correspondence, and σ represents each center point μj2 times the mean of the distances from its neighboring center points; [. the]TIndicating that a transpose process is performed;
(S204) using the objective function constructed in the above substeps and the obtained linear parameterization result, two parameters theta needed to be estimated are determined accordinglykAndi,jthus, the curved surface manifold learning process of the part to be processed is completed.
As a further preference, in the step (S3), obtaining corresponding discrete data points on the curved manifold is preferably performed by: firstly, the starting point and the end point of the guide track of the virtual clamp are appointed, and the step length alpha is increased, so that discrete data points on the curved manifold are obtained.
As a further preferable mode, in the step (S3), after obtaining discrete data points on the surface manifold, it is preferable to perform an Akima spline interpolation process, thereby obtaining a virtual jig guiding locus.
As a further preferable mode, the part to be processed includes an aerospace engine blade, a wind power blade, a high-speed rail body in white, and the like.
According to another aspect of the present invention, there is also provided a corresponding method for machining a complex curved surface by a robot, the method comprising the steps of:
(i) aiming at a complex curved surface serving as a part to be processed, teaching learning is performed on the surface of the complex curved surface in a kinesthesia teaching mode, and a corresponding teaching data set { x is collectedi}i0: N; wherein x isiRepresenting the ith data point sequentially numbered in the teaching data set, wherein N is the total number of samples of the teaching data set;
(ii) processing the teaching data set by adopting a manifold learning algorithm based on the acquired teaching data set, thereby finishing the curved manifold learning of the part to be processed;
(iii) obtaining corresponding discrete data points on the curved manifold by using the curved manifold learning result, and carrying out interpolation processing according to the discrete data points to obtain a track curve so as to generate a guide track of the virtual clamp meeting the requirements of the part to be processed;
(iv) and according to the generated virtual clamp guide track, assisting an operator to finish the machining process facing the part to be machined.
As a further preference, in step (iii), the generated virtual fixture is preferably represented according to the following expression:
xvm＝Ls(svm)
wherein s isvmCurve parameters representing the guide trajectory of the virtual gripper consisting of
The components of the composition are as follows,
is svmA derivative of (a); x'j,x′j-1Are discrete data points on the surface manifold; l issIs a virtual fixture geometric model obtained by Akima spline interpolation; j. the design is a squaresIs the Jacobian matrix of the virtual fixture, which is specifically represented as
xvmPoints on the trajectory are guided for the virtual gripper, and
is the derivative thereof.
As a further preference, in step (iv), the virtual clamp, during the completion of the machining process towards the part to be machined by the operator, preferably calculates the virtual restraining force generated according to the following expression:
wherein, FcRepresenting a virtual restraining force generated by a virtual clamp; x is the number ofvm,
Respectively obtaining the guide tracks of the virtual clamps generated in the previous step; x is the number ofrobot,
Respectively the displacement and the speed of the tail end of the actual robot; k and B are respectively a rigidity coefficient and a damping coefficient for generating the restraint force of the virtual clamp.
Generally, compared with the prior art, the above technical solution conceived by the present invention mainly has the following technical advantages:
1. according to the method, the curved surface Manifold of the part to be processed is obtained by introducing a Manifold Learning (Manifold Learning) algorithm, and the virtual fixture is generated by teaching the curved surface Manifold, so that the method does not need to rely on the existing geometric model, is simple in overall operation and convenient to control, and can better meet the characteristics of the actual working condition of processing the complex curved surface;
2. the method further utilizes the generalization characteristic of the curved manifold, and accordingly can construct virtual fixtures with similar tasks more quickly, so that the design period is shortened;
3. the method can generate the required complex curved surface processing virtual clamp with higher efficiency and higher precision, has the advantages of good stability, strong adaptability and the like, and further contributes to obviously improving the processing quality of the finally obtained robot workpiece.
Drawings
FIG. 1 is a schematic diagram of the overall process of robotic machining of a virtual fixture constructed in accordance with the present invention;
FIG. 2 is a schematic diagram of a virtual fixture control framework in accordance with a preferred embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Fig. 1 is a schematic diagram of the overall process of a robot machining virtual fixture constructed in accordance with the present invention. As shown in fig. 1, the key improvement of the process method is to introduce a Manifold Learning (modified Learning) algorithm to obtain a curved Manifold of a part to be processed, and further generate a corresponding virtual fixture and perform part processing based on the curved Manifold, so that the required complex curved surface processing virtual fixture can be generated more efficiently and more accurately than the prior art. Each of these steps will be specifically explained below.
Step one, teaching data acquisition of a part to be processed.
In this step, specifically, teaching learning may be performed on a surface of a complex curved surface as a part to be processed by means of kinesthetic teaching, and a corresponding teaching data set { x } may be acquiredi}i＝0:N(ii) a Wherein x isiRepresenting the ith data point sequentially numbered in the teaching data set, wherein N is the total number of samples of the teaching data set;
and step two, a curved surface manifold learning step of the part to be processed.
And processing the teaching data set by adopting a manifold learning algorithm based on the acquired teaching data set, thereby finishing the curved manifold learning of the part to be processed. The basic principles and processes of manifold learning algorithms are well known in the art.
For the sake of clarity, the present invention provides the following specific processes:
first, each data point x in the teaching data set can be addressediFinding a plurality of adjacent points closest to the Euclidean distance based on the Euclidean distance, and calculating at each data point x by adopting the following expressions (one) and (two)iCentral estimate of the directional derivative of (a)i,j：
Wherein x isjIs representative of the distance from said data point xiOne of the nearest plurality of neighboring points and itself also belonging to said teach data set;
representing the simultaneous proximity of these two data points xi、xjA center point of (a); h (x) represents a curved manifold characterization function constructed for the part to be machined,i,jrepresents the data point xi、xjA small variation in the local slice space, which needs to be estimated later;
then, a plurality of center estimated values Δ calculated based on the abovei,jContinuing to construct an objective function of the curved manifold characterization function H (x) of the part to be machined, wherein the objective function is shown in the following expression (three):
wherein the content of the first and second substances,
the expression (III) is calculated by taking the minimum value; i | · | purple wind2Calculating by taking a two-norm; λ represents a preset weight coefficient;
expressing Frobenius norm; j' denotes the data point xiSubscript number of the nearest neighbor;
then two data points x are representedi、xj′A center point of (a);
then, a linear parameterization process is performed on the surface manifold characterization function h (x) by using the following expression (four), and each data point x is described by using the following expressions (five) and (six)iThe characteristics of (A):
H(x)＝[θ1f(x) … θDf(x)]T(IV)
f(x)＝[f1(x) … fp(x)]T(V)
fi(x)＝exp(-||x-μj||2/2σ2) (VI)
Wherein, in the expression (IV), θkAnother parameter which needs to be estimated subsequently is shown, and is numbered as k being 1,2, …, D in sequence, and D shows the total number of the parameters theta which need to be estimated in the expression; in expressions (five) and (six), fi(x) Representing an ith radial basis function of the defined p radial basis functions; x represents the parametric variable of the radial basis function, passing the data point x in this expression (six)iSubstituting; mu.sjRepresents the jth center point of the p center points obtained by correspondence, and σ represents each center point μj2 times the mean of the distances from its neighboring center points; [. the]TIndicating that a transpose process is performed;
finally, the two parameters theta needing to be estimated are correspondingly determined by using the objective function constructed above and the obtained linear parameterization resultkAndi,jthus, the curved surface manifold learning process of the part to be processed is completed.
And step three, generating a guide track of the virtual clamp.
In the step, the corresponding discrete data points on the curved manifold are obtained by using the above curved manifold learning result, and interpolation processing is performed according to the discrete data points to obtain a trajectory curve, so as to generate a guide trajectory of the virtual fixture meeting the requirement of the part to be processed, thereby completing the generation process of the whole robot processing virtual fixture.
According to a preferred embodiment of the present invention, in this step, obtaining corresponding discrete data points on the surface manifold is preferably performed by: firstly, the starting point and the end point of the guide track of the virtual clamp are appointed, and the step length alpha is increased, so that discrete data points on the curved manifold are obtained.
More specifically, the projection characteristic of h (x) can be used to specify the start point and the end point of the virtual clamp guiding track to be obtained, and the step length α is increased to obtain the discrete data point x' on the curved manifold:
x'←x'+αH'H'T(x-x')
H'＝orth(H(x'))
where x is a point above the surface manifold, x 'is an approximate projected point on the surface manifold after increasing by step α, H' represents a regularized tangent plane at x ', H'TRepresenting a projection matrix.
According to another preferred embodiment of the present invention, after obtaining discrete data points on the surface manifold, it is preferably processed by Akima spline interpolation, thereby obtaining a virtual jig guide trajectory.
More specifically, the specific process of generating a parameterized virtual fixture guide trajectory via Akima spline interpolation can be explained as follows:
xvm＝Ls(svm)
wherein s isvmIs a curve parameter of the guide track of the virtual clamp, consisting of
The components of the composition are as follows,
is svmA derivative of (a); x'j,x′j-1Discrete data points on the curved manifold obtained in the previous step; l issIs a virtual fixture geometric model obtained by Akima spline interpolation; j. the design is a squaresIs the Jacobian matrix of the virtual fixture, which is specifically represented as
xvmFor the obtained virtual gripper guide points on the trajectory
Is the derivative thereof.
In addition, the invention also provides a corresponding method for processing the complex curved surface based on the virtual clamp, which is characterized by comprising the following steps:
firstly, aiming at a complex curved surface as a part to be processed, teaching learning is carried out on the surface of the complex curved surface in a kinesthetic teaching mode, and a corresponding teaching data set { x is collectedi}i＝0:N(ii) a Wherein x isiRepresenting the ith data point sequentially numbered in the teaching data set, wherein N is the total number of samples of the teaching data set;
secondly, processing the teaching data set by adopting a manifold learning algorithm based on the acquired teaching data set, thereby finishing the curved manifold learning of the part to be processed;
then, obtaining corresponding discrete data points on the curved manifold by using the curved manifold learning result, and carrying out interpolation processing according to the discrete data points to obtain a track curve so as to generate a guide track of the virtual fixture meeting the requirements of the part to be processed;
and finally, assisting an operator to finish the machining process facing the part to be machined according to the generated virtual clamp guide track.
According to a preferred embodiment of the present invention, the virtual fixture generated as described above can be preferably expressed according to the following expression:
xvm＝Ls(svm)
wherein s isvmCurve parameters representing the guide trajectory of the virtual gripper consisting of
The components of the composition are as follows,
is svmA derivative of (a); x'j,x′j-1Are discrete data points on the surface manifold; l issIs a virtual fixture geometric model obtained by Akima spline interpolation; j. the design is a squaresIs the Jacobian matrix of the virtual fixture, which is specifically represented as
xvmPoints on the trajectory are guided for the virtual gripper, and
is the derivative thereof.
According to another preferred embodiment of the present invention, the virtual clamp may preferably calculate the generated virtual restraining force according to the following expression during the process of assisting the operator in completing the process facing the part to be processed:
wherein, FcRepresenting a virtual restraining force generated by a virtual clamp; x is the number ofvm,
Respectively obtaining the guide tracks of the virtual clamps generated in the previous step; x is the number ofrobot,
Respectively the displacement and the speed of the tail end of the actual robot; k and B are respectively a rigidity coefficient and a damping coefficient for generating the restraint force of the virtual clamp.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. A method for generating a virtual fixture for robotic machining, the method comprising the steps of:
(S1) teaching data acquisition step of part to be processed
Aiming at a complex curved surface serving as a part to be processed, teaching learning is performed on the surface of the complex curved surface in a kinesthesia teaching mode, and a corresponding teaching data set { x is collectedi}i＝0:N(ii) a Wherein x isiRepresenting the ith data point sequentially numbered in the teaching data set, wherein N is the total number of samples of the teaching data set;
(S2) curved surface manifold learning step of the part to be machined
Processing the teaching data set acquired in the step (S1) by using a manifold learning algorithm, thereby completing the curved manifold learning of the part to be processed;
(S3) virtual jig guide trajectory generation step
And (S2) obtaining corresponding discrete data points on the curved manifold by using the curved manifold learning result of the step (S2), and carrying out interpolation processing according to the discrete data points to obtain a track curve so as to generate a guide track of the virtual clamp meeting the requirement of the part to be processed, thereby completing the generation process of the whole robot processing virtual clamp.
2. The method for generating a virtual jig for robotic machining as claimed in claim 1, wherein in step (S2), the learning process of the curved manifold of the part to be machined specifically includes the following sub-steps:
(S201) for each data point x in the teaching data setiFinding a plurality of adjacent points closest to the Euclidean distance based on the Euclidean distance, and calculating at each data point x by adopting the following expressions (one) and (two)iCentral estimate of the directional derivative of (a)i,j：
Wherein x isjIs representative of the distance from said data point xiOne of the nearest plurality of neighboring points and itself also belonging to said teach data set;
representing the simultaneous proximity of these two data points xi、xjA center point of (a); h (x) represents a curved manifold characterization function constructed for the part to be machined,i,jrepresents the data point xi、xjA small variation in the local slice space, which needs to be estimated later;
(S202) a plurality of center estimated values Delta calculated based on the abovei,jContinuing to construct an objective function of the surface manifold representation function h (x), which is expressed by the following expression (three):
wherein the content of the first and second substances,
the expression (III) is calculated by taking the minimum value; i | · | purple wind2Calculating by taking a two-norm; λ represents a preset weight coefficient;
expressing Frobenius norm; j' denotes the data point xiSubscript number of the nearest neighbor;
then two data points x are representedi、xj′A center point of (a);
(S203) performing a linear parameterization on the surface manifold characterization function h (x) using the following expression (four), and describing each data point x by using the following expressions (five) and (six)iThe characteristics of (A):
H(x)＝[θ1f(x) … θDf(x)]T(IV)
f(x)＝[f1(x) … fp(x)]T(V)
fi(x)＝exp(-||x-μj||2/2σ2) (VI)
Wherein, in the expression (IV), θkAnother parameter which needs to be estimated subsequently is shown, and is numbered as k being 1,2, …, D in sequence, and D shows the total number of the parameters theta which need to be estimated in the expression; in expressions (five) and (six), fi(x) Representing an ith radial basis function of the defined p radial basis functions; x represents the parametric variable of the radial basis function, passing the data point x in this expression (six)iSubstituting; mu.sjRepresents the jth center point of the p center points obtained by correspondence, and σ represents each center point μj2 times the mean of the distances from its neighboring center points; [. the]TIndicating that a transpose process is performed;
(S204) the objective function constructed with the above substeps, and the obtained linearityParameterizing the result, determining the two parameters theta to be estimated accordinglykAndi,jthus, the curved surface manifold learning process of the part to be processed is completed.
3. The method for generating a robotic machining virtual fixture as claimed in claim 1, wherein in step (S3), obtaining corresponding discrete data points on the curved manifold is performed by: firstly, the starting point and the end point of the guide track of the virtual clamp are appointed, and the step length alpha is increased, so that discrete data points on the curved manifold are obtained.
4. The method for generating a virtual jig for robot machining according to any one of claims 1 to 3, wherein in step (S3), after discrete data points on the surface manifold are obtained, a virtual jig guide trajectory is obtained by Akima spline interpolation processing.
5. The method for generating the virtual fixture for the robot machining according to any one of claims 1 to 3, wherein the parts to be machined comprise aerospace engine blades, wind power blades and high-speed rail white bodies.
6. A method for machining a complex curved surface by a robot, comprising the steps of:
(i) aiming at a complex curved surface serving as a part to be processed, teaching learning is performed on the surface of the complex curved surface in a kinesthesia teaching mode, and a corresponding teaching data set { x is collectedi}i＝0:N(ii) a Wherein x isiRepresenting the ith data point sequentially numbered in the teaching data set, wherein N is the total number of samples of the teaching data set;
(ii) processing the teaching data set by adopting a manifold learning algorithm based on the acquired teaching data set, thereby finishing the curved manifold learning of the part to be processed;
(iii) obtaining corresponding discrete data points on the curved manifold by using the curved manifold learning result, and carrying out interpolation processing according to the discrete data points to obtain a track curve so as to generate a guide track of the virtual clamp meeting the requirements of the part to be processed;
(iv) and according to the generated virtual clamp guide track, assisting an operator to finish the machining process facing the part to be machined.
7. The method of claim 6, wherein in step (iii), the generated virtual fixture is represented according to the following expression:
xvm＝Ls(svm)
wherein s isvmCurve parameters representing the guide trajectory of the virtual gripper consisting of
The components of the composition are as follows,
is svmA derivative of (a); x'j,x′j-1Are discrete data points on the surface manifold; l issIs a virtual fixture geometric model obtained by Akima spline interpolation; j. the design is a squaresIs the Jacobian matrix of the virtual fixture, which is specifically represented as
xvmPoints on the trajectory are guided for the virtual gripper, and
is the derivative thereof.
8. The method according to claim 7, wherein in step (iv), the virtual clamp calculates the virtual restraining force generated during the completion of the machining process by the operator facing the part to be machined according to the following expression:
wherein, FcRepresenting a virtual restraining force generated by a virtual clamp; x is the number ofvm,
Respectively obtaining the guide tracks of the virtual clamps generated in the previous step; x is the number ofrobot,
Respectively the displacement and the speed of the tail end of the actual robot; k and B are respectively a rigidity coefficient and a damping coefficient for generating the restraint force of the virtual clamp.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910247278.1A CN109822576B (en) | 2019-03-29 | 2019-03-29 | Method for generating virtual fixture for robot machining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910247278.1A CN109822576B (en) | 2019-03-29 | 2019-03-29 | Method for generating virtual fixture for robot machining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109822576A CN109822576A (en) | 2019-05-31 |
| CN109822576B true CN109822576B (en) | 2020-12-08 |
Family
ID=66874513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910247278.1A Active CN109822576B (en) | 2019-03-29 | 2019-03-29 | Method for generating virtual fixture for robot machining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109822576B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992777B (en) * | 2019-11-20 | 2020-10-16 | 华中科技大学 | Multi-mode fusion teaching method and device, computing equipment and storage medium |
| CN111709095B (en) * | 2020-05-27 | 2022-08-16 | 华中科技大学 | Method for constructing 6D virtual clamp for complex curved surface |
| CN111660307B (en) * | 2020-05-27 | 2021-07-20 | 华中科技大学 | Robot operation high-assistance precision virtual clamp control method and system |
| CN113305836B (en) * | 2021-05-21 | 2022-09-27 | 华中科技大学 | Virtual-guided local iteration correction method and system |
| CN113386142A (en) * | 2021-07-07 | 2021-09-14 | 天津大学 | Grinding and cutting integrated processing system and method of teleoperation robot based on virtual clamp |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1947961A (en) * | 2005-10-12 | 2007-04-18 | 发那科株式会社 | Offline teaching apparatus for robot |
| CN102622461A (en) * | 2011-09-07 | 2012-08-01 | 华南理工大学 | Method for generating three-dimensional pipeline according to three-dimensional feasible path |
| CN103207566A (en) * | 2013-01-18 | 2013-07-17 | 西北工业大学 | Space teleoperation method dynamically assisted by speed type virtual force feedback |
| CN106152935A (en) * | 2015-03-25 | 2016-11-23 | 苏州北硕检测技术有限公司 | It is applicable to the laser measurement system without feature space curved surface blank and processing positioning method thereof |
| CN106598224A (en) * | 2016-11-22 | 2017-04-26 | 西北工业大学 | Method for enhancing teleoperation telepresence based on virtual environment reconstruction |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016040862A2 (en) * | 2014-09-12 | 2016-03-17 | Chizeck Howard Jay | Integration of auxiliary sensors with point cloud-based haptic rendering and virtual fixtures |
-
2019
- 2019-03-29 CN CN201910247278.1A patent/CN109822576B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1947961A (en) * | 2005-10-12 | 2007-04-18 | 发那科株式会社 | Offline teaching apparatus for robot |
| CN102622461A (en) * | 2011-09-07 | 2012-08-01 | 华南理工大学 | Method for generating three-dimensional pipeline according to three-dimensional feasible path |
| CN103207566A (en) * | 2013-01-18 | 2013-07-17 | 西北工业大学 | Space teleoperation method dynamically assisted by speed type virtual force feedback |
| CN106152935A (en) * | 2015-03-25 | 2016-11-23 | 苏州北硕检测技术有限公司 | It is applicable to the laser measurement system without feature space curved surface blank and processing positioning method thereof |
| CN106598224A (en) * | 2016-11-22 | 2017-04-26 | 西北工业大学 | Method for enhancing teleoperation telepresence based on virtual environment reconstruction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109822576A (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109822576B (en) | Method for generating virtual fixture for robot machining | |
| CN108919760B (en) | Intelligent workshop autonomous production process dynamic linkage control method based on digital twins | |
| CN110262394B (en) | Method for compensating contour error in numerical control machining | |
| CN108115705A (en) | A kind of robot polishing control system and method | |
| CN110315396B (en) | Industrial robot constant-force grinding and polishing method based on big data | |
| CN109434843A (en) | A kind of device and method of the Robot Force console keyboard mill blade based on dragging teaching | |
| Lakshminarayanan et al. | An adaptive framework for robotic polishing based on impedance control | |
| CN110992777B (en) | Multi-mode fusion teaching method and device, computing equipment and storage medium | |
| CN107030702B (en) | A kind of method for planning track of mechanical arm | |
| CN109848989B (en) | Robot execution tail end automatic calibration and detection method based on ruby probe | |
| Burghardt et al. | Experimental study of Inconel 718 surface treatment by edge robotic deburring with force control | |
| CN110989490B (en) | Method for acquiring optimal installation position of workpiece based on contour error | |
| Feng et al. | A novel feature-guided trajectory generation method based on point cloud for robotic grinding of freeform welds | |
| CN108608425B (en) | Off-line programming method and system for milling of six-axis industrial robot | |
| CN114131611A (en) | Joint error offline compensation method, system and terminal for robot gravity pose decomposition | |
| CN106054814B (en) | Computer aided building method based on image grayscale | |
| CN110281152B (en) | Robot constant-force polishing path planning method and system based on online touch test | |
| CN110174871B (en) | Control device, machine learning device, and system | |
| CN105313119A (en) | Mixed control method and system for 5-axis industrial robot and 6-axis industrial robot | |
| Leco et al. | A two-step machining and active learning approach for right-first-time robotic countersinking through in-process error compensation and prediction of depth of cuts | |
| CN109446721B (en) | Machine tool process interaction algorithm based on identifier software thread execution sequence arrangement | |
| CN112114557B (en) | Dynamic precision detection method and system for five-axis linkage numerical control machine tool and storage medium | |
| CN113276112B (en) | Mobile double-robot-based weak rigid member machining process planning method | |
| CN111061218B (en) | Complex curved surface machining cutting force prediction method and device based on ACIS | |
| CN114460903A (en) | Special-shaped injection molding joint line machining method and device based on five-axis linkage machine tool |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |