CN111055286A - Industrial robot track generation method, system, device and storage medium - Google Patents
Industrial robot track generation method, system, device and storage medium Download PDFInfo
- Publication number
- CN111055286A CN111055286A CN202010031229.7A CN202010031229A CN111055286A CN 111055286 A CN111055286 A CN 111055286A CN 202010031229 A CN202010031229 A CN 202010031229A CN 111055286 A CN111055286 A CN 111055286A
- Authority
- CN
- China
- Prior art keywords
- data points
- data
- error
- curve
- point
- 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.)
- Granted
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
- B25J9/1656—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
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a method, a system and a storage medium for generating a track of an industrial robot, wherein the method comprises the following steps: acquiring original data of a robot track to be generated, and filtering the original data to obtain a plurality of data points; acquiring discrete curvature of each data point, and acquiring a fitting curve by combining the discrete curvature and the data points; and calculating the error between the fitted curve and the data point, and generating the track of the industrial robot according to the fitted curve when the error is smaller than a preset tolerance. According to the method, noise points and error points in original data are removed, a fitting curve is obtained by combining with discrete curvature, and finally an industrial robot track is generated according to the fitting curve, so that the robot track is smoother, the processing speed and the processing quality are improved, and the method can be widely applied to the field of robot path planning.
Description
Technical Field
The invention relates to the field of robot path planning, in particular to a method and a system for generating a track of an industrial robot and a storage medium.
Background
At present, the application of the robot in the field of industrial production and manufacturing is more and more extensive, and the combination of the robot and a three-dimensional camera scanner is more and more common. The method is characterized in that the method is influenced by various factors such as surface roughness of an object, a light source position, material color of an object to be scanned, vibration of a control console and the like, a scanned model cannot be avoided to generate noise, so that discrete data extracted from the model have noise points or even error points, if the discrete data are directly used for generating a processing track of the robot, the processing track cannot be smooth, the tail end of the robot shakes, the processing speed is greatly influenced, and the processing quality cannot reach the standard.
Disclosure of Invention
In order to solve the above technical problems, it is an object of the present invention to provide a method, a system and a storage medium for generating a trajectory of an industrial robot more smoothly.
The first technical scheme adopted by the invention is as follows:
an industrial robot trajectory generation method comprising the steps of:
acquiring original data of a robot track to be generated, and filtering the original data to obtain a plurality of data points;
acquiring discrete curvature of each data point, and acquiring a fitting curve by combining the discrete curvature and the data points;
and calculating the error between the fitted curve and the data point, and generating the track of the industrial robot according to the fitted curve when the error is smaller than a preset tolerance.
Further, the step of obtaining a plurality of data points after filtering the raw data specifically includes the following steps:
sequentially acquiring initial data points from the original data, and rejecting the initial data points when the initial data points are detected to be noise points;
and processing the coordinates of the initial data points in a preset mode, and obtaining final data points.
Further, whether the initial data point is a noise point is detected by the following method:
acquiring two initial data points adjacent to the front and rear positions of the initial data point, and acquiring angle values of the three initial data points after being sequentially connected;
and judging whether the angle value is smaller than a first preset angle or not, and judging the initial data point as a noise point when the angle value is smaller than the first preset angle.
Further, the step of processing the coordinates of the initial data point in a preset manner and obtaining a final data point specifically includes:
judging whether the angle value is larger than a second preset angle or not, and if so, taking the coordinates of the initial data point as a final data point; otherwise, combining the coordinates of the three initial data points to calculate new coordinates as final data points;
wherein the second preset angle is greater than the first preset angle.
Further, the step of acquiring the discrete curvature of each data point and acquiring the fitting curve by combining the discrete curvature and the data point specifically includes the following steps:
a1, acquiring the discrete curvature of each data point, and calculating the cumulative sum of the discrete curvatures of all the data points;
a2, obtaining an initial average discrete curvature by combining the accumulated sum of the discrete curvatures and the preset number of fitting nodes;
a3, obtaining a node vector of a fitting curve by combining the discrete curvature and the initial average discrete curvature;
and A4, combining the data points and the node vectors to obtain a final fitting curve.
Further, the step a4 specifically includes:
and (4) combining the data points, the node vectors and the least square curve fitting mode to obtain a final fitting curve.
Further, the step of calculating the error between the fitted curve and the data point, and generating the industrial robot track according to the fitted curve when the error is smaller than a preset tolerance specifically comprises the following steps:
calculating the error of the fitted curve and the data point;
if the error is smaller than the Maxerror, discretizing all data points on the fitting curve to obtain discrete data points;
if the error is larger than the Maxerror, returning to execute the step A4 until the error is smaller than the Maxerror;
if the error is larger than t × Maxerror, after the number of the fitting nodes is reset, returning to execute the steps A1-A4 until the error is smaller than Maxerror;
generating a robot track according to the discrete data points;
the Maxerror is a preset tolerance, and t is a positive integer.
The second technical scheme adopted by the invention is as follows:
an industrial robot trajectory generation system comprising:
the data filtering module is used for acquiring original data of the robot track to be generated, and obtaining a plurality of data points after filtering the original data;
the curve fitting module is used for acquiring the discrete curvature of each data point and acquiring a fitting curve by combining the discrete curvature and the data points;
and the error calculation module is used for calculating the error between the fitting curve and the data point and generating the track of the industrial robot according to the fitting curve when the error is smaller than the preset tolerance.
The third technical scheme adopted by the invention is as follows:
an industrial robot trajectory generation device comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The fourth technical scheme adopted by the invention is as follows:
a storage medium having stored therein processor-executable instructions for performing the method as described above when executed by a processor.
The invention has the beneficial effects that: according to the method, noise points and error points in original data are removed, a fitting curve is obtained by combining with discrete curvature, and finally the track of the industrial robot is generated according to the fitting curve, so that the track of the robot is smoother, and the processing speed and the processing quality are improved.
Drawings
FIG. 1 is a flow chart of steps of a method for trajectory generation for an industrial robot in accordance with an exemplary embodiment;
FIG. 2 is a block diagram of an industrial robot trajectory generation system in accordance with an exemplary embodiment;
FIG. 3 is a schematic illustration of an industrial robot trajectory generated by a prior art method;
FIG. 4 is a schematic illustration of an industrial robot trajectory generated using a particular embodiment method;
fig. 5 is a flowchart illustrating an industrial robot trajectory generation method according to an exemplary embodiment.
Detailed Description
As shown in fig. 1, the present embodiment provides an industrial robot trajectory generation method, including the following steps:
s1, acquiring original data of the robot track to be generated, and filtering the original data to acquire a plurality of data points;
s2, obtaining discrete curvatures of the data points, and obtaining a fitting curve by combining the discrete curvatures and the data points;
and S3, calculating the error of the fitted curve and the data points, and generating the track of the industrial robot according to the fitted curve when the error is smaller than the preset tolerance.
In the method of the embodiment, the original data of the robot trajectory to be generated is filtered and deleted, and the data points with obvious errors are removed, wherein the data points can be removed by adopting the existing data filtering mode, for example, by comparing the coordinate distance between two adjacent points or the vector change between the points. After the filtering process, a plurality of data points are obtained. Calculating the discrete curvature of each data point according to the coordinates of the data points, obtaining a fitting curve by combining the discrete curvature, the data points and a preset curve fitting mode, and generating the industrial robot track according to the fitting curve when the error between the fitting curve and the data points is smaller than a preset tolerance, for example, the fitting curve can be used as the robot track, and points of the fitting curve can be discretized again and then combined. By the method, noise points and error points in the original data are removed, a fitting curve is obtained by combining with the discrete curvature, and finally the track of the industrial robot is generated according to the fitting curve, so that the track of the robot is smoother, and the processing speed and the processing quality are improved.
Wherein, the step S1 specifically includes steps S11 to S12:
s11, sequentially acquiring initial data points from the original data, and rejecting the initial data points when the initial data points are detected to be noise points;
and S12, processing the coordinates of the initial data point in a preset mode, and obtaining a final data point.
Specifically, step S11 specifically includes steps S111 to S112:
s111, acquiring two initial data points adjacent to the front and rear positions of the initial data point, and acquiring angle values of the three initial data points after being sequentially connected;
and S112, judging whether the angle value is smaller than a first preset angle or not, and judging the initial data point as a noise point when the angle value is smaller than the first preset angle.
Step S12 specifically includes: judging whether the angle value is larger than a second preset angle or not, and if so, taking the coordinates of the initial data point as a final data point; otherwise, combining the coordinates of the three initial data points to calculate new coordinates as final data points; wherein the second preset angle is greater than the first preset angle.
The sharp noise points in the data points are filtered and smoothed, and the method specifically comprises the following steps:
step 1, removing error points in original data: three adjacent data points Pi-1,Pi,Pi+1To find ∠ Pi-1PiPi+1Angle if ∠ Pi-1PiPi+1<At 30 deg., the point P is considerediFor noise points, point PiRemoving;
step 2, ∠ P obtained in step 1i-1PiPi+1Make a judgment if ∠ Pi-1PiPi+1>90 deg., then point P is considerediThe data is normal data and is not processed;
step 3, if ∠ Pi-1PiPi+1<Calculate segment | P at 90 °i-1Pi|、|PiPi+1Length of | if | Pi-1Pi|=|PiPi+1If is at the line segment Pi-1Pi+1And (3) taking a point P to ensure that P satisfies the following conditions: p ═ Pi-1+Pi+1) /2, instead of point Pi(ii) a If Pi-1Pi|>|PiPi+1If, then calculate the proportionality coefficientOn line segment Pi-1PiTaking a point P to ensure that the point P meets the following conditions: p ═ Pi+α*(Pi-1-Pi) Substituting P point coordinates for PiPoint coordinates; if Pi-1Pi|<|PiPi+1If, then calculate the proportionality coefficientOn line segment Pi+1PiTaking a point P to ensure that the point P meets the following conditions: p ═ Pi+α*(Pi+1-Pi) Substituting P point coordinates for PiPoint coordinates.
The step S2 specifically includes steps S21 to S24:
s21, acquiring the discrete curvature of each data point, and calculating the cumulative sum of the discrete curvatures of all the data points;
s22, obtaining an initial average discrete curvature by combining the accumulated sum of the discrete curvatures and the preset number of fitting nodes;
s23, obtaining a node vector of the fitting curve by combining the discrete curvature and the initial average discrete curvature;
and S24, acquiring a final fitting curve by combining the data points and the node vectors.
Step S24 specifically includes: and (4) combining the data points, the node vectors and the least square curve fitting mode to obtain a final fitting curve.
Wherein, the step S3 specifically includes steps S31 to S33:
s31, calculating the error between the fitted curve and the data point;
s32, discretizing all data points on the fitting curve if the error is smaller than the Maxerrer to obtain discrete data points; if the error is larger than the Maxerror, returning to execute the step A4 until the error is smaller than the Maxerror; if the error is larger than t × Maxerror, after the number of the fitting nodes is reset, returning to execute the steps A1-A4 until the error is smaller than Maxerror;
s33, generating a robot track according to the discrete data points;
the Maxerror is a preset tolerance, and t is a positive integer.
In the present embodiment, the specific implementation is as follows.
Step 1: setting a maximum allowance maxerr, the number InitNum of fitting nodes and the maximum iteration number N;
wherein, after data filtering, the data point is represented as q0,q1,q2…qmAnd InitNum<m+1。
Step 2: calculating discrete curvature of initial data given in the first step, and calculating three adjacent points Pi-1,Pi,Pi+1Separately obtain | Pi-1Pi|、|PiPi+1Modulo of | if | Pi-1Pi|≥|PiPi+1I, make di=|PiPi+1I, orderAt Pi-1PiAnd calculating a point P to ensure that the coordinate of the point P satisfies the following conditions: p ═ Pi+α*(Pi-1-Pi) Then, D is obtainedi=|Pi+1P |, point PiHas a discrete curvature of If Pi-1Pi|<|PiPi+1I, make di=|PiPi-1I, orderAt Pi+1PiAnd calculating a point P to ensure that the coordinate of the point P satisfies the following conditions: p ═ Pi+α*(Pi+1-Pi) Then, D is obtainedi=|Pi-1P |, point PiHas a discrete curvature ofCalculating the cumulative sum of the discrete curvatures of all data pointssum。
And step 3: solving the node vector of the fitting curve according to the discrete curvature, and solving the node vector m _ aU of the initial data point according to the accumulated chord length parameterizationiAccording to the number InitNum of the fitting node vectors set in the step 1 and the discrete curvature cumulative sum C calculated in the step 2sumDetermining the initial mean discrete curvature of the approximation curve, i.e.Then traversing the discrete curvature of the initial data point to obtain the initial node vector of the fitting curve, if the discrete curvature of the jth data point meets the condition And then the ith node vector is obtained,wherein i has a value in the range of 0<i≤InitNum。
And 4, step 4: and (3) approximation of a least square spline curve, namely solving a least square B spline approximation curve according to the node vector and the initial data point obtained in the step (3), wherein the formula is as follows
Wherein N isj,k(u) is a B-spline basis function, k represents the degree of times, j represents the number; djRepresenting the control points of the least squares curve approximation.
And 5: solving the maximum error of the data points:
according to the least square objective function as the optimization target, the end point constraint condition, namely q, is met0=p(0),qmAnd p (1), the initial data points obtained in the first step are approximately approximated in a least squares sense:
wherein q isiRepresents the ith initial data point; p (u)i) The point position on the least square curve corresponding to the node vector of the ith data point;
step 6: the approximation curve error value is compared with the maximum tolerance:
comparing the error value of the least square approximation curve obtained in the step 5 with the maximum tolerance;
if f is greater than Maxerror and the approximation curve is greater than the tolerance, re-approximating curve fitting is needed, if f is greater than t × Maxerror, approximating a curve node InitNum' ═ InitNum + t, repeating the steps 2-6, and iterating for times + 1;
if f is less than Maxerror, the flow is ended, and the data point is discretized again.
Wherein t is a positive integer.
And 7: and (4) generating a robot processing track for the discrete data obtained in the step (6).
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
The above method is explained in detail below with reference to specific embodiments of the sole gluing trajectory of an industrial robot, with reference to fig. 3-5.
Referring to fig. 5, step one: and filtering the robot track data points to be generated.
Wherein, the first step comprises S101 to S101:
step S101, eliminating error points in the original data: three adjacent data points Pi-1,Pi,Pi+1To find ∠ Pi-1PiPi+1Angle if ∠ Pi-1PiPi+1<At 30 deg., the point P is considerediFor noise points, point PiRemoving;
step S101 for ∠ P obtained in step S101i-1PiPi+1Make a judgment if ∠ Pi-1PiPi+1>90 deg., then point P is considerediThe data is normal data and is not processed;
step S101, if ∠ Pi-1PiPi+1<Calculate segment | P at 90 °i-1Pi|、|PiPi+1Length of | if | Pi-1Pi|=|PiPi+1If is at the line segment Pi-1Pi+1And (3) taking a point P to ensure that P satisfies the following conditions: p ═ Pi-1+Pi+1) /2, instead of point Pi(ii) a If Pi-1Pi|>|PiPi+1If, then calculate the proportionality coefficientOn line segment Pi-1PiTaking a point P to ensure that the point P meets the following conditions: p ═ Pi+α*(Pi-1-Pi) Substituting P point coordinates for PiPoint coordinates; if Pi-1Pi|<|PiPi+1If, then calculate the proportionality coefficientOn line segment Pi+1PiTaking a point P to ensure that the point P meets the following conditions: p ═ Pi+α*(Pi+1-Pi) Substituting P point coordinates for PiPoint coordinates.
Step two: and setting an approximation curve node vector according to the discrete curvature.
Wherein, the second step comprises steps S201 to S207
Step S201 sets a maximum tolerance Maxerror, the number InitNum of fitting nodes and a maximum iteration number N;
after the data filtering in the first step, the number of data points is m +1, and InitNum is less than m + 1.
S202, solving the discrete curvature of the initial data given in the first step, and solving the three adjacent points Pi-1,Pi,Pi+1Separately obtain | Pi-1Pi|、|PiPi+1Modulo of | if | Pi-1Pi|≥|PiPi+1I, make di=|PiPi+1I, orderAt Pi-1PiAnd calculating a point P to ensure that the coordinate of the point P satisfies the following conditions: p ═ Pi+α*(Pi-1-Pi) Then, D is obtainedi=|Pi+1P |, point PiHas a discrete curvature ofIf Pi-1Pi|<|PiPi+1I, make di=|PiPi-1I, orderAt Pi+1PiAnd calculating a point P to ensure that the coordinate of the point P satisfies the following conditions: p ═ Pi+α*(Pi+1-Pi) Then, D is obtainedi=|Pi-1P |, point PiHas a discrete curvature ofCalculating the cumulative sum of the discrete curvatures of all data pointssum。
Step S203, the node vector of the fitting curve is solved according to the discrete curvature, and the node vector m _ aU of the initial data point is solved according to the accumulated chord length parameterizationiThe formula is as follows;
wherein k is the number of fits, k >1, and n is the number of data points;
according to the number InitNum of the fitting node vectors set in the step S201 and the discrete curvature accumulated sum C obtained in the step S202sumFinding the mean discrete curvature, i.e.Then traversing the discrete curvature of the initial data point to obtain the initial node vector of the fitting curve, if the discrete curvature of the jth data point meets the conditionAnd then the ith node vector is obtained,
step S204, fitting a least square spline curve, and solving a least square B-spline approximation curve according to the node vector and the initial data point solved in the step 3, wherein the formula is as follows
(NTN)D=R (5)
Wherein the formula (3) is an approximation curve formula, Nj,k(u) is a B-spline basis function, k represents the degree of times, j represents the number; djRepresenting the control points of the least squares curve approximation. Equation (4) is a B-spline basis function, equation (5) is a control point recurrence equation, where N is an (m-1) × (N-1) order scalar matrix, and the control points are solved by equations (5) - (8).
Step S205 finds the maximum error of the data point:
according to the least square objective function as the optimization target, the end point constraint condition, namely q, is met0=p(0),qmAnd p (1), the initial data points obtained in the first step are approximately approximated in a least squares sense:
wherein q isiDenotes the ith initial data point, p (u)i) Is the point position on the least square curve corresponding to the node vector of the ith data point.
Step S206, comparing the approximation curve error value with the maximum tolerance:
comparing the error value of the least square approximation curve found in step S205 with the maximum tolerance;
if f is greater than Maxerror and the approximation curve is greater than the tolerance, re-approximating curve fitting is needed, if f is greater than t × Maxerror, approximating a curve node InitNum' ═ InitNum + t, repeating the steps 2-6, and iterating for times + 1;
if f is less than Maxerror, the flow is ended, and the data point is discretized again.
Wherein t is a positive integer.
Step S207, generating a robot processing track for the discrete data obtained in step 6, as shown in fig. 3, where the track is a sole gluing track of an industrial robot obtained by a general method and has many sharp places; and as shown in fig. 4, the curve of the sole gluing track of the industrial robot obtained by the method of the embodiment is smoother, so that the tail end of the robot cannot shake, and the requirement of high-quality industrial production is met.
As shown in fig. 2, the present embodiment also provides an industrial robot trajectory generation system including:
the data filtering module is used for acquiring original data of the robot track to be generated, and obtaining a plurality of data points after filtering the original data;
the curve fitting module is used for acquiring the discrete curvature of each data point and acquiring a fitting curve by combining the discrete curvature and the data points;
and the error calculation module is used for calculating the error between the fitting curve and the data point and generating the track of the industrial robot according to the fitting curve when the error is smaller than the preset tolerance.
The industrial robot trajectory generation system provided by the embodiment of the invention can execute the industrial robot trajectory generation method provided by the embodiment of the method of the invention, can execute any combination of the implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
The present embodiment also provides an industrial robot trajectory generation device including:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The industrial robot track generation device provided by the embodiment of the invention can execute the industrial robot track generation method provided by the embodiment of the method of the invention, can execute any combination of the implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
The present embodiments also provide a storage medium having stored therein processor-executable instructions, which when executed by a processor, are configured to perform the method as described above.
The storage medium of the embodiment can execute the industrial robot track generation method provided by the method embodiment of the invention, can execute any combination of the implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. An industrial robot trajectory generation method, characterized by comprising the steps of:
acquiring original data of a robot track to be generated, and filtering the original data to obtain a plurality of data points;
acquiring discrete curvature of each data point, and acquiring a fitting curve by combining the discrete curvature and the data points;
and calculating the error between the fitted curve and the data point, and generating the track of the industrial robot according to the fitted curve when the error is smaller than a preset tolerance.
2. The method according to claim 1, wherein the step of obtaining a plurality of data points after filtering the raw data comprises the following steps:
sequentially acquiring initial data points from the original data, and rejecting the initial data points when the initial data points are detected to be noise points;
and processing the coordinates of the initial data points in a preset mode, and obtaining final data points.
3. An industrial robot trajectory generation method according to claim 2, characterized in that it is detected whether the initial data points are noise points by:
acquiring two initial data points adjacent to the front and rear positions of the initial data point, and acquiring angle values of the three initial data points after being sequentially connected;
and judging whether the angle value is smaller than a first preset angle or not, and judging the initial data point as a noise point when the angle value is smaller than the first preset angle.
4. The method according to claim 3, wherein the step of processing the coordinates of the initial data points in a preset manner and obtaining the final data points comprises:
judging whether the angle value is larger than a second preset angle or not, and if so, taking the coordinates of the initial data point as a final data point;
otherwise, combining the coordinates of the three initial data points to calculate new coordinates as final data points;
wherein the second preset angle is greater than the first preset angle.
5. The method according to claim 1, wherein the step of obtaining the discrete curvature of each data point and obtaining the fitting curve by combining the discrete curvature and the data point comprises the following steps:
a1, acquiring the discrete curvature of each data point, and calculating the cumulative sum of the discrete curvatures of all the data points;
a2, obtaining an initial average discrete curvature by combining the accumulated sum of the discrete curvatures and the preset number of fitting nodes;
a3, obtaining a node vector of a fitting curve by combining the discrete curvature and the initial average discrete curvature;
and A4, combining the data points and the node vectors to obtain a final fitting curve.
6. The method according to claim 5, wherein said step A4 is specifically:
and (4) combining the data points, the node vectors and the least square curve fitting mode to obtain a final fitting curve.
7. The method for generating the trajectory of the industrial robot according to claim 5 or 6, wherein the step of calculating the error of the fitted curve from the data points and generating the trajectory of the industrial robot according to the fitted curve when the error is smaller than a preset tolerance comprises the following steps:
calculating the error of the fitted curve and the data point;
if the error is smaller than the Maxerror, discretizing all data points on the fitting curve to obtain discrete data points;
if the error is larger than the Maxerror, returning to execute the step A4 until the error is smaller than the Maxerror;
if the error is larger than t × Maxerror, after the number of the fitting nodes is reset, returning to execute the steps A1-A4 until the error is smaller than Maxerror;
generating a robot track according to the discrete data points;
the Maxerror is a preset tolerance, and t is a positive integer.
8. An industrial robot trajectory generation system, characterized by comprising:
the data filtering module is used for acquiring original data of the robot track to be generated, and obtaining a plurality of data points after filtering the original data;
the curve fitting module is used for acquiring the discrete curvature of each data point and acquiring a fitting curve by combining the discrete curvature and the data points;
and the error calculation module is used for calculating the error between the fitting curve and the data point and generating the track of the industrial robot according to the fitting curve when the error is smaller than the preset tolerance.
9. An industrial robot trajectory generation device, characterized by comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement an industrial robot trajectory generation method according to any of claims 1-7.
10. A storage medium having stored therein processor-executable instructions, which when executed by a processor, are configured to perform the method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010031229.7A CN111055286B (en) | 2020-01-13 | 2020-01-13 | Industrial robot track generation method, system, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010031229.7A CN111055286B (en) | 2020-01-13 | 2020-01-13 | Industrial robot track generation method, system, device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111055286A true CN111055286A (en) | 2020-04-24 |
CN111055286B CN111055286B (en) | 2021-08-03 |
Family
ID=70307259
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010031229.7A Active CN111055286B (en) | 2020-01-13 | 2020-01-13 | Industrial robot track generation method, system, device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111055286B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112231844A (en) * | 2020-10-30 | 2021-01-15 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Curved surface discrete method, device, equipment and storage medium of part model |
CN113341886A (en) * | 2021-05-25 | 2021-09-03 | 深圳市汇川技术股份有限公司 | Smooth feed speed planning method, device and computer readable storage medium |
CN113654457A (en) * | 2021-07-22 | 2021-11-16 | 太原理工大学 | Spectrum confocal measuring head wavelength and displacement mapping relation calibration device and fitting method |
CN113791578A (en) * | 2021-08-23 | 2021-12-14 | 五邑大学 | Track filtering method and device based on numerical control machining system and electronic equipment |
CN113847894A (en) * | 2021-09-23 | 2021-12-28 | 深圳市人工智能与机器人研究院 | Robot multi-positioning system coordinate unification method and system |
CN116372927A (en) * | 2023-04-06 | 2023-07-04 | 深圳市康士达科技有限公司 | Robot teaching track generation method, device, equipment and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106826829A (en) * | 2017-02-22 | 2017-06-13 | 武汉工程大学 | A kind of industrial robot fairing trace generator method of Controllable Error |
CN106959666A (en) * | 2017-03-31 | 2017-07-18 | 华南理工大学 | A kind of space free curve approximating method based on NURBS |
CN107808415A (en) * | 2017-11-17 | 2018-03-16 | 中国科学院合肥物质科学研究院 | Sole edge track and gluing pose extracting method based on machine vision |
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 |
WO2019089995A1 (en) * | 2016-11-01 | 2019-05-09 | Brachium Labs Llc | Vision guided robot path programming |
-
2020
- 2020-01-13 CN CN202010031229.7A patent/CN111055286B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019089995A1 (en) * | 2016-11-01 | 2019-05-09 | Brachium Labs Llc | Vision guided robot path programming |
CN106826829A (en) * | 2017-02-22 | 2017-06-13 | 武汉工程大学 | A kind of industrial robot fairing trace generator method of Controllable Error |
CN106959666A (en) * | 2017-03-31 | 2017-07-18 | 华南理工大学 | A kind of space free curve approximating method based on NURBS |
CN107808415A (en) * | 2017-11-17 | 2018-03-16 | 中国科学院合肥物质科学研究院 | Sole edge track and gluing pose extracting method based on machine vision |
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 |
Non-Patent Citations (1)
Title |
---|
赵德安: "静电喷涂机器人变量喷涂轨迹优化关键技术研究", 《中国博士学位论文全文数据库-信息科技辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112231844A (en) * | 2020-10-30 | 2021-01-15 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Curved surface discrete method, device, equipment and storage medium of part model |
CN112231844B (en) * | 2020-10-30 | 2024-05-28 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Curved surface discrete method, device, equipment and storage medium of part model |
CN113341886A (en) * | 2021-05-25 | 2021-09-03 | 深圳市汇川技术股份有限公司 | Smooth feed speed planning method, device and computer readable storage medium |
CN113654457A (en) * | 2021-07-22 | 2021-11-16 | 太原理工大学 | Spectrum confocal measuring head wavelength and displacement mapping relation calibration device and fitting method |
CN113791578A (en) * | 2021-08-23 | 2021-12-14 | 五邑大学 | Track filtering method and device based on numerical control machining system and electronic equipment |
WO2023024264A1 (en) * | 2021-08-23 | 2023-03-02 | 五邑大学 | Trajectory filtering method and apparatus based on numerical control machining system, and electronic device |
CN113847894A (en) * | 2021-09-23 | 2021-12-28 | 深圳市人工智能与机器人研究院 | Robot multi-positioning system coordinate unification method and system |
CN113847894B (en) * | 2021-09-23 | 2024-03-29 | 深圳市人工智能与机器人研究院 | Robot multi-positioning system coordinate unifying method and system |
CN116372927A (en) * | 2023-04-06 | 2023-07-04 | 深圳市康士达科技有限公司 | Robot teaching track generation method, device, equipment and medium |
CN116372927B (en) * | 2023-04-06 | 2024-03-22 | 深圳市康士达科技有限公司 | Robot teaching track generation method, device, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN111055286B (en) | 2021-08-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111055286B (en) | Industrial robot track generation method, system, device and storage medium | |
CN108656117B (en) | Mechanical arm space trajectory optimization method for optimal time under multi-constraint condition | |
TWI776113B (en) | Object pose estimation method, device and computer readable storage medium thereof | |
CN111897349B (en) | Autonomous obstacle avoidance method for underwater robot based on binocular vision | |
CN108972554B (en) | Complex surface robot path point extraction method based on fitted curve curvature characteristics | |
CN114063570B (en) | Robot spraying control method and device, electronic equipment and storage medium | |
CN111474946A (en) | Edge detection method and device and control method and device for robot edge cleaning | |
CN111240275B (en) | Feed rate planning method based on logarithmic probability function under motion and error limitation | |
CN111352430B (en) | Path planning method and device and robot | |
CN116117813A (en) | Mechanical arm control method, mechanical arm, robot and storage medium | |
CN115457510A (en) | Self-adaptive cooperative target tracking method based on variational Bayes | |
CN114115131B (en) | Time spline curve fitting and interpolation method applied to five-axis numerical control machine tool | |
JPWO2020179798A1 (en) | Machining program conversion device, numerical control device, machining program conversion method and machine learning device | |
CN114186189A (en) | Method, device and equipment for calculating coordinate transformation matrix and readable storage medium | |
WO2004090782A1 (en) | Accurate linear parameter estimation with noisy inputs | |
CN113932799A (en) | Laser map updating method, system, electronic device, medium, and program product | |
CN114488941A (en) | Trace fairing method and medium for micro line segments and machine tool numerical control equipment | |
CN111546337B (en) | Industrial robot full-coverage path generation method and system based on free-form surface | |
CN113256692A (en) | Rigid body registration method and equipment based on adaptive neighborhood weight learning | |
CN110275895B (en) | Filling equipment, device and method for missing traffic data | |
CN113927606B (en) | Robot 3D vision grabbing method and system | |
CN113204892B (en) | Centroid trajectory generation method and device, computer readable storage medium and robot | |
CN107967691B (en) | Visual mileage calculation method and device | |
CN114186190A (en) | Method, device and equipment for calculating coordinate transformation matrix and readable storage medium | |
CN111767981B (en) | Approximate calculation method of Mish activation function |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20220520 Address after: 510230 room J, 16 / F, No. 308, Binjiang Middle Road, Haizhu District, Guangzhou, Guangdong Patentee after: Zhongzheng Data Technology Co.,Ltd. Address before: 511356 No. 97, Tianyuan Road, Yonghe Development Zone, Guangzhou, Guangdong Patentee before: GUANGZHOU START TO SAIL INDUSTRIAL ROBOT Co. |