CN114924565A - Welding robot path planning method, electronic equipment and storage medium - Google Patents
Welding robot path planning method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114924565A CN114924565A CN202210581995.XA CN202210581995A CN114924565A CN 114924565 A CN114924565 A CN 114924565A CN 202210581995 A CN202210581995 A CN 202210581995A CN 114924565 A CN114924565 A CN 114924565A
- Authority
- CN
- China
- Prior art keywords
- path
- welding
- point
- welding robot
- points
- 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
- 238000003466 welding Methods 0.000 title claims abstract description 248
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 49
- 230000003111 delayed effect Effects 0.000 claims abstract description 4
- 238000005070 sampling Methods 0.000 claims description 85
- 230000007704 transition Effects 0.000 claims description 30
- 230000036544 posture Effects 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 13
- 230000004888 barrier function Effects 0.000 claims description 10
- 239000006185 dispersion Substances 0.000 claims description 8
- 238000004088 simulation Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 description 14
- 238000004364 calculation method Methods 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manipulator (AREA)
- Numerical Control (AREA)
Abstract
The invention relates to the technical field of welding robots, in particular to a path planning method of a welding robot, electronic equipment and a storage medium, wherein the method comprises the following steps: modeling to obtain a simulated welding environment; acquiring welding requirements, and determining all path sections to be planned and a planning sequence; and according to the planning sequence, finishing the path planning of the delayed collision detection for each path segment to be planned: after the planning of all path segments is completed, a complete path of the welding robot from the start point to the end point of the welding is generated. The invention can rapidly and efficiently realize automatic collision-free path planning.
Description
Technical Field
The present invention relates to the field of welding robot technology, and in particular, to a method for planning a path of a welding robot, an electronic device, and a storage medium.
Background
And (3) planning the path of the welding robot, namely searching a transition path of the welding robot system in the welding process, wherein the transition path considers the complete collision-free path of the welding robot starting from the starting point of welding, sequentially reaching each welding seam end point and finally reaching the end point. The automatic path design can improve the efficiency and the intelligent production degree of a welding task, ensure stable welding quality and reduce the labor cost.
Currently, path planning for welding robots is mostly performed by highly experienced engineers through manual teaching or offline programming. The manual teaching has low automation degree, unstable quality and long scheme making time. The automation degree of off-line programming is higher, but the flexibility is poor and the time consumption is long. When the task environment is more variable and the requirement on the real-time performance of the welding task is higher, the prior art is difficult to realize the rapid and efficient collision-free path planning. Therefore, in order to improve the production efficiency and meet the production requirements, a more efficient path planning scheme for the welding robot needs to be provided.
Disclosure of Invention
Based on the problem of poor instantaneity of path planning of the welding robot, the embodiment of the invention provides a path planning method of the welding robot, electronic equipment and a storage medium, and can realize automatic collision-free path planning more quickly and efficiently.
In a first aspect, an embodiment of the present invention provides a method for planning a path of a welding robot, including:
modeling to obtain a simulated welding environment; the simulation welding environment comprises a welding robot and models of various obstacles, the welding robot comprises a robot body and a welding gun, and the obstacles comprise workpieces to be welded;
acquiring welding requirements, and determining all path sections to be planned and a planning sequence;
according to the planning sequence, executing the following steps for each path segment to be planned, and completing the path planning of the delayed collision detection:
A. determining a stage starting point and a target point of the path section in the simulated welding environment, and constructing a path map by a sampling method;
B. searching the route map to obtain a route which can pass from the starting point of the stage to the target point and has the minimum cost, and taking the route as a preselected route;
C. dispersing the preselected path into a plurality of transition points, and sequentially carrying out collision detection on a local path between every two adjacent transition points;
if no collision event is detected in all the local paths, the preselected path is reserved, and the planning of the path section is completed;
if a collision event of the welding gun and the workpiece is detected in any local path, adjusting the pose of the welding robot based on the collision state of the welding gun and the workpiece in the collision event, and continuing to perform collision detection on the local path;
if a collision event except that the welding gun collides with the workpiece is detected in any local path, setting transition points at two ends of the local path as passing-through inhibiting points, returning to the step B, and updating the preselected path;
after the planning of all path segments is completed, a complete path of the welding robot from the start point to the end point of the welding is generated.
Optionally, the modeling results in a simulated welding environment, comprising:
acquiring digital-to-analog files of the welding robot and each obstacle;
modeling by a point cloud method based on a digital-analog file of the welding robot to obtain a model of the welding robot;
modeling is carried out through a grid method based on the digital-analog files of all the obstacles to obtain corresponding models of the obstacles;
and unifying all the obtained models to a coordinate system of the simulation welding environment.
Optionally, the modeling obtains a simulated welding environment, further comprising:
after unifying all the obtained models to the coordinate system of the simulated welding environment, acquiring the position of each obstacle in the actual welding environment;
and correcting the position of the model in the simulated welding environment according to the acquired position of each obstacle.
Optionally, in step a, constructing a roadmap by a sampling method, including:
judging whether to carry out local planning or not based on a space formed by the stage starting point and the target point and a model external space of the barrier, if so, carrying out low-dispersion sampling, otherwise, carrying out uniform sampling with fixed step length to obtain a corresponding sampling point;
and connecting the obtained sampling points to form the route map.
Optionally, the performing low dispersion sampling includes:
calculating the minimum radius between any two sampling points based on the space formed by the stage starting point and the target point and the model circumscribed space of the barrier;
randomly sampling to obtain sampling points, judging whether the obtained sampling points are larger than the minimum radius relative to the existing sampling points or not, if so, keeping the sampling points, otherwise, deleting the sampling points;
and repeating the steps of randomly sampling to obtain sampling points and judging until the existing sampling points reach the number of preset target sampling points.
Optionally, in the step B, searching the route map to obtain a route that is passable from the start point to the destination point and has a minimum cost includes:
establishing an artificial repulsion field in the simulated welding environment; the manual repulsion field comprises at least one group of repulsion grids, each group of repulsion grids takes a model of a barrier as a core, the repulsion value is gradually reduced from an inner layer to an outer layer;
establishing a cost function for introducing a punishment of an artificial repulsive force field; let i sample point x in the path i Cost function Cost of (1) (i) The expression is as follows:
where dist (x, y) represents the linear distance between two points x and y, x and y represent two points, s j Representing the slave sample point x j-1 To sample point x j The value of the repulsive force of the repulsive grid through which the path between, mu, is controlledPunishment parameter for controlling repulsion force scaling, i is more than or equal to 2, x 1 Denotes the start of the phase, x goal Representing a target point;
expanding sampling points to a target point from a stage starting point according to the route map to generate a passable route; the rule for expanding the sampling points is to select the sampling point connected with the last sampling point with the smallest cost function for expansion.
Optionally, in the step C, performing collision detection on a local path formed by every two adjacent transition points, including:
generating one or more detection points on a local path formed by the two transition points;
configuring the postures of the welding robot at the transition point and the detection point;
for each transition point and detection point, sequentially judging whether the model of the welding robot and the model of the obstacle are not overlapped, if so, judging that no collision event is detected, otherwise, judging that a collision event occurs;
and after the collision event is judged to occur, if the collision event is that models of the welding gun and the workpiece in the model of the welding robot are overlapped, judging that the collision event of the welding gun and the workpiece is detected, otherwise, judging that the collision event except the collision of the welding gun and the workpiece is detected.
Optionally, the adjusting the pose of the welding robot based on the collision state of the welding gun with the workpiece in the collision event to continue performing collision detection on the local path includes:
determining an adjustment direction based on an area where a welding gun overlaps a model of a workpiece in the model of the welding robot;
adjusting the pose of the welding robot with the collision event in a stepping mode according to the adjustment direction and a preset adjustment step length, wherein the stepping times do not exceed a preset threshold value;
if no overlapped area exists after adjustment, configuring a new detection point according to the adjusted pose of the welding robot, and continuing to perform collision detection on the local path;
and when the stepping times reach a preset threshold value and the overlapped area still exists, setting transition points at two ends of the local path as passing-forbidden points, returning to the step B, and updating the preselected path.
In a second aspect, an embodiment of the present invention further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor executes the computer program to implement the method described in any embodiment of this specification.
In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed in a computer, the computer program causes the computer to execute the method described in any embodiment of the present specification.
The embodiment of the invention provides a welding robot path planning method, electronic equipment and a storage medium, and in the collision detection process, for the condition that a welding gun collides with a workpiece, the closest path capable of solving the collision is quickly searched in a mode of fine tuning the position and the posture of the welding robot, so that the success rate of collision detection can be improved, the waste of computing resources is reduced, the path searching efficiency is improved, and the automatic collision-free path planning is more efficiently realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a method for planning a path of a welding robot according to an embodiment of the present invention;
FIG. 2(a) is a mathematical model of a workpiece;
FIG. 2(b) is a model obtained by the grid method modeling of the workpiece shown in FIG. 2 (a);
FIG. 3 is a schematic diagram illustrating a repulsive grid and a repulsive value distribution of an artificial repulsive field according to an embodiment of the present invention;
FIG. 4 is a schematic illustration of a no collision event in an embodiment of the present invention;
FIG. 5 is a schematic view of a process for adjusting a torch according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
As mentioned above, the path planning of the welding robot is mostly performed by highly experienced engineers through manual teaching or off-line programming. When the task environment is more changeable and the real-time requirement on the welding task is higher, particularly for a 6-freedom-degree welding robot with an external shaft (such as a sliding rail), the freedom degree is higher, the welding task is more complex, and the prior art is difficult to realize rapid and efficient collision-free path planning. In view of this, the invention provides an automatic path planning scheme for a welding robot, and in the collision detection process, the success rate of collision detection and the path planning efficiency are improved by purposefully fine-tuning the pose of the welding robot.
Specific implementations of the above concepts are described below.
Referring to fig. 1, an embodiment of the present invention provides a method for planning a path of a welding robot, where the method includes:
102, acquiring welding requirements, and determining all path sections to be planned and a planning sequence;
A. determining a stage starting point and a target point of the path section in the simulated welding environment, and constructing a route map from the stage starting point to the target point by a sampling method;
B. searching the route map to obtain a route which can pass from the starting point of the stage to the target point and has the minimum cost, and taking the route as a preselected route;
C. dispersing the preselected path into a plurality of transition points, and sequentially carrying out collision detection on a local path between every two adjacent transition points;
if no collision event is detected in all the local paths, the preselected path is reserved, and the planning of the path section is completed;
if a collision event of the welding gun and the workpiece is detected in any local path, adjusting the pose of the welding robot based on the collision state of the welding gun and the workpiece in the collision event, and continuing to perform collision detection on the local path;
if a collision event except that the welding gun collides with the workpiece is detected in any local path, setting transition points at two ends of the local path as passing-forbidding points, returning to the step B, updating the preselected path, and executing the step C again;
and 106, generating a complete path from the starting point to the end point of the welding by the welding robot after the planning of all path sections is completed.
In the embodiment of the invention, for the condition that the welding gun collides with the workpiece, the closest path capable of solving the collision is searched by purposefully and finely adjusting the pose of the welding robot, so that the success rate of collision detection can be improved, the waste of computing resources is reduced, the efficiency of path search is further improved, and the automatic collision-free path planning is more quickly realized. The invention can efficiently search the shortest collision-free welding path for different types of workpieces under the condition of unfixed environment.
The manner in which the various steps shown in fig. 1 are performed is described below.
For step 100, the modeling the simulated welding environment further comprises:
acquiring digital-analog files of the welding robot and each barrier;
modeling by a point cloud method based on a digital-analog file of the welding robot to obtain a model of the welding robot;
modeling by a grid method based on the digital-analog files of all the obstacles to obtain corresponding models of the obstacles;
and unifying all the obtained models to a coordinate system of the simulation welding environment.
In the above embodiment, the point cloud method may be used to obtain a point set representing a solid area of the welding robot, and the grid method may be used to obtain a point set representing an obstacle space formed after the obstacle is rasterized, as shown in fig. 2(a) and 2(b), which are both related to the prior art. It should be noted that the modeling by the grid method may cause the obstacle space of the obstacle to expand outward compared to the obstacle entity, and if a plurality of obstacle entities are close to each other, after modeling, the obstacle space is close to or overlapped, and then the obstacle may be considered as one obstacle. In the modeling process, the coordinate systems of all objects (welding robot and obstacle, if there are entities other than the workpiece to be welded, also known as obstacles) are unified, and a unique coordinate system for the welding environment is established. In order to facilitate collision detection calculation, a working space in a simulation welding environment can be divided into a plurality of grid cubes, then the position of an obstacle is determined and a grid matrix is established based on the grid cubes contained in the obstacle model at the initial position, so that better calculation efficiency and accuracy are obtained, the working space is rasterized, and the problems of subsequent adjustment of the position of the obstacle in the actual welding environment and collision detection are solved.
Further, the modeling to obtain the simulated welding environment further comprises:
after unifying all the obtained models to the coordinate system of the simulated welding environment, acquiring the positions of all obstacles in the actual welding environment;
and correcting the position of the corresponding model in the simulated welding environment according to the acquired position of each obstacle.
The above-described embodiment corrects the simulated welding environment based on the actual welding environment. Preferably, the infrared laser sensor can be used for scanning the actual welding environment, the position of each obstacle in the actual welding environment is obtained, the rotation angle and the offset of each obstacle (including a workpiece) relative to the initial position used for modeling are obtained, and real-time adjustment is achieved. Alternatively, considering that the worktable of a general welding robot is placed parallel to the ground, the obstacle can be regarded as being placed horizontally, and the obstacle changes from the initial position, usually by rotating around the z-axis and then moving along the x-axis or y-axis in the coordinate system simulating the welding environment, the corrected obstacle position P' can be expressed as:
wherein P ═ P x ,p y ,p z ,1]' is the initial position of the obstacle, theta is the relative rotation angle of the obstacle, Rot (Z, theta) represents the transformation matrix, offset x 、offset y And offset z Respectively, the offset of the obstacle on three coordinate axes.
By adopting the embodiment, aiming at the unfixed welding environment, a mixed modeling method is adopted to establish the model, the infrared laser sensor is utilized to scan the actual scene, the environment information is obtained in real time, the virtual model is adjusted, and the calculation speed and the calculation precision are both considered.
For step 102, the acquiring of the welding requirement, and the determining of all path segments to be planned and the planning sequence further include:
determining the positions of a starting point and an end point of welding, and the positions and the sequence of the required points based on the welding requirements; wherein, the position of the necessary passing point is determined according to the end point position of the welding seam, and the sequence is determined according to the welding sequence of the welding seam;
determining the postures of the welding robot at a starting point, an end point and each necessary passing point based on the welding requirements;
taking a path section without a definite welding robot moving track in a complete path from the starting point to the ending point as a path section to be planned;
and determining a planning sequence based on the passing sequence of each path segment to be planned in the complete path.
The above-described embodiment determines the positions of all key points (including the start point, the end point, and each required point) of the welding and the postures of the welding robot at the key points, that is, the positions to which the welding gun tips of the welding robot must reach, based on the welding requirements. For the key points with corresponding requirements, such as the starting point and the ending point, the welding robot is required to reach a certain preset posture, the posture (position and posture) of the welding robot of the key points is fixed, and for the key points without requiring the posture of the welding robot, namely only the tail end of the welding gun is required to reach the position of the key points but the welding robot is not required to reach a certain posture, the three-dimensional posture information of the welding robot at the position of the key points can be obtained in a random mode.
Further, since the grid method modeling defines a grid cube including part of obstacles as an obstacle space, the obstacle space occupied by the modeled object is actually enlarged, and the weld seam attached to the surface of the workpiece is classified as an obstacle space, so that a feasible path cannot be found. Therefore, when the position of the necessary passing point is determined according to the end point position of the welding line, the welding line can be moved outwards, moved out of the obstacle space and moved to the welding line adjusting position, for example, in the working condition of welding the vertical stiffened plate in the welding process of a ship small assembly, the welding line can float upwards along the vertical direction to be far away from a workpiece, and planning is carried out. For the welding seam l, after the welding seam l moves outwards, the positions of the end points of the welding seam l and the welding seam l 'are considered to be indispensable points in the actual welding process, but in the early stage process of path planning, the end point of the welding seam l' can be used as the indispensable point, when a complete path from the welding starting point to the end point of the welding robot is generated in step 106, a path from the welding seam l 'to the welding seam l is added (the path of the part can be considered to be not required to be planned, and the path from the welding seam l' to the welding seam l can be completed in a translation mode and the like), so that a path required by actual welding is obtained. In the way, the approximate welding seam end point is used for replacing the actual welding seam end point in the early process of path planning, namely, the welding robot is made to move to the welding seam adjusting position above the workpiece firstly and then planning is carried out, so that the phenomenon that the collision risk is increased in the moving process of the robot near the original welding seam is avoided, and the calculation efficiency can be improved.
With reference to step 104, in step a, constructing a roadmap from the stage starting point to the target point by a sampling method, further includes:
judging whether local planning is carried out or not based on a space formed by the stage starting point and the target point and a model external space of the barrier, if so, carrying out low-dispersion sampling, otherwise, carrying out uniform sampling with fixed step length to obtain a corresponding sampling point;
and connecting the obtained sampling points to form the route map.
For the path section close to the obstacle, the embodiment adopts low-dispersion sampling because the path section is located in the working space close to the obstacle, so that the sampling points are dispersedly distributed, the wide space can be covered under the condition that the number of the sampling points is less, and the working space far away from the obstacle can be filled by adopting the uniform sampling points with fixed step length, so that the calculation efficiency is improved. The space formed by the stage starting point and the target point, namely the cubic space formed by taking the stage starting point and the target point as vertexes, and the model circumscribed space of the obstacle, namely the circumscribed cubic space of the model of the obstacle are different from the obstacle space. It should be noted that, because the model circumscribed space of the obstacle is further expanded outward relative to the obstacle space, if there are a plurality of circumscribed cubes of the obstacle that are adjacent to each other or overlap with each other, the plurality of circumscribed cubes may be combined into a whole or further expanded into a larger circumscribed cube, that is, considered as one large model circumscribed space, or considered as a plurality of model circumscribed spaces separately.
Further, the determining whether to perform local planning includes:
and comparing the overlapping degree of the space formed by the stage starting point and the target point and the model external space of the obstacle, and judging the path section to carry out local planning if the space formed by the stage starting point and the target point and the model external space of one or more obstacles are overlapped.
In the above embodiment, whether the space1 formed by the phase start point and the target point overlaps with the model circumscribed space2 of one or more obstacles is used as a condition for judging whether to perform local planning. If there is an overlapping space3 of space1 and space2, the path segment can be considered to be near an obstacle and should be locally planned.
Further, the low-dispersion sampling includes the following steps:
a1, calculating the minimum radius R between any two sampling points based on the space formed by the phase starting point and the target point and the model circumscribed space of the obstacle;
a2, randomly sampling to obtain sampling points and judging, and judging whether the obtained sampling points are larger than the minimum radius R relative to the existing sampling points or not, if so, keeping the sampling points as the existing sampling points, otherwise, deleting the sampling points;
and A3, repeating the step A2 until the existing sampling points reach the preset target sampling point number.
Optionally, the expression of the minimum radius R is:
χ space ＝χ obs ∪χ init ∪χ goal
where N denotes the number of preset sampling points, λ denotes a positive scaling factor, m is 1,2, and 3 denote three coordinate axes of a three-dimensional space, and χ init As the starting point of stage, χ goal As target point, x obs Set of points, χ, of a grid cube representing the space circumscribed by the model of the obstacle obs The corresponding space is x init 、χ goal The spaces constructed for the vertices have an overlap, χ space To represent a set of points of a grid cube for sampling a space with low dispersion, χ space (m) represents a set of points χ space The coordinates of the point in (1) in the direction of the m coordinate axis.
In the embodiment of the invention, the Leeberg volume formula is used for measuring the minimum radius R between two small balls taking two random sampling points as the circle centers, the sampling points with the distance greater than the radius of the small balls are reserved, the distribution of the sampling points is improved, the blind search is favorably reduced, and the path search efficiency is improved.
In step B, searching the route map to obtain a route that can pass from the stage starting point to the destination point and has the smallest cost, further comprising:
establishing an artificial repulsion field in the simulated welding environment; the artificial repulsion field comprises at least one group of repulsion grids, each group of repulsion grids takes a model of an obstacle as a core, and the repulsion value is gradually reduced from an inner layer to an outer layer;
establishing a cost function for introducing a punishment of an artificial repulsive force field; let i sample point x in the path i Cost function Cost of (i) The expression is as follows:
where dist (x, y) represents the linear distance between two points x and y, x and y represent two points, s j Representing the slave sample point x j-1 To sample point x j The repulsive force value of the repulsive force grid passed by the path between the two paths, mu is a punishment parameter for controlling the contraction and enlargement of the repulsive force, i is more than or equal to 2, x 1 Denotes the start of the phase, x goal Representing a target point;
expanding sampling points to a target point from a stage starting point according to the route map to generate a passable route; wherein the rule for extending the sampling point is from all the sampling points to the last sampling pointAnd selecting the sampling points with the minimum cost function for expansion. That is, the ith sample point x in the extended path i Then searching the ith-1 sampling point x in all the AND paths in the road map i-1 The sampling points which can be connected are compared with the cost function of the sampling points, the sampling point with the minimum cost function is selected as the ith sampling point x i Join the path. The cost function can be used for judging the priority of the sampling points, and helps the algorithm to sequentially screen out the optimal sampling points in the extensible nodes, and finally a path with the minimum cost is generated. Alternatively, searching the roadmap for feasible paths may utilize prior art algorithms, such as the a-algorithm. By using an A-star algorithm with an improved cost (or called fitness value) calculation mode, the path search considering the action of the artificial repulsive force field can be realized.
In the embodiment, the distance cost function with the added artificial repulsive force field is used as the improved cost function, so that the collision possibility is reduced, the calculation convergence is accelerated, the shortest feasible path length obtained at the tail end of the welding gun and the safe distance between the robot and the obstacle are ensured, and the time consumed by collision detection can be reduced, thereby improving the calculation efficiency and quickly obtaining a feasible path. Cost function Cost (i) For an improved cost function, g (x) init ,x i ) Represents the cost from the phase starting point to the ith sampling point, including the distance cost and the repulsive force penalty cost, h (x) i ,x goal ) Is the estimated cost value from the ith sample point to the target point, i.e., dist (x) i ,x goal ). And if a path passes through the artificial repulsive force field, taking the sum of the repulsive force values of all the repulsive force grids passed by the path to punish the path. This increases the cost function value and allows the algorithm to be controlled to select a path with less cost away from the obstacle. For convenient calculation, the repulsion field is also divided by a grid method, and the repulsion values of the manual repulsion fields which are different from the obstacles are also different. As shown in fig. 3, in the rasterized workspace, the barrier-free grid may be defined as a free grid, the repulsive force value is 0, the barrier-containing grid is a barrier grid, a set of repulsive force grids cover the periphery of the set of barrier grids, and the magnitude of the repulsive force value is gradually reduced from the inside to the outside(as in fig. 3, the repulsion value of the obstacle grid is 3, the repulsion value of the adjacent outer layer grid is 2, the repulsion value of the outward grid is 1, and the layers decrease gradually), and the specific values and distribution can be set according to actual needs. The repulsive grid still belongs to the free grid, but has repulsive values.
Optionally, as shown in fig. 4, in the step C, performing collision detection on a local path formed by every two adjacent transition points, further includes:
generating one or more detection points on a local path formed by the two transition points;
configuring the postures of the welding robot at the transition point and the detection point;
for each transition point and detection point, sequentially judging whether the model of the welding robot and the model of the obstacle are not overlapped, if so, judging that no collision event is detected, otherwise, judging that a collision event occurs;
and after the collision event is judged to occur, if the collision event is that models of the welding gun and the workpiece in the model of the welding robot are overlapped, judging that the collision event of the welding gun and the workpiece is detected, otherwise, judging that the collision event except the collision of the welding gun and the workpiece is detected. The collision event other than the collision of the welding gun with the workpiece may be the collision of the robot body with the obstacle, or the collision of the welding gun with another obstacle other than the workpiece, or the collision of the robot body with the external axis if a welding robot with an external axis is used. Both of these cases obtain a new path by searching.
Preferably, whether the model of the welding robot and the model of the obstacle are overlapped or not is judged, after the pose of the welding robot is determined, the model of the welding robot in the form of point cloud is rasterized, namely, a grid cube contained in a rasterized working space of the model of the welding robot is determined, and whether the grid occupied by the model of the welding robot and the grid occupied by the model of the obstacle are not intersected or not is compared, so that whether the model of the welding robot and the model of the obstacle are overlapped or not can be quickly judged.
In the above embodiment, the postures of the welding robot at the transition point and the detection point are configured, and the three-dimensional posture information of the welding robot can be obtained in a random sampling manner. The method for judging whether the model of the welding robot and the model of the obstacle are not overlapped is to compare the grid vertex set of the welding robot at the point position (namely the position of the transition point or the detection point) with the grid vertex set of the obstacle space of the obstacle, check whether an intersection exists, if the intersection does not exist, indicate that the current path is not collided at the point position, if the intersection exists, indicate that an overlapped area is generated between the robot and the obstacle, and consider that a collision event is detected. At the moment, if the collision between the welding gun and the workpiece is judged, an attitude adjustment strategy is triggered, the path is finely adjusted, and then the collision detection stage is returned again; otherwise, setting the transition points at the two ends of the local path as the passing-forbidden points and then replanning the feasible path, wherein the new path should not pass through two or more passing-forbidden points. By adopting the embodiment, the waste of computing resources can be reduced, the success rate of collision detection and the efficiency of path search are improved, the welding gun posture adjustment strategy is adopted only when the collision detection between the welding gun and the workpiece fails, the adjustment process is only used during the transition path search, and the fixed posture and the welding quality during welding cannot be influenced.
Optionally, the adjusting the pose of the welding robot based on the collision state of the welding gun with the workpiece in the collision event to continue performing collision detection on the local path further includes:
determining an adjustment direction based on an area where a welding gun overlaps a model of a workpiece in the model of the welding robot;
adjusting the pose of the welding robot with the collision event in a stepping mode according to the adjustment direction and a preset adjustment step length, wherein the stepping times do not exceed a preset threshold value;
if no overlapped area exists after adjustment, configuring a new detection point according to the adjusted pose of the welding robot, and continuing to perform collision detection on the local path;
and when the stepping times reach a preset threshold value and an overlapped area still exists, setting transition points at two ends of the local path as passing-forbidden points, returning to the step B, and updating the preselected path.
The key point of the welding gun posture adjustment strategy is to find a proper welding gun moving direction to adjust the position and posture of the robot, and the embodiment finely adjusts the posture of the welding robot in a stepping mode to eliminate collision events, shorten the collision detection time and improve the success rate of collision detection.
Optionally, the determining an adjustment direction based on an area of the model of the welding robot where the welding gun overlaps the model of the workpiece further includes:
determining the center point p of the welding torch gun Overlap region P with collision grid Calculating a directional resultant force F of the welding gun required to move, wherein the expression is as follows:
where K denotes the total number of grid cubes contained in the overlap region caused by the collision, p grid,i Indicating the point of the ith grid cube within the overlap region resulting from the collision, P grid Set of points, p, representing a grid cube contained in an overlapping region resulting from a collision gun A point representing a center point of the torch;
and determining an adjusting direction based on the directional resultant force F, wherein the adjusting direction is F/| F |, and | F | represents the modulus of F.
Further, the pose of the welding robot with the collision event is adjusted in a stepping mode according to the adjustment direction and a preset adjustment step length, the stepping times do not exceed a preset threshold value, and the pose is expressed in an expression form as follows:
wherein sl represents a preset adjustment step length, the grid size of the working space can be selected to be consistent with that of the working space, p represents the position and posture of the welding robot with the detected collision event, and p represents new The adjusted pose of the welding robot is represented, t represents the adjustment times, namely the stepping times, the preset threshold value can be set according to the requirement, for example, the threshold value is set to be 20, namely, t is less than or equal to 20, and when the adjustment times exceed the preset threshold valueIf the threshold value still cannot find the proper welding robot posture, the path is searched again.
As shown in fig. 5, after a collision event between the welding gun and the workpiece occurs, the above embodiment gradually adjusts the pose of the welding robot according to the specific situation of the collision until a new collision-free point is found on the path and collision detection is continued, or the path is searched again. The welding gun adjusting strategy adopted by the invention increases the possibility of collision detection, saves computing resources and computing time, and has higher efficiency and strong expansibility.
The invention provides a complete welding robot path planning method which comprises the steps of welding environment modeling, path planning, collision detection and welding gun posture adjustment, and has the advantages of calculation efficiency and path quality, higher efficiency and robustness and strong flexibility, and is suitable for operation scenes of robots such as moving robots, arc welding robots, spot welding robots and the like. The scheme of the invention has stronger searching capability and higher efficiency, can plan a feasible shorter robot path in a shorter time, effectively solves the problem of on-line planning of a collision-free path of the arc welding robot with an external shaft in an unfixed environment, and improves the welding efficiency and the production process intellectualization while ensuring the safety.
The embodiment of the invention also provides electronic equipment which comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for planning the path of the welding robot in any embodiment of the invention is realized.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, causes the processor to execute a method for planning a path of a welding robot in any of the embodiments of the present invention.
Specifically, a system or an apparatus equipped with a storage medium on which software program codes that realize the functions of any of the above-described embodiments are stored may be provided, and a computer (or a CPU or MPU) of the system or the apparatus is caused to read out and execute the program codes stored in the storage medium.
In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.
Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, optical disks (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.
Further, it should be clear that the functions of any one of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform a part or all of the actual operations based on instructions of the program code.
Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then causes a CPU or the like mounted on the expansion board or the expansion module to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the above-described embodiments.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an …" does not exclude the presence of other similar elements in the process, method, article, or apparatus that comprises the element.
Those of ordinary skill in the art will understand that: all or part of the steps of implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer-readable storage medium, and when executed, executes the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A welding robot path planning method is characterized by comprising the following steps:
modeling to obtain a simulated welding environment; the simulation welding environment comprises a welding robot and models of various obstacles, the welding robot comprises a robot body and a welding gun, and the obstacles comprise workpieces to be welded;
acquiring welding requirements, and determining all path sections to be planned and a planning sequence;
according to the planning sequence, executing the following steps for each path segment to be planned, and completing the path planning of the delayed collision detection:
A. determining a stage starting point and a target point of the path section in the simulated welding environment, and constructing a path map by a sampling method;
B. searching the route map to obtain a route which can pass from the stage starting point to the target point and has the minimum cost, and taking the route as a preselected route;
C. dispersing the preselected path into a plurality of transition points, and carrying out collision detection on a local path between every two adjacent transition points in sequence;
if no collision event is detected in all the local paths, the preselected path is reserved, and the planning of the path section is completed;
if a collision event of the welding gun and the workpiece is detected in any local path, adjusting the pose of the welding robot based on the collision state of the welding gun and the workpiece in the collision event, and continuing to perform collision detection on the local path;
if a collision event except that the welding gun collides with the workpiece is detected in any local path, setting transition points at two ends of the local path as passing-forbidding points, returning to the step B, and updating the preselected path;
after the planning of all path segments is completed, a complete path of the welding robot from the start point to the end point of the welding is generated.
2. The welding robot path planning method according to claim 1, wherein the modeling results in a simulated welding environment, comprising:
acquiring digital-to-analog files of the welding robot and each obstacle;
modeling by a point cloud method based on a digital-analog file of the welding robot to obtain a model of the welding robot;
modeling by a grid method based on the digital-analog files of all the obstacles to obtain corresponding models of the obstacles;
and unifying all the obtained models to a coordinate system of the simulation welding environment.
3. The welding robot path planning method according to claim 2, wherein the modeling yields a simulated welding environment, further comprising:
after unifying all the obtained models to the coordinate system of the simulated welding environment, acquiring the positions of all obstacles in the actual welding environment;
and correcting the position of the model in the simulated welding environment according to the acquired position of each obstacle.
4. The welding robot path planning method according to claim 1,
in the step a, a roadmap is constructed by a sampling method, including:
judging whether local planning is carried out or not based on a space formed by the stage starting point and the target point and a model external space of the barrier, if so, carrying out low-dispersion sampling, otherwise, carrying out uniform sampling with fixed step length to obtain a corresponding sampling point;
and connecting the obtained sampling points to form the route map.
5. The welding robot path planning method according to claim 4,
the low dispersion sampling comprises the following steps:
calculating the minimum radius between any two sampling points based on the space formed by the stage starting point and the target point and the model circumscribed space of the barrier;
randomly sampling to obtain sampling points and judging, and judging whether the obtained sampling points meet the condition that the distance between any two sampling points is larger than the minimum radius relative to the existing sampling points, if so, keeping the sampling points, otherwise, deleting the sampling points;
and repeating the steps of randomly sampling to obtain sampling points and judging until the existing sampling points reach the number of preset target sampling points.
6. The welding robot path planning method according to claim 1,
in step B, searching the route map to obtain a route that can pass from the stage starting point to the destination point and has the smallest cost, including:
establishing an artificial repulsion field in the simulated welding environment; the artificial repulsion field comprises at least one group of repulsion grids, each group of repulsion grids takes a model of an obstacle as a core, and the repulsion value is gradually reduced from an inner layer to an outer layer;
establishing a cost function for introducing a punishment of an artificial repulsive force field; let i sample point x in the path i Cost function Cost of (1) (i) The expression is as follows:
where dist (x, y) represents the linear distance between two points x and y, x and y represent two points, s j Representing the slave sample point x j-1 To sample point x j The repulsive force value of the repulsive force grid passed by the path between the two paths, mu is a punishment parameter for controlling the scaling of the repulsive force, i is more than or equal to 2, x 1 Denotes the start of the phase, x goal Representing a target point;
expanding sampling points to a target point from a stage starting point according to the route map to generate a passable route; the rule for expanding the sampling points is to select the sampling point connected with the last sampling point with the smallest cost function for expansion.
7. The welding robot path planning method according to claim 1,
in step C, performing collision detection on a local path formed by every two adjacent transition points, including:
generating one or more detection points on a local path formed by the two transition points;
configuring the postures of the welding robot at the transition point and the detection point;
for each transition point and detection point, sequentially judging whether the model of the welding robot and the model of the obstacle are not overlapped, if so, judging that no collision event is detected, otherwise, judging that a collision event occurs;
and after the collision event is judged to occur, if the collision event is that models of the welding gun and the workpiece in the model of the welding robot are overlapped, judging that the collision event of the welding gun and the workpiece is detected, otherwise, judging that the collision event except the collision of the welding gun and the workpiece is detected.
8. The welding robot path planning method according to claim 7,
based on the state that welder and work piece collided in the collision incident, adjust welding robot position appearance, continue to carry out collision detection to this local route, include:
determining an adjustment direction based on an area where a welding gun overlaps a model of a workpiece in the model of the welding robot;
adjusting the pose of the welding robot with the collision event in a stepping mode according to the adjustment direction and a preset adjustment step length, wherein the stepping times do not exceed a preset threshold value;
if no overlapped area exists after adjustment, configuring a new detection point according to the adjusted pose of the welding robot, and continuing to perform collision detection on the local path;
and when the stepping times reach a preset threshold value and an overlapped area still exists, setting transition points at two ends of the local path as passing-forbidden points, returning to the step B, and updating the preselected path.
9. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the method according to any of claims 1-8.
10. A storage medium having stored thereon a computer program, characterized in that the computer program, when executed in a computer, causes the computer to execute the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210581995.XA CN114924565A (en) | 2022-05-26 | 2022-05-26 | Welding robot path planning method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210581995.XA CN114924565A (en) | 2022-05-26 | 2022-05-26 | Welding robot path planning method, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114924565A true CN114924565A (en) | 2022-08-19 |
Family
ID=82809689
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210581995.XA Pending CN114924565A (en) | 2022-05-26 | 2022-05-26 | Welding robot path planning method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114924565A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115229772A (en) * | 2022-08-23 | 2022-10-25 | 深圳市越疆科技有限公司 | Robot, robot control method, robot control device, robot control equipment, storage medium and mechanical arm |
-
2022
- 2022-05-26 CN CN202210581995.XA patent/CN114924565A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115229772A (en) * | 2022-08-23 | 2022-10-25 | 深圳市越疆科技有限公司 | Robot, robot control method, robot control device, robot control equipment, storage medium and mechanical arm |
| CN115229772B (en) * | 2022-08-23 | 2023-07-18 | 深圳市越疆科技股份有限公司 | Robot, control method, control device, control equipment, storage medium and mechanical arm thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109764886B (en) | Path planning method | |
| CN106166750B (en) | A kind of modified D* mechanical arm dynamic obstacle avoidance paths planning method | |
| CN110231824B (en) | Intelligent agent path planning method based on straight line deviation method | |
| CN111780777A (en) | Unmanned vehicle route planning method based on improved A-star algorithm and deep reinforcement learning | |
| CN111515503B (en) | Non-collision path planning method for arc welding robot | |
| CN110887484A (en) | Mobile robot path planning method based on improved genetic algorithm and storage medium | |
| CN105955262A (en) | Mobile robot real-time layered path planning method based on grid map | |
| CN112985408B (en) | Path planning optimization method and system | |
| CN107631734A (en) | A kind of dynamic smoothing paths planning method based on D*_lite algorithms | |
| CN112068588A (en) | Unmanned aerial vehicle trajectory generation method based on flight corridor and Bezier curve | |
| CN114510057A (en) | ROS-based mobile robot autonomous navigation method in indoor environment | |
| CN112539750B (en) | Intelligent transportation vehicle path planning method | |
| CN112486178A (en) | Dynamic path planning method based on directed D (delta) algorithm | |
| CN114924565A (en) | Welding robot path planning method, electronic equipment and storage medium | |
| CN115933671A (en) | AGV path planning and autonomous obstacle avoidance method based on MBESP optimization | |
| CN112947486A (en) | Path planning method and chip of mobile robot and mobile robot | |
| CN114281084A (en) | Intelligent vehicle global path planning method based on improved A-x algorithm | |
| CN117124335B (en) | Improved RRT path planning method based on path marking backtracking strategy | |
| CN114596360A (en) | Double-stage active instant positioning and graph building algorithm based on graph topology | |
| CN113467445A (en) | Four-legged robot swing leg obstacle avoidance method based on vision and path planning | |
| CN110849385B (en) | Track planning method and system based on double-layer heuristic search conjugate gradient descent | |
| CN117075607A (en) | Unmanned vehicle path planning method suitable for improving JPS in complex environment | |
| CN116518978A (en) | Robot path planning method, device, equipment and storage medium | |
| CN116619381A (en) | Obstacle avoidance path planning method for industrial robot | |
| CN115420296A (en) | Path searching method and system based on multi-resolution topological map |
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 |