An obstacle avoidance path planning method for industrial robots

Abstract

The present invention relates to the field of industrial robot technology, and more particularly to an obstacle avoidance path planning method for an industrial robot, comprising: determining a configuration space for a welding task; determining a starting point and an ending point for the path planning task; determining a sampling range for the first and second external translation axis parameters of sampling points during the path planning process based on first and second external translation axis parameters of the starting and ending points, combined with a preset expansion amount; constructing a node tree with the starting and ending points as root nodes, respectively, and expanding the two node trees by performing a point search until the two node trees intersect. The present invention can implement high-dimensional freedom path planning for a dual welding robot with a gantry external device, and has good planning efficiency and stability.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of industrial robots, and in particular to an obstacle avoidance path planning method for an industrial robot. Background Art

[0002] The robot path planning problem involves finding a collision-free path for an industrial robot from a given initial state (or starting point) to a target state (or ending point) within a constrained configuration space. Generally speaking, shorter paths and shorter planning times indicate more effective path planning methods, making them more suitable for engineering applications.

[0003] Currently, path planning for industrial robots used for welding is primarily accomplished through manual instruction. In scenarios where workpieces are flexibly placed, programming efficiency is low and quality cannot be guaranteed. This is especially true for welding robots equipped with external devices. The increased degree of freedom further increases the difficulty of instructional programming. Summary of the Invention

[0004] Based on the problem of low efficiency in teaching programming for high-dimensional freedom path planning of industrial robots, an embodiment of the present invention provides an industrial robot obstacle avoidance path planning method, electronic equipment and storage medium, which can automatically realize high-dimensional freedom dual welding robot path planning with gantry external devices, and has good planning efficiency and stability.

[0005] In a first aspect, an embodiment of the present invention provides an industrial robot obstacle avoidance path planning method, comprising:

[0006] Suitable for a dual welding robot with a gantry external device; the dual welding robot includes two robotic arms, each equipped with a welding gun; the gantry external device includes a first external translation axis and a second external translation axis that move in the x and y directions in the horizontal plane, respectively, and an external rotation axis that rotates about the vertical z axis; the dual welding robot is installed on the gantry external device and can change its overall posture under the drive of the gantry external device, and can independently change the posture of each joint of the two robotic arms;

[0007] The method includes:

[0008] Determine the configuration space of welding tasks;

[0009] Determine the starting point and the ending point of the path planning task; the starting point and the ending point each include multiple parameters for representing the joint postures of the two robotic arms and the current state of the external device of the gantry;

[0010] Determining a sampling range of the first external translation axis parameter and the second external translation axis parameter of the sampling point during the path planning process according to the first external translation axis parameter and the second external translation axis parameter of the starting point and the ending point, in combination with a preset expansion amount;

[0011] Constructing a node tree with the starting point and the ending point as root nodes respectively, and expanding the two node trees by performing point search until the two node trees intersect;

[0012] For any node tree, point search includes:

[0013] Determine the root node and target point;

[0014] Generate and determine sampling points for indicating the expansion direction according to the configuration space of the welding task and the determined sampling range;

[0015] Based on the determined sampling point and the preset expansion step, a new node x is expanded for the current node tree. new , and for the new node x new Perform collision detection. If it passes, continue to the next steps. If it fails, delete the new node x. new Then, return to the step of determining the sampling point;

[0016] Based on the new node x new and the preset first radius R1, determine the new node x new The nodes in the neighboring point set are taken from the current node tree and are related to the new node x new The distance does not exceed the first radius R1;

[0017] Based on the new node x new and the preset second radius R2, to determine whether there is a point in the neighboring point set that is related to the new node x new The distance to the node that does not exceed the second radius R2, if it does not exist, continue to perform subsequent steps, if it exists, then remove the new node x new Then, return to the step of determining the sampling point; the second radius R2 is smaller than the first radius R1;

[0018] The new node x new Add to the current node tree and perform re-parent node selection and rewiring operations on the new node;

[0019] Perform collision detection again. If it passes, update the current node tree. If it fails, delete the new node x from the current node tree. new Then, return to the step of determining the sampling point.

[0020] Optionally, generating and determining a sampling point for indicating an extension direction includes:

[0021] According to the preset target bias probability, N sampling points are randomly generated; N is a positive integer not less than 3;

[0022] For the two dimensions of the first external translation axis parameter and the second external translation axis parameter, the offset degree of each sampling point relative to the line connecting the root node and the target point is calculated respectively, and the sampling point with the smallest offset degree is selected.

[0023] Optionally, the degree of deviation of the sampling point relative to the line connecting the root node and the target point is calculated in the following manner:

[0024] Calculate the sampling point x for the two dimensions of the first external translation axis parameter and the second external translation axis parameter rand The corresponding Cos value is expressed as:

[0025]

[0026] Among them, e 1,s With e 2,s 、e 1,e With e 2,e and e 1,r With e 2,r Represent the root node, target point and sampling point x respectively rand The first external translation axis parameter and the second external translation axis parameter, |||| represents the norm calculation;

[0027] The step of selecting the sampling point with the smallest deviation includes:

[0028] Select the sampling point with the largest corresponding Cos value.

[0029] Optionally, determining the configuration space of the welding task includes:

[0030] Determining a workspace accessible for welding based on the operating parameters of the gantry external device and the dual welding robot;

[0031] An obstacle model is established to determine the obstacle space; the obstacle model includes a dual welding robot model and a welding workpiece model.

[0032] Optionally, the preset expansion amount is determined according to the height of the welding workpiece.

[0033] Optionally, the robotic arm is a six-axis robotic arm.

[0034] Optionally, two nodes x a and x b The distance between them is calculated using the following formula:

[0035]

[0036] Among them, θ i,a and θ i,b Represents node x respectively a and node x b The i-th robot joint parameter, i = 1, ..., 6 represents the joint serial number of one robot arm in the dual welding robot, i = 7, ..., 12 represents the joint serial number of the other robot arm, e 1,a and e 1,b 、e 2,a and e 2,b and e 3,a and e 3,b Represents node x respectively a and node x b The first external translation axis parameter, the second external translation axis parameter, and the external rotation axis parameter are represented by ||, where || represents absolute value calculation.

[0037] Optionally, the second radius R2 is 1 / 5 to 1 / 4 of the first radius R1.

[0038] In a second aspect, an embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in any embodiment of this specification is implemented.

[0039] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed in a computer, the computer is caused to execute the method described in any embodiment of this specification.

[0040] Embodiments of the present invention provide an obstacle avoidance path planning method, electronic device, and storage medium for an industrial robot. This method limits the sampling range of external axis parameters at sampling points based on the characteristics of the gantry's external devices and the starting and ending points of path planning, thereby improving path planning quality and shortening processing time. Furthermore, the method introduces a nearest node constraint during the path search process, effectively addressing path planning problems in environments with sparse obstacles and saving computational time. This method can automatically implement high-dimensional path planning for a dual-welding robot with gantry external devices, demonstrating excellent planning efficiency and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 This is a flow chart of an industrial robot obstacle avoidance path planning method provided by one embodiment of the present invention;

[0043] Figure 2 Schematic diagram of a method for determining a limit on the nearest node in one embodiment of the present invention;

[0044] Figure 3(a) is a schematic diagram of a node tree without limiting the nearest node;

[0045] Figure 3(b) is a schematic diagram of the node tree with the nearest node restricted;

[0046] FIG4( a ) shows a top view of a scene 1 for welding testing;

[0047] FIG4( b ) shows a top view of scene 2 for welding testing;

[0048] Figure 5(a) shows the path length results obtained by running various path planning methods 20 times independently in scenario 1;

[0049] Figure 5(b) shows the path length results obtained by running various path planning methods 20 times independently in scenario 2;

[0050] Figure 6(a) shows the time taken by various path planning methods to run 20 times independently in scenario 1;

[0051] Figure 6(b) shows the time taken by various path planning methods to run 20 times independently in scenario 2. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0053] As previously mentioned, path planning for industrial robots used for welding is primarily accomplished through manual instruction. In scenarios where workpieces are flexibly positioned, programming efficiency is low and quality cannot be guaranteed. This is especially true for welding robots equipped with external devices, where the increased degrees of freedom further increases the difficulty of instructional programming. For a dual-welding robot with a gantry external device, if the robotic arm holding the welding gun has six degrees of freedom, the dual-welding robot with the gantry external device can achieve fifteen degrees of freedom as a whole. In this case, using instructional programming or conventional path planning methods makes it difficult to quickly search for a high-quality path. In light of this, the present invention provides an improved bidirectional RRT* method for implementing obstacle avoidance path planning for industrial robots. The present invention simultaneously expands from both the starting point and the end point, and limits the sampling range based on the gantry system structure, improving path quality and reducing unnecessary path searches. Furthermore, by limiting the nearest node strategy, the search time is optimized, improving search efficiency, and ultimately achieving high-dimensional path planning for welding robots.

[0054] The specific implementation of the above concept is described below.

[0055] Please refer to Figure 1 , an embodiment of the present invention provides an industrial robot obstacle avoidance path planning method, which is applicable to a dual welding robot with a gantry external device;

[0056] The dual welding robot includes two robotic arms, each of which is provided with a welding gun. The gantry external device includes a first external translation axis and a second external translation axis, which move respectively along the x-direction and the y-direction in the horizontal plane, and an external rotation axis, which rotates around the vertical z-axis. The nested relationship of the three external axes (i.e., the first external translation axis, the second external translation axis and the external rotation axis) can be that the first external translation axis is movably provided on the gantry and can move relative to the gantry along the x-direction, the second external translation axis is movably provided on the first external translation axis and can move relative to the first external translation axis along the y-direction, and the external rotation axis is rotatably provided on the second external translation axis and can rotate relative to the second external translation axis. In other embodiments, other nesting methods can also be used to ensure that the gantry external device can provide the dual welding robot with an additional three degrees of freedom.

[0057] The dual welding robot is arranged on the external device of the gantry, and can change the overall posture under the drive of the external device of the gantry, and can independently change the posture of each joint of the two robotic arms; wherein a single robotic arm is preferably a six-axis robotic arm. At this time, the two robotic arms of the dual welding robot have a total of twelve degrees of freedom, and with the external device of the gantry, it can reach fifteen degrees of freedom.

[0058] The industrial robot obstacle avoidance path planning method includes:

[0059] Step 100, determining the configuration space of the welding task;

[0060] Step 102: Determine the starting point and the ending point of the path planning task; the starting point and the ending point each include multiple parameters for representing the joint postures of the two robotic arms and the current state of the gantry's external devices (i.e., three external axis parameters);

[0061] Step 104: Determine the sampling range of the first external translation axis parameter and the second external translation axis parameter of the sampling point during the path planning process based on the first external translation axis parameter and the second external translation axis parameter of the starting point and the ending point in combination with a preset expansion amount;

[0062] Assume that the first external translation axis parameter and the second external translation axis parameter of the starting point are e 1,i and e 2,i The first external translation axis parameter and the second external translation axis parameter of the end point are e 1,t and e 2,t The preset expansion amount includes the expansion amount ex in the x direction and the expansion amount ey in the y direction. The sampling range of the first external translation axis of the sampling point in the path planning process is min(e 1,i , e 1,t )-ex to max(e 1,i , e 1,t )+ex, the sampling range of the second external translation axis of the sampling point is min(e 2,i , e 2,t )-ey to max(e 2,i , e 2,t )+ey;

[0063] Step 106, constructing a node tree with the starting point and the ending point as root nodes respectively, and expanding the two node trees by performing point search until the two node trees intersect;

[0064] For any node tree, point search includes:

[0065] Step 106-0, determine the root node and target point;

[0066] For a node tree constructed with the starting point as the root node, the target point is the ending point; for a node tree constructed with the ending point as the root node, the target point is the starting point; expanding from both the starting point and the ending point simultaneously helps to shorten the time for searching the path;

[0067] Step 106-2: Generate and determine sampling points for indicating the expansion direction according to the configuration space of the welding task and the determined sampling range;

[0068] Step 106-4: Based on the determined sampling point and the preset expansion step, a new node x is expanded for the current node tree. new , and for the new node x new Perform collision detection. If it passes, continue to the next steps. If it fails, delete the new node x. new Then, return to the step of determining the sampling point, that is, return to step 106-2 to obtain a new sampling point;

[0069] Step 106-6, based on the new node x new and the preset first radius R1, determine the new node x new The nodes in the neighboring point set are taken from the current node tree, and the nodes in the neighboring point set are the same as the new node x new The distance does not exceed the first radius R1;

[0070] Step 106-8, based on the new node x new and the preset second radius R2, to determine whether there is a point in the neighboring point set that is related to the new node x new The distance to the node that does not exceed the second radius R2, if it does not exist, continue to perform subsequent steps, if it exists, then remove the new node x new Then, return to the step of determining the sampling point, that is, return to step 106-2 to obtain a new sampling point; the second radius R2 is smaller than the first radius R1;

[0071] Step 106-10, the new node x new Add to the current node tree and perform re-parent node selection and rewiring operations on the new node;

[0072] The specific process of this part can be referred to the RRT* method, and will not be further described here;

[0073] Step 106-12, perform collision detection again, if it passes, update the current node tree, if it fails, delete the new node x from the current node tree new Then, the process returns to the step of determining the sampling point, that is, returns to step 106-2, to obtain a new sampling point.

[0074] The embodiment of the present invention takes into account that the gantry external device (or gantry system structure) has three external axes, of which two translation axes (i.e., the first external translation axis and the second external translation axis) have a large motion range. If sampling is performed within the entire stroke, the path quality will be poor. Therefore, the sampling range of the external axis parameters in the sampling points is restricted to improve the path planning quality and shorten the processing time.

[0075] At the same time, considering that the dual welding robot with gantry external device has high degree of freedom, each path point has more parameters, and the configuration space of welding tasks is usually large, and the obstacle environment is sparse and dense, in order to reduce the burden of sampling and collision detection in sparse obstacle environments and improve processing efficiency, Figure 2 As shown, the present invention introduces the nearest node restriction. When the new node x new The distance from the node in the current node tree is too small (that is, there is a node, the new node x new Its distance d is less than the second radius R2), then the new node x new Delete and search for new nodes again, so that the node distribution in the node tree is more uniform, which is more conducive to the exploration of unknown space in a sparse obstacle environment, thereby avoiding collision detection in close areas and saving computing time. Figure 3 (a) and Figure 3 (b) show the use of RRT* method to start from the root node x start To the target point x end Schematic diagrams of the node tree obtained without and with the nearest node restricted. The black boxes in Figures 3(a) and 3(b) represent obstacles. It can be seen that restricting the nearest node results in a sparser node tree. Setting the second radius R2 too small may have little effect on evenly distributing nodes and have limited effect on improving paths. Setting the second radius R2 too large may make it difficult to search for suitable new nodes. More preferably, the second radius R2 is 1 / 5 to 1 / 4 of the first radius R1.

[0076] Optionally, step 100 further includes:

[0077] Determining a workspace accessible for welding based on the operating parameters of the gantry external device and the dual welding robot;

[0078] Build an obstacle model and determine the obstacle space. The obstacle model includes the dual welding robot model and the welding workpiece model. If other obstacles exist, their models must also be determined in this step.

[0079] After determining the accessible working space for welding, remove the space with obstacles and the remaining space can be considered as free space.

[0080] Optionally, for step 104 , the preset expansion amount is determined according to the height of the welding workpiece.

[0081] Step 104 expands the path by a predetermined amount based on the first and second external translation axis parameters at the starting and ending points. This is to account for the height obstruction of the welding workpiece, which may reduce the success rate of path planning. To effectively bypass the welding workpiece and provide a feasible welding path, the present invention determines a predetermined expansion amount based on the height of the welding workpiece. Preferably, the expansion amount is no less than 1 times the height of the welding workpiece.

[0082] Optionally, in step 106-2, determining the sampling point further includes:

[0083] Step 106-2-0, randomly generate N sampling points according to the preset target bias probability;

[0084] Wherein, N is a positive integer not less than 3; N is preferably 3 to 5;

[0085] The sampling points include a plurality of parameters for representing the postures of the joints of the two manipulators and the current state of the external device of the gantry, wherein the first external translation axis parameter and the second external translation axis parameter do not exceed a determined sampling range;

[0086] Specifically, let the target deviation probability be p, generate a random number P∈(0,1], if P≤p, let the target point be the generated sampling point, if P>p, let the randomly generated random point be the sampling point; p is preferably 0.1;

[0087] Step 106-2-2, for the two dimensions of the first external translation axis parameter and the second external translation axis parameter, respectively calculate the offset of each sampling point relative to the line connecting the root node and the target point, and select the sampling point with the smallest offset.

[0088] Taking into account the structural characteristics of the gantry's external devices, the two translation axes have a large range of motion and a greater impact. In order to shorten the overall welding path length, the present invention targets the parameters corresponding to the two translation axes, adopts a method of multiple sampling in one search, and selects sampling points with shorter translation axis movement to indicate the expansion direction, so that the search path is as close as possible to the projection of the line connecting the starting point and the end point on the horizontal plane formed by the x-direction and the y-direction. In this way, the planned path tends to be close to the line connecting the starting point and the end point, effectively avoiding problems such as the robot taking detours in free space and excessive offset.

[0089] Furthermore, in step 106-2-2, the offset degree of the sampling point relative to the line connecting the root node and the target point is calculated in the following manner:

[0090] Calculate the sampling point x for the two dimensions of the first external translation axis parameter and the second external translation axis parameter rand Corresponding Cos value; sampling point x rand The corresponding Cos value expression is:

[0091]

[0092] Among them, e 1,s With e 2,s 、e 1,e With e 2,e and e1,r With e 2,r Represent the root node, target point and sampling point x respectively rand The first external translation axis parameter and the second external translation axis parameter, e 1,s With e 2,s They represent the first external translation axis parameter and the second external translation axis parameter of the root node of the node tree, respectively. 1,r With e 2,r Represents the sampling point x rand The first external translation axis parameter and the second external translation axis parameter, e 1,e With e 2,e They represent the first external translation axis parameter and the second external translation axis parameter of the target point of the node tree, respectively. 1,e -e 1,s ,e 2,e -e 2,s ) represents the two-dimensional vector formed by the line connecting the root node and the target point for the two dimensions of the first external translation axis parameter and the second external translation axis parameter, and || || represents the norm calculation;

[0093] The step of selecting the sampling point with the smallest deviation includes:

[0094] Select the sampling point with the largest corresponding Cos value.

[0095] A larger Cos value indicates that the sampling point is closer to the line connecting the root node and the target point (i.e., the line connecting the starting point and the ending point). By calculating the Cos values ​​corresponding to the sampling points based solely on the first and second external translation axis parameters, the above embodiment can quickly select the sampling points that are closer to the line connecting the root node and the target point from among multiple sampling points. For the gantry's external devices, this approach minimizes the movement of the first and second external translation axes, which move in the x and y directions, respectively, within the horizontal plane.

[0096] Optionally, in step 106, two nodes x a and x b The distance between them can be calculated using the following formula:

[0097]

[0098] Among them, θ i,a and θ i,b Represents node x respectively a and node x b The i-th robot joint parameter, i = 1, ..., 6 represents the joint serial number of one robot arm in the dual welding robot, i = 7, ..., 12 represents the joint serial number of the other robot arm, e 1,a and e 1,b、e 2,a and e 2,b and e 3,a and e 3,b Represents node x respectively a and node x b The first external translation axis parameter, the second external translation axis parameter, and the external rotation axis parameter are represented by ||, where || represents absolute value calculation.

[0099] The above embodiment provides a method for calculating the two nodes x for the case where the robot arm is a six-axis robot arm. a and x b In other embodiments, if the robotic arm is a four-axis robotic arm, the corresponding calculation formula should be adjusted, and the value range and specific corresponding meaning of i change. For a four-axis robotic arm, 1≤i≤8, i=1,...,4 represents the joint number of one robotic arm in the dual welding robot, and i=5,...,8 represents the joint number of the other robotic arm.

[0100] In step 106, collision detection is performed both after expanding the new node and after adding the new node to the node tree to ensure that the searched path can achieve collision-free welding. Preferably, a hierarchical bounding box method is used for the dual welding robot and the welded workpiece to achieve more efficient collision detection. For example, the robot arm joints are segmented into 1st, 2nd, and 3rd level bounding boxes, and the detection process is performed on the hierarchical bounding boxes constructed from the two binary trees in a synchronous descending manner. In other embodiments, other methods can also be used to implement collision detection, which is not further limited here.

[0101] The present invention also selects four existing robot obstacle avoidance path planning methods, namely RRT, RRT*, RRT-connect and IB-RRT*, as comparisons, and uses scene 1 shown in FIG4(a) and scene 2 shown in FIG4(b) to test to verify the comprehensive performance of the industrial robot obstacle avoidance path planning method provided by the present invention (hereinafter referred to as the present invention method). FIG5(a) shows the maximum value (max), minimum value (min) and average value (avg) of the path length obtained by independently running RRT, RRT*, RRT-connect, IB-RRT* and the present invention method 20 times in scene 1. FIG5(b) shows the maximum value (max), minimum value (min) and average value (avg) of the path length obtained by independently running RRT, RRT*, RRT-connect, IB-RRT* and the present invention method 20 times in scene 1. , RRT*, RRT-connect, IB-RRT* and the method of the present invention are run 20 times independently in scenario 2, and the maximum, minimum and average values ​​of the path length are obtained. FIG6(a) shows the maximum (max), minimum (min) and average (avg) values ​​of the time consumed by RRT, RRT*, RRT-connect, IB-RRT* and the method of the present invention when they are run 20 times independently in scenario 1. FIG6(b) shows the maximum, minimum and average values ​​of the time consumed by RRT, RRT*, RRT-connect, IB-RRT* and the method of the present invention when they are run 20 times independently in scenario 2. For the convenience of display, Figures 5(a) to 6(b) In the text, “Improved RRT*” is used to refer to the method of the present invention. Figures 5(a) to 6(b) It can be seen that in the path obtained by the method provided by the present invention, the average, maximum and minimum values ​​of the path length are all optimal, and the time consumption is also the shortest, which verifies that the path planning method adopted by the present invention has high search efficiency and stable search quality, which is beneficial to practical engineering applications.

[0102] An embodiment of the present invention further provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, an industrial robot obstacle avoidance path planning method according to any embodiment of the present invention is implemented.

[0103] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes an industrial robot obstacle avoidance path planning method according to any embodiment of the present invention.

[0104] Specifically, a system or device equipped with a storage medium can be provided, on which software program codes that implement the functions of any of the above-mentioned embodiments are stored, and a computer (or CPU or MPU) of the system or device can be enabled to read and execute the program codes stored in the storage medium.

[0105] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute part of the present invention.

[0106] Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code can be downloaded from a server computer via a communication network.

[0107] In addition, it should be clear that the functions of any of the above embodiments can be achieved not only by executing the program code read by the computer, but also by enabling the operating system operating on the computer to complete part or all of the actual operations based on the instructions of the program code.

[0108] In addition, it can be understood that the program code read from the storage medium is written into a memory provided in an expansion board inserted into the computer or into a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above embodiments.

[0109] Each embodiment of the present invention has at least the following beneficial effects:

[0110] 1. In one embodiment of the present invention, a method for obstacle avoidance path planning for an industrial robot is provided. This method analyzes the gantry system and limits the node sampling range to improve planning quality. Furthermore, the method limits the nearest node during the sampling process to achieve sparse sampling, further reducing planning time. This method is highly targeted to the gantry system and can effectively handle path planning problems in environments with sparse obstacles, effectively shortening search time and solving path planning problems for gantry robot systems with high degrees of freedom. This method reduces labor costs, improves the automation and intelligence of the production process, and is more suitable for engineering applications.

[0111] 2. In one embodiment of the present invention, a method for obstacle avoidance path planning for an industrial robot is provided. This method utilizes a sampling pool mechanism to perform multiple samplings in a single search, selecting nodes with shorter external translation axis movement, thereby reducing path length and improving path quality. Furthermore, the selection criteria can be adjusted based on the scenario, resulting in good adaptability.

[0112] 3. In one embodiment of the present invention, an industrial robot obstacle avoidance path planning method is provided, which performs a hierarchical bounding box method on the robot joints and workpieces to achieve a more efficient collision detection process.

[0113] It should be noted that, in this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0114] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc. Various media that can store program codes.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for obstacle avoidance path planning for an industrial robot, characterized in that: Suitable for a dual welding robot with a gantry external device; the dual welding robot includes two robotic arms, each equipped with a welding gun; the gantry external device includes a first external translation axis and a second external translation axis that move in the x and y directions in the horizontal plane, respectively, and an external rotation axis that rotates about the vertical z axis; the dual welding robot is installed on the gantry external device and can change its overall posture under the drive of the gantry external device, and can independently change the posture of each joint of the two robotic arms; The method includes: Determine the configuration space of welding tasks; Determine the starting point and the ending point of the path planning task; the starting point and the ending point each include multiple parameters for representing the joint postures of the two robotic arms and the current state of the external device of the gantry; Determining a sampling range of the first external translation axis parameter and the second external translation axis parameter of the sampling point during the path planning process according to the first external translation axis parameter and the second external translation axis parameter of the starting point and the ending point, in combination with a preset expansion amount; Constructing a node tree with the starting point and the ending point as root nodes respectively, and expanding the two node trees by performing point search until the two node trees intersect; For any node tree, point search includes: Determine the root node and target point; Generate and determine sampling points for indicating the expansion direction according to the configuration space of the welding task and the determined sampling range; Based on the determined sampling point and the preset expansion step, a new node x is expanded for the current node tree. new , and for the new node x new Perform collision detection. If it passes, continue to the next steps. If it fails, delete the new node x. new Then, return to the step of determining the sampling point; Based on the new node x new and the preset first radius R1, determine the new node x new The nodes in the neighboring point set are taken from the current node tree and are related to the new node x new The distance does not exceed the first radius R1; Based on the new node x new and the preset second radius R2, to determine whether there is a point in the neighboring point set that is related to the new node x new The distance to the node that does not exceed the second radius R2, if it does not exist, continue to perform subsequent steps, if it exists, then remove the new node x new Then, return to the step of determining the sampling point; the second radius R2 is smaller than the first radius R1; The new node x new Add the new node to the current node tree and reselect the parent node and rewire the new node. Perform collision detection again. If it passes, update the current node tree. If it fails, delete the new node x from the current node tree. new Then, return to the step of determining the sampling point.

2. The method according to claim 1, characterized in that The generating and determining the sampling point for indicating the extension direction includes: According to the preset target bias probability, N sampling points are randomly generated; N is a positive integer not less than 3; For the two dimensions of the first external translation axis parameter and the second external translation axis parameter, the offset degree of each sampling point relative to the line connecting the root node and the target point is calculated respectively, and the sampling point with the smallest offset degree is selected.

3. The method according to claim 2, characterized in that The offset of the sampling point relative to the line connecting the root node and the target point is calculated in the following manner: Calculate the sampling point x for the two dimensions of the first external translation axis parameter and the second external translation axis parameter rand The corresponding Cos value is expressed as: Among them, e 1,s With e 2,s 、e 1,e With e 2,e and e 1,r With e 2,r Represent the root node, target point and sampling point x respectively rand The first external translation axis parameter and the second external translation axis parameter, || || represents the norm calculation; The step of selecting the sampling point with the smallest deviation includes: Select the sampling point with the largest corresponding Cos value.

4. The method according to claim 1, wherein The configuration space for determining the welding task includes: Determining a workspace accessible for welding based on the operating parameters of the gantry external device and the dual welding robot; An obstacle model is established to determine the obstacle space; the obstacle model includes a dual welding robot model and a welding workpiece model.

5. The method according to claim 1, characterized in that The preset expansion amount is determined according to the height of the welding workpiece.

6. The method according to claim 1, characterized in that The robotic arm is a six-axis robotic arm.

7. The method according to claim 6, characterized in that Two nodes x a and x b The distance between them is calculated using the following formula: Among them, θ i,a and θ i,b Represents node x respectively a and node x b The i-th robot joint parameter, i = 1, ..., 6 represents the joint serial number of one robot arm in the dual welding robot, i = 7, ..., 12 represents the joint serial number of the other robot arm, e 1,a and e 1,b 、e 2,a and e 2,b and e 3,a and e 3,b Represents node x respectively a and node x b The first external translation axis parameter, the second external translation axis parameter, and the external rotation axis parameter are represented by ||.

8. The method according to claim 1, characterized in that The second radius R2 is 1 / 5 to 1 / 4 of the first radius R1.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 8.

Images