Welding robot path planning method, device, electronic equipment and storage medium

Abstract

The present application provides a welding robot path planning method, device, electronic device and storage medium, which relate to the field of navigation and path planning. The method includes: obtaining the starting point and end point of the welding robot in the welding transition process, as well as the position of obstacles in the welding environment; generating multiple initial paths according to the positions of the starting point, end point and obstacles, and obtaining the path length of each initial path; performing smooth optimization on the initial path with the shortest path length to obtain a smooth path; generating a weighted graph structure based on the smooth path; searching for the optimal path between the starting point and end point in the weighted graph structure; and determining the welding transition path of the welding robot in the welding transition process based on the optimal path. The present application can perform obstacle avoidance planning on the welding transition path of the welding robot, reduce redundant nodes, improve the smoothness of the path, meet the process requirements of welding, and improve production efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of navigation and path planning, and in particular to a welding robot path planning method, device, electronic device and storage medium. Background Art

[0002] The prefabrication of large-scale steel bridge components is a core step in bridge construction, and the efficiency and quality of welding directly impact the overall construction schedule and structural safety. Currently, automated welding of steel components relies primarily on manual instruction programming, which, while simple to operate, lacks adaptability. Repeated programming and debugging are required for components of varying specifications, and a single deployment can take hours. To further improve production efficiency, path planning for welding robots and automated welding are crucial.

[0003] In automated welding, the welding transition path refers to the trajectory that a welding robot follows after completing one weld and moving to the starting position of the next weld. Planning the welding transition path requires ensuring smoothness and minimizing idle travel time while avoiding obstacles in three dimensions to ensure production efficiency. Related technologies primarily employ path planning algorithms, such as the A* algorithm and the Rapidly-Exploring Random Trees (RRT) algorithm. The inventors have discovered that while these algorithms can achieve three-dimensional obstacle avoidance, the generated paths contain redundant nodes and abrupt route transitions, making them difficult to meet welding process requirements. Summary of the Invention

[0004] The embodiments of the present application provide a welding robot path planning method, device, electronic device and storage medium to perform obstacle avoidance planning on the welding transition path of the welding robot, reduce redundant nodes, improve the smoothness of the path, meet the process requirements of welding, and improve production efficiency.

[0005] In a first aspect, an embodiment of the present application provides a welding robot path planning method, comprising:

[0006] Obtain the starting and ending points of the welding robot during the welding transition process, as well as the locations of obstacles in the welding environment;

[0007] Generate multiple initial paths according to the starting point, the ending point, and the position of the obstacle, and obtain the path length of each initial path;

[0008] Perform smooth optimization on the initial path with the shortest path length to obtain a smooth path;

[0009] Based on the smooth path, generating a weighted graph structure;

[0010] Searching for an optimal path between the starting point and the ending point in the weighted graph structure;

[0011] Based on the optimal path, a welding transition path of the welding robot during a welding transition process is determined.

[0012] In a possible implementation, the obstacles include static obstacles and dynamic obstacles;

[0013] The generating of multiple initial paths according to the starting point, the ending point, and the position of the obstacle, and obtaining the path length of each initial path, includes:

[0014] Predicting a motion trajectory of the dynamic obstacle based on the position of the dynamic obstacle;

[0015] Based on a preset path planning algorithm, the position of the static obstacle and the motion trajectory of the dynamic obstacle, generating multiple initial paths from the starting point to the end point, and obtaining the path length of each initial path;

[0016] Each time a new node is generated, the position prediction range of the dynamic obstacle corresponding to the new node is determined based on the motion trajectory of the dynamic obstacle, and based on the position prediction range, it is detected whether the path extending the new node has the risk of collision with the dynamic obstacle; if so, the new node is removed.

[0017] In a possible implementation, the initial path includes a plurality of nodes;

[0018] The step of performing smooth optimization on the initial path with the shortest path length to obtain a smooth path includes:

[0019] Performing interpolation fitting according to the nodes of the initial path with the shortest path length to obtain a fitting curve;

[0020] Resampling is performed between the nodes of the fitting curve to obtain a plurality of new nodes;

[0021] Detecting whether there is a curve segment on the fitting curve that does not meet a preset curvature constraint;

[0022] If there is a curve segment on the fitting curve that does not satisfy the curvature constraint, the nodes in the curve segment are adjusted; the fitting curve is regenerated based on all the adjusted nodes, and the step of "detecting whether there is a curve segment on the fitting curve that does not satisfy the preset curvature constraint" and subsequent steps are re-executed until the fitting curve satisfies the curvature constraint;

[0023] The fitted curve that satisfies the curvature constraint is taken as the smooth path.

[0024] In a possible implementation, the smooth path includes a plurality of nodes;

[0025] Generating a weighted graph structure based on the smooth path includes:

[0026] Determining a node distance between any two nodes on the smooth path;

[0027] For any two nodes whose node distance is less than a preset node threshold, establishing an edge connection between the two nodes;

[0028] The weight of each edge is determined based on the node distance between the two nodes of each edge and the curvature of the local path;

[0029] A weighted graph structure is generated based on each node, each edge and the weight of each edge of the smooth path.

[0030] In a possible implementation, searching for an optimal path between the starting point and the ending point in the weighted graph structure includes:

[0031] Based on a preset ant colony algorithm, searching for an optimal path between the starting point and the end point in the weighted graph structure;

[0032] In each iteration of the ant colony algorithm, the path taken by each ant is evaluated according to a preset path evaluation function; wherein the path evaluation function is determined according to the length and curvature of the path taken by the ant.

[0033] In a possible implementation, the preset ant colony algorithm includes a heuristic function and a pheromone update formula;

[0034] The heuristic function is determined according to the weight of each edge in the weighted graph structure;

[0035] The pheromone update formula is determined based on the pheromone of each edge in the previous iteration, the path length and path curvature of the path taken by each ant.

[0036] In a possible implementation, determining the welding transition path of the welding robot during the welding transition process based on the optimal path includes:

[0037] Determining the path length, path curvature, and distance from the obstacle of the optimal path;

[0038] If the path length of the optimal path is greater than the path length of the smooth path, or the path curvature of the optimal path is greater than the path curvature of the smooth path, or the distance between the optimal path and the obstacle is less than a preset safety distance threshold, then the position of the obstacle in the welding environment is re-acquired, and the step of "generating multiple initial paths for the welding transition process according to the starting point, the end point, and the position of the obstacle, and obtaining the path length of each initial path" and subsequent steps are performed until the obtained optimal path is qualified;

[0039] The qualified optimal path is used as the welding transition path of the welding robot in the welding transition process.

[0040] In a second aspect, an embodiment of the present application provides a welding robot path planning device, comprising:

[0041] An acquisition module is used to obtain the starting point and ending point of the welding robot in the welding transition process, as well as the position of obstacles in the welding environment;

[0042] A path generation module, configured to generate a plurality of initial paths according to the starting point, the ending point, and the position of the obstacle, and obtain the path length of each initial path;

[0043] A smoothing module is used to perform smooth optimization on the initial path with the shortest path length to obtain a smooth path;

[0044] A graph structure module, configured to generate a weighted graph structure based on the smooth path;

[0045] An optimization module, configured to search for an optimal path between the starting point and the end point in the weighted graph structure;

[0046] A determination module is used to determine a welding transition path of the welding robot during a welding transition process based on the optimal path.

[0047] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method in the first aspect or any possible implementation of the first aspect is implemented.

[0048] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method in the first aspect or any possible implementation of the first aspect.

[0049] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method in the first aspect or any possible implementation of the first aspect.

[0050] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0051] The embodiment of the present application generates multiple feasible initial paths through the starting point and ending point of the welding robot in the welding transition process, as well as the position of obstacles in the welding environment, and obtains the path length of each initial path; the initial path with the shortest path length is screened out for smooth optimization to obtain a smooth path. The initial path with the shortest path length can be used as a benchmark to reduce redundant nodes in the generated path, ensure the smoothness of the obtained path, and reduce the curvature of the path; generate a weighted graph structure through the smooth path, which can provide a basis for further optimizing the path between the starting point and the ending point; by searching for the optimal path between the starting point and the ending point in the weighted graph structure, the search can be performed in the weighted graph structure to further reduce redundant nodes in the path and reduce the curvature of the path, so that the final path can be more in line with the welding process requirements and improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0053] Figure 1 This is a flow chart of an implementation method of a welding robot path planning method provided in one embodiment of the present application;

[0054] Figure 2 is a schematic diagram of the initial path provided in an embodiment of the present application;

[0055] Figure 3 Schematic diagram comparing the initial path, smoothed path, and optimal path provided in the embodiment of the present application;

[0056] Figure 4 is a schematic diagram of a weighted graph structure provided by an embodiment of the present application;

[0057] Figure 5 is a schematic diagram of the optimal path provided by an embodiment of the present application;

[0058] Figure 6 is a flow chart of an implementation method of a welding robot path planning method provided by another embodiment of the present application;

[0059] Figure 7 Schematic diagram of the structure of the welding robot path planning device provided in an embodiment of the present application;

[0060] Figure 8 Schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0062] The inventors have discovered that in the field of steel structure welding, welding robots often face complex three-dimensional obstacle avoidance path planning problems. Although the RRT algorithm can achieve three-dimensional obstacle avoidance, the generated path has problems such as node redundancy and abrupt turns, and cannot meet the welding process's requirements for continuous and smooth motion. The ant colony algorithm has high computational complexity, especially when dealing with obstacles such as dense support beams and bolted connectors of large steel components. It is difficult to adapt to the real-time planning requirements of dense welds of steel components, which can easily lead to path collision risks or uneven motion. Therefore, it is necessary to consider a technology for welding robot path planning.

[0063] The invention aims to improve the smoothness of the path planned by the welding robot and enhance production efficiency. In the embodiment of the present application, multiple feasible initial paths are generated, and the initial path with the shortest path length is selected for smooth optimization to ensure a short path length and reduce abrupt path turns; a weighted graph structure is then generated based on the smoothed path and converted into a structure that can be optimized. The weighted graph structure is used for path optimization, which can remove redundant nodes in the path, reduce the curvature of the path, thereby reducing the path length, improving the smoothness of the path, and achieving improved production efficiency.

[0064] In order to make the purpose, technical solutions and advantages of this application clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0065] Before planning the welding robot's path, a 3D grid map of the welding environment can be constructed to define the obstacle model and welding task constraints for the steel structure welding workpiece. Obstacles include static and dynamic obstacles, such as welding fixtures, pipe connectors, mobile equipment, truss lifting equipment, and collaborative robots. The bounding box method can be used to enclose complex objects and simplify obstacles into simple geometric entities.

[0066] When establishing a three-dimensional grid map of the welding environment, laser vision sensors and force sensors can be used to collect welding environment data, establish dynamic obstacles and static obstacles in the welding environment, and extract weld information or weld features of steel structures in the welding environment to facilitate subsequent path planning by the welding robot.

[0067] Figure 1 The following is a flowchart of a welding robot path planning method according to an embodiment of the present invention:

[0068] Step 101: Acquire the starting point and ending point of the welding robot in the welding transition process, as well as the positions of obstacles in the welding environment.

[0069] In this embodiment, the welding transition process refers to the process in which the welding robot moves from the end point of the first welding operation to the starting point of the second welding operation. In this process, the path along which the welding robot moves is the welding transition path.

[0070] The end point of the first welding operation is the starting point of the welding transition process, and the starting point of the second welding operation is the end point of the welding transition process. The above end points can be obtained by extracting weld information or weld features in the welding environment.

[0071] Here, the positions of static and dynamic obstacles in the welding environment can be obtained in real time. For dynamic obstacles, the movement trajectory of the dynamic obstacles can be predicted in real time based on the position or motion data of the dynamic obstacles, and the emergence of new dynamic obstacles can be detected in a timely manner.

[0072] Step 102: Generate multiple initial paths based on the starting point, the ending point, and the position of the obstacle, and obtain the path length of each initial path.

[0073] In this embodiment, if Figure 2 As shown, a path planning algorithm can be used to find multiple feasible paths from the starting point to the end point that do not pass through obstacles, which are the initial paths.

[0074] Each feasible path may be obtained using a different path planning algorithm or using the same path planning algorithm.

[0075] Since the length of the path that the welding robot moves will affect the production efficiency, the path length of each initial path can be calculated for subsequent screening.

[0076] Step 103 : performing smoothing optimization on the initial path with the shortest path length to obtain a smoothed path.

[0077] In this embodiment, in order to ensure that the welding transition path of the welding robot is short and does not affect the production cycle, the initial path with the shortest path length can be selected for smooth optimization and subsequent processing, that is, Figure 2 Medium pink path.

[0078] Taking into account the presence of broken lines and abrupt turns in the initial path generated by the path planning algorithm, which will cause the welding robot to move unsmoothly and increase energy consumption, the selected initial path is smoothed and optimized so that the smooth path maintains a shorter distance while also having better continuity and smoothness, which is more suitable for the movement of the welding robot.

[0079] Optionally, if there are multiple initial paths with the same path length, the initial path with the shortest path length and the smallest curvature may be selected for smoothing optimization.

[0080] Step 104: Generate a weighted graph structure based on the smoothed path.

[0081] In this embodiment, considering that the path generated by the path planning algorithm may contain redundant nodes, resulting in a relatively long path length, and curve segments with large curvature may still exist after smoothing, the smoothed path may be further optimized.

[0082] In order to remove redundant nodes and optimize node positions, a weighted graph structure corresponding to the smooth path can be established first, so that subsequent optimization can be performed based on the weighted graph structure to find a better path and remove redundant nodes in the path.

[0083] Step 105: Search for the optimal path between the starting point and the end point in the weighted graph structure.

[0084] In this embodiment, an optimization algorithm may be used to search for an optimal path in a weighted graph structure, reduce redundant nodes in a smooth path, and select a path with a smaller curvature.

[0085] like Figure 3 As shown in the figure, the optimal path is shorter and has a smaller curvature than the smooth path and the initial path, that is, the path is smoother and more in line with the movement needs of the welding robot.

[0086] Optionally, considering the presence of obstacles in the welding environment, each edge can be checked when generating the weighted graph structure to see if it will pass through an obstacle, and edges that do can be removed. Alternatively, when searching for the optimal path, edges can be checked to see if they will pass through an obstacle, and edges that do can be removed.

[0087] Step 106: Determine a welding transition path of the welding robot during the welding transition process based on the optimal path.

[0088] In this embodiment, the optimal path can be directly used as the welding transition path.

[0089] Furthermore, considering that dynamic obstacles are moving and that the welding transition process needs to meet corresponding process requirements, the optimal path can also be tested. If it meets the welding process requirements, the optimal path will be used as the welding transition path. If it does not meet the welding process requirements, the path planning can be re-performed until the optimal path meets the process requirements.

[0090] The embodiment of the present application generates multiple feasible initial paths through the starting point and ending point of the welding robot in the welding transition process, as well as the position of obstacles in the welding environment, and obtains the path length of each initial path; the initial path with the shortest path length is screened out for smooth optimization to obtain a smooth path. The initial path with the shortest path length can be used as a benchmark to reduce redundant nodes in the generated path, ensure the smoothness of the obtained path, and reduce the curvature of the path; generate a weighted graph structure through the smooth path, which can provide a basis for further optimizing the path between the starting point and the ending point; by searching for the optimal path between the starting point and the ending point in the weighted graph structure, the search can be performed in the weighted graph structure to further reduce redundant nodes in the path and reduce the curvature of the path, so that the final path can be more in line with the welding process requirements and improve production efficiency.

[0091] In some embodiments, obstacles include static obstacles and dynamic obstacles.

[0092] Reference Figure 2 In this embodiment, multiple initial paths are generated based on the starting point, the ending point, and the position of the obstacle, and the path length of each initial path is obtained. The motion trajectory of the dynamic obstacle can be predicted based on the position of the dynamic obstacle; based on a preset path planning algorithm, the position of the static obstacle, and the motion trajectory of the dynamic obstacle, multiple initial paths are generated from the starting point to the ending point, and the path length of each initial path is obtained.

[0093] Among them, each time a new node is generated, the position prediction range of the dynamic obstacle corresponding to the new node is determined according to the motion trajectory of the dynamic obstacle, and based on the position prediction range, it is detected whether the path extending the new node has the risk of collision with the dynamic obstacle; if so, the new node is removed.

[0094] In this embodiment, since the position of a dynamic obstacle is variable, in order to properly consider the impact of the obstacle during path planning, its future trajectory can be predicted based on its current position. The prediction can also take into account the type of dynamic obstacle and the process or steps being executed.

[0095] After predicting the motion trajectory of a dynamic obstacle, it can be converted into a static obstacle for collision judgment through the correspondence between the time and position of the dynamic obstacle.

[0096] Here, a path planning algorithm can be used to generate an initial path between the starting point and the end point. In the process of generating the initial path, each time a new node is generated, it can be detected whether the path extending the new node has the risk of collision with static obstacles and dynamic obstacles, and the nodes without collision risk are retained, and the nodes with collision risk are removed.

[0097] Among them, the number of nodes between each new node and the starting point is fixed, which can clearly determine the time when the welding robot moves to the new node, thereby corresponding to the time and position in the motion trajectory of the dynamic obstacle to judge the collision risk with the dynamic obstacle.

[0098] By determining the path of the welding robot in extending the new node and the time to the new node in the motion trajectory of the dynamic obstacle, the position prediction range of the dynamic obstacle can be obtained, that is, the position of the dynamic obstacle within the time or time period.

[0099] Since the time for the welding robot to execute the planned path may deviate, a larger time range can be used, or the obtained position prediction range can be expanded to expand the range to ensure the accuracy of collision detection.

[0100] When performing collision detection, spherical obstacles can be detected by performing a ray-sphere intersection test. To determine whether the path extending the new node will collide with the spherical obstacle, mathematical calculations are performed to determine whether the path intersects with the sphere's surface. If so, the path will collide with the spherical obstacle; if not, the path is safe and will not collide with the spherical obstacle.

[0101] For rectangular obstacles, the space occupied by the obstacle is determined by segmenting the space. The space occupied by the obstacle can be segmented to determine whether the space traversed by the path overlaps with the space occupied by the obstacle. If there is overlap, it means that the path will collide with the obstacle; if there is no overlap, it means that the path is feasible and will not collide with the obstacle.

[0102] Optionally, the path planning algorithm may adopt an RRT algorithm, an RRT* algorithm, or the like.

[0103] When randomly sampling in the welding space and determining the growth direction of new nodes, the nodes can be expanded in the direction of the next welding operation or towards the end point, thereby reducing invalid searches and improving path planning efficiency.

[0104] A random number can be generated. If the random number is less than a set probability threshold, the end point (or a point randomly selected from the weld of the next welding operation) is set as the random sampling point to determine the new node. If the random number is not less than the set probability threshold, uniform random sampling is performed within the weld space to determine the random point to determine the new node.

[0105] In some embodiments, the initial path includes a plurality of nodes, which may include nodes generated on the initial path using a path planning algorithm, as well as a starting point and an ending point.

[0106] In this embodiment, smoothing optimization is performed on the initial path with the shortest path length to obtain a smoothed path, which may include:

[0107] Step 1: Perform interpolation fitting based on the nodes of the initial path with the shortest path length to obtain a fitting curve.

[0108] Here, differential fitting means fitting the curve so that the resulting curve passes through the nodes of the initial path with the shortest path length. Because the welding environment is prone to numerous obstacles and the welding robot's starting and ending points are fixed, curve fitting must be performed on the previously planned initial path to avoid obstacles. Approximate fitting cannot be used.

[0109] Optionally, a B-spline curve, such as a cubic B-spline curve, may be used for difference fitting.

[0110] Step 2: resample between the nodes of the fitting curve to obtain multiple new nodes.

[0111] In this embodiment, since the path planning algorithm generates an initial path with fewer nodes and a larger distance between nodes, the fitting curve can be discretized and resampled between two adjacent nodes to obtain dense and uniform nodes for subsequent adjustment of the fitting curve.

[0112] For example, 10 nodes or 15 nodes are added between two adjacent nodes, etc. The number of nodes added is only an example and is not intended to be limiting, and can be selected based on the length of the path.

[0113] Step three: Check whether there is a curve segment on the fitting curve that does not meet the preset curvature constraint.

[0114] Step 4: If there is a curve segment on the fitting curve that does not meet the curvature constraint, the nodes in the curve segment are adjusted; the fitting curve is regenerated based on all the adjusted nodes, and the step of "detecting whether there is a curve segment on the fitting curve that does not meet the preset curvature constraint" and subsequent steps are re-executed until the fitting curve meets the curvature constraint.

[0115] Step 5: The fitting curve that satisfies the curvature constraint is used as the smooth path.

[0116] In this embodiment, the welding transition path needs to maintain a certain degree of smoothness, so the curvature at each position on the fitting curve can be detected.

[0117] If there are curve segments on the fitting curve that do not meet the curvature constraints, it means that the path corresponding to the fitting curve does not meet the requirements of the welding process. In this case, the corresponding nodes can be adjusted, such as translating control points (reducing curvature) or inserting / deleting control points (changing local density).

[0118] After the adjustment, the curve can be refitted to ensure that the obtained fitting curve passes through all the nodes after the adjustment. Since the nodes are dense and uniform at this time, the curve fitting here can use the same curve fitting method as in step 1, or a different curve fitting method can be used.

[0119] If all curve segments on the fitting curve meet the curvature constraint, it means that the current fitting curve meets the requirements of the welding process and no smoothing adjustment is required.

[0120] In some embodiments, the smooth path includes a plurality of nodes, where the nodes may include a starting point, an ending point, and all nodes between the starting point and the ending point on the smooth path.

[0121] This embodiment generates a weighted graph structure based on a smooth path. This can involve first determining the node distance between any two nodes on the smooth path. For any two nodes whose node distance is less than a preset node threshold, an edge connection is established between the two nodes. The weight of each edge is then determined based on the node distance between the two nodes of each edge and the curvature of the local path. Finally, a weighted graph structure is generated based on each node, each edge, and each edge weight on the smooth path.

[0122] See also Figure 4 The schematic diagram of the weighted graph structure shown in Figure 1 is a diagram of a weighted graph structure, where the blue origin is the node on the smooth path and the gray lines are the connections between the nodes, i.e., the edges in the weighted graph structure.

[0123] In this embodiment, the nodes of the smooth path may be used as a node set of a weighted graph structure of the smooth path, and an edge set may be established based on the node set.

[0124] Here, the preset node threshold can be selected based on the path length. For example, because the nodes on a smooth path are densely packed and uniform, i.e., the node distance between all two adjacent nodes (referred to as the adjacent node distance) is the same, the preset node threshold can be 1.5 times the adjacent node distance, 2 times the adjacent node distance, or even 3 times the adjacent node distance. The specific multiples are for illustration only and are not intended to be limiting, and can be selected based on actual circumstances.

[0125] The curvature of the local path of each edge can be calculated based on the two nodes of the edge and a node adjacent to the edge. The node adjacent to the edge can be selected based on the direction from the starting point to the ending point on the smooth path, or from the ending point to the starting point.

[0126] Taking a node adjacent to the edge as the next node of the edge as an example, the smooth curve includes nodes A, B, C, D, E, F, G and H, among which A and B are connected by edge ab, A and C are connected by edge ac, B and C are connected by edge bc, B and D are connected by edge bd, B and E are connected by edge be, B and F are connected by edge bf, C and D are connected by edge cd, ..., F and H are connected by edge fh, G and H are connected by edge gh, etc.

[0127] For edge ab, if its next node is C, then the path it is on is the path formed by nodes A, B, and C. That is, the curvature of the local path formed by nodes A, B, and C is calculated to determine the weight of edge ab. For edge ac, if its next node is D, then the path it is on is the path formed by nodes A, C, and D. The curvature of the local path formed by nodes A, C, and D is calculated to determine the weight of edge ac. For edge bc, if its next node is D, then the path it is on is the path formed by nodes B, C, and D. The curvature of the local path formed by nodes B, C, and D is calculated to determine the weight of edge bc.

[0128] For edges with one node as the endpoint, since there is no next node, the adjacent node for that edge can be the previous node. For example, if node H is the last node and the previous node for edge fh is E, the curvature of the local path formed by nodes E, F, and H is calculated to determine the weight of edge fh. For edge gh, whose previous node is F, the curvature of the local path formed by nodes F, G, and H is calculated to determine the weight of edge gh.

[0129] Optionally, the weight of each edge may be obtained by performing a weighted calculation based on the node distance between two nodes of each edge and the curvature of the local path where the edge resides.

[0130] The specific calculation formula can be: Where, Representation node and nodes The edges The weight of Representation node and nodes The distance between nodes, Representation node The location coordinates of Representation node The location coordinates of Represents an edge The curvature of the local path, and Represents the weight coefficient, which is used to balance the node distance and smoothness requirements.

[0131] Optionally, due to the presence of dynamic obstacles in the welding environment, it is necessary to detect the position of dynamic obstacles in real time and predict the future trajectory. Therefore, when establishing the weighted graph structure, all edges that meet the distance condition (node ​​distance is less than the preset node threshold) can be retained. When searching for the optimal path later, it is determined whether the obstacle will be passed through.

[0132] In some embodiments, searching for the optimal path between the starting point and the end point in the weighted graph structure may be based on a preset ant colony algorithm to search for the optimal path between the starting point and the end point in the weighted graph structure; see Figure 5 The diagram below shows an optimal path. The hollow circles represent nodes ants pass through, and the solid circles on either side represent the starting and ending points. In each iteration of the ant colony algorithm, each ant's path is evaluated based on a preset path evaluation function, which is determined based on the length and curvature of the path.

[0133] In this embodiment, since the welding transition path of the welding robot needs to consider the path length and path curvature, the path evaluation function can be determined according to the path length and path curvature of the path taken by the ants.

[0134] Optionally, the calculation formula of the path evaluation function can be: Where, Indicates in In the iteration The path evaluation value of the path taken by the ants, Indicates in In the iteration The length of the path taken by the ants, Indicates in In the iteration The curvature of the path taken by the ants, and Represents the weight coefficient.

[0135] here, and It can be the same or different. and Can be the same or different. For example, You can take 0.7, The above is only an illustrative example and is not intended to be limiting.

[0136] Alternatively, in the ant colony algorithm, after each ant selects the next node to visit, it can determine whether moving from the current node to the next node will cross an obstacle. If it is possible to cross an obstacle, it reselects the next node to visit from the remaining nodes.

[0137] Among them, for dynamic obstacles, the position of the dynamic obstacle can be obtained in real time, the motion trajectory of the dynamic obstacle can be re-predicted, and the position prediction range of the dynamic obstacle can be updated to ensure the accuracy of the judgment on whether to pass through the obstacle.

[0138] In addition, the following method can also be used to remove paths that pass through obstacles: during each iteration of the ant colony algorithm, after obtaining multiple optimized paths between the starting point and the end point, it is determined whether each optimized path will pass through an obstacle, and the optimized paths that pass through the obstacle are removed, while the optimized paths that do not pass through the obstacle are retained.

[0139] Optionally, the preset ant colony algorithm includes a heuristic function and a pheromone update formula.

[0140] Among them, the heuristic function reflects the ants' judgment on the local attractiveness of the path when choosing a path. The heuristic function can be determined according to the weight of each edge in the weighted graph structure, guiding the ants to give priority to better paths.

[0141] The pheromone update formula combines pheromone volatilization and enhancement to dynamically adjust the pheromone concentration along the path, preserving the preference for high-quality paths while preventing the algorithm from falling into local optima. The pheromone update formula can be determined based on the pheromone content of each edge in the previous iteration, the path length of each ant's optimized path, and the path curvature.

[0142] The pheromone update formula can be: Where, Indicates in Nodes in iterations The pheromones in the path between Indicates in Nodes in iterations The pheromones in the path between represents the dynamic volatility factor, Indicates the pheromone intensity, Indicates the The length of the path taken by the ants, Indicates the The curvature penalty term of the path taken by the ants, Represents the weight coefficient.

[0143] The above dynamic volatility factor It can decay exponentially with the increase of the number of iterations. The specific expression can be: Where, Indicates in The dynamic volatility factor in the iteration, represents the initial dynamic volatility factor, Represents the decay rate parameter.

[0144] In some embodiments, see Figure 6 The flowchart of another embodiment of the welding robot path planning method is shown, which determines the welding transition path of the welding robot during the welding transition process based on the optimal path. It can be:

[0145] Determine the path length, path curvature, and distance to obstacles for the optimal path.

[0146] If the path length of the optimal path is greater than the path length of the smooth path, or the path curvature of the optimal path is greater than the path curvature of the smooth path, or the distance between the optimal path and the obstacle is less than the preset safety distance threshold, the position of the obstacle in the welding environment is re-acquired, and the step of "generating multiple initial paths of the welding transition process according to the starting point, end point and the position of the obstacle, and obtaining the path length of each initial path" and subsequent steps are executed until the obtained optimal path is qualified.

[0147] The qualified optimal path is used as the welding transition path of the welding robot in the welding transition process.

[0148] In this embodiment, the optimal path is evaluated based on its length, curvature, and distance to obstacles to determine whether it is feasible. If the optimal path is not feasible, replanning is performed. If the optimal path is feasible, the welding robot can be controlled to move along the optimal path.

[0149] Among them, for obstacles, the position of the obstacle can be re-acquired and the trajectory prediction can be re-performed to accurately determine the distance between the optimal path and the obstacle.

[0150] In some specific embodiments, to verify the feasibility of the welding robot path planning method proposed in this application, simulation software can be used for programming and visualization. A simulation was performed using actual welding task data from a steel plant as a test set. The simulation parameters are shown in Table 1, the path details are shown in Table 2, and the point coordinates of the optimal path are shown in Table 3.

[0151] Table 1 Simulation parameters

[0152]

[0153] Table 2 Path details table

[0154]

[0155] Table 3 Point coordinate data table of the optimal path

[0156]

[0157] The above simulation results show that although the RRT* algorithm can find an obstacle avoidance transition path for a welding robot, the initial path, the generated path is usually composed of discrete line segments with jagged turns, which makes the welding robot unable to move and execute the welding path. Therefore, it is necessary to ensure the continuous curvature of the trajectory to avoid mechanical vibration or interference with the welding process. Using a B-spline curve fitting, the nodes of the initial path are smoothed to eliminate redundant nodes and ensure path continuity. The smoothed path can be discretized into dense and evenly distributed nodes. On this basis, a weighted graph structure is constructed, and the ant colony optimization algorithm is integrated to search for the optimal path in the weighted graph structure through pheromone guidance, thus generating an optimal path. Compared with the smoothed path, the optimal path has 60% fewer path points, 6.27% shorter path length, 94.5% lower average curvature, and the maximum curvature is reduced from 1699.143 to 21.087. This not only eliminates the redundant nodes generated by the RRT* algorithm and reduces the path length, but also maintains the path smoothness. Based on this, it can be seen that the welding robot path planning method proposed in this application is feasible in automated welding systems.

[0158] The embodiment of the present application can realize the construction from no path to a path by generating multiple feasible initial paths between the starting point and the end point of the welding transition process. By smoothly optimizing the initial path with the shortest path length, discretizing the obtained fitting curve, and establishing a corresponding weighted graph structure, the initial path with the shortest path length can be converted into a structure that can be optimized. By presetting the ant colony algorithm, the optimal path between the starting point and the end point is searched in the weighted graph structure. The redundant nodes therein can be removed by the optimization algorithm to improve the smoothness of the curve, thereby finding the optimal path. Through the coordination of the above steps, path generation, smoothing and optimization can be achieved, and the welding transition path of the welding robot can be effectively planned.

[0159] The initial path generated by the path planning algorithm is usually composed of discrete line segments with jagged turns. If it is not smoothed and the ant colony algorithm is used directly to find the optimal path, the path will become infeasible. The welding robot cannot execute a path containing sharp turns. The continuous curvature of the trajectory must be ensured to avoid mechanical vibration or affecting the welding process. It will also reduce the optimization of the path. The nodes generated by the path planning algorithm are distributed in a disorderly manner, and there will be a large number of invalid nodes and invalid edges. This will cause the convergence speed of the algorithm to drop significantly and the optimal path cannot be quickly obtained. In addition, the nodes generated by the path planning algorithm can lead to sparse node distribution or local over-density, and the directly converted graph structure is difficult to cover the potential optimization area.

[0160] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0161] The following are device embodiments of the present application. For details not fully described therein, please refer to the corresponding method embodiments described above.

[0162] Figure 7 The following is a schematic diagram of the structure of the welding robot path planning device provided in an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown, which are detailed as follows:

[0163] like Figure 7 As shown, the welding robot path planning device 70 includes:

[0164] An acquisition module 71 is used to acquire the starting point and the ending point of the welding robot during the welding transition process, as well as the position of obstacles in the welding environment;

[0165] A path generation module 72 is used to generate multiple initial paths according to the starting point, the end point and the position of the obstacle, and obtain the path length of each initial path;

[0166] A smoothing module 73 is used to perform smoothing optimization on the initial path with the shortest path length to obtain a smoothed path;

[0167] A graph structure module 74, for generating a weighted graph structure based on a smooth path;

[0168] Optimization module 75, used for searching the optimal path between the starting point and the end point in the weighted graph structure;

[0169] The determination module 76 is used to determine the welding transition path of the welding robot during the welding transition process based on the optimal path.

[0170] In one possible implementation, the obstacles include static obstacles and dynamic obstacles;

[0171] The path generation module 72 is specifically used for:

[0172] Predict the trajectory of dynamic obstacles based on their positions;

[0173] Based on the preset path planning algorithm, the positions of static obstacles and the motion trajectories of dynamic obstacles, multiple initial paths from the starting point to the end point are generated, and the path length of each initial path is obtained;

[0174] Among them, each time a new node is generated, the position prediction range of the dynamic obstacle corresponding to the new node is determined according to the motion trajectory of the dynamic obstacle, and based on the position prediction range, it is detected whether the path extending the new node has the risk of collision with the dynamic obstacle; if so, the new node is removed.

[0175] In one possible implementation, the initial path includes a plurality of nodes;

[0176] The smoothing module 73 is specifically used for:

[0177] Perform interpolation fitting based on the nodes of the initial path with the shortest path length to obtain a fitting curve;

[0178] Resampling is performed between the nodes of the fitting curve to obtain multiple new nodes;

[0179] Detect whether there is a curve segment on the fitting curve that does not meet the preset curvature constraint;

[0180] If there is a curve segment on the fitting curve that does not meet the curvature constraint, the nodes in the curve segment are adjusted; the fitting curve is regenerated based on all the adjusted nodes, and the step of "detecting whether there is a curve segment on the fitting curve that does not meet the preset curvature constraint" and subsequent steps are re-executed until the fitting curve meets the curvature constraint;

[0181] The fitted curve that satisfies the curvature constraint is taken as the smooth path.

[0182] In one possible implementation, the smooth path includes a plurality of nodes;

[0183] The graph structure module 74 is specifically used for:

[0184] Determine the node distance between any two nodes on the smooth path;

[0185] For any two nodes whose node distance is less than a preset node threshold, establish an edge connection between the two nodes;

[0186] The weight of each edge is determined based on the node distance between the two nodes of each edge and the curvature of the local path;

[0187] Based on each node, each edge and the weight of each edge of the smooth path, a weighted graph structure is generated.

[0188] In a possible implementation, the optimization module 75 is specifically configured to:

[0189] Based on the preset ant colony algorithm, the optimal path between the starting point and the end point is searched in the weighted graph structure;

[0190] In each iteration of the ant colony algorithm, the path taken by each ant is evaluated according to a preset path evaluation function; wherein the path evaluation function is determined based on the path length and path curvature of the path taken by the ant.

[0191] In one possible implementation, the preset ant colony algorithm includes a heuristic function and a pheromone update formula;

[0192] The heuristic function is determined based on the weight of each edge in the weighted graph structure;

[0193] The pheromone update formula is determined based on the pheromone of each edge in the previous iteration, the path length of each ant’s path, and the path curvature.

[0194] In a possible implementation, the determination module 76 is specifically configured to:

[0195] Determine the path length, path curvature, and distance to obstacles of the optimal path;

[0196] If the path length of the optimal path is greater than the path length of the smooth path, or the path curvature of the optimal path is greater than the path curvature of the smooth path, or the distance between the optimal path and the obstacle is less than the preset safety distance threshold, then the position of the obstacle in the welding environment is re-acquired, and the step of "generating multiple initial paths of the welding transition process according to the starting point, the end point and the position of the obstacle, and obtaining the path length of each initial path" and subsequent steps are performed until the obtained optimal path is qualified;

[0197] The qualified optimal path is used as the welding transition path of the welding robot in the welding transition process.

[0198] Figure 8 Schematic diagram of an electronic device provided in an embodiment of the present application. Figure 8 As shown, electronic device 80 of this embodiment includes a processor 81 and a memory 82. Memory 82 stores a computer program 83. When processor 81 executes computer program 83, it implements the steps of the aforementioned method embodiments. Alternatively, when processor 81 executes computer program 83, it implements the functions of the modules / units in the aforementioned device embodiments.

[0199] For example, the computer program 83 may be divided into one or more modules / units, which are stored in the memory 82 and executed by the processor 81 to implement the present application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 83 in the electronic device 80.

[0200] The electronic device 80 may include, but is not limited to, a processor 81 and a memory 82. Those skilled in the art will appreciate that Figure 8 This is merely an example of the electronic device 80 and does not constitute a limitation of the electronic device 80 . The electronic device 80 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0201] The processor 81 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0202] The memory 82 can be an internal storage unit of the electronic device 80, such as the hard drive or memory of the electronic device 80. The memory 82 can also be an external storage device of the electronic device 80, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the electronic device 80. Furthermore, the memory 82 can include both the internal storage unit of the electronic device 80 and an external storage device. The memory 82 is used to store computer programs and other programs and data required by the electronic device. The memory 82 can also be used to temporarily store data that has been output or is about to be output.

[0203] For the sake of convenience and brevity, the division of the above functional modules / units is only used as an example. In actual applications, the above functions can be assigned to different functional modules / units as needed. The above modules / units can be implemented in the form of hardware, software, or a combination of hardware and software.

[0204] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods in the above-mentioned method embodiments.

[0205] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the methods in the above-mentioned method embodiments.

[0206] The term "computer program" includes computer program code, which may be in source code form, object code form, executable file, or some intermediate form. Computer-readable media may include any entity or device capable of carrying computer program code, recording media, USB flash drives, removable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunications signals, and software distribution media.

[0207] In the above embodiments, the descriptions of each embodiment have their own focus. For parts not described or recorded in detail in one embodiment, please refer to the relevant descriptions of other embodiments. Unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features of different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0208] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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. 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 application, and should all be included in the scope of protection of the present application.

Claims

1. A welding robot path planning method, characterized in that: include: Obtain the starting and ending points of the welding robot during the welding transition process, as well as the locations of obstacles in the welding environment; Generate multiple initial paths according to the starting point, the ending point, and the position of the obstacle, and obtain the path length of each initial path; Perform smooth optimization on the initial path with the shortest path length to obtain a smooth path; Based on the smooth path, generating a weighted graph structure; Searching for an optimal path between the starting point and the ending point in the weighted graph structure; Based on the optimal path, determining a welding transition path of the welding robot during a welding transition process; The smooth path includes a plurality of nodes; Generating a weighted graph structure based on the smooth path includes: Determining a node distance between any two nodes on the smooth path; For any two nodes whose node distance is less than a preset node threshold, establishing an edge connection between the two nodes; The weight of each edge is determined based on the node distance between the two nodes of each edge and the curvature of the local path; A weighted graph structure is generated based on each node, each edge and the weight of each edge of the smooth path.

2. The welding robot path planning method according to claim 1, characterized in that: The obstacles include static obstacles and dynamic obstacles; The generating of multiple initial paths according to the starting point, the ending point, and the position of the obstacle, and obtaining the path length of each initial path, includes: Predicting a motion trajectory of the dynamic obstacle based on the position of the dynamic obstacle; Based on a preset path planning algorithm, the position of the static obstacle and the motion trajectory of the dynamic obstacle, generating multiple initial paths from the starting point to the end point, and obtaining the path length of each initial path; Each time a new node is generated, the position prediction range of the dynamic obstacle corresponding to the new node is determined based on the motion trajectory of the dynamic obstacle, and based on the position prediction range, it is detected whether the path extending the new node has the risk of collision with the dynamic obstacle; if so, the new node is removed.

3. The welding robot path planning method according to claim 1, characterized in that: The initial path includes a plurality of nodes; The step of performing smooth optimization on the initial path with the shortest path length to obtain a smooth path includes: Performing interpolation fitting according to the nodes of the initial path with the shortest path length to obtain a fitting curve; Resampling is performed between the nodes of the fitting curve to obtain a plurality of new nodes; Detecting whether there is a curve segment on the fitting curve that does not meet a preset curvature constraint; If there is a curve segment on the fitting curve that does not satisfy the curvature constraint, the nodes in the curve segment are adjusted; the fitting curve is regenerated based on all the adjusted nodes, and the step of "detecting whether there is a curve segment on the fitting curve that does not satisfy the preset curvature constraint" and subsequent steps are re-executed until the fitting curve satisfies the curvature constraint; The fitted curve that satisfies the curvature constraint is taken as the smooth path.

4. The welding robot path planning method according to any one of claims 1 to 3, characterized in that: The searching for the optimal path between the starting point and the ending point in the weighted graph structure includes: Based on a preset ant colony algorithm, searching for an optimal path between the starting point and the end point in the weighted graph structure; In each iteration of the ant colony algorithm, the path taken by each ant is evaluated according to a preset path evaluation function; wherein the path evaluation function is determined according to the path length and path curvature of the path taken by the ant.

5. The welding robot path planning method according to claim 4, characterized in that: The preset ant colony algorithm includes a heuristic function and a pheromone update formula; The heuristic function is determined according to the weight of each edge in the weighted graph structure; The pheromone update formula is determined based on the pheromone of each edge in the previous iteration, the path length and path curvature of the path taken by each ant.

6. The welding robot path planning method according to any one of claims 1 to 3, characterized in that: Determining the welding transition path of the welding robot during the welding transition process based on the optimal path includes: Determining the path length, path curvature, and distance from the obstacle of the optimal path; If the path length of the optimal path is greater than the path length of the smooth path, or the path curvature of the optimal path is greater than the path curvature of the smooth path, or the distance between the optimal path and the obstacle is less than a preset safety distance threshold, then the position of the obstacle in the welding environment is re-acquired, and the step of "generating multiple initial paths for the welding transition process based on the starting point, the end point, and the position of the obstacle, and obtaining the path length of each initial path" and subsequent steps are performed until the obtained optimal path is qualified; The qualified optimal path is used as the welding transition path of the welding robot in the welding transition process.

7. A welding robot path planning device, characterized in that: include: An acquisition module is used to obtain the starting point and ending point of the welding robot in the welding transition process, as well as the position of obstacles in the welding environment; A path generation module, configured to generate a plurality of initial paths according to the starting point, the ending point, and the position of the obstacle, and obtain the path length of each initial path; A smoothing module is used to perform smooth optimization on the initial path with the shortest path length to obtain a smooth path; A graph structure module, configured to generate a weighted graph structure based on the smooth path; An optimization module, configured to search for an optimal path between the starting point and the end point in the weighted graph structure; A determination module, configured to determine a welding transition path of the welding robot during a welding transition process based on the optimal path; The smooth path includes a plurality of nodes; The graph structure module is specifically used for: Determining a node distance between any two nodes on the smooth path; For any two nodes whose node distance is less than a preset node threshold, establishing an edge connection between the two nodes; The weight of each edge is determined based on the node distance between the two nodes of each edge and the curvature of the local path; A weighted graph structure is generated based on each node, each edge and the weight of each edge of the smooth path.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images