An additive manufacturing multi-robot path planning method based on collision prediction, device and medium

Abstract

The application discloses a kind of additive manufacturing multi-robot path planning methods, equipment and medium based on collision prediction, it is related to robot path planning field, the method comprises: obtaining the structure parameter of printing target;According to the structure parameter of printing target, the path planning of printing path is carried out using grid method, and preliminary optimization path is obtained;Real-time simulation simulation is carried out using the structure parameter of printing target and preliminary optimization path to printing trajectory, and real-time simulation simulation data is obtained;According to real-time simulation simulation data, printing collision prediction is carried out, and prediction result is obtained;According to prediction result, preliminary optimization path is adjusted, and optimal path planning is obtained.The application simplifies the calculation process of path planning under the printing scene of multi-robot, improves the accuracy and safety of multi-robot path planning, and then realizes the distributed collaborative work of multi-robot, improves the printing efficiency.

Description

Technical Field

[0001] This application relates to the field of robot path planning, and in particular to a method, device and medium for multi-robot path planning in additive manufacturing based on collision prediction. Background Technology

[0002] Arc additive manufacturing technology uses an electric arc as a heat source to melt metal wire and deposit it layer by layer along a pre-planned path to form three-dimensional solid metal components. It boasts advantages such as low manufacturing cost, high deposition efficiency, and large forming size, making it ideal for manufacturing large metal components. It has already begun to be applied in aerospace, marine, and automotive fields, and the requirements for product precision and manufacturing efficiency are gradually increasing. Currently, arc additive manufacturing lacks a mature path planning and simulation system. Setting and adjusting path parameters for different printed structures requires significant manual intervention, heavily relying on operator experience and knowledge, resulting in long manufacturing cycles. Therefore, its manufacturing cost, manufacturing precision, product quality, and automation level all face challenges.

[0003] Currently, multi-robot collaborative additive manufacturing technology refers to the use of multiple robots or automated equipment to work collaboratively to achieve additive manufacturing of large and complex metal components. However, due to the involvement of multiple heat sources and multiple processes, the calculation and design of path planning become more complex. In terms of task allocation and basic synchronous operation of multiple robots, there is a lack of integrated mechanisms for mutual coupling and correlation. The designed paths often have the risk of collision, and the accuracy and safety are generally not high. Summary of the Invention

[0004] The purpose of this application is to provide a collision prediction-based additive manufacturing multi-robot path planning method, device, and medium, which can simplify the path planning calculation process in multi-robot printing scenarios, improve the accuracy and safety of multi-robot path planning, realize distributed collaborative work of multiple robots, and improve printing efficiency.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] Firstly, this application provides a collision prediction-based multi-robot path planning method for additive manufacturing. This method is applied to a multi-robot additive printing platform and includes: acquiring the structural parameters of the printing target; performing path planning on the printing path using a grid method based on the structural parameters of the printing target to obtain a preliminary optimized path; the preliminary optimized path includes the coordinate information of the grid paths of multiple robots; using the structural parameters of the printing target and the preliminary optimized path to perform real-time simulation of the printing trajectory to obtain real-time simulation data; performing printing collision prediction based on the real-time simulation data to obtain a prediction result; when the prediction result indicates a collision, adjusting the preliminary optimized path according to the location of the collision, updating the preliminary optimized path, and returning "using the structural parameters of the printing target and the preliminary optimized path to perform real-time simulation of the printing trajectory to obtain real-time simulation data"; when the prediction result indicates no collision, continuing collision prediction until printing ends to obtain the optimal path planning.

[0007] Secondly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described additive manufacturing multi-robot path planning method based on collision prediction.

[0008] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described collision prediction-based additive manufacturing multi-robot path planning method.

[0009] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0010] This application simplifies the path planning calculation process in multi-robot printing scenarios by using a grid method for path planning of multiple robots. It obtains real-time simulation data through simulation and performs collision prediction based on the real-time simulation data. The preliminary optimized path is continuously corrected and updated based on the collision prediction results until the collision prediction ends, and the optimal path planning is obtained. This improves the accuracy and safety of multi-robot path planning, thereby realizing distributed collaborative work of multiple robots and improving printing efficiency. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating a collision prediction-based multi-robot path planning method for additive manufacturing, provided in this application embodiment. Figure 1 .

[0013] Figure 2 A flowchart illustrating a collision prediction-based multi-robot path planning method for additive manufacturing, provided in this application embodiment. Figure 2 .

[0014] Figure 3 This is a top view of the multi-robot additive printing platform provided in an embodiment of this application.

[0015] Figure 4 A schematic diagram of the placement of printing targets provided in the embodiments of this application. Figure 1 .

[0016] Figure 5 A schematic diagram of the placement of printing targets provided in the embodiments of this application. Figure 2 .

[0017] Figure 6 A schematic diagram of the placement of printing targets provided in the embodiments of this application. Figure 3 .

[0018] Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] Example 1, as Figures 1-3As shown, this embodiment provides a collision prediction-based multi-robot path planning method for additive manufacturing. This collision prediction-based multi-robot path planning method is applied to a multi-robot additive printing platform. The collision prediction-based multi-robot path planning method includes:

[0022] S1. Obtain the structural parameters of the printing target.

[0023] Optionally, when the structure of the printing target is a lattice structure, the structural parameters include: lattice length, lattice width, lattice cell size, and number of printing layers.

[0024] S2. Based on the structural parameters of the printing target, the grid method is used to plan the printing path to obtain a preliminary optimized path; the preliminary optimized path includes the coordinate information of the grid paths of multiple robots.

[0025] Furthermore, step S2 specifically includes:

[0026] S21. List the placement methods of the printing target according to the structural parameters of the printing target; the placement methods include a first placement method and a second placement method; the first placement method is a placement method in which the longest side of the printing area of ​​the multi-robot additive printing platform is parallel to the longest side of the printing target; the second placement method is a placement method in which the longest side of the printing area of ​​the multi-robot additive printing platform is perpendicular to the longest side of the printing target.

[0027] Optional, such as Figure 4 As shown, the formulas for calculating the target number of columns and rows to be printed in the first layout mode are as follows:

[0028]

[0029] Where, N c To print the target number of columns, N r To print the target number of lines, n c To print the number of dots along the length of the target, n r This specifies the number of dots in the upper part of the target width direction for printing.

[0030] like Figure 5 As shown, the formulas for calculating the target number of columns and rows to be printed in the second layout are as follows:

[0031]

[0032] Where, N c To print the target number of columns, N r To print the target number of lines, n c To print the number of dots along the length of the target, n rThis specifies the number of dots in the upper part of the target width direction for printing.

[0033] In practical applications: such as Figure 6 As shown, when the shortest side of the printing area of ​​the multi-robot additive printing platform is less than the shortest length of the printing target in the first placement method (i.e., the printing area of ​​the multi-robot additive printing platform cannot be placed in the second placement method), the placement method of the printing target only exists in the first placement method.

[0034] S22. Under different placement methods, the structural parameters are converted into grid information using the number of welding gun heads of each robot to obtain first grid information and second grid information; the first grid information is the grid size corresponding to the printing area of ​​each robot under the first placement method; the second grid information is the grid size corresponding to the printing area of ​​each robot under the second placement method.

[0035] Furthermore, the structural parameters are converted into grid information using the number of welding torch heads of each robot, specifically including:

[0036] The total grid size is calculated based on the structural parameters using the number of welding torches on each robot. The total grid size includes the total number of grid rows and the total number of grid columns. Specifically, each robot's robotic arm carries a row of welding torches.

[0037] The formula for calculating the total grid size is as follows:

[0038]

[0039] In the formula, R r This represents the total number of raster rows. To round up, R c Let N be the total number of grid columns, n be the number of welding torch heads for each robot, and N be the total number of columns. c To print the target number of columns, N r Set the target number of rows to print.

[0040] The printing area is divided according to the total grid size, with the goal of ensuring that each robot prints an equal area (with equal printing time). The sub-grid size corresponding to the printing area of ​​each robot is obtained as grid information. The sub-grid size includes the number of sub-grid rows and the number of sub-grid columns.

[0041] The formula for calculating the sub-grid size is as follows:

[0042]

[0043] In the formula, R ri Let R be the number of grid rows corresponding to the printing area of ​​robot i, where i∈[2,m] and m is the number of robots; ci R is the number of grid columns corresponding to the printing area of ​​robot i; rThis represents the total number of raster rows. To round down; R c This represents the total number of raster columns.

[0044] Optionally, when m = 3, R c1 R c3 The value is an integer rounded down, R c2 =R c -R c1 -R c3 .

[0045] S23. Based on the first grid information and the second grid information, the number of steps of the reciprocating path of the printing robot under each placement method is calculated using the grid method.

[0046] S24. Under each placement method, select the reciprocating path with the fewest steps as the motion path of the printing robot.

[0047] S25. Generate a printing path based on the structural parameters of the printing target.

[0048] S26. Construct a preliminary optimized path using the motion path and the printing path.

[0049] Optionally, after step S2, the method further includes: visualizing the preliminary optimized path and generating a preview image of the preliminary optimized path; the preview image of the preliminary optimized path specifically includes at least: the printing starting point of each robot, the running direction of each robot, and the motion trajectory of each robot.

[0050] Optionally, the initial optimization path can be in the form of executable CNC code.

[0051] S3. Using the structural parameters of the printing target and the path optimization, perform real-time simulation of the printing trajectory to obtain real-time simulation data.

[0052] Step S3 specifically includes:

[0053] S31. Construct a simulation model using the structural parameters of the printing target; the simulation model includes: mobile device models of multiple robots, printing target model and droplet preform; the droplet preform is used to simulate the droplets in the printing process; the mobile device includes at least: welding torch head, welding torch head fixture, wire feed tube, wire feed tube fixture, monitoring camera and monitoring camera fixture.

[0054] S32. The process of instantiating the molten droplet preform is used to simulate the arc initiation, wire feeding, and arc extinguishing operations, and the printing process is simulated in real time to obtain real-time printing simulation data.

[0055] S33. Simulate the positional movement between multiple mobile device models of robots and the target model using the preliminary optimized path, and perform real-time simulation of the movement process to obtain real-time movement simulation data.

[0056] S34. Construct real-time simulation data based on real-time printing simulation data and real-time movement simulation data.

[0057] In practical applications, a simulation model is used to predict collisions between multiple robots and the printing target using a multi-robot collaborative approach. During the printing process, collisions may occur between the mobile device models of multiple robots (additive manufacturing mobile devices) and the printing target. If the mobile device models of multiple robots pass through the printing area or travel path of other robots, collisions between devices may occur. If such collisions are predicted, the preliminary optimized path (CNC code) is modified until there are no collisions during the entire printing process. If the simulation is successful, the preliminary optimized path (CNC code) is sent to the robot.

[0058] During the simulation, as each welding torch head moves, real-time three-dimensional coordinate information of the bottom of the welding torch head is acquired every 0.02 seconds. Based on the actual distance (arc length) between the welding torch head and the molten pool during the experiment, the center point of the preform generation is set to satisfy:

[0059] Z b -Z c =6~7mm.

[0060] Among them, Z b Z is the z-coordinate of the bottom of the welding torch head. c The z-coordinate is the center point of the precast structure.

[0061] Design a droplet preform (a spherical preform to simulate the shape of a droplet). The droplet preform is continuously instantiated based on the acquired three-dimensional coordinate information. Design a switch for the preform instantiation to simulate the arc initiation, wire feeding, and arc extinguishing operations in actual situations. Since the droplet preform is continuously generated during this process, and the spacing between the various positional information is very small, the continuous instantiation of the droplet preform forms a continuous trajectory, realizing the simulation of the visual printing trajectory.

[0062] S4. Based on real-time simulation data, perform print collision prediction and obtain the prediction results.

[0063] Step S4 specifically includes:

[0064] A spherical collider is constructed in the simulation model based on the radius of the molten droplet preform.

[0065] Based on real-time simulation data, a spherical collider is used to predict the target distance for real-time printing collision. If the target distance is less than or equal to the diameter of the spherical collider, the prediction result is that a collision has occurred; if the target distance is greater than the diameter of the spherical collider, the prediction result is that no collision has occurred. The target distance is the distance between robot models or the distance between a robot model and the printing target model.

[0066] Furthermore, the formula for calculating the radius of the spherical collider is as follows:

[0067] R s =1.1×R m .

[0068] In the formula, R s R is the radius of the spherical collider. m denoted as the radius of the droplet preform.

[0069] In step 6, collision prediction, such as detecting collisions between multiple robot mobile device models (welding torch head, welding torch head fixture, wire feed tube, wire feed tube fixture, monitoring camera, and monitoring camera fixture) and the printing target model during the printing process, uses mesh collision detection: based on the colliding objects, i.e., the mobile device models of multiple robots, their surfaces are divided into meshes to generate the mobile device mesh, and the mobile device mesh is made to coincide with the mobile device model. The mesh collider function built into the simulation engine is added to the mobile device model of each robot, and the corresponding spherical collider component is configured in the settings panel of the mobile device object. Since the printing structure is generated in real time during program execution, it is not possible to directly use the mesh collider function built into the simulation engine for configuration. Therefore, the corresponding code is added to the instantiation of the droplet preform script to complete the required configuration, thereby realizing a physics-based collision detection mechanism. When the mobile device model comes into contact with the printing structure model, the corresponding callback function is triggered to realize the function of popping up a text prompt box after a collision and the function of stopping the machine tool.

[0070] S5. When the prediction result is that a collision has occurred, adjust the preliminary optimized path according to the location of the collision, update the preliminary optimized path, and return to step S3. When the prediction result is that no collision has occurred, continue to perform collision prediction until the printing ends, and obtain the optimal path planning.

[0071] The technical effects of this application are as follows:

[0072] This application simplifies the path planning calculation process in multi-robot printing scenarios by utilizing a grid method for path planning of multiple robots. Real-time simulation data is obtained through simulation, and collision prediction is performed based on this data. The initial optimized path is continuously corrected and updated based on the collision prediction results until the collision prediction ends, resulting in the optimal path plan. This improves the accuracy and safety of multi-robot path planning, thereby enabling distributed collaborative work among multiple robots and increasing printing efficiency. Specifically, this application performs path planning for the 3D additive manufacturing process. Through reasonable path design, unnecessary robot movements are reduced, thus shortening printing time. Simultaneously, distributed collaborative work among multiple robots allows for effective task allocation for each robot, significantly improving printing efficiency. Reducing manual path adjustments and controlling accumulated errors improves the quality of printed products. Through 3D simulation, engineers can intuitively and dynamically observe the machine's movement status and the entire printing process. When printing errors or welding machine collisions occur, the CNC code can be adjusted promptly, reducing the cost of traditional trial-and-error experiments and improving the utilization rate of printing materials and the success rate of printing. The entire process is highly integrated, simple to operate, and highly versatile, reducing the preliminary work for engineers and lowering the difficulty of three-dimensional spatial structure arc additive manufacturing. Motion and trajectory simulations are performed on the CNC code to predict potential collisions, avoiding collisions between the welding torch and other mobile equipment and structural components during actual printing, thus increasing printing safety.

[0073] Example 2: This application also provides a computer device, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores and processes data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When executed by the processor, the computer program implements a collision prediction-based additive manufacturing multi-robot path planning method.

[0074] Those skilled in the art will understand that Figure 7The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0075] Example 3: This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0076] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0077] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0078] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A collision prediction-based multi-robot path planning method for additive manufacturing, wherein the collision prediction-based multi-robot path planning method is applied to a multi-robot additive printing platform, characterized in that, The additive manufacturing multi-robot path planning method based on collision prediction includes: Obtain the structural parameters of the printing target; Based on the structural parameters of the printing target, a grid method is used to plan the printing path to obtain a preliminary optimized path; the preliminary optimized path includes the coordinate information of the grid paths of multiple robots; Using the structural parameters of the printing target and [other parameters], a preliminary path optimization was performed to conduct real-time simulation of the printing trajectory, obtaining real-time simulation data, specifically including: A simulation model is constructed using the structural parameters of the printing target; the simulation model includes: mobile device models of multiple robots, a printing target model, and a droplet preform; the droplet preform is used to simulate the droplets during the printing process; the mobile device includes at least: a welding torch head, a welding torch head clamp, a wire feed tube, a wire feed tube clamp, a monitoring camera, and a monitoring camera clamp; The process of instantiating the molten droplet preform is used to simulate the arc initiation and wire feeding and the arc extinguishing and wire stopping operations. The printing process is simulated in real time to obtain real-time printing simulation data. The positional movement between multiple mobile device models of robots and the target model is simulated using preliminary optimized paths. The movement process is simulated in real time to obtain real-time movement simulation data. Real-time simulation data is constructed based on real-time printing simulation data and real-time movement simulation data; Printing collision prediction is performed based on real-time simulation data to obtain prediction results; When the prediction result indicates a collision, the preliminary optimized path is adjusted based on the location of the collision, the preliminary optimized path is updated, and the "real-time simulation of the printing trajectory is performed using the structural parameters of the printing target and the preliminary optimized path to obtain real-time simulation data" is returned. When the prediction result indicates no collision, collision prediction continues until printing ends, and the optimal path planning is obtained. Based on the structural parameters of the printing target, a raster method is used to plan the printing path, resulting in a preliminary optimized path, which includes: List the placement methods of the printing target based on the structural parameters of the printing target; the placement methods include a first placement method and a second placement method; the first placement method is a placement method in which the longest side of the printing area of ​​the multi-robot additive printing platform is parallel to the longest side of the printing target; the second placement method is a placement method in which the longest side of the printing area of ​​the multi-robot additive printing platform is perpendicular to the longest side of the printing target. Under different placement methods, the structural parameters are converted into grid information using the number of welding gun heads of each robot, resulting in first grid information and second grid information. The first grid information is the grid size corresponding to the printing area of ​​each robot under the first placement method; the second grid information is the grid size corresponding to the printing area of ​​each robot under the second placement method. Based on the first grid information and the second grid information, the number of steps of the reciprocating path of the printing robot under each placement method is calculated using the grid method. Under each placement method, the reciprocating path with the fewest steps is selected as the motion path of the printing robot; Generate a printing path based on the structural parameters of the printing target; Construct an initial optimized path using motion paths and printing paths; The structural parameters are converted into grid information using the number of welding torch heads on each robot, specifically including: The total grid size is calculated based on the structural parameters using the number of welding torch heads for each robot; the total grid size includes: the total number of grid rows and the total number of grid columns; The printing area is divided according to the total grid size with the goal of ensuring that the printing area of ​​each robot is equal. The sub-grid size corresponding to the printing area of ​​each robot is obtained as grid information. The sub-grid size includes the number of sub-grid rows and the number of sub-grid columns. The formula for calculating the total grid size is as follows: ； In the formula, This represents the total number of raster rows. To round up, This represents the total number of raster columns. The number of welding torch heads for each robot, To print the target number of columns, To print the target number of rows; The formula for calculating the sub-grid size is as follows: ； In the formula, For robots The number of raster rows corresponding to the print area. , The number of robots; For robots The number of grid columns corresponding to the printing area; This represents the total number of raster rows. To round down; This represents the total number of raster columns.

2. The additive manufacturing multi-robot path planning method based on collision prediction according to claim 1, characterized in that, Based on real-time simulation data, print collision prediction is performed to obtain the prediction results, which include: A spherical collider is constructed in the simulation model based on the radius of the molten droplet preform. Based on real-time simulation data, a spherical collider is used to predict the target distance for real-time printing collision. If the target distance is less than or equal to the diameter of the spherical collider, the prediction result is that a collision has occurred; if the target distance is greater than the diameter of the spherical collider, the prediction result is that a collision has not occurred. The target distance is the distance between robot models or the distance between a robot model and the printing target model.

3. The additive manufacturing multi-robot path planning method based on collision prediction according to claim 2, characterized in that, The formula for calculating the radius of the spherical collider is as follows: ； In the formula, Let be the radius of the spherical collider. denoted as the radius of the droplet preform.

4. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the additive manufacturing multi-robot path planning method based on collision prediction as described in any one of claims 1-3.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the additive manufacturing multi-robot path planning method based on collision prediction as described in any one of claims 1-3.

Images