Simulation teaching robot spraying and paint spraying self-learning method based on programming-free

Abstract

The invention discloses a programming-free simulation teaching robot spraying paint spraying self-learning method, and belongs to the technical field of spraying teaching, and the method specifically comprises the steps: carrying out n times of simulation teaching paint spraying on products of the same type, generating corresponding simulation teaching tracks, and dividing the surface of a painted product into a plurality of areas; for any time of simulation teaching paint spraying, obtaining a corresponding time period from paint spraying starting to paint spraying ending of each product area in the simulation teaching paint spraying process, and intercepting a corresponding sub-track; for any product area, calculating the score of each simulation teaching paint spraying according to the paint spraying index, selecting the simulation teaching paint spraying with the highest score, marking the simulation teaching paint spraying as the optimal teaching of the product area, and marking the sub-track of the optimal teaching as the optimal sub-track of the area; and combining the optimal sub-tracks corresponding to all the product areas, and smoothing the joints of the sub-tracks to obtain an optimal simulation teaching track.

Description

Technical Field

[0001] The invention relates to the technical field of spraying teaching, and in particular to a spraying and painting self-learning method of a simulation teaching robot based on programming-free teaching. Background Art

[0002] With the continuous development of automation technology, robots are increasingly used in industrial production. Especially in the field of spraying, robot spraying technology has gradually replaced the traditional manual spraying method, improving production efficiency and product quality. The existing robot spraying and painting method requires on-site industrial robot software programming and on-site position trajectory teaching of the spraying and painting path. The teaching time is long, the technical requirements of personnel are high, and professional programming technicians are required on site, which affects the switching and debugging efficiency and requires high labor costs.

[0003] Therefore, a programming-free simulation teaching method came into being. On-site operators only need to hold a simulation teaching pendant to demonstrate the spraying and painting path. The system can automatically learn and complete the spraying and painting path teaching required by the robot. No professional programming skills are required to quickly complete the spraying and painting teaching. Make the robot spraying and painting application simple and fast, and let the robot replace manual spraying and painting operations.

[0004] Since the spraying and painting path still requires manual simulation teaching, and since there are differences in the levels of the same skilled worker or between different skilled workers, determining the robot's spraying and painting path by relying solely on a single simulation teaching cannot achieve the best product painting effect. Therefore, it is necessary to analyze multiple simulation teaching paths to obtain the optimal robot spraying and painting path. Summary of the invention

[0005] The purpose of the present invention is to provide a self-learning method for spraying paint by a simulation teaching robot based on programming-free, so as to solve the following technical problems:

[0006] The spraying and painting path still requires manual simulation teaching. However, due to the differences in the levels of the same skilled worker or between different skilled workers, determining the robot's spraying and painting path by relying solely on a single simulation teaching cannot achieve the best product painting effect.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] The method for self-learning spray painting of a simulation teaching robot based on programming-free includes the following steps:

[0009] Perform n simulated teaching spray painting on the same type of product, where n is a positive integer, and generate corresponding simulated teaching trajectories to divide the surface of the product to be painted into several areas;

[0010] For any simulated teaching painting, obtain the time period corresponding to each product area from the start of painting to the end of painting during the simulated teaching painting process, and intercept the sub-trajectory corresponding to each time period of the simulated teaching trajectory;

[0011] For any product area, a painting index is obtained according to the product surface image, and a score of each simulated painting teaching is calculated according to the painting index. The simulated painting teaching with the highest score is selected, and the simulated painting teaching is marked as the best teaching of the product area, and the sub-trajectory of the best teaching is marked as the best sub-trajectory of the area;

[0012] The best sub-trajectories corresponding to all product areas are merged, and the connections of the sub-trajectories are smoothed to obtain the best simulation teaching trajectory.

[0013] As a further solution of the present invention: the distribution method of the n times of simulated teaching of spray painting includes multiple teachings by a single person, single teaching by multiple people, and multiple teaching by multiple people.

[0014] As a further solution of the present invention, the specific process of dividing the surface of the painted product into several areas is as follows:

[0015] The product surface is divided according to the structure, the areas on the same smooth surface are marked as the same initial area, the initial area with an area greater than the set threshold max is divided into several areas less than the set threshold, and the adjacent initial areas with an area less than the set threshold min are merged into one area.

[0016] As a further solution of the present invention: the specific process of obtaining the time period corresponding to the start and end of the painting of each product area during the simulated teaching painting process is:

[0017] Monitor the area ratio of any area covered by paint in real time, and calculate the rate of change of the area ratio over time. When both the area ratio and the rate of change are greater than the set threshold, it is determined that the area has started to be painted, and the current time t1 is recorded;

[0018] When the area ratio of the area being painted reaches 100%, the topcoat ratio and change rate of other areas are obtained. When the area ratio and change rate of other areas are greater than the set threshold, it is determined that the area is finished painting and the current time t2 is recorded;

[0019] The time period between time t1 and time t2 is marked as the painting time period corresponding to the area.

[0020] As a further solution of the present invention: obtaining the painting index according to the product surface image specifically includes:

[0021] Based on computer vision technology, the color difference, glossiness, coating flatness, coating thickness and number of defects of the product surface paint are collected.

[0022] As a further solution of the present invention: the process of calculating the score of each simulated teaching painting according to the painting index is:

[0023] The painting index is converted into a quantitative index X according to the percentage difference between the painting index and the set index, and an n×m matrix is ​​constructed based on the quantitative index X, where m represents the number of quantitative indexes X, and the jth quantitative index X of the i-th simulated teaching painting is calculated. ij The Euclidean distance Po between the minimum value of the same type of quantitative indicators i , and the quantitative index X ij The Euclidean distance Ne between the maximum value of the same type of quantitative index i , X ij Indicates that i∈n, j∈m, and the calculation formula of Euclidean distance is:

[0024]

[0025] For any product area, the score S of the i-th simulated teaching painting is i The calculation formula is:

[0026]

[0027] As a further solution of the present invention: the specific process of merging the best sub-trajectories corresponding to all product areas to obtain the best simulation teaching trajectory is:

[0028] For any product area, select the sub-trajectories corresponding to the N simulation teaching painting with the highest score ranking, mark them as pending sub-trajectories, N < n, count the pending sub-trajectories of all product areas, and obtain the simulation teaching painting to which each optimized sub-trajectory belongs. If the number of pending sub-trajectories of any simulation teaching painting accounts for less than 50% of the total number, then all the best sub-trajectories are time-sorted to generate a trajectory sequence, and the trajectory sequences are merged in turn to obtain the best simulation teaching trajectory;

[0029] If more than 50% of the pending sub-trajectories belong to the same simulation teaching painting, all sub-trajectories of the simulation teaching painting are marked as preferred sub-trajectories. For the remaining best sub-trajectories in the trajectory sequence except the preferred sub-trajectory, if there is any other best sub-trajectory whose before and after time periods are both the preferred sub-trajectory, then the remaining best sub-trajectory in the trajectory sequence is replaced by the preferred sub-trajectory of the same time period, and the replaced trajectory sequences are merged in sequence to obtain the best simulation teaching trajectory.

[0030] As a further solution of the present invention, the process of smoothing the connection of the sub-trajectories is as follows:

[0031] Create an overlapping area at the connection of the sub-trajectories, obtain the extension lines of the two sub-trajectories in the overlapping area, assign weights to the two sub-trajectories according to the ratio of the scores of the two sub-trajectories, perform weighted averaging on the sub-trajectory coordinate points in the overlapping area, take the weighted average of the two sub-trajectory coordinate points in the overlapping area, and generate the coordinates of the overlapping trajectory.

[0032] Beneficial effects of the present invention:

[0033] The present invention generates a corresponding simulation teaching trajectory through multiple simulation teaching spraying. For any simulation teaching spraying, the time period corresponding to each product area from the beginning to the end of the spraying during the simulation teaching spraying is obtained, and the sub-trajectory corresponding to each time period of the simulation teaching trajectory is intercepted. Then, the spraying index is obtained according to the product surface image, the score of each simulation teaching spraying is calculated, the simulation teaching spraying with the highest score is selected, and the simulation teaching spraying is marked as the best teaching of the product area, and the sub-trajectory of the best teaching is marked as the best sub-trajectory of the area. Finally, the best sub-trajectories corresponding to all product areas are merged, and the connection of the sub-trajectories is smoothed to obtain the best simulation teaching trajectory; through multiple simulation teaching spraying, the best spraying trajectory can be automatically learned; the spraying index is obtained according to the product surface image, and an accurate spraying effect can be achieved; the best sub-trajectories corresponding to all product areas are merged, and the connection of the sub-trajectories is smoothed to ensure the continuity and stability of the spraying trajectory. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present invention will be further described below in conjunction with the accompanying drawings.

[0035] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] See also Figure 1 As shown, the present invention is a self-learning method for spraying paint by a simulation teaching robot based on programming-free, comprising the following steps:

[0038] Staffing: First, we will assign 10 experienced workers to participate in this project. Each worker will be responsible for performing 3 simulated teaching spray painting tasks on the same type of product, completing a total of 30 operations. This will not only ensure data diversity, but also reduce the impact of accidental errors through multiple repetitions.

[0039] Simulation teaching and trajectory generation: During each simulation teaching, workers need to follow the established process and use relevant equipment to record the path of the spray gun movement during the entire process (i.e., simulation teaching trajectory). These trajectory data are crucial for subsequent analysis because they directly reflect the best practices in actual operations and possible room for improvement.

[0040] Surface area division:

[0041] After collecting enough simulation teaching information, the next step is to conduct a detailed structural analysis of the product surface. The entire surface is subdivided into multiple smaller parts or "initial regions" according to its geometric characteristics. It should be noted here that all parts on the same smooth surface should be classified into the same region.

[0042] Next, a maximum area threshold value max is set. If the area of ​​an initial region exceeds this value, it is further divided into several smaller sub-regions until each newly formed region meets the requirement of being less than or equal to max. The purpose of this is to ensure the uniformity of the coating thickness and avoid affecting the overall effect due to local excessive thickness.

[0043] At the same time, the minimum area threshold min should also be considered. For those initial areas that are small but adjacent to each other and whose total area does not exceed min, they can be merged into a larger single area for processing. This helps to simplify the subsequent programming logic and also better control the spraying quality at the edge.

[0044] Final partition result: After the above steps, we can get a complete coverage solution consisting of several small areas that meet specific conditions (such as area size, shape, etc.). The specific spraying parameters (such as speed, distance, etc.) in each small area can be adjusted individually according to the actual situation to achieve the best coating effect.

[0045] Real-time monitoring of area ratio and change rate:

[0046] During each simulated teaching painting process, high-precision sensors and image recognition technology are used to monitor the proportion of each area covered by paint in real time. These sensors can accurately capture the distribution of paint on the product surface and transmit the data to the control system in real time.

[0047] At the same time, the rate of change of the area ratio of each area over time is calculated. This indicator reflects the speed and uniformity of painting and is crucial for adjusting the spraying parameters.

[0048] Start painting judgment:

[0049] Set an area ratio threshold and a change rate threshold. When both the area ratio and the change rate of a certain area exceed these two thresholds, the system automatically determines that the area starts painting and records the current time t1. This step ensures that the painting operation will only be started when specific conditions are met, thereby avoiding quality problems caused by spraying too early or too late.

[0050] End of painting judgment:

[0051] When the painted area ratio of a certain area reaches 100%, the system will check the topcoat ratio and change rate of other areas. If the area ratio and change rate of all other areas also exceed the preset threshold, the area is judged to be finished painting and the current time t2 is recorded. This ensures that the entire product surface is evenly sprayed without omission or repeated spraying.

[0052] Painting time period marking and trajectory interception:

[0053] The time period between time t1 and time t2 is marked as the painting time period corresponding to the area. The data during this period will be used for subsequent analysis and optimization.

[0054] The sub-trajectories corresponding to each painting time period are intercepted from the simulated teaching trajectory. These sub-trajectories represent the movement path of the spray gun during the actual spraying process and can be used to evaluate the spraying effect, adjust parameters, and train the automation system.

[0055] Index detection:

[0056] For any product area, using advanced computer vision technology, the system will automatically collect and analyze multiple key quality indicators of product surface painting. These indicators include but are not limited to color difference, glossiness, coating flatness, coating thickness, and number of defects. Through high-precision cameras and image recognition algorithms, the system can monitor the painting effect of each product area in real time to ensure that the color is consistent with the standard sample, the glossiness meets the predetermined requirements, the coating surface is smooth without bumps and unevenness, the coating thickness is uniform and meets the design specifications, and any possible defects such as scratches, bubbles or impurities are accurately detected.

[0057] Quantitative indicator conversion:

[0058] First, we need to convert the key performance indicators of the painting process into quantitative indicators. These quantitative indicators are calculated based on the percentage difference between the actual measured value and the preset target value. Specifically, if the actual value of a certain indicator is A and the preset target value is T, the quantitative indicator X can be expressed as:

[0059] X = |AT| / T×100%;

[0060] Suppose we have n simulated teaching spray painting, and each spray painting has m quantitative indicators X. We organize these quantitative indicators into an n×m matrix, where each row represents all the quantitative indicators of a simulated teaching spray painting, and each column represents the value of a specific quantitative indicator in all simulated teaching spray painting.

[0061] Calculate the Euclidean distance:

[0062] For each element X in the matrix ij (represents the jth quantitative index of the i-th simulated teaching painting), we calculate the Euclidean distance Po between it and the minimum value of the same type of quantitative index i , and the Euclidean distance Ne from the maximum value i The calculation formula of Euclidean distance is:

[0063]

[0064] For any product area, the score S of the i-th simulated teaching painting is i The calculation formula is:

[0065]

[0066] This formula takes into account the relative closeness of each quantitative metric to the best and worst case scenarios to give an overall score.

[0067] According to the above scoring system, we can find the highest-scoring simulation teaching spray painting. This simulation teaching spray painting will be marked as the best teaching for this product area. Correspondingly, the sub-track of this simulation teaching spray painting will also be marked as the best sub-track for this area.

[0068] Select pending sub-trajectories: For any product area, select the sub-trajectories corresponding to the highest N simulated teaching spray painting according to the score sorting, and mark them as pending sub-trajectories. Here N is less than the total number of simulated teaching spray painting n, to ensure that we only consider the highest-scoring teachings.

[0069] Count pending sub-trajectories: Count the pending sub-trajectories of all product areas, and obtain the simulated teaching painting to which each optimized sub-trajectory belongs. This step is to understand which simulated teaching painting is selected as a pending sub-trajectory in multiple product areas.

[0070] Determine the preferred sub-trajectory: If the number of pending sub-trajectories in any simulation teaching painting accounts for less than 50% of the total number, all the best sub-trajectories are time-sorted to generate a trajectory sequence, and the trajectory sequences are merged in sequence to obtain the best simulation teaching trajectory. This means that if no simulation teaching painting dominates all product areas, we will generate the final best simulation teaching trajectory by merging all the best sub-trajectories.

[0071] Handling more than 50% of the cases: If more than 50% of the pending sub-trajectories belong to the same simulation teaching painting, all sub-trajectories of the simulation teaching painting will be marked as preferred sub-trajectories. For the remaining best sub-trajectories in the trajectory sequence except the preferred sub-trajectory, if there is any other best sub-trajectory whose time periods before and after are both the preferred sub-trajectory, then the remaining best sub-trajectory in the trajectory sequence will be replaced with the preferred sub-trajectory of the same time period, and the replaced trajectory sequences will be merged in sequence to obtain the best simulation teaching trajectory. This step ensures that when a simulation teaching painting performs well in multiple product areas, its sub-trajectories will be given priority and used to generate the best simulation teaching trajectory.

[0072] Create overlapping areas: Create an overlapping area at the connection of the sub-trajectories, obtain the extension lines of the two sub-trajectories in the overlapping area, assign weights to the two sub-trajectories according to the ratio of the scores of the two sub-trajectories, perform weighted averaging on the coordinate points of the sub-trajectory in the overlapping area, take the weighted average of the coordinate points of the two sub-trajectory in the overlapping area, generate the coordinates of the overlapping trajectory, smooth the connection of the sub-trajectories, and obtain the best simulation teaching trajectory. This step is to ensure that the transition between sub-trajectories is natural and smooth to avoid abrupt jumps or faults.

[0073] In this way, we can not only ensure the spraying quality of each area, but also significantly improve the efficiency and consistency of the entire production process. At the same time, this data-based optimization method also lays the foundation for more advanced production automation in the future.

[0074] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0075] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0076] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0077] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0078] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0079] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0081] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0082] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

[0083] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A self-learning method for spray painting based on a programming-free simulation teaching robot, characterized in that: The following steps are involved: Perform n simulated teaching spray painting on the same type of product, where n is a positive integer, and generate corresponding simulated teaching trajectories to divide the surface of the product to be painted into several areas; For any simulated teaching painting, obtain the time period corresponding to each product area from the start of painting to the end of painting during the simulated teaching painting process, and intercept the sub-trajectory corresponding to each time period of the simulated teaching trajectory; For any product area, a painting index is obtained according to the product surface image, and a score of each simulated painting teaching is calculated according to the painting index. The simulated painting teaching with the highest score is selected, and the simulated painting teaching is marked as the best teaching of the product area, and the sub-trajectory of the best teaching is marked as the best sub-trajectory of the area; The best sub-trajectories corresponding to all product areas are merged, and the connections of the sub-trajectories are smoothed to obtain the best simulation teaching trajectory.

2. The method for self-learning spray painting based on a programming-free simulation teaching robot according to claim 1 is characterized in that: The allocation method of the n times of simulated teaching spray painting includes multiple teaching by one person, single teaching by multiple people, and multiple teaching by multiple people.

3. The self-learning method for spray painting based on programming-free simulation teaching robot according to claim 1 is characterized in that: The specific process of dividing the surface of the painted product into several areas is as follows: The product surface is divided according to the structure, the areas on the same smooth surface are marked as the same initial area, the initial area with an area greater than the set threshold max is divided into several areas less than the set threshold, and the adjacent initial areas with an area less than the set threshold min are merged into one area.

4. The method for self-learning spray painting based on programming-free simulation teaching robot according to claim 1 is characterized in that: The specific process of obtaining the time period corresponding to the start and end of painting for each product area during the simulated teaching painting process is as follows: Monitor the area ratio of any area covered by paint in real time, and calculate the rate of change of the area ratio over time. When both the area ratio and the rate of change are greater than the set threshold, it is determined that the area has started to be painted, and the current time t1 is recorded; When the area ratio of the area being painted reaches 100%, the topcoat ratio and change rate of other areas are obtained. When the area ratio and change rate of other areas are greater than the set threshold, it is determined that the area is finished painting and the current time t2 is recorded; The time period between time t1 and time t2 is marked as the painting time period corresponding to the area.

5. The method for self-learning spray painting based on programming-free simulation teaching robot according to claim 1 is characterized in that: The specific paint indicators obtained based on the product surface image include: Based on computer vision technology, the color difference, glossiness, coating flatness, coating thickness and number of defects of the product surface paint are collected.

6. The method for self-learning spray painting based on programming-free simulation teaching robot according to claim 5 is characterized in that: The process of calculating the score of each simulated teaching painting according to the painting index is as follows: The painting index is converted into a quantitative index X according to the percentage difference between the painting index and the set index, and an n×m matrix is ​​constructed based on the quantitative index X, where m represents the number of quantitative indexes X, and the jth quantitative index X of the i-th simulated teaching painting is calculated. ij The Euclidean distance Po between the minimum value of the same type of quantitative indicators i , and the quantitative index X ij The Euclidean distance Ne between the maximum value of the same type of quantitative index i , X ij Indicates that i∈n, j∈m, and the calculation formula of Euclidean distance is: For any product area, the score S of the i-th simulated teaching painting is i The calculation formula is:

7. The self-learning method for spray painting based on programming-free simulation teaching robot according to claim 1 is characterized in that: The specific process of merging the best sub-trajectories corresponding to all product areas to obtain the best simulation teaching trajectory is as follows: For any product area, select the sub-trajectories corresponding to the N simulation teaching painting with the highest score ranking, mark them as pending sub-trajectories, N < n, count the pending sub-trajectories of all product areas, and obtain the simulation teaching painting to which each optimized sub-trajectory belongs. If the number of pending sub-trajectories of any simulation teaching painting accounts for less than 50% of the total number, then all the best sub-trajectories are time-sorted to generate a trajectory sequence, and the trajectory sequences are merged in turn to obtain the best simulation teaching trajectory; If more than 50% of the pending sub-trajectories belong to the same simulation teaching painting, all sub-trajectories of the simulation teaching painting are marked as preferred sub-trajectories. For the remaining best sub-trajectories in the trajectory sequence except the preferred sub-trajectory, if there is any other best sub-trajectory whose before and after time periods are both the preferred sub-trajectory, then the remaining best sub-trajectory in the trajectory sequence is replaced by the preferred sub-trajectory of the same time period, and the replaced trajectory sequences are merged in sequence to obtain the best simulation teaching trajectory.

8. The method for self-learning spray painting based on programming-free simulation teaching robot according to claim 1 is characterized in that: The process of smoothing the connections of sub-trajectories is: Create an overlapping area at the connection of the sub-trajectories, obtain the extension lines of the two sub-trajectories in the overlapping area, assign weights to the two sub-trajectories according to the ratio of the scores of the two sub-trajectories, perform weighted averaging on the sub-trajectory coordinate points in the overlapping area, take the weighted average of the two sub-trajectory coordinate points in the overlapping area, and generate the coordinates of the overlapping trajectory.

Images