Intelligent spraying path planning method and system for constructional engineering robot and medium

Abstract

The embodiment of the invention discloses a building engineering robot intelligent spraying path planning method and method and a medium, and the method comprises the steps that a three-dimensional laser scanning device scans the surface of a building to obtain three-dimensional point cloud data; converting the three-dimensional point cloud data to a robot coordinate system, performing noise reduction processing and data splicing on the data, and constructing a complete building surface model; based on the building surface model, geometrical characteristics of the model are extracted, spraying gun parameters including the movement speed, the spraying flow and the coverage range are set in combination with spraying process requirements, and a preliminary spraying path is planned; and optimizing the initial path through a collision detection algorithm, and if collision is detected, adjusting the path. According to the method, accurate spraying path planning of the constructional engineering robot is achieved, the spraying quality and efficiency are improved, the labor cost is reduced, and the method is suitable for application and popularization.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application relates to the technical field of construction engineering robots, and particularly relates to a construction engineering robot intelligent spraying path planning method, system and medium. BACKGROUND

[0002] In the current construction engineering field, spraying operations are mostly completed by manual work. Manual spraying has many drawbacks, which greatly limits the efficiency and quality of construction. In terms of efficiency, manual spraying is slow, and the spraying area that can be completed by a skilled worker in one day is limited, which cannot meet the needs of large-scale and time-constrained construction projects. For example, in the spraying of the outer wall of a large commercial complex, manual spraying requires a large amount of time, resulting in a prolonged construction period. Moreover, the quality of manual spraying is greatly affected by factors such as the technical level and working state of the worker, and the effects of spraying by different workers are uneven, and the spraying quality of the same worker at different times is also difficult to maintain consistency, which easily causes problems such as uneven coating thickness, sagging, and missed spraying, seriously affecting the appearance and protection performance of the building. At the same time, the labor cost of manual spraying is high, and with the continuous rise of labor costs, this cost accounts for an increasingly large proportion of the total construction cost. Furthermore, workers in the spraying operation will be exposed to a large amount of coating volatile matter, such as volatile organic compounds (VOC), heavy metals, formaldehyde and other harmful substances, which can cause damage to the respiratory system, nervous system, liver and other organs of the workers, and cause health problems such as chronic respiratory disease, memory loss, insomnia, headache, hepatitis, cirrhosis, skin allergy, dermatitis, etc., endangering the health of the workers.

[0003] To solve the problem of manual spraying, spraying robots have gradually been applied in construction engineering. However, the current path planning of spraying robots is mostly in a preset fixed mode. When facing complex and variable building structures, such as special-shaped buildings and buildings with a large number of decorative components, the preset path is difficult to accurately adapt, and spraying dead angles or excessive spraying may easily occur. When encountering spraying defects such as unevenness, cracks and holes on the building surface, the existing robots lack effective sensing and self-adaptive adjustment capabilities, and cannot optimize the spraying path in a timely manner according to the actual situation, which makes it difficult to guarantee the spraying quality and fully exert the advantages of robot spraying. Therefore, it is urgent to improve the path planning method of the spraying robot.

[0004] The above problems need to be solved. SUMMARY

[0005] To solve the problems in the related art, the present application provides a construction engineering robot intelligent spraying path planning method, system and medium to solve the problems mentioned in the background section.

[0006] To achieve the above object, the embodiment of the present application adopts the following technical solution: In a first aspect, the embodiments of the present application provide a building engineering robot intelligent spraying path planning method, comprising: A three-dimensional laser scanning device scans a building surface to obtain three-dimensional point cloud data; The three-dimensional point cloud data is converted to a robot coordinate system, and the data is subjected to noise reduction processing and data splicing to construct a complete building surface model; Based on the building surface model, the geometric features of the model are extracted, and the spraying gun parameters including the movement speed, spraying flow and coverage range are set in combination with the spraying process requirements to plan a preliminary spraying path; The preliminary path is optimized by a collision detection algorithm, and if a collision is detected, the path is adjusted.

[0007] As an optional implementation, the preliminary path is optimized by a collision detection algorithm, and if a collision is detected, the path is adjusted, and then further comprising: The path is globally optimized by a genetic algorithm, and the spraying time and paint consumption are minimized as the objective function, the population size, crossover probability and mutation probability parameters of the genetic algorithm are set, and the globally optimal path is obtained.

[0008] As an optional implementation, the path is globally optimized by a genetic algorithm, and the spraying time and paint consumption are minimized as the objective function, the population size, crossover probability and mutation probability parameters of the genetic algorithm are set, and the globally optimal path is obtained, and then further comprising: The globally optimal path is converted into control instructions executable by the building engineering robot, the coordinates of the path points are converted into control signals such as angles of joints of the building engineering robot or pulse numbers of motors according to a kinematic model of the building engineering robot, and the control signals are sent to a controller of the building engineering robot to drive the robot to perform the spraying operation.

[0009] As an optional implementation, the three-dimensional laser scanning device is a combination of a line laser radar and a surface array camera; wherein the line laser radar is used to obtain the contour information of the building surface; and the surface array camera is used to collect the surface texture details.

[0010] As an optional implementation, the data splicing comprises: In the data splicing process, a pre-alignment step based on feature matching is introduced, feature points in the point cloud data are extracted, feature matching is performed by using a descriptor, fast coarse alignment is achieved, and then ICP algorithm is used for fine alignment.

[0011] In a second aspect, the embodiments of the present application provide a building engineering robot intelligent spraying path planning system, which adopts the building engineering robot intelligent spraying path planning method of any one of the above-mentioned first aspect embodiments, and comprises: The three-dimensional point cloud data acquisition module is configured to acquire three-dimensional point cloud data by scanning a building surface through a three-dimensional laser scanning device. The building surface model construction module is configured to convert the three-dimensional point cloud data to a robot coordinate system, perform noise reduction processing and data splicing on the data, and construct a complete building surface model. The preliminary spraying path planning module is configured to extract geometric features of the model based on the building surface model, set spraying gun parameters including a movement speed, a spraying flow, and a coverage range according to spraying process requirements, and plan a preliminary spraying path. The path adjustment module is configured to optimize the preliminary path through a collision detection algorithm, and adjust the path if a collision is detected.

[0012] As an optional implementation, the building engineering robot intelligent spraying path planning system further includes: The path optimization module is configured to globally optimize the path by using a genetic algorithm, set population size, crossover probability, and mutation probability parameters of the genetic algorithm, and obtain a globally optimal path with a target function of minimizing spraying time and paint consumption.

[0013] As an optional implementation, the building engineering robot intelligent spraying path planning system further includes: The globally optimal path execution module is configured to convert the globally optimal path into control instructions executable by the building engineering robot, convert coordinates of path points into control signals such as angles of joints of the building engineering robot or pulse numbers of motors according to a kinematic model of the building engineering robot, send the control signals to a building engineering robot controller, and drive the robot to perform a spraying operation.

[0014] As an optional implementation, the three-dimensional laser scanning device is a combination of a line laser radar and a surface array camera; the line laser radar is configured to acquire contour information of the building surface; and the surface array camera is configured to acquire surface texture details.

[0015] In a third aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium storing computer execution instructions, the computer execution instructions being executed by a processor to implement the building engineering robot intelligent spraying path planning method in the first aspect.

[0016] The technical scheme provided by the embodiment of the application enables the building engineering robot to quickly plan an optimal spraying path. The robot adopting the method has high spraying efficiency under the same conditions, and the working time can be flexibly arranged according to the project requirements, thereby greatly shortening the spraying operation time. Through accurate path planning, the robot can strictly perform the operation according to the set spraying parameters and path, effectively avoiding problems such as missed spraying and uneven spraying. The coating thickness deviation can be controlled within ±0.05 mm, greatly improving the uniformity and consistency of the coating. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate and understand the technical solutions in the embodiments of the application, the drawings needed to be used in the background art and the embodiment description of the application will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the contents of the embodiments of the application and the drawings.

[0018] Figure 1 The building engineering robot intelligent spraying path planning method provided by the embodiment of the application is shown in the flowchart. DETAILED DESCRIPTION

[0019] In order to make the technical problems solved by the application, the technical solutions adopted and the technical effects achieved more clear, the technical solutions of the embodiments of the application will be further described in detail below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0020] Embodiment one Please refer to Figure 1 The, Figure 1 The building engineering robot intelligent spraying path planning method provided by the embodiment of the application is shown in the flowchart. As shown in the figure, the building engineering robot intelligent spraying path planning method in the embodiment includes: S101. A three-dimensional laser scanning device scans the building surface to obtain three-dimensional point cloud data; S102. Convert the three-dimensional point cloud data to the robot coordinate system, and perform noise reduction processing and data splicing on the data to construct a complete building surface model; S103. Based on the building surface model, extract the geometric features of the model, set the spray gun parameters including the movement speed, spraying flow and coverage range according to the spraying process requirements, and plan a preliminary spraying path; S104. Optimizing the preliminary path through a collision detection algorithm, and adjusting the path if a collision is detected.

[0021] In this embodiment, the step S101 of scanning the building surface by the three-dimensional laser scanning device to obtain three-dimensional point cloud data specifically includes: comprehensively scanning the building surface by the three-dimensional laser scanning device to obtain high-precision three-dimensional point cloud data, and adjusting the position and angle of the scanning device during the scanning process to ensure that each area of the building surface is effectively covered.

[0022] In this embodiment, the step S102 of converting the three-dimensional point cloud data to the robot coordinate system, performing noise reduction processing and data splicing on the data, and constructing a complete building surface model specifically includes: converting the obtained three-dimensional point cloud data to the robot coordinate system, performing noise reduction processing on the data by using a bilateral filtering algorithm to remove noise points generated due to scanning errors, environmental interference, etc., and then using an ICP (Iterative Closest Point) algorithm for data splicing to construct a complete and accurate building surface model.

[0023] In this embodiment, during the data splicing process, a pre-alignment step based on feature matching is introduced, feature points (such as corner points and edge points) in the point cloud data are extracted, and a descriptor (such as SIFT or SURF) is used for feature matching to achieve fast coarse alignment, and then an ICP algorithm is used for fine alignment to improve the splicing efficiency and accuracy.

[0024] In this embodiment, a dynamic weight heuristic function is used in the improved A* algorithm, the weight of the heuristic function is adjusted in real time according to the complexity of the building surface and the spraying process requirements to balance the breadth and depth of the path search, and the efficiency and quality of the path planning are improved. In the collision detection algorithm, a hierarchical collision detection strategy is used, coarse detection based on bounding boxes is performed first to quickly exclude areas that obviously will not collide, and then fine detection based on triangular mesh is performed on areas that may collide to improve the detection accuracy and efficiency. When the path is optimized by using the genetic algorithm, an elite reservation strategy is used to ensure that the path with the best fitness in each generation directly enters the next generation, avoiding the loss of optimal solution and accelerating the convergence of the algorithm. When the robot performs the spraying operation, the spraying pressure and flow of the spray gun are monitored in real time by using pressure sensors and flow sensors, and the spraying parameters are automatically adjusted according to the feedback data to ensure the uniformity of the coating thickness.

[0025] In this embodiment, the application also includes a communication interface with external devices (such as monitoring cameras, construction management systems) to transmit real-time data during spraying (such as robot position, spraying progress, paint remaining) to external devices to achieve remote monitoring and management. For different building structures (such as flat walls, cylindrical surfaces, and irregular curved surfaces), a corresponding path planning template library is established, and when planning the path, the appropriate template is quickly matched and called according to the geometric characteristics of the building surface model, improving the efficiency and adaptability of path planning.

[0026] The building engineering robot intelligent spraying path planning method proposed in this embodiment can quickly plan the optimal spraying path for the building engineering robot. A worker can complete about 100-200 square meters of spraying area per day using traditional manual spraying, which is limited by factors such as physical strength and rest time. However, the building engineering robot using the present application can complete 80-120 square meters of spraying per hour under the same conditions, and the working time can be flexibly arranged according to project requirements, greatly shortening the spraying operation time. In a large construction project such as a 50,000 square meter commercial plaza exterior wall spraying project, traditional manual spraying requires 80 workers to work continuously for 45 days, while using 10 robots equipped with the path planning method, combined with a small number of auxiliary personnel, the entire spraying task can be completed within 20 days, reducing the construction period by more than half, significantly improving the construction efficiency and accelerating the overall project progress. Through precise path planning, the robot can strictly follow the set spraying parameters and path, effectively avoiding problems such as missed spraying and uneven spraying. Traditional manual spraying has a coating thickness deviation of ±0.2mm due to differences in worker skill levels and operation methods, and is prone to problems such as sagging and missed spraying, requiring a lot of post-repair work. The present method can control the coating thickness deviation to within ±0.05mm, greatly improving the uniformity and consistency of the coating. In a high-end residential complex exterior wall coating project, the use of this method significantly improves the coating quality, with a smooth and even surface and uniform color, reducing post-repair costs due to poor spraying quality by more than 70%, and improving the overall aesthetics and durability of the building.

[0027] Embodiment two The embodiment of the present application provides a building engineering robot intelligent spraying path planning system, which adopts the building engineering robot intelligent spraying path planning method of embodiment one, comprising: a three-dimensional point cloud data acquisition module for scanning the building surface through a three-dimensional laser scanning device to obtain three-dimensional point cloud data; a building surface model construction module for converting the three-dimensional point cloud data to a robot coordinate system, performing noise reduction processing and data splicing on the data, and constructing a complete building surface model; A preliminary spraying path planning module is configured to extract geometric features of the model based on the building surface model, set spraying gun parameters including motion speed, spraying flow and coverage range in combination with spraying process requirements, and plan a preliminary spraying path; A path adjustment module is configured to optimize the preliminary path by a collision detection algorithm, and adjust the path if a collision is detected.

[0028] Illustratively, the building engineering robot intelligent spraying path planning system further comprises: A path optimization module is configured to globally optimize the path by a genetic algorithm, set population size, crossover probability and mutation probability parameters of the genetic algorithm, and obtain a globally optimal path with a target function of minimizing spraying time and paint consumption.

[0029] Illustratively, the building engineering robot intelligent spraying path planning system further comprises: A globally optimal path execution module is configured to convert the globally optimal path into control instructions executable by the building engineering robot, convert coordinates of path points into control signals such as angles of joints or pulse numbers of motors of the building engineering robot according to a kinematic model of the building engineering robot, send the control signals to a controller of the building engineering robot, and drive the robot to perform spraying work.

[0030] Illustratively, the three-dimensional laser scanning device is a combination of a line laser radar and a surface array camera; the line laser radar is configured to obtain contour information of the building surface; and the surface array camera is configured to collect surface texture details.

[0031] In this embodiment, the three-dimensional point cloud data acquisition module is specifically configured to acquire high-precision three-dimensional point cloud data by using a three-dimensional laser scanning device to perform all-around scanning on the building surface; during the scanning process, the position and angle of the scanning device are adjusted to ensure that each region of the building surface is effectively covered.

[0032] In this embodiment, the building surface model construction module is specifically configured to convert the acquired three-dimensional point cloud data to a robot coordinate system, perform noise reduction processing on the data by using a bilateral filtering algorithm to remove noise points generated due to scanning errors, environmental interference and the like, and then perform data splicing by using an ICP (Iterative Closest Point) algorithm to construct a complete and accurate building surface model.

[0033] In this embodiment, during the data splicing process, a pre-alignment step based on feature matching is introduced; feature points (such as corner points and edge points) in the point cloud data are extracted, a descriptor (such as SIFT or SURF) is used for feature matching, fast coarse alignment is achieved, and then the ICP algorithm is used for fine alignment, thereby improving splicing efficiency and accuracy.

[0034] In this embodiment, the improved A* algorithm adopts a dynamic weight heuristic function, which adjusts the weight of the heuristic function in real time according to the complexity of the building surface and the requirements of the spraying process, to balance the breadth and depth of the path search and improve the efficiency and quality of the path planning. In the collision detection algorithm, a hierarchical collision detection strategy is adopted, which first performs coarse detection based on bounding boxes to quickly exclude areas that obviously will not collide, and then performs fine detection based on triangular mesh for areas that may collide to improve detection accuracy and efficiency. When optimizing the path using genetic algorithm, the elite reservation strategy is adopted to ensure that the path with the best fitness in each generation directly enters the next generation, avoiding the loss of optimal solution and accelerating the convergence of the algorithm. When the robot performs spraying operation, the spraying pressure and flow of the spray gun are monitored in real time through pressure sensors and flow sensors, and the spraying parameters are automatically adjusted according to the feedback data to ensure uniform coating thickness.

[0035] In this embodiment, the application also includes a communication interface with external devices (such as surveillance cameras, construction management systems) to transmit real-time data (such as robot position, spraying progress, paint remaining) during spraying to external devices for remote monitoring and management. For different building structures (such as flat walls, cylindrical surfaces, irregular curved surfaces), a corresponding path planning template library is established, and when planning the path, the appropriate template is quickly matched and called according to the geometric characteristics of the building surface model, improving the efficiency and adaptability of path planning.

[0036] The building engineering robot intelligent spraying path planning system provided in the embodiment can make the building engineering robot quickly plan an optimal spraying path. A worker can complete spraying of an area of about 100-200 square meters per day by traditional manual spraying, and is limited by factors such as physical strength and rest time. However, the building engineering robot using the present application can complete spraying of an area of 80-120 square meters per hour under the same conditions, and the working time can be flexibly arranged according to the project requirements, greatly shortening the spraying operation time. In a large building project such as spraying of the outer wall of a 50,000 square meter commercial plaza, 80 workers are needed to continuously work for 45 days to complete the spraying by traditional manual spraying, while only 10 robots equipped with the path planning method are needed to complete the entire spraying task within 20 days, with a construction period shortened by more than half, significantly improving the construction efficiency and accelerating the overall progress of the project. Through accurate path planning, the robot can strictly follow the set spraying parameters and path to work, effectively avoiding problems such as missed spraying and uneven spraying. Due to differences in technical level and operation method of workers, the coating thickness deviation of traditional manual spraying can reach ±0.2 mm, and phenomena such as sagging and missed spraying easily occur, requiring a lot of post repair work. The method of the present application can control the coating thickness deviation within ±0.05 mm, greatly improving the uniformity and consistency of the coating. In an outer wall coating project of a high-end residential area, the coating quality is significantly improved after using the method, with a smooth and flat surface, uniform color, and a repair cost due to spraying quality problems reduced by more than 70%, improving the overall aesthetics and durability of the building.

[0037] The building engineering robot precise spraying path planning system provided in the embodiment realizes precise spraying path planning of the building engineering robot, improves the spraying quality and efficiency, and reduces the labor cost.

[0038] It should be noted that the readable storage medium can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0039] Note that the above merely describes preferred embodiments of the present application and the principles of the technology applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, modifications and substitutions can be made without departing from the scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for intelligent spraying path planning of construction engineering robots, characterized in that, The method comprises the following steps: a three-dimensional laser scanning device scans a building surface to obtain three-dimensional point cloud data; the three-dimensional point cloud data is converted to a robot coordinate system, and the data is denoised and spliced to construct a complete building surface model; based on the building surface model, the geometric features of the model are extracted, and the spray gun parameters including the movement speed, spray flow and coverage range are set according to the spraying process requirements to plan a preliminary spraying path; the preliminary path is optimized by a collision detection algorithm, and if a collision is detected, the path is adjusted.

2. The intelligent spraying path planning method for construction engineering robots according to claim 1, characterized in that, The method further comprises the following steps after the preliminary path is optimized by the collision detection algorithm and if a collision is detected, the path is adjusted: a global optimization of the path is performed by using a genetic algorithm, and the spray time and paint consumption are minimized as the objective function, and the population size, crossover probability and mutation probability parameters of the genetic algorithm are set to obtain a globally optimal path.

3. The intelligent spraying path planning method for construction engineering robots according to claim 2, characterized in that, The method further comprises the following steps after the global optimization of the path is performed by using the genetic algorithm and the spray time and paint consumption are minimized as the objective function, and the population size, crossover probability and mutation probability parameters of the genetic algorithm are set to obtain the globally optimal path: the globally optimal path is converted into control instructions executable by a construction robot, the coordinates of the path points are converted into control signals such as the angles of the joints of the construction robot or the pulse numbers of the motors according to the kinematic model of the construction robot, and the control signals are sent to a construction robot controller to drive the robot to perform the spraying operation.

4. The intelligent spraying path planning method for construction robots according to one of claims 1 to 3, characterized in that, The three-dimensional laser scanning device is a combination of a line laser radar and a surface array camera; wherein the line laser radar is used to obtain the contour information of the building surface; and the surface array camera is used to collect the surface texture details.

5. The intelligent spraying path planning method for construction engineering robots according to claim 4, characterized in that, The data splicing comprises the following steps: In the data splicing process, a pre-alignment step based on feature matching is introduced, feature points in the point cloud data are extracted, feature matching is performed by using a descriptor, fast coarse alignment is achieved, and then ICP algorithm is used for fine alignment.

6. A construction engineering robot intelligent spraying path planning system, characterized in that, The system adopts the intelligent spraying path planning method of the construction robot according to claim 1, which comprises: a three-dimensional point cloud data acquisition module for scanning a building surface by a three-dimensional laser scanning device to obtain three-dimensional point cloud data; a building surface model construction module for converting the three-dimensional point cloud data to a robot coordinate system, denoising and splicing the data, and constructing a complete building surface model; a preliminary spraying path planning module for extracting geometric features of the model based on the building surface model, setting spray gun parameters including movement speed, spray flow and coverage range according to spraying process requirements, and planning a preliminary spraying path; a path adjustment module for optimizing the preliminary path by a collision detection algorithm, and adjusting the path if a collision is detected.

7. The intelligent spraying path planning system for construction robots according to claim 6, characterized in that, The intelligent spraying path planning system of the construction robot further comprises: a path optimization module for globally optimizing the path by using a genetic algorithm, minimizing the spray time and paint consumption as the objective function, setting the population size, crossover probability and mutation probability parameters of the genetic algorithm, and obtaining a globally optimal path.

8. The intelligent spraying path planning system for construction robots according to claim 7, characterized in that, The intelligent spraying path planning system of the construction robot further comprises: The global optimal path execution module is configured to convert the global optimal path into control instructions executable by the construction engineering robot, convert coordinates of the path points into control signals such as angles of joints of the construction engineering robot or pulse numbers of motors according to a kinematic model of the construction engineering robot, and send the control signals to a controller of the construction engineering robot to drive the robot to perform the spraying operation.

9. The intelligent spraying path planning system for construction robots according to one of claims 6 to 8, characterized in that The three-dimensional laser scanning device is a combination of a line laser radar and a surface array camera; the line laser radar is configured to acquire profile information of a building surface; and the surface array camera is configured to collect surface texture details.

10. A computer readable storage medium having stored therein computer- executable instructions, wherein, The computer-executed instructions, when executed by a processor, are configured to implement the intelligent spraying path planning method of the construction engineering robot according to claim 1.

Images