Three-dimensional modeling design method and system based on multi-machine cooperation of building robots

Abstract

The invention provides a three-dimensional modeling design method based on multi-robot cooperation of building robots. The method comprises the following steps: taking a set of tasks and paths allocated to each robot as task allocation information; a task execution scheme after error correction based on real-time feedback and task distribution information; performing global analysis on execution errors of all robots according to the corrected task execution scheme; based on the optimized task execution scheme, constructing a task-robot cooperation matrix, and performing task scheduling on the task-robot cooperation matrix by using a cooperation scheduling algorithm; and combining the adjusted point cloud data and the optimized three-dimensional model into a complete three-dimensional model. According to the invention, by optimizing a collaborative operation mechanism of the robot cluster and introducing an error correction mechanism of dynamic task allocation and real-time feedback, the defects in the existing building robot technology are overcome, so that the efficiency of building construction and the modeling precision are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of three-dimensional modeling design, and particularly relates to a three-dimensional modeling design method and system based on multi-robot cooperation of construction robots. Background Art

[0002] With the continuous improvement of the requirements for construction efficiency, precision, and automation in the construction industry, the application of construction robot technology in the field of construction has received extensive attention. Especially in three-dimensional modeling and automated construction, construction robots have significant advantages. Through the autonomous navigation, environmental perception, and operation execution of robots, the precision of construction can be significantly improved, manual intervention can be reduced, and the construction process can be optimized. However, the current construction robot technology still faces multiple challenges, especially in multi-robot cooperation, dynamic task allocation, spatial error correction, and the adaptability of robots to complex environments.

[0003] Existing multi-robot cooperation systems generally rely on preset path planning and task allocation mechanisms. Although these systems can achieve a certain degree of automation, there are still some significant deficiencies. First, task allocation often lacks flexibility. Robots can only execute tasks according to the predetermined order and path. When the construction environment changes, they lack the ability of real-time adjustment and dynamic optimization. For example, when obstacles, schedule lags, or construction parameter changes occur at the construction site, the existing systems often cannot adjust tasks or robot paths in a timely manner, resulting in low task execution efficiency and even wasting a large amount of time and resources. Second, when construction robots execute three-dimensional modeling tasks, they usually rely on high-precision sensors for spatial perception and positioning. However, due to factors such as sensor errors during robot movement, environmental interference (such as light changes, vibrations, thermal expansion, etc.), and occlusion by external objects, positioning errors are likely to occur. These errors will gradually amplify over time and ultimately lead to deviations in the modeling results, affecting the final construction precision. Although some advanced error correction algorithms such as filtering algorithms and Kalman filters have been proposed and applied in single-machine systems, when multiple robots work together, the error correction effects of these technologies are still limited by the system scale, cooperation precision, and real-time feedback mechanism, and it is difficult to achieve effective error control globally. Finally, in the cooperative operation of a multi-robot cluster, although modern robot scheduling systems can achieve basic task allocation, they lack a global optimization strategy across robots and tasks. In a complex construction site, a single robot may be inefficient or conflict due to factors such as position, task progress, and workload. Traditional scheduling systems often lack flexible responses to these dynamic changes and are difficult to achieve efficient cooperation among robots and optimal resource allocation.

[0004] Therefore, in current construction robot technology, there are still a series of problems such as inflexible task allocation, insufficient spatial error correction, and low robot collaboration efficiency, which limit the automation and intelligence levels in the construction process. Especially in complex environments, ensuring the collaboration of robot swarms and the accuracy of 3D modeling remains an urgent problem to be solved. Summary of the Invention

[0005] The objective of the present invention is to design a 3D modeling design method and system based on multi-robot collaboration of construction robots. By optimizing the collaborative operation mechanism of the robot swarm, introducing a dynamic task allocation and real-time feedback error correction mechanism, the deficiencies in existing construction robot technology are overcome, thereby significantly improving the efficiency of construction and the accuracy of modeling.

[0006] To achieve the above objective, in the first aspect of the present invention, a 3D modeling design method based on multi-robot collaboration of construction robots is provided. The method includes:

[0007] S1. Based on the environmental data of the construction site, robot status information, and task requirement data, perform dynamic task allocation and path planning to obtain a set of tasks and paths assigned to each robot as task allocation information. Among them, the robot status information includes the current position and the target task position;

[0008] In step S1, a multi-objective optimization function is used to allocate tasks to the robots, and a hybrid method of dynamic programming and the A* algorithm is used for path optimization;

[0009] S2. Collect the real-time feedback of each robot's task execution. Based on the real-time feedback and the error of the task allocation information, monitor the local spatial error of each robot respectively. Use machine learning to dynamically calculate the path correction amount of the current robot according to the magnitude of the local spatial error and the urgency of the task. The robot updates the current path according to the correction amount to obtain a corrected task execution plan. Among them, the corrected task execution plan includes the task number, robot number, corrected path cost, and updated robot position;

[0010] S3. For the corrected task execution plan, perform a global analysis of the execution errors of all robots to obtain a global error. Based on the global error, dynamically adjust the task allocation and path planning to obtain a task execution plan after global task rescheduling and path optimization. Among them, the optimized task execution plan includes the task number, robot number, optimized path planning, and optimized path cost;

[0011] S4. Based on the optimized task execution plan, construct a task-robot collaboration matrix, and use a collaborative scheduling algorithm to perform task scheduling on the task-robot collaboration matrix to determine the task allocation plan after optimized scheduling and the current position of each robot after adjustment;

[0012] S5. Obtain the original point cloud data, generate a preliminary 3D model, and at the same time obtain the task execution error when the robot executes the task. Based on the task execution error, correct the preliminary original point cloud data and adjust the task allocation plan to obtain the adjusted point cloud data, the position of each robot, and the optimized 3D model. Merge the adjusted point cloud data and the optimized 3D model into a complete 3D model.

[0013] Further, the multi-objective optimization function dynamically calculates the matching degree between tasks and robots in a weighted average manner for task allocation; the hybrid method of using dynamic programming and the A* algorithm for path optimization is expressed as:

[0014] Define the current position of the robot as r j =(x k , y k ), and the target task position is t i =(x i , y i ); where the goal of path planning is to minimize the path cost C j from r i to t path , and the path cost C path considers the path length, obstacle avoidance, and the load capacity of the robot, and is expressed as:

[0015]

[0016] where (x k , y k ) are the coordinates of each node in the path; is an indicator function indicating whether there is an obstacle at path node k, where the obstacle is 1 and the blank area is 0; λ4 is the weighted factor for obstacle avoidance, and n is the total number of nodes.

[0017] Further, the spatial error monitoring is the local spatial error Δr j between the current position r i of the robot and the task target t j ; then

[0018] Obtain an adaptive correction amount based on the local spatial error Δr j ; where the adaptive correction amount is based on the local spatial error Δr j, and dynamically adjust according to the importance and urgency of the task; the robot obtains the adaptive correction amount, and updates the current path through the cost function according to the adaptive correction amount to obtain a new path cost; the cost function is an obstacle collision determination function, indicating whether the robot encounters an obstacle during path correction.

[0019] Further, the global error is the total error of the local spatial error Δr j ; the global error matrix of the global error is calculated based on the distance between the robot and the task target position, and gives the total error of all tasks.

[0020] Further, dynamically adjust the task allocation and path planning based on the global error to obtain a task execution plan after global task rescheduling and path optimization, including:

[0021] Obtain the global error;

[0022] Globally correct the priority of the task based on the global error to obtain the error correction amount of task i;

[0023] Obtain a new path cost, and combine the error correction amount of task i to determine a new task allocation plan.

[0024] Further, the obtaining of the new path cost, combining the error correction amount of task i, and determining the new task allocation plan:

[0025] Calculate by minimizing the task execution cost, including:

[0026]

[0027] Among them, T′ assign is the new task allocation plan; α j is the adjustment weight of robot j; C′ psth (j, i) is the path cost for robot j to execute task i after correction; γ is the adjustment factor of the path cost, used to balance the weights of path optimization and error correction.

[0028] Further, the task-robot cooperation matrix represents the cooperation relationship between tasks and robots; the elements of the matrix represent the cooperation effect between task i and robot j; the task-robot cooperation matrix is expressed as:

[0029]

[0030] Among them, α i is the priority weight of task i, β j is the state adjustment factor of robot j, d(r′ j , t i) is the error distance between the robot j and the target of task i, d max is the maximum tolerable error distance of task i;

[0031] Then, based on the task-robot collaboration matrix, a dynamic scheduling algorithm is used to assign the most suitable robot to each task; a resource adjustment factor is introduced in the dynamic scheduling algorithm to optimize task scheduling, and a dynamic feedback correction factor is introduced to adjust the task assignment of robot j in real time.

[0032] Furthermore, the task execution error E j (t) when the robot executes the task is expressed as:

[0033] E j (t) = λ1∥r′ j (t) - t i ∥ + λ2|ΔT j (t)| + λ3∥ΔL j (t)∥

[0034] where r′ j (t) is the actual position of robot j at time t; t i is the expected position of the target task i; ΔT j (t) is the time error of robot j executing the task; ΔL j (t) is the load error; λ1, λ2, λ3 are weighting coefficients;

[0035] Then, based on the task execution error E j (t), the point cloud data is corrected, expressed as:

[0036]

[0037] where P i corrected is the corrected point cloud data, P i preprocessed is the original point cloud data; μ(t) is a dynamic adjustment factor that adjusts the correction intensity based on the resources of the robot; E max is the maximum error allowed in the task;

[0038] According to the corrected point cloud data P i corrected the original 3D model is weighted and optimized to obtain the optimized 3D model M optimized (t) at the current moment;

[0039] The corrected point cloud data P i corrected is fused with the optimized 3D model M optimized (t) at the current moment to obtain the final complete 3D model.

[0040] In the second aspect of the present invention, a three-dimensional modeling design system based on multi-robot cooperation of construction robots is provided. The system includes:

[0041] An environmental data acquisition unit, which is used to perform dynamic task allocation and path planning according to the environmental data of the construction site, the robot status information, and the task requirement data, and obtain a set of tasks and paths assigned to each robot as task allocation information; wherein, the robot status information includes the current position and the target task position;

[0042] In the environmental data acquisition unit, tasks are allocated to robots through a multi-objective optimization function, and a hybrid method of dynamic programming and the A* algorithm is used for path optimization;

[0043] A task scheduling unit, which is used to collect the real-time feedback of each robot's task execution, perform local space error monitoring on each robot based on the real-time feedback and the error of the task allocation information, use machine learning to dynamically calculate the path correction amount of the current robot according to the size of the local space error and the urgency of the task, and the robot updates the current path according to the correction amount to obtain a corrected task execution plan; wherein, the corrected task execution plan includes the task number, the robot number, the corrected path cost, and the updated robot position;

[0044] A global optimization unit, which is used to perform a global analysis on the execution errors of all robots for the corrected task execution plan to obtain a global error, and dynamically adjust the task allocation and path planning based on the global error to obtain a task execution plan after global task rescheduling and path optimization; wherein, the optimized task execution plan includes the task number, the robot number, the optimized path planning, and the optimized path cost;

[0045] A collaborative optimization unit, which is used to construct a task-robot collaboration matrix based on the optimized task execution plan, perform task scheduling on the task-robot collaboration matrix using a collaborative scheduling algorithm, and determine the optimized task allocation plan and the adjusted current position of each robot;

[0046] A three-dimensional modeling unit, which is used to obtain the original point cloud data, generate a preliminary three-dimensional model, and at the same time obtain the task execution error when the robot executes the task, correct the preliminary original point cloud data based on the task execution error and adjust the task allocation plan to obtain the adjusted point cloud data, the position of each robot, and the optimized three-dimensional model, and merge the adjusted point cloud data and the optimized three-dimensional model into a complete three-dimensional model.

[0047] The beneficial technical effects of the present invention are at least as follows:

[0048] Task-driven dynamic task allocation mechanism: Traditional robot cluster task allocation mechanisms usually rely on preset paths and fixed task allocations, which can easily lead to robots being unable to adapt to changes in real time in environments with large variations at construction sites. To overcome this problem, the present invention proposes a task-driven dynamic task allocation algorithm that dynamically adjusts task allocation and path planning according to real-time construction requirements, task progress, and robot status (including battery power, work progress, sensor status, etc.). This mechanism can flexibly respond to complex changes at the construction site, avoid resource waste, and ensure that robots can work efficiently in cooperation.

[0049] Spatial error correction and real-time feedback optimization mechanism: Existing error correction methods mainly rely on the self-correction of a single robot and are difficult to effectively perform global error control when multiple robots work in cooperation. To address this problem, the present invention realizes global error correction of robots during the execution of modeling tasks by introducing a spatial error correction and feedback optimization mechanism. During the execution of tasks, each robot obtains real-time sensor data of the surrounding environment, compares it with the predetermined building model, and detects and corrects spatial errors. When an error occurs in a certain robot, the system will immediately feedback the error information to other robots to cooperate in adjusting the path and tasks, ensuring that the entire robot cluster maintains a high modeling accuracy globally.

[0050] Global cooperation and resource optimization scheduling: To further improve the efficiency of multi-robot cooperation, the present invention proposes a global optimization scheduling mechanism that can ensure that there are no conflicts in the cooperative work of robots, avoid resource waste, and maximize task execution efficiency through the integration and optimization scheduling of the tasks, progress, and resource status of multiple robots. This mechanism intelligently schedules tasks among robots by calculating the task load, spatial positioning, and working status of each robot in real time, ensuring that construction site tasks can be evenly distributed among each robot, and at the same time adjusting the priority of tasks according to the construction progress to avoid construction delays caused by a certain robot being overloaded or having path conflicts.

[0051] Through these innovations, the present invention can adjust robot tasks and paths in real time in complex construction environments, reduce the impact of spatial errors, and optimize the overall cooperation efficiency of the robot cluster. Ultimately, it can significantly improve the automation level, accuracy, and construction speed of building construction, thus solving the problems of inflexible task allocation, insufficient spatial error correction, and low robot cooperation efficiency in the existing technology, and promoting the development of the building industry towards a more intelligent and efficient direction. Brief Description of the Drawings

[0052] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the following drawings without creative efforts.

[0053] Figure 1 This is a flowchart of the three-dimensional modeling design method based on multi-robot cooperation of construction robots of the present invention.

[0054] Figure 2 This is a framework diagram of the three-dimensional modeling design system based on multi-robot cooperation of construction robots of the present invention. Detailed implementation manners

[0055] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention.

[0056] In one or more embodiments, as Figure 1 shown, a three-dimensional modeling design method based on multi-robot cooperation of construction robots is disclosed. The method includes the following steps S1 - S5:

[0057] S1. According to the environmental data, robot status information, and task requirement data of the construction site, perform dynamic task allocation and path planning to obtain a set of tasks and paths assigned to each robot as task allocation information; wherein, the robot status information includes the current position and the target task position.

[0058] Specifically, the input data of step S1 comes from the overall environmental perception and task allocation module of the system, and these data include the following aspects:

[0059] Environmental data: Real-time data collection system from the construction site, including structure diagrams, obstacle distributions, construction progress, etc. These data are collected in real time through on-site sensors, laser scanners, vision sensors and other devices, and are processed through data fusion algorithms.

[0060] Robot status data: Real-time status data of each robot, including power, load, current position, available tools, task priority, etc. These information are obtained through sensors and internal computing modules on the robot and are transmitted to the control system.

[0061] Task requirement data: According to the construction plan and building progress, the system dynamically generates specific requirements for each task as needed, including the timeliness, priority, required resources, etc. of the task. These task requirements are generated by the scheduling system and combined with the status information of the robot to provide the priority ranking of the tasks.

[0062] Furthermore, according to the resource status and environmental conditions of the robot cluster, tasks to be completed by each robot at a specific moment are dynamically allocated. Multiple factors are considered, such as task priority, the idle resources of the robot, the current task load of the robot, etc.

[0063] Among them, the task allocation strategy:

[0064] Set a multi-objective optimization function to balance the goals of task allocation. This objective function includes but is not limited to task priority, the spatial location of the task, the robot load situation, etc.

[0065] Define the priority function of the task as P i , where i represents the task number, and P i represents the importance or timeliness of the task.

[0066] Define the weight function of the robot state as W j , where j represents the robot number, and W j represents the current idle resources of the robot, and W j is evaluated according to the battery power, load, task history, etc. of the robot.

[0067] Based on these inputs, the matching degree between the task and the robot is dynamically calculated by the weighted average method:

[0068]

[0069] Among them, P i is the priority of task i; W | is the current resource weight of robot j; d(i,j) is the distance between task i and robot j (which can be the Euclidean distance between the task location and the current location of the robot); λ1, λ2, λ3 are the weighting factors for adjusting task priority, robot resources, and distance.

[0070] This optimization objective function represents the comprehensive priority of task allocation. Each robot will match with the task according to the value of this function, so as to efficiently allocate tasks at each moment.

[0071] Furthermore, for each task, the system needs to plan an optimal path for the robot from its current location to the target task location, ensuring that the path avoids obstacles and takes into account the length of the path and the robot's workload.

[0072] Path planning method: A hybrid method of dynamic programming (DP) and the A* algorithm is used for path optimization. Each robot, based on its current task and location, uses the A* algorithm for preliminary path planning and combines dynamic programming to fine-tune the path to avoid congested areas and obstacles.

[0073] Define the current location of the robot as r j =(x j , y j ), and the target task location as t i =(x i , y i ). The goal of path planning is to minimize the path cost C j from r i to t path , and this cost function takes into account path length, obstacle avoidance, and the robot's load capacity:

[0074]

[0075] where (x k , y k ) are the coordinates of each node in the path; is an indicator function indicating whether there is an obstacle at path node k (1 for obstacle, 0 for clear area); λ4 is the weighting factor for obstacle avoidance.

[0076] The optimization goal of this path cost function is to minimize the path cost from the robot's current location to the target task location, ensuring that the robot can reach the target location efficiently and safely.

[0077] Finally, the output of step S1 is the specific tasks assigned to each robot and the corresponding path planning. This information will be used as the input for step S2, providing the task execution framework and path planning data for the robot.

[0078] Among them, each task i is assigned to robot j, and robot j will move from its current location r j to the target task location t i .

[0079] The output data format is a set of tasks and paths

[0080]

[0081] Among them, i represents the task number; j represents the robot number assigned to this task; r j and t i are respectively the current position and the target task position of robot j; C path (j, i) is the path cost from robot j to task i.

[0082] In the whole scheme, the core role of step S1 is to perform dynamic task allocation and path planning according to the existing environmental data, robot status and task requirements. Through this process, the system can optimize the working efficiency and task execution priority of the robot cluster, and provide accurate task and path information for the subsequent steps. The output of this step (task allocation and path planning results) will be used as the input of step 2 for further task execution and spatial error correction.

[0083] S2. Collect the real-time feedback of each robot's task execution, perform local spatial error monitoring on each robot based on the errors of the real-time feedback and task allocation information, use machine learning to dynamically calculate the path correction amount of the current robot according to the size of the local spatial error and the urgency of the task, and the robot updates the current path according to the correction amount to obtain the corrected task execution plan; among them, the corrected task execution plan includes the task number, robot number, corrected path cost and updated robot position.

[0084] Specifically, the input of step 2 directly comes from the output of step 1 - task allocation and path planning results. Specifically, the input data includes:

[0085] Task allocation information The target position t of each task i , the corresponding robot number j, task priority and the path planning cost C path (j, i), etc.

[0086] Robot status information r j : The current position, load, power, available tools, etc. of each robot, as well as the real-time status during task execution.

[0087] These information will be passed as input to the error monitoring and feedback module, aiming to perform spatial error monitoring according to the task execution status and the real-time position of the robot, and provide necessary feedback adjustment for task execution.

[0088] Furthermore, error monitoring: real-time spatial error calculation and environmental interference assessment:

[0089] Through the fusion of multi-sensor data in the system, the current position r of the robot is obtained in real time j and the task target t iThe spatial error between them, define the error vector as:

[0090] Δr j = r j - t i (4)

[0091] where r j is the current position of robot j; t i is the target position of task i; Δr j is the error vector between the current position of the robot and the task target.

[0092] In addition to the basic error calculation, it is also necessary to consider the impact of dynamic changes in the built environment (such as obstacles, the behavior of other robots, etc.) on the error. The present invention designs an environmental interference factor γ j to dynamically correct the error value, and the formula is as follows:

[0093]

[0094] where γ j is a dynamic adjustment factor, reflecting the impact of the robot's task urgency and workload; is a complex non-linear function for the current position of the robot, the target position and the distribution of environmental obstacles to estimate the impact of the environment on the error. The adjusted error provides a more accurate measurement of spatial error, considering the impact of environmental dynamic changes, and is the basis for error feedback and path correction.

[0095] Furthermore, based on real-time error monitoring, the present invention proposes a feedback mechanism based on machine learning adaptive correction, which can dynamically adjust the path correction amount according to the size of the error and the urgency of the task. In traditional methods, the error correction amount is usually static, but in this patent, the present invention introduces an adaptive correction amount c j , so that the feedback mechanism can be flexibly adjusted with changes in the environment and tasks. It is defined as:

[0096]

[0097] where α is the weighted coefficient of error correction, adjusting the intensity of error correction; β is the weight factor of task urgency; is the urgency indication function of the task (1 for urgent, 0 for ordinary task); λ j is the weight coefficient for adjusting the path correction amount and error correction; ΔC path (j,i) is the change in path cost, indicating the cost change of the robot from the original path to the corrected path. By adding the change in path cost term ΔC path(j, i), this solution can dynamically balance the task priority and the cost of path correction, ensuring that while correcting the path, it will not cause excessive efficiency loss. The adaptive correction amount c j is the feedback amount of the current path adjustment of the robot. After applying this amount, the path adjustment of the robot can more balance the relationship among the task urgency, the path cost, and the error correction.

[0098] Further, after obtaining the adaptive correction amount, the robot needs to update the current path according to the correction amount c j This invention proposes a method based on weighted shortest path optimization, specifically by optimizing the path cost function to adjust the motion trajectory of the robot. The new path cost C′ path (j, i) is determined jointly by the original path cost C path (j, i) and the correction amount c j :

[0099]

[0100] where, ∥c j ∥ is the Euclidean norm of the correction amount c j , representing the intensity of error correction; γ is the influence coefficient of the correction amount on the path cost; is the obstacle collision determination function, indicating whether the robot hits an obstacle during path correction; ν is the weight of the collision correction term, reflecting the priority of avoiding obstacle collision.

[0101] By adding the collision correction term this solution can, while ensuring error correction, avoid the path correction causing the robot to collide with obstacles.

[0102] Finally, the corrected path cost C′ path (j, i) provides a new path planning result, optimizing the navigation effect of the robot in a dynamic environment.

[0103] Further, the output of step 2 is the corrected task execution plan where each task and the path planning result of the robot have undergone error correction. This output includes the task number i, the robot number j, the corrected path cost C′ path (j, i), and the adjusted robot position r′ j :

[0104]

[0105] This task and path information will be used as the input of step 3 (task execution and spatial accuracy optimization), helping the robot complete tasks more precisely and effectively reducing the error and efficiency loss during the execution process.

[0106] The real-time spatial error monitoring and error feedback in step S2 are the core modules in this patent. They receive the task assignment and path planning results from step 1, and solve the accuracy problems existing when the construction robot cluster executes tasks in a dynamic environment through precise error monitoring, dynamic error correction, and path optimization. Through the adaptive correction strategy, weighted path optimization, and collision correction, it is ensured that the robot can execute tasks efficiently and precisely in a complex and uncertain construction environment. The output of this step provides more accurate task execution information for step 3 and is a key part in the whole system to ensure the task success rate and execution efficiency.

[0107] S3. For the corrected task execution plan, globally analyze the execution errors of all robots to obtain the global error, and dynamically adjust the task assignment and path planning based on the global error to obtain the task execution plan after global task rescheduling and path optimization; wherein, the optimized task execution plan includes task numbers, robot numbers, optimized path planning, and optimized path costs.

[0108] Specifically, in step 2, the present invention has performed local correction on the error between each robot and the task through real-time spatial error monitoring. However, the error is not only local and may accumulate into a global error, affecting the execution efficiency of the entire task. Therefore, the primary task of step 3 is to globally analyze the execution errors of all robots.

[0109] Furthermore, the present invention first defines a global error matrix E global , which is used to evaluate the overall error situation of the robot cluster in the current task execution. The global error matrix E global is calculated based on the distance between robot j and the task target position t i , and gives the total error of all tasks. The formula is:

[0110]

[0111] where r′ j is the current position (updated position) of robot j, t i is the target position of task i, is the set of all robots. This matrix evaluates the spatial deviation of all robots in task execution. If the error is large, it indicates that the robot cluster fails to complete the task precisely, which provides a basis for the subsequent global adjustment and correction.

[0112] Furthermore, error correction and global adjustment based on task priorities:

[0113] The correction of errors is not just about simply reducing the deviation between the robot and the target position. The urgency of the task also needs to be considered. For tasks that need to be completed as soon as possible (such as emergency repair tasks at a construction site), the intensity of error correction should be greater to ensure that the task can be completed on time.

[0114] To achieve this, the present invention introduces a priority factor α for each task i , and uses it to adjust the intensity of error correction. In addition, the task deviation correction of each robot j is also affected by factors such as its current workload and resource situation. Therefore, the present invention introduces an adjustment factor β for each robot j .

[0115] On this basis, the present invention introduces weights and adjustment factors for the error correction amount of each task, and finally defines the error correction amount c of task i i as:

[0116]

[0117] where c i is the error correction amount of task i; α i is the priority adjustment factor of task i; β j is the correction factor of robot j, used to reflect its load and status. In this way, the urgency of the task and the status of the robot will jointly determine the error correction strategy for each task. This design can ensure that tasks with higher priorities receive stronger correction support, while robots with heavier loads or fewer resources will receive lower correction intensities.

[0118] Furthermore, global task rescheduling and path replanning:

[0119] Based on the error correction amount c in the previous step i , the present invention will dynamically adjust the task assignment and path planning. This is the core part to ensure that the robot can flexibly respond to the changing construction site, task priorities, and real-time status.

[0120] Assume that each task i has a corresponding path cost C′ path (j,i), representing the path time consumption or cost when robot j executes task i. The present invention proposes a dynamic task scheduling method based on the error correction amount, which combines the error correction with the path cost to calculate the optimal path and execution strategy for each task.

[0121] Specifically, the new task assignment matrix T′ assign can be calculated by minimizing the task execution cost. The task assignment matrix T′ assign can be obtained through the following optimization formula:

[0122]

[0123] Among them, T′ assign is the new task allocation scheme; α j is the adjustment weight of robot j; C′ path (j,i) is the path cost for robot j to execute task i; γ is the adjustment factor of the path cost, which is used to balance the weights of path optimization and error correction.

[0124] Through this optimization process, the system can not only reallocate tasks, but also quickly adjust the robot paths after each task adjustment, maximizing the task execution efficiency. In particular, the optimization of the robot paths not only depends on the current error correction amount, but also takes into account the urgency of the tasks and the workload of the robots, further improving the collaborative efficiency of global task execution.

[0125] Furthermore, the output of step S3 is the task execution plan and the path planning result r′ j after global task rescheduling and path optimization. These information will be used as the input for the subsequent step 4 (task execution and feedback correction) to help the system dynamically adjust the tasks and the collaboration strategy between robots during the execution process. The output data includes:

[0126]

[0127] These data will continue to be used to guide the task execution of the robots in the subsequent steps and further optimize the execution process through the feedback correction mechanism.

[0128] S4. Based on the optimized task execution plan, construct a task-robot collaboration matrix, use the collaborative scheduling algorithm to schedule the tasks in the task-robot collaboration matrix, and determine the optimized task allocation plan and the current position of each robot after adjustment.

[0129] Specifically, the input of step 4 comes from the output of step 3, that is, the task allocation plan and the path planning r′ j obtained after global error correction and task adjustment. These outputs contain the work undertaken by each robot in a specific task, as well as information such as its path, load, and execution duration.

[0130] Furthermore, the construction of the task-robot collaboration matrix:

[0131] Construct a task-robot collaboration matrix C collab , which is used to describe the collaboration relationship between tasks and robots. The element C collab (i,j) of this matrix represents the collaboration effect between task i and robot j.

[0132] The calculation of the synergy effect is not only based on the physical capabilities of the robots, but also includes task priorities, the current status of the robots (such as battery level, load, etc.), and the results after error correction.

[0133] The elements of the synergy matrix are expressed as:

[0134]

[0135] where α i is the priority weight of task i, β j is the status adjustment factor of robot j, d(r′ j , t i ) is the error distance between robot j and the target of task i, and d max is the maximum tolerance error distance of task i.

[0136] Furthermore, the collaborative scheduling algorithm:

[0137] Based on the synergy matrix C collab , the dynamic scheduling algorithm is used to assign the most suitable robot to each task. The scheduling model is expressed as:

[0138]

[0139] where T schrfi;r ″ is the task scheduling scheme, is the set of all robots, is the set of all tasks, r′ k is the current position of robot j, and t o is the target position of task i.

[0140] Furthermore, resource optimization scheduling:

[0141] By introducing information such as the battery level of the robot, the battery consumption rate, and the load, the resource adjustment factor γ k is introduced. The resource adjustment factor is expressed as:

[0142]

[0143] where E k is the current battery level of robot j, E max is the maximum battery level of robot j, L k is the current load of robot j, L max is the maximum load of robot j, and λ is the adjustment factor. This factor reflects the impact of the robot's status on task assignment and is used to prevent robots with insufficient resources from being assigned high-priority tasks.

[0144] Furthermore, dynamic feedback correction of tasks and resources:

[0145] Introduce a dynamic feedback correction factor δ j (t) to adjust the task assignment of robot j in real time. The feedback correction factor is expressed as:

[0146]

[0147] where ΔE j (t) is the power change of robot j at time t, and ΔL j (t) is the load change of robot j at time t. μ is the dynamic adjustment factor. Through real-time feedback, the system can adjust the task assignment so that the robot can better adapt to the changes occurring during the execution process.

[0148] The output of step S4 is the task assignment scheme T schedule after optimized scheduling and the adjusted robot state r j . This information will be used as input in subsequent steps to ensure that the robot can execute tasks efficiently and accurately. The output data format is:

[0149] T schedule ″ ={(i, j, r j , t i , γ j )} (17).

[0150] S5. Obtain the original point cloud data, generate a preliminary three-dimensional model, and at the same time obtain the task execution error when the robot executes the task. Based on the task execution error, correct the preliminary original point cloud data and adjust the task assignment scheme to obtain the adjusted point cloud data and the positions of each robot, as well as the optimized three-dimensional model. Merge the adjusted point cloud data and the optimized three-dimensional model into a complete three-dimensional model.

[0151] Specifically, the robot collects the original point cloud data P i through sensors, and these data reflect the environmental information of the robot. Then, the present invention needs to process these data to generate a preliminary three-dimensional model.

[0152] Input: Original sensor data P o .

[0153] Processing process:

[0154] Denoising: Use a filtering algorithm (such as statistical filtering, voxel grid filtering, etc.) to remove unnecessary noise.

[0155] Registration: If the data comes from multiple sensors or perspectives, it is necessary to align these point cloud data through a registration algorithm.

[0156] Simplification: Reduce the redundancy of the point cloud through sampling or clustering algorithms to improve computational efficiency.

[0157] Preprocessing formula:

[0158] P i preprocessed = f preprocess (P i ) (18)

[0159] where f preprocess is a combination of operations such as denoising, filtering, and registration.

[0160] Furthermore, after preliminary modeling, when the robot executes tasks, it may be affected by many factors (e.g., positioning errors, environmental interference, etc.), resulting in the deviation of the point cloud data from the actual situation. At this time, the present invention needs to correct these errors through the feedback information during task execution.

[0161] Furthermore, when the robot executes tasks, each robot may have position errors, execution duration errors, etc. For example, when robot j executes a task, the error between its actual position and the target position may affect the final 3D modeling accuracy. This error is called the task execution error, and the present invention corrects it by adding this information to the model.

[0162] Furthermore, the error E j (t) of task execution can be quantified by the following formula:

[0163] E j (t)= λ1∥r′ j (t)-t i ∥+ λ2|ΔT j (t)|+ λ3∥ΔL j (t)∥ (19)

[0164] where r′ k (t) is the actual position of robot j at time t. t i is the expected position of the target task i. ΔT j (t) is the time error of robot j executing the task. ΔL k (t) is the load error. λ1, λ2, λ3 are weighting coefficients.

[0165] Furthermore, according to the execution error E j (t), the present invention corrects the point cloud data. The degree of correction depends on the size of the error and the resource status of the robot. The corrected point cloud data is:

[0166]

[0167] Among them, μ(t) is a dynamic adjustment factor, which adjusts the correction strength based on the resources of the robot (such as power and load). E max is the maximum error allowed in the task.

[0168] Furthermore, the adaptive adjustment factor μ(t) reflects the influence of the robot's resource status on error correction. It can be calculated using the following formula:

[0169]

[0170] Among them, λ is a constant that adjusts the sensitivity of the correction factor. R j (t) is the resource consumption of robot j at time t. R max is the maximum value of resource consumption in the task.

[0171] Furthermore, the task scheduling scheme T schedule and the adjusted robot state r j play important roles in this step. They determine the order, manner, and resource allocation of the robot to execute tasks, thus affecting the accuracy of the final 3D model.

[0172] Task scheduling and state adjustment formula:

[0173] Task scheduling considers the current state of the robot and task constraints:

[0174]

[0175] Among them, T schedule final is the adjusted task scheduling, c j (t) is the cost function related to resource consumption, d j (t) is the cost related to task execution delay or error.

[0176] Based on the scheduling, the state r j (t) of the robot is dynamically adjusted through the obtained scheduling scheme:

[0177] r j (t) = r j (t - 1) + Δr j (t) (23)

[0178] Among them, Δr j (t) is the state change amount adjusted according to the scheduling scheme and feedback error.

[0179] Furthermore, through task scheduling and error correction, the closed-loop feedback mechanism will continuously optimize the 3D modeling process. The execution result of each task will provide feedback for the execution of the next task, thereby improving the accuracy of the final model.

[0180] The point cloud data P after error correction and task scheduling optimization i corrected and the updated robot state r j . Using the feedback information (error feedback and task progress feedback), the 3D model is weighted and optimized. The optimized 3D model will gradually fit the actual environment. Closed-loop optimization formula:

[0181] M optimized (t) = M optimized (t - 1)+α(P i corrected -M optimized (t - 1))(24)

[0182] Among them, M optimized (t) is the optimized 3D model at the current moment. α is the optimization step size, used to control the magnitude of the correction. P i corrected is the point cloud data after error correction.

[0183] Furthermore, during the task execution, the robot collects point cloud data from different angles. Through the task scheduling T schedule ′, the present invention determines which data has a higher priority for merging, so as to optimize the final model.

[0184] Input: The point cloud data P after error correction i corrected and the optimized 3D model M optimized .

[0185] Data fusion process: Using techniques such as weighted average method, redundancy removal and gap filling, the data from different sources are merged into a complete 3D model.

[0186] 3D model fusion formula:

[0187] M 3D = merge(M optimized , P i corrected )(25)

[0188] Furthermore, the specific fusion method is:

[0189] Step 1: Registration of point cloud data, aligning the data from different sensors.

[0190] Step 2: Eliminate redundant points, and use the weighted average method to fuse the data in the overlapping areas.

[0191] Step 3: Fill the gap areas, and use interpolation or image filling methods to process the unscanned areas.

[0192] In one or more embodiments, as Figure 2 shown, a three-dimensional modeling design system based on multi-robot cooperation of construction robots is disclosed. The system includes:

[0193] An environmental data acquisition unit 31, configured to perform dynamic task allocation and path planning according to the environmental data of the construction site, the robot status information, and the task requirement data, and obtain a set of tasks and paths assigned to each robot as task allocation information; wherein, the robot status information includes the current position and the target task position;

[0194] In the environmental data acquisition unit, the robot performs task allocation through a multi-objective optimization function, and a hybrid method of dynamic programming and A* algorithm is used for path optimization;

[0195] A task scheduling unit 32, configured to collect the real-time feedback of each robot executing tasks, monitor the local space error of each robot respectively based on the real-time feedback and the error of the task allocation information, use machine learning to dynamically calculate the path correction amount of the current robot according to the magnitude of the local space error and the urgency of the task, and the robot updates the current path according to the correction amount to obtain a corrected task execution plan; wherein, the corrected task execution plan includes the task number, the robot number, the corrected path cost, and the updated robot position;

[0196] A global optimization unit 33, configured to perform a global analysis on the execution errors of all robots for the corrected task execution plan to obtain a global error, and dynamically adjust the task allocation and path planning based on the global error to obtain a task execution plan after global task rescheduling and path optimization; wherein, the optimized task execution plan includes the task number, the robot number, the optimized path planning, and the optimized path cost;

[0197] A cooperative optimization unit 34, configured to construct a task-robot cooperation matrix based on the optimized task execution plan, perform task scheduling on the task-robot cooperation matrix using a cooperative scheduling algorithm, and determine the optimized task allocation plan and the adjusted current position of each robot;

[0198] A three-dimensional modeling unit 35, configured to obtain the original point cloud data, generate a preliminary three-dimensional model, and at the same time obtain the task execution error when the robot executes tasks, correct the preliminary original point cloud data based on the task execution error and adjust the task allocation plan to obtain the adjusted point cloud data, the position of each robot, and the optimized three-dimensional model, and merge the adjusted point cloud data and the optimized three-dimensional model into a complete three-dimensional model.

[0199] It should be noted that the specific working process of the 3D modeling design system based on multi-robot cooperation of construction robots provided in the embodiments of the present invention is the same as that of the 3D modeling design method based on multi-robot cooperation of construction robots described in the above embodiments, and will not be elaborated here.

[0200] Compared with the prior art, the 3D modeling design system based on multi-robot cooperation of construction robots provided in the embodiments of the present invention performs dynamic task allocation and path planning according to the environmental data, robot state information, and task requirement data on the construction site, and obtains the set of tasks and paths assigned to each robot as task allocation information; wherein, the robot state information includes the current position and the target task position; the robot performs task allocation through a multi-objective optimization function, and adopts a hybrid method of dynamic programming and A algorithm for path optimization; collects the real-time feedback of each robot performing tasks, and performs local space error monitoring on each robot based on the errors between the real-time feedback and the task allocation information, and uses machine learning to dynamically calculate the path correction amount of the current robot according to the magnitude of the local space error and the urgency of the task, and the robot updates the current path according to the correction amount to obtain a corrected task execution plan; wherein, the corrected task execution plan includes task number, robot number, corrected path cost, and updated robot position; for the corrected task execution plan, globally analyze the execution errors of all robots to obtain a global error, and dynamically adjust the task allocation and path planning based on the global error to obtain a task execution plan after global task rescheduling and path optimization; wherein, the optimized task execution plan includes task number, robot number, optimized path planning, and optimized path cost; based on the optimized task execution plan, construct a task-robot cooperation matrix, and use a cooperative scheduling algorithm to perform task scheduling on the task-robot cooperation matrix to determine the optimized task allocation plan and the adjusted current position of each robot; obtain the original point cloud data, generate a preliminary 3D model, and at the same time obtain the task execution error when the robot performs tasks, correct the preliminary original point cloud data based on the task execution error and adjust the task allocation plan to obtain the adjusted point cloud data, the position of each robot, and the optimized 3D model, and merge the adjusted point cloud data and the optimized 3D model into a complete 3D model.

[0201] The embodiments of the present invention also provide a 3D modeling design device based on multi-robot cooperation of construction robots, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps in the embodiments of the 3D modeling design method based on multi-robot cooperation of construction robots as described above, for example Figure 1The steps S1 to S5 described in [reference]; or, when the processor executes the computer program, the functions of the modules in the above system embodiments are implemented.

[0202] Exemplarily, the computer program can be divided into one or more modules. The one or more modules are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the three-dimensional modeling design device based on multi-robot cooperation of construction robots.

[0203] The three-dimensional modeling design device based on multi-robot cooperation of construction robots can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The three-dimensional modeling design device based on multi-robot cooperation of construction robots may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the three-dimensional modeling design device based on multi-robot cooperation of construction robots may further include input / output devices, network access devices, a bus, etc.

[0204] The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the three-dimensional modeling design device based on multi-robot cooperation of construction robots, and connects various parts of the entire three-dimensional modeling design device based on multi-robot cooperation of construction robots through various interfaces and lines.

[0205] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory and invoking the data stored in the memory, the processor can implement various functions of the 3D modeling design device based on multi-robot cooperation of construction robots. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc.; the data storage area can store data created according to the operation of the air conditioner controller, etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0206] Among them, if the modules integrated in the 3D modeling design device based on multi-robot cooperation of construction robots are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0207] Those of ordinary skill in the art can understand that to implement all or part of the processes in the above-mentioned embodiment methods, it can be completed by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. Among them, the storage medium can be a magnetic disk, optical disc, read-only memory (ROM), or random access memory (RAM), etc.

[0208] The above are the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A three-dimensional modeling design method based on multi-robot collaborative operation of construction robots, characterized in that, The method includes: S1. Perform dynamic task allocation and path planning based on the environmental data of the construction site, the robot status information, and the task requirement data, and obtain the set of tasks and paths assigned to each robot as task allocation information; wherein, the robot status information includes the current position and the target task position. In step S1, task allocation is performed on the robot through a multi-objective optimization function, and a hybrid method of dynamic programming and the A* algorithm is used for path optimization. S2. Collect the real-time feedback of each robot executing the task, perform local space error monitoring on each robot based on the real-time feedback and the error of the task allocation information, use machine learning to dynamically calculate the path correction amount of the current robot according to the magnitude of the local space error and the urgency of the task, and the robot updates the current path according to the correction amount to obtain the corrected task execution plan; wherein, the corrected task execution plan includes the task number, the robot number, the corrected path cost, and the updated robot position. S3. For the corrected task execution plan, perform a global analysis on the execution errors of all robots to obtain the global error, and perform dynamic adjustment on the task allocation and path planning based on the global error to obtain the task execution plan after global task rescheduling and path optimization; wherein, the optimized task execution plan includes the task number, the robot number, the optimized path planning, and the optimized path cost. S4. Based on the optimized task execution plan, construct a task-robot collaboration matrix, and use a collaborative scheduling algorithm to perform task scheduling on the task-robot collaboration matrix to determine the optimized task allocation plan and the adjusted current position of each robot. S5. Obtain the original point cloud data, generate a preliminary 3D model, and at the same time obtain the task execution error when the robot executes the task. Based on the task execution error, correct the preliminary original point cloud data and adjust the task allocation plan to obtain the adjusted point cloud data, the position of each robot, and the optimized 3D model. The adjusted point cloud data and the optimized 3D model are combined into a complete 3D model.

2. The 3D modeling design method based on multi-robot collaborative operation of construction robots according to claim 1, wherein, The multi-objective optimization function dynamically calculates the matching degree between tasks and robots in a weighted average manner to perform task allocation; the hybrid method of using dynamic programming and the A* algorithm for path optimization is expressed as: Define the current position of the robot as r j =(x j , y j ), and the target task position as t i =(x i , y i ); where the goal of path planning is to minimize the path cost C j from r i to t path , and the path cost C path takes into account the path length, obstacle avoidance, and the load capacity of the robot, and is expressed as: where (x k , y k ) are the coordinates of each node in the path; is an indicator function indicating whether there is an obstacle at path node k, where the obstacle is 1 and the blank area is 0; λ4 is the weighting factor for obstacle avoidance, and n is the total number of nodes.

3. The 3D modeling design method based on multi-robot collaborative operation of construction robots according to claim 1, characterized in that The spatial error monitoring is the local spatial error Δr between the current position r of the robot j and the task target t i ; then k ; Based on the local spatial error Δr j an adaptive correction amount is obtained; wherein, the adaptive correction amount is dynamically adjusted according to the local spatial error Δr j and the urgency of the task; the robot obtains the adaptive correction amount, and updates the current path through a cost function according to the adaptive correction amount to obtain a new path cost; the cost function is an obstacle collision determination function, indicating whether the robot encounters an obstacle during path correction.

4. The 3D modeling design method based on multi-robot collaborative operation of construction robots according to claim 3, characterized in that The global error is the total error of the local spatial error Δr j ; the global error matrix of the global error is calculated based on the distance between the robot and the task target position, giving the total error of all tasks.

5. The three-dimensional modeling design method based on multi-robot collaborative operation of construction robots according to claim 4, characterized in that, The dynamic adjustment of the task allocation and path planning based on the global error to obtain the task execution plan after global task rescheduling and path optimization includes: Obtain the global error. Perform a global correction on the priority of the task based on the global error to obtain the error correction amount of task i. Obtain the new path cost, and combine it with the error correction amount of task i to determine the new task allocation plan.

6. The three-dimensional modeling design method based on multi-robot collaborative operation of construction robots according to claim 5, characterized in that, The obtaining of the new path cost and combining it with the error correction amount of task i to determine the new task allocation plan: It is calculated by minimizing the task execution cost, including: Among them, T' assihn is the new task assignment scheme; α j is the adjustment weight of robot j; C' path (j, i) is the path cost for robot j to execute task i after correction; γ is the adjustment factor of the path cost, which is used to balance the weights of path optimization and error correction.

7. The three-dimensional modeling design method based on multi-robot collaborative operation of construction robots according to claim 1, characterized in that The task-robot collaboration matrix represents the collaboration relationship between tasks and robots; the elements of the matrix represent the collaboration effect between task i and robot j; the task-robot collaboration matrix is expressed as: Among them, α i is the priority weight of task i, β j is the state adjustment factor of robot j, d(r′ j , t i ) is the error distance between robot j and the target of task i, d max is the maximum tolerable error distance of task i; Based on the task-robot collaboration matrix, a dynamic scheduling algorithm is used to allocate the most suitable robot for each task; a resource adjustment factor is introduced in the dynamic scheduling algorithm to optimize task scheduling, and a dynamic feedback correction factor is introduced to adjust the task allocation of robot j in real time.

8. The three-dimensional modeling design method based on multi-robot collaborative operation of construction robots according to claim 7, wherein, The task execution error E of the robot when performing a task j (t), is expressed as: E j \(r(t)=\lambda_1 \parallel r'\) j \(r(t)-t\) i \(\parallel+\lambda_2|\Delta T\) j (t)|+\lambda_3 \parallel \Delta L j \(r(t)\parallel\) where r′ j (t) is the actual position of robot j at time t; t i is the expected position of target task i; ΔT j (t) is the time error of robot j in performing the task; ΔL j (t) is the load error; λ1, λ2, λ3 are weighting coefficients; Then, based on the task execution error E j (t) corrects the point cloud data, expressed as: Among them, P i corrected is the corrected point cloud data, and P i preprocessed is the original point cloud data; μ(t) is a dynamic adjustment factor that adjusts the correction strength based on the resources of the robot; E max is the maximum error allowed in the task; According to the corrected point cloud data P i corrected Perform weighted optimization on the original 3D model to obtain the optimized 3D model M at the current moment optimized (t); The corrected point cloud data P i corrected is fused with the optimized three-dimensional model M optimized (t) at the current moment to obtain the final complete three-dimensional model.

9. A three-dimensional modeling design system based on multi-robot collaborative operation of construction robots, characterized in that, The system includes: An environmental data acquisition unit, which is used to perform dynamic task allocation and path planning according to the environmental data of the construction site, the robot status information, and the task requirement data, and obtain the set of tasks and paths assigned to each robot as task allocation information; among them, the robot status information includes the current position and the target task position. In the environmental data acquisition unit, the robot is assigned tasks through a multi-objective optimization function, and a hybrid method of dynamic programming and A algorithm is used for path optimization. A task scheduling unit, which is used to collect the real-time feedback of each robot executing tasks, monitor the local space error of each robot respectively based on the real-time feedback and the error of the task allocation information, use machine learning to dynamically calculate the path correction amount of the current robot according to the size of the local space error and the urgency of the task, and the robot updates the current path according to the correction amount to obtain the corrected task execution plan; among them, the corrected task execution plan includes the task number, the robot number, the corrected path cost, and the updated robot position. A global optimization unit, which is used to globally analyze the execution errors of all robots for the corrected task execution plan to obtain the global error, and dynamically adjust the task allocation and path planning based on the global error to obtain the task execution plan after global task rescheduling and path optimization; among them, the optimized task execution plan includes the task number, the robot number, the optimized path planning, and the optimized path cost. A collaborative optimization unit, which is used to construct a task-robot collaboration matrix based on the optimized task execution plan, use a collaborative scheduling algorithm to schedule the task-robot collaboration matrix, and determine the optimized task allocation plan and the adjusted current position of each robot. A 3D modeling unit, which is used to obtain the original point cloud data, generate a preliminary 3D model, and at the same time obtain the task execution error when the robot executes the task, correct the preliminary original point cloud data based on the task execution error and adjust the task allocation plan to obtain the adjusted point cloud data, the position of each robot, and the optimized 3D model, and merge the adjusted point cloud data and the optimized 3D model into a complete 3D model.

Images