BIM (Building Information Modeling) and measurement robot cooperative intelligent measurement method, system, equipment and medium

Abstract

The invention discloses a BIM (Building Information Modeling) and measurement robot cooperative intelligent measurement method, system, equipment and medium, and relates to the technical field of robots, and the method comprises the steps that a robot receives BIM data and collects real-time data of a sensor, and the real-time data and the BIM data are preprocessed; fusing the real-time data and the BIM data, taking the fused data as input, and constructing a navigation model through a genetic algorithm and tabu search; and the navigation model outputs an optimal path, and the robot moves to a target position along the optimal path to measure the target. According to the method, the BIM data and the real-time data of the sensor are fused, so that the measurement precision is remarkably improved, errors are reduced, and the accuracy of a result is ensured. The system has automatic navigation and measurement functions, manual operation is reduced, and efficiency is improved; and through fault detection and recovery functions, the robustness and stability of the system are enhanced. The application of the genetic algorithm and the tabu search optimizes the path planning and improves the navigation efficiency.

Description

Technical Field

[0001] The present invention relates to the field of robot technology, and in particular to a BIM and measurement robot collaborative intelligent measurement method, system, equipment and medium. Background Art

[0002] With the continuous development of the construction industry, traditional measurement robots can no longer meet the needs of the contemporary engineering industry, and the existing technical level will greatly limit their performance and application scope. The actual measurement robot may be limited by sensor accuracy, data processing algorithms or mechanical structure, resulting in insufficient accuracy of measurement results to meet certain strict construction requirements. The robot system may be too complex, requiring complex operation and maintenance processes, and may be affected by environmental conditions and have poor stability. Some older actual measurement robots may be too dependent on specific hardware or software, and when these components fail or become outdated, the performance of the system may be seriously affected. Due to technical level and design limitations, older actual measurement robots may only be suitable for specific types of construction measurement tasks and cannot meet diverse needs. There may be problems with low data processing efficiency, especially for large-scale construction projects or complex structures. The data processing capacity may be insufficient. The manufacturing cost of older actual measurement robots may be high, and professional personnel may be required for operation and maintenance, resulting in higher overall costs. In some cases, the operation of the robot may involve safety issues, such as the risk of collision with personnel or other equipment.

[0003] These shortcomings may limit the efficiency and reliability of older measurement robots in practical applications and need to be solved through technological improvements or upgrades. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: solving the problems of insufficient accuracy, low efficiency and reliance on manual operation in traditional building measurement. Traditional methods are difficult to achieve accurate navigation and measurement in complex environments, and lack effective response mechanisms when facing dynamic obstacles. In addition, poor data fusion and consistency, insufficient path planning optimization, and weak fault detection and system recovery capabilities are also key issues in traditional measurement methods.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a BIM and measurement robot collaborative intelligent measurement method, comprising a robot receiving BIM data and collecting real-time data from sensors, and preprocessing the real-time data and BIM data.

[0007] The real-time data and BIM data are integrated, and the integrated data is used as input to build a navigation model through genetic algorithm and taboo search.

[0008] The navigation model outputs the optimal path, and the robot moves along the optimal path to the target position and measures the target.

[0009] The integration of real-time data and BIM data includes using a joint filtering strategy of an extended Kalman filter and a particle filter for data fusion.

[0010] The construction of the navigation model includes the optimal path planning by combining genetic algorithm with taboo search. In the genetic algorithm part, roulette selection method, cross mapping and mutation operations are introduced to improve the diversity of path search and global optimization capabilities.

[0011] In the taboo search part, a dynamic taboo table is used to adjust the search depth, optimize the search efficiency and improve the path quality.

[0012] As a preferred solution of the BIM and surveying robot collaborative intelligent measurement method described in the present invention, wherein: receiving BIM data includes receiving the structure, size and layout information of the building.

[0013] Collecting real-time sensor data includes collecting the relationship between the robot and surrounding objects and the robot's own physical quantity data through the iDAR, camera, IMU, GPS, ultrasonic sensor, contact sensor, temperature sensor and optical sensor carried by the robot.

[0014] As a preferred solution of the BIM and measurement robot collaborative intelligent measurement method described in the present invention, the preprocessing includes converting BIM data and real-time data into a standard point cloud format, judging the missing data and invalid data parts in the BIM data and real-time data through statistical analysis methods and noise filtering algorithms, deleting the invalid data parts and classifying them as missing data parts, filling the missing data parts through interpolation algorithms and extended Kalman filter data fusion methods, aligning the converted and filled data in the same coordinate system, and performing spatial registration and time synchronization.

[0015] As a preferred solution of the BIM and measurement robot collaborative intelligent measurement method described in the present invention, the fusion of real-time data and BIM data includes combining the extended Kalman filter and the particle filter through a joint filtering strategy, and fusing the pre-processed BIM data and real-time data through the combined algorithm.

[0016] Output at time BIM and measurement robot collaborative intelligent measurement method, system, equipment and medium moment fusion consistency error, according to the output at time The fusion consistency error at each moment checks whether the fused data is consistent in space, time and attributes.

[0017] As a preferred solution of the BIM and surveying robot collaborative intelligent measurement method described in the present invention, wherein: the construction of the navigation model includes combining the fused environmental data and BIM data with the target position to generate multiple initial paths, each path consisting of a continuous node sequence from the starting point to the target point.

[0018] Construct a fitness function to evaluate the quality of each path.

[0019] The path quality is optimized through genetic algorithm and taboo search. The optimization of the path through genetic algorithm includes using roulette wheel selection method to select individuals with high fitness as parents, exchanging parts of the two parent paths through cross mapping to generate a new path; the generated new path is a sub-path, and the sub-path is mutated.

[0020] The mutation operation includes randomly selecting nodes in the path and changing the order of nodes in the path to increase the diversity of the population.

[0021] In each generation, several individuals with the highest fitness are retained as elite individuals. Elite individuals do not require crossover and mutation operations. From the retained elite individuals, 30% to 50% of the elite individuals are selected for taboo search based on the experimenter's experience.

[0022] Taboo search optimizes the path by exchanging the order of two nodes in the path to generate a neighborhood solution set for each elite individual, recording the most recently visited neighborhood solution, adding the neighborhood solution to the taboo table, dynamically adjusting the depth of the taboo search, and optimizing the search efficiency and path quality.

[0023] The fitness of the elite individuals after taboo search optimization is recalculated. When the fitness is improved, the elite individuals are updated and enter the next generation. When the fitness does not improve or decreases, the original elite individuals are retained.

[0024] If the individual optimized by taboo search performs better than the original version, the original individual is replaced by the optimized individual.

[0025] The elite individuals optimized by taboo search and the newly generated offspring individuals form a new generation population, and continue to perform crossover, mutation, elite retention, and local search operations until the ideal optimal path is found.

[0026] As a preferred solution of the BIM and surveying robot collaborative intelligent measurement method described in the present invention, wherein: the moving to the target position along the optimal path includes: the robot moving according to the obtained optimal path, and using CNN combined with laser radar data to identify the obstacle type in real time, measure the position and size of the obstacle, and input the real-time identified obstacle type and the position and size of the obstacle into the obstacle detection function.

[0027] The obstacle state is judged through the output of the obstacle detection function, and the robot's movement behavior is corrected according to the judgment result.

[0028] When the obstacle passability measurement value is greater than or equal to the set value, the threshold function is equal to 1, and the obstacle is judged to be circumventable. When the obstacle is judged to be circumventable, the cruise model is used again for path planning.

[0029] When the obstacle passability measurement value is less than the set value, the threshold function is equal to 0, and the obstacle is judged to be unavoidable. When the obstacle is unavoidable, the reason for the unavoidability is determined.

[0030] As a preferred solution of the BIM and surveying robot collaborative intelligent measurement method described in the present invention, the reason for determining the non-bypassable reason includes determining whether the robot has a fault and the degree of the fault by a real-time health score obtained by monitoring its own status.

[0031] When it is determined that the robot has not malfunctioned, but it is determined that the robot has encountered an obstacle that it cannot bypass, it immediately sends an alarm to the operator and waits for instructions.

[0032] When the robot is judged to have a fault, subsequent selection is made based on the fault score. When the fault score is less than or equal to 80, the robot switches to recovery mode and tries to automatically repair the problem. When the fault score is greater than 80, the robot stops the task and notifies the operator for manual intervention.

[0033] Automatic repair includes using MLP combined with sensor data for fault detection and diagnosis algorithms to identify the source of the fault, automatically perform recovery operations based on the diagnosis results, and evaluate the state after recovery through sensor data and compare it with the standard state.

[0034] Another object of the present invention is to provide a BIM and measurement robot collaborative intelligent measurement system, which can solve the problems of current traditional building measurement technology, including insufficient measurement accuracy, reliance on manual operation, insufficiently intelligent path planning, and poor environmental adaptability, by combining multi-source fusion and intelligent navigation algorithms of BIM data and real-time sensor data.

[0035] As a preferred solution of the BIM and measurement robot collaborative intelligent measurement system described in the present invention, it includes: a data acquisition and processing module, a data fusion and navigation model construction module, and an optimization model and target measurement module. The data acquisition and processing module is used for the robot to receive BIM data and collect real-time data from sensors, and pre-process the real-time data and BIM data. The data fusion and navigation model construction module is used to fuse real-time data and BIM data, and use the fused data as input to construct a navigation model through genetic algorithm and taboo search. The optimization model and target measurement module is used for the navigation model to output the optimal path, and the robot moves to the target position along the optimal path to measure the target.

[0036] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of a BIM and a measuring robot collaborative intelligent measurement method.

[0037] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a BIM and a measuring robot collaborative intelligent measurement method.

[0038] Beneficial effects of the invention: The BIM and measurement robot collaborative intelligent measurement method provided by the invention combines BIM data with real-time sensor data for fusion, significantly improves measurement accuracy, reduces errors, and ensures the accuracy of results. The system has automated navigation and measurement functions, reduces manual operations, and improves efficiency; through fault detection and recovery functions, the robustness and stability of the system are enhanced. The application of genetic algorithms and taboo searches optimizes path planning and improves navigation efficiency. The overall design enables the system to have stronger adaptability and security in complex environments, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0040] Figure 1 An overall flow chart of the BIM and surveying robot collaborative intelligent measurement method provided for the first embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0042] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a BIM and measurement robot collaborative intelligent measurement method, including: S1: The robot receives BIM data and collects real-time data from sensors, and pre-processes the real-time data and BIM data.

[0043] Receiving BIM data includes receiving structural, dimension and layout information of the building.

[0044] Collecting real-time sensor data includes collecting the relationship between the robot and surrounding objects and the robot's own physical quantity data through the iDAR, camera, IMU, GPS, ultrasonic sensor, contact sensor, temperature sensor and optical sensor carried by the robot.

[0045] The preprocessing process includes converting BIM data and real-time data into a standard point cloud format, determining the missing data and invalid data in the BIM data and real-time data through statistical analysis methods and noise filtering algorithms, deleting the invalid data and classifying it as missing data, filling the missing data through interpolation algorithms and extended Kalman filter data fusion methods, aligning the converted and filled data in the same coordinate system, and performing spatial registration and time synchronization.

[0046] It should be noted that the robot receives BIM data and collects real-time data. This step ensures that the structure, size and layout information of the building can be accurately obtained, and combined with the real-time data collected by the sensor system, it provides a basis for subsequent data processing and analysis. Through this process, a comprehensive understanding of the building can be achieved and the foundation for accurate measurement can be laid.

[0047] S2: Fusion of real-time data and BIM data, using the fused data as input to construct a navigation model through genetic algorithm and taboo search.

[0048] The fusion of real-time data and BIM data includes combining the extended Kalman filter and the particle filter through a joint filtering strategy, and fusing the pre-processed BIM data with the real-time data through the combined algorithm.

[0049] A preferred solution of the data fusion algorithm is: ; in, Indicates at time Moment, The estimated value of the fusion state of particles, represents the number of particles, Indicates at time Moment, The weight of a particle, Indicates the description at time At this moment, input control quantity For Particle state The impact of Indicates at time The Kalman gain at time t, Indicates at time The observed value at time, represents the observation model function, Indicates at time Moment, The state of a particle, Indicates at time The control input at the moment, represents the number of the particle, Represents the observation model.

[0050] A preferred solution for checking the formula is: ; in, Indicates at time The fusion consistency error at the moment, Indicates at time Moment, The fused spatial data values, Indicates the first Spatial data values, Indicates at time Moment, The fused time data value, Indicates the first Time data values, Indicates at time Moment, The fused attribute data value, Indicates the first attribute data value, Indicates the total amount of spatial data, Indicates the total number of time data, Indicates the total number of attribute data, Indicates the number of spatial data. Indicates the number of time data, A number indicating attribute data.

[0051] The value range is 0 to 10. The experimenters set the fusion consistency error threshold to 8 based on the experimental data analysis.

[0052] when , it is determined that the data fusion consistency is good and there is no need to perform data fusion again.

[0053] It is judged as a fusion error and data fusion needs to be performed again.

[0054] Furthermore, constructing a navigation model through fused data includes combining the fused environmental data with the BIM data and the target location to generate multiple initial paths, each path consisting of a continuous sequence of nodes from the starting point to the target point.

[0055] Construct a fitness function to evaluate the quality of the path. An optimal solution for constructing the fitness function is: ; in, Indicates the path The fitness function of Indicates the path Length, C Indicates that the path is at location The curvature function at represents the curvature attenuation coefficient, Indicates the path Cost function for the middle and upper obstacles, represents the weight coefficient, express The standard deviation of energy consumption of each node in Indicates the path The total length of the route; the quality of the path is measured by path length, path curvature, obstacle cost, energy consumption standard deviation, and total energy consumption.

[0056] The path quality is optimized by genetic algorithm and taboo search. The optimization of the path by genetic algorithm includes using roulette wheel selection method to select individuals with high fitness as parents, and exchanging parts of the two parent paths through cross mapping to generate new paths. The generated new paths are sub-paths, and mutation operations are performed on the sub-paths.

[0057] The mutation operation includes randomly selecting nodes in the path and changing the order of nodes in the path to increase the diversity of the population.

[0058] In each generation, several individuals with the highest fitness are retained as elite individuals. Elite individuals do not need crossover and mutation operations. From the retained elite individuals, 30% to 50% of the elite individuals are selected according to the experience of the experimenters for taboo search. An optimal solution for taboo search is: ; ; ; ; in, Indicates the path Optimize search results, Indicates the path The neighborhood solution set of Indicates the path In Location The state vector at Indicates the path The depth of taboo search, B Indicates the path The breadth of taboo search, represents the adjustment factor, Indicates that the path Neighborhood solution set Find the path that minimizes the subsequent expression , Indicates the path The neighborhood solution set of Indicates the path exist The state vector is Indicates the path Cannot belong to the taboo list, Represents the index of a specific node in the path. represents the total length of the path, represents a dynamically adjusted function for the tabu search depth, Indicates the path The number of times it was visited during the tabu search process.

[0059] Furthermore, the taboo search optimizes the path by exchanging the order of two nodes in the path to generate a neighborhood solution set for each elite individual, recording the most recently visited neighborhood solution, adding the neighborhood solution to the taboo table, and dynamically adjusting the depth of the taboo search to optimize the search efficiency and path quality. A preferred solution for dynamically adjusting the depth of the taboo search is: ; in, represents a dynamically adjusted function for the tabu search depth, and represents the parameter that controls the variation of tabu search depth over time, Indicates time. The value threshold is between 0 and 1. The value is positively correlated with the search depth.

[0060] It should be noted that the fitness of the elite individuals after taboo search optimization is recalculated. When the fitness is improved, the elite individuals are updated and enter the next generation. When the fitness does not improve or decreases, the original elite individuals are retained.

[0061] If the individual optimized by tabu search performs better than its original version, the original individual is replaced by the optimized one.

[0062] The elite individuals optimized by taboo search and the newly generated offspring individuals form a new generation population, and continue to perform crossover, mutation, elite retention, and local search operations until the ideal optimal path is found.

[0063] S3: The navigation model outputs the optimal path, the robot moves along the optimal path to the target position, and measures the target.

[0064] The robot moves to the target position based on the navigation model, including: the robot moves according to the obtained optimal path, and uses CNN combined with laser radar data to identify the obstacle type in real time, measure the position and size of the obstacle, and input the real-time identified obstacle type and the position and size of the obstacle into the obstacle detection function. A preferred solution of the obstacle detection function is: ; in, represents the output of the obstacle detection function, Indicates the location of the obstacle. Indicates the size of the obstacle. Indicates the fusion result of environmental data and BIM data. Indicates the obstacle type identified by the CNN model combined with lidar data. Represents the Sigmoid function used to dynamically adjust the obstacle detection threshold. Represents the parameter that controls the steepness of the Sigmoid function, Indicates the current time. Indicates the initial time, Represents a set value in the threshold function, which is used to determine when to switch the obstacle detection result. Represents the threshold function.

[0065] Further, through The obstacle state is judged, and the robot's movement behavior is corrected according to the judgment result. The judgment process is specifically expressed as follows:

[0066] when hour, , it is determined that the obstacle can be circumvented. When it is determined that the obstacle can be circumvented, the cruise model is used again for path planning.

[0067] when hour, , determine that the obstacle cannot be circumvented, and when the obstacle cannot be circumvented, determine the reason why it cannot be circumvented.

[0068] It should be noted that when it is determined that an obstacle cannot be circumvented, the real-time health score obtained by monitoring its own status is used to determine whether the robot has a fault and the degree of the fault.

[0069] When it is determined that the robot has not malfunctioned, but it is determined that the robot has encountered an obstacle that it cannot bypass, the system immediately sends an alarm to the operator and waits for instructions.

[0070] When the robot is judged to have a fault, subsequent selection is made based on the fault score. When the fault score is less than or equal to 80, the robot switches to recovery mode and tries to automatically repair the problem. When the fault score is greater than 80, the robot stops the task and notifies the operator for manual intervention.

[0071] Automatic repair includes that the system uses MLP combined with sensor data for fault detection and diagnosis algorithms to identify the source of the fault, automatically performs recovery operations based on the diagnosis results, and evaluates the system status through sensor data after recovery and compares it with the standard status.

[0072] A preferred solution for system status assessment is: ; in, Indicates the comprehensive evaluation result of the restoration effect, Represents the total number of sensors, represents the time interval for evaluation, Indicates The influence weight of each sensor, Indicates the rate of change of the system state during the recovery process, represents the change in time, Indicates Sensors at time The measurement data at the moment, Indicates reference data under standard conditions. Indicates The state variables of the sensors are Represents an index used to identify different sensors. The threshold of is a positive real number, A large value indicates a good recovery effect and the system status is restored to a close standard state.

[0073] Example 2 is an embodiment of the present invention, which provides a BIM and measurement robot collaborative intelligent measurement method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0074] First, a multi-storey commercial building was selected as the experimental object. The building structure is complex and includes various types of obstacles and measurement targets. The BIM model of the building contains information such as structure, size, and layout. In the experimental preparation stage, the three-dimensional model data of the building was exported through the BIM platform, including key information such as the floor plan of each floor, column grid layout, wall thickness, and door and window locations. These data were input into the robot's data processing module in a standard format.

[0075] The robot is equipped with a variety of sensor systems, including lidar, camera, inertial measurement unit, global positioning system, ultrasonic sensor, contact sensor, temperature sensor and optical sensor. These sensors are used to collect real-time environmental data inside the building, such as obstacle location, temperature change, light intensity, etc. In order to ensure the consistency and accuracy of the data, the preprocessing module performs format conversion, noise filtering, spatial registration and time synchronization operations on BIM data and real-time data collected by sensors.

[0076] After data processing is completed, the pre-processed BIM data is fused with real-time data by combining extended Kalman filter and particle filter to build an accurate navigation model. The navigation model generates multiple initial paths through genetic algorithm, and uses optimization algorithm for path evaluation and selection, and finally generates an optimal path to guide the robot's navigation inside the building.

[0077] After the experiment started, the robot began to cruise along the preset path. During the cruise, the obstacle detection algorithm continuously monitored the dynamic changes in the environment. When a circumventable obstacle was detected, the path was automatically adjusted to ensure the robot's safe passage; when an obstacle that could not be circumvented was encountered, it switched to monitoring mode and sent an alert to the operator. After the robot successfully navigated to the target location, it automatically switched to measurement mode and began to accurately measure the structure, size and layout of the building.

[0078] The entire experimental process was repeated many times to verify the stability and accuracy of the system under different environments. After each experiment, the measured data and BIM model data were compared and analyzed to evaluate the accuracy of the measurement results. The experimental data are shown in Table 1.

[0079] Table 1 Experimental data table Parameter name Subject 1 Subject 2 Subject 3 Subject 4 Subject 5 Subject 6 Subject 7 Navigation path length (m) 120 135 110 150 125 140 130 Navigation time(s) 300 320 290 340 310 330 305 Measurement error(mm) 2.5 3 2 3.5 2.7 3.2 2.9 Obstacle detection rate (%) 98.5 97 99 96.5 98 97.5 98.2 Data fusion consistency (score) 9.5 9.2 9.6 9 9.3 9.4 9.5 Genetic Algorithm Convergence Algebra 50 55 48 60 53 57 52 Final path selection rate (%) 92 90.5 93.5 89 91.5 90.8 92.3

[0080] From the experimental data, it can be seen that the BIM measurement robot's system performs well in different experimental objects. The navigation path length and time show that it can effectively plan the path and achieve efficient navigation in complex environments. The optimization algorithm shortens the calculation time and quickly generates the optimal path in a dynamic environment, ensuring that the robot quickly reaches the target location. The measurement error is controlled within 3.5 mm, showing high accuracy and meeting the strict requirements of building measurement. Compared with existing measurement systems, the processing method that combines BIM data with sensor data significantly improves measurement consistency and accuracy.

[0081] The obstacle detection rate is close to 100%, indicating that it can accurately identify and process obstacles in the environment and reduce navigation errors. The combination of CNN and LiDAR performs well in real-time detection, greatly improving the accuracy and response speed of detection. The data fusion score is high, and the combination of extended Kalman filter and particle filter ensures the consistency and stability of the data, especially when processing multi-source data, which is more reliable than a single filtering algorithm.

[0082] In path planning, the improved genetic algorithm improves the convergence speed of the algorithm and the effectiveness of path selection by introducing the elite retention strategy and taboo search, and reduces the problem of local optimal solutions. In actual operation, these algorithms are applied to automate navigation and measurement of complex building environments, which significantly improves the operation efficiency and reliability, demonstrating the innovation and practical application value of the invention in building intelligent measurement.

[0083] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0084] Embodiment 3 is an embodiment of the present invention, which provides a BIM and measurement robot collaborative intelligent measurement system, including a data acquisition and processing module 100, a data fusion and navigation model construction module 200, and an optimization model and target measurement module 300.

[0085] Among them, the data acquisition and processing module 100 is used for the robot to receive BIM data and collect real-time data from sensors, and pre-process the real-time data and BIM data.

[0086] The data fusion and navigation model building module 200 is used to fuse real-time data and BIM data, and use the fused data as input to build a navigation model through genetic algorithm and taboo search.

[0087] The optimization model and target measurement module 300 is used for the navigation model to output the optimal path, and the robot moves to the target position along the optimal path to measure the target.

[0088] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0089] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0090] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0091] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logical function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. The BIM and measurement robot collaborative intelligent measurement method is characterized by: include: The robot receives BIM data and collects real-time data from sensors, and pre-processes the real-time data and BIM data; Fusion of real-time data and BIM data, using the fused data as input to construct a navigation model through genetic algorithm and taboo search; The navigation model outputs the optimal path, and the robot moves along the optimal path to the target position and measures the target; Fusion of real-time data and BIM data includes data fusion using a joint filtering strategy of an extended Kalman filter and a particle filter; Building a navigation model This includes using a combination of genetic algorithm and taboo search to plan the optimal path. In the genetic algorithm part, roulette selection, cross-mapping and mutation operations are introduced to improve the diversity of path search and global optimization capabilities. In the taboo search part, a dynamic taboo table is used to adjust the search depth, optimize the search efficiency and improve the path quality.

2. The BIM and measurement robot collaborative intelligent measurement method according to claim 1, characterized in that: The receiving of BIM data comprises: receiving information on the structure, dimensions and layout of the building; Collecting real-time sensor data includes collecting the relationship between the robot and surrounding objects and the robot's own physical quantity data through the iDAR, camera, IMU, GPS, ultrasonic sensor, contact sensor, temperature sensor and optical sensor carried by the robot.

3. The BIM and measurement robot collaborative intelligent measurement method according to claim 1 or 2, characterized in that: The pretreatment includes: Convert BIM data and real-time data into standard point cloud format, determine missing data and invalid data in BIM data and real-time data through statistical analysis method and noise filtering algorithm, delete invalid data and classify them as missing data, fill missing data through interpolation algorithm and extended Kalman filter data fusion method, align converted and filled data in the same coordinate system, and perform spatial registration and time synchronization.

4. The BIM and measurement robot collaborative intelligent measurement method according to claim 3, characterized in that: The integration of real-time data and BIM data includes: The extended Kalman filter and the particle filter are combined through a joint filtering strategy, and the pre-processed BIM data and real-time data are fused through the combined algorithm; Output at time The fusion consistency error at the moment is calculated according to the output at time The fusion consistency error at each moment checks whether the fused data is consistent in space, time and attributes.

5. The BIM and measurement robot collaborative intelligent measurement method according to claim 1, 2 or 4, characterized in that: The constructing of the navigation model comprises: Combine the fused environmental data with the BIM data and the target location to generate multiple initial paths, each of which consists of a continuous sequence of nodes from the starting point to the target point; Construct a fitness function to evaluate the quality of each path; The path quality is optimized by genetic algorithm and taboo search. The optimization of the path by genetic algorithm includes using roulette wheel selection method to select individuals with high fitness as parents, exchanging parts of two parent paths through cross mapping to generate new paths; the generated new paths are sub-paths, and mutation operations are performed on the sub-paths; The mutation operation includes randomly selecting nodes in the path and changing the order of nodes in the path to increase the diversity of the population; In each generation, several individuals with the highest fitness are retained as elite individuals. Elite individuals do not need crossover and mutation operations. From the retained elite individuals, 30% to 50% of the elite individuals are selected for taboo search based on the experience of the experimenters. The taboo search optimizes the path by exchanging the order of two nodes in the path to generate a neighborhood solution set for each elite individual, recording the most recently visited neighborhood solution, adding the neighborhood solution to the taboo table, and dynamically adjusting the depth of the taboo search to optimize the search efficiency and path quality. Recalculate the fitness of the elite individuals after taboo search optimization. When the fitness is improved, update the elite individuals and enter the next generation. When the fitness is not improved or decreases, retain the original elite individuals. If the individual optimized by taboo search performs better than the original version, replace the original individual with the optimized one; The elite individuals optimized by taboo search and the newly generated offspring individuals form a new generation population, and continue to perform crossover, mutation, elite retention, and local search operations until the ideal optimal path is found.

6. The BIM and measurement robot collaborative intelligent measurement method according to claim 5, characterized in that: The moving to the target position along the optimal path includes: The robot moves according to the optimal path obtained, and uses CNN combined with lidar data to identify the obstacle type in real time, measure the location and size of the obstacle, and input the real-time identified obstacle type and the location and size of the obstacle into the obstacle detection function; The obstacle state is judged through the output of the obstacle detection function, and the robot's movement behavior is corrected according to the judgment result; When the obstacle passability measurement value is greater than or equal to the set value, the threshold function is equal to 1, and it is judged that the obstacle can be circumvented. When it is judged that the obstacle can be circumvented, the cruise model is used again for path planning; When the obstacle passability measurement value is less than the set value, the threshold function is equal to 0, and the obstacle is judged to be unavoidable. When the obstacle is unavoidable, the reason for the unavoidability is determined.

7. The BIM and measurement robot collaborative intelligent measurement method according to claim 1, 2, 4 or 6, characterized in that: The reasons for determining that the detour is not possible include: The real-time health score obtained by monitoring its own status determines whether the robot has a fault and the degree of the fault; When it is determined that the robot has not failed, it is determined that the robot has encountered an obstacle that it cannot bypass, and an alarm is immediately sent to the operator to wait for instructions; When the robot is judged to have a fault, subsequent selection is made according to the fault score. When the fault score is less than or equal to 80, the robot switches to recovery mode and tries to automatically repair the problem. When the fault score is greater than 80, the robot stops the task and notifies the operator for manual intervention. Automatic repair includes using MLP combined with sensor data for fault detection and diagnosis algorithms to identify the source of the fault, automatically perform recovery operations based on the diagnosis results, and evaluate the state after recovery through sensor data and compare it with the standard state. 8.BIM and measurement robot collaborative intelligent measurement system, characterized by: It includes a data acquisition and processing module (100), a data fusion and navigation model building module (200), and an optimization model and target measurement module (300); The data acquisition and processing module (100) is used for the robot to receive BIM data and collect real-time data from sensors, and to pre-process the real-time data and BIM data; The data fusion and navigation model construction module (200) is used to fuse real-time data and BIM data, and use the fused data as input to construct a navigation model through genetic algorithm and taboo search; The optimization model and target measurement module (300) is used for the navigation model to output the optimal path, and the robot moves to the target position along the optimal path to measure the target.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the BIM and surveying robot collaborative intelligent measurement method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the BIM and surveying robot collaborative intelligent measurement method described in any one of claims 1 to 7 are implemented.

Images