Dynamic UAV path planning method, system, equipment and medium based on BIM construction simulation

Abstract

The present invention discloses a dynamic UAV path planning method, system, equipment and medium based on BIM construction deduction, which relates to the field of building construction inspection technology, including constructing a BIM construction deduction model, integrating real-time data, generating a deduction sequence of the construction stage, and sensing the construction scene status in real time; developing an intelligent UAV path planning system, generating an optimal flight path, and automatically planning the UAV inspection path; based on SLAM technology and multi-sensor fusion, the UAV collaborative control dynamically adjusts the path, uses deduction to verify intelligent obstacle avoidance, and processes inspection data in real time; the method of the present invention dynamically generates and optimizes the inspection path, adapts to the real-time changes of the construction site, and improves the inspection efficiency and coverage; adopts a path planning algorithm to balance time and obstacle avoidance requirements, and improves the accuracy and timeliness of the inspection plan; introduces SLAM technology and depth sensors to ensure the safety and reliability of the inspection task and avoid flight interruptions or collisions.

Description

Technical Field

[0001] The present invention relates to the field of building construction inspection technology, and specifically to a dynamic drone path planning method, system, equipment and medium based on BIM construction deduction. Background Art

[0002] In construction management, BIM is used to generate information models of building components and systems, which can be used for schedule planning, resource management, and conflict detection. By integrating BIM with construction plans, project managers can better understand the construction process, optimize resource allocation, and reduce potential errors and conflicts. However, traditional BIM models are typically created during the design phase and may not reflect the dynamic changes in the construction process. The construction process involves a large number of temporary structures, equipment, and materials, which may not be fully accounted for in the BIM model. As a result, path planning based on static BIM models may not be able to adapt to actual changes in the construction process.

[0003] On the other hand, the application of drone technology in the construction sector is also rapidly developing. Drones can be used for a variety of purposes, such as surveying, inspection, monitoring, and mapping. Drone technology can quickly and accurately collect data, reduce human intervention, and improve safety. In construction management, drones can be used to monitor progress, check structural integrity, and generate real-time updates on construction sites.

[0004] While BIM and drone technology offer their respective advantages in the construction industry, existing technologies combining them for dynamic path planning still have some shortcomings. Existing drone path planning often relies on a static representation of the environment. On construction sites, the environment is dynamic, with workers, equipment, and materials constantly moving. Existing path planning algorithms may not be able to effectively handle these dynamic obstacles, resulting in inaccurate and unsafe path planning.

[0005] Furthermore, the integration of BIM and drone data often requires manual work or the use of different software tools, which can lead to inconsistent data and inefficient operations. The lack of automatic integration and updating of real-time data makes dynamic path planning based on BIM difficult to achieve. Summary of the Invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problems solved by the present invention are: the existing technical drone construction inspection path planning method relies on the static BIM construction simulation model, which makes it impossible to dynamically adapt to changes in construction scenarios, the synchronization efficiency of real-time data and BIM construction simulation model is low, and the path planning and obstacle avoidance decision-making are not intelligent enough. It also solves the problems of how to achieve dynamic coordination between construction simulation and drone path, how to verify obstacle avoidance strategy through multi-sensor fusion, and how to efficiently integrate the Internet of Things and BIM system.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: a dynamic UAV path planning method based on BIM construction deduction, including constructing a BIM construction deduction model, integrating real-time data, generating a deduction sequence for the construction phase, and sensing the status of the construction scene in real time; developing an intelligent UAV path planning system, generating an optimal flight path, and automatically planning the UAV inspection path; based on SLAM technology and multi-sensor fusion, the UAV collaborative control dynamically adjusts the path, uses deduction to verify intelligent obstacle avoidance, and processes inspection data in real time; integrating real-time data includes constructing real-time synchronization between the physical state of the construction site and the BIM construction deduction model, and establishing a bridge between the BIM construction deduction model and the Internet of Things platform; generating a deduction sequence for the construction phase includes seamlessly integrating the static BIM construction deduction model with the dynamic construction plan to form a time-space integrated construction deduction system; automatically planning the UAV inspection path includes deeply integrating BIM construction information and UAV path planning to construct an intelligent inspection path; using deduction to verify intelligent obstacle avoidance includes introducing SLAM real-time mapping and obstacle avoidance mechanism to control dynamic construction environment changes in real time.

[0009] As a preferred solution of the dynamic drone path planning method based on BIM construction deduction described in the present invention, the construction of the BIM construction deduction model includes creating a building information model based on BIM software, combining the BIM construction deduction model with the time dimension, using construction simulation software to generate a deduction sequence of construction stages, and predicting construction progress and site changes.

[0010] As a preferred solution of the dynamic drone path planning method based on BIM construction deduction described in the present invention, the integration of real-time data includes building a sensor network, synchronizing with the BIM construction deduction model in real time through the Internet of Things platform, and dynamically sensing and updating the construction scene; based on the API plug-in, seamlessly integrating the BIM construction deduction model with the real-time data of the construction site sensor network.

[0011] As a preferred solution of the dynamic UAV path planning method based on BIM construction deduction described in the present invention, the development of an intelligent UAV path planning system includes extracting the spatial layout data and construction stage information of the BIM construction deduction model, and converting the spatial layout data and construction stage information into the format required for UAV path planning.

[0012] As a preferred solution of the dynamic UAV path planning method based on BIM construction deduction described in the present invention, the generation of the optimal flight path includes generating the optimal flight path based on the intelligent path planning algorithm according to the construction scene of the BIM construction deduction model and the real-time data of the construction site sensor network, introducing a heuristic method to optimize the UAV flight path, and intelligently generating and adjusting the UAV inspection path.

[0013] As a preferred solution of the dynamic UAV path planning method based on BIM construction deduction described in the present invention, the UAV collaborative control dynamically adjusts the path, including using real-time positioning and SLAM technology to enable the UAV to perform self-positioning and path adjustment during flight.

[0014] As a preferred solution of the dynamic UAV path planning method based on BIM construction deduction described in the present invention, the use of deduction to verify intelligent obstacle avoidance includes, based on multi-sensor fusion technology, combined with SLAM technology, real-time detection of obstacles in front, combined with real-time data from the sensor network, to detect and dynamically avoid obstacles in front of the UAV.

[0015] Another object of the present invention is to provide a dynamic UAV path planning system based on BIM construction simulation, which can solve the problems of the current UAV construction inspection system, such as the disconnection between static models and dynamic construction scenes, low efficiency of multi-source data collaboration, and reliance on manual intervention in obstacle avoidance strategies, by integrating BIM construction simulation models, real-time data of the Internet of Things, and intelligent path planning algorithms. It can realize the dynamic coupling of construction simulation and UAV paths, autonomous obstacle avoidance under real-time perception of environmental changes, and efficient integration of BIM and Internet of Things platforms.

[0016] As a preferred solution of the dynamic UAV path planning system based on BIM construction deduction described in the present invention, it includes: a data fusion module, a path planning module, a UAV control module, and an intelligent analysis module; the data fusion module is used to integrate the BIM construction deduction model and real-time sensor data to construct a dynamically updated construction scene model; the path planning module is used to generate and optimize the UAV's inspection path based on the construction scene model provided by the data fusion module using an intelligent algorithm to adapt to the dynamic changes of the construction site; the UAV control module is used to control the UAV to inspect according to the path generated by the path planning module, dynamically adjust according to real-time data, collect images, videos and sensor data, and transmit them to the control center in real time; the intelligent analysis module is used to preprocess and format the inspection data collected by the UAV, compare and analyze it with the BIM construction deduction model, identify construction deviations, defects and potential risks, and generate a visual report.

[0017] 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 dynamic unmanned aerial vehicle path planning method based on BIM construction deduction.

[0018] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a dynamic unmanned aerial vehicle path planning method based on BIM construction deduction.

[0019] Beneficial effects of the present invention: The dynamic UAV path planning method based on BIM construction deduction provided by the present invention seamlessly integrates the static BIM construction deduction model with the dynamic construction plan through space-time integrated modeling, combines SLAM, multi-sensor data and real-time synchronization of the Internet of Things, realizes dynamic perception and prediction of construction scenes, and significantly improves the adaptability and accuracy of UAV inspections; generates the optimal inspection path based on the BIM construction deduction sequence, and dynamically optimizes it through intelligent algorithms, combines real-time obstacle avoidance and collaborative control, solves the autonomy and safety problems of path planning in complex construction environments, and reduces the need for manual intervention; efficiently integrates the BIM construction deduction model and the Internet of Things data through API, constructs a "physical-digital" real-time mapping, combines the intelligent analysis module to quickly identify construction deviations and risks, realizes closed-loop control of construction progress, quality and safety, and improves construction management efficiency; organically integrates SLAM mapping, heuristic path planning, multi-sensor fusion and other technologies to form a complete technology chain covering data collection, path optimization, dynamic obstacle avoidance and result analysis, and provides a full-process solution for smart construction sites. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is an overall flow chart of the dynamic UAV path planning method based on BIM construction deduction provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0022] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0023] Example 1, reference Figure 1 , as one embodiment of the present invention, provides a dynamic UAV path planning method based on BIM construction deduction, including:

[0024] S1: Build a BIM construction simulation model, integrate real-time data, generate simulation sequences for the construction phase, and perceive the status of the construction scene in real time.

[0025] Furthermore, constructing a BIM construction simulation model includes creating a building information model based on BIM software, combining the BIM construction simulation model with the time dimension, using construction simulation software to generate a simulation sequence of the construction phase, and predicting construction progress and site changes.

[0026] Furthermore, BIM software includes, but is not limited to, Autodesk Revit and Navisworks, which analyzes and creates the building's three-dimensional geometry, construction phase plan, key checkpoints, and site layout, and constructs a detailed three-dimensional model. Construction simulation software includes, but is not limited to, Navisworks Simulate and Synchro, which adds a time dimension to the BIM construction simulation model and transmits the generated simulation sequence and information to the drone's path planning solution.

[0027] It should be noted that integrating real-time data includes building a sensor network, synchronizing with the BIM construction simulation model in real time through the Internet of Things platform, dynamically sensing and updating the construction scene; and seamlessly integrating the BIM construction simulation model with the real-time data of the construction site sensor network based on API plug-ins.

[0028] It should also be noted that building a sensor network involves deploying cameras, lidar, RFID, and temperature and humidity sensors at the construction site to collect environmental data, personnel and equipment locations, and dynamic change information. The sensor data is integrated into the data fusion module using MQTT and the Azure IoT Hub IoT platform. Sensors are bound to BIM components using unified identification rules to enhance real-time perception of site conditions and synchronize updates with the BIM construction simulation model. The periodic refresh of component properties in the BIM system is represented as:

[0029] ;

[0030] in, Represents component properties, Expressed as temperature and noise level.

[0031] It should also be noted that the present invention realizes dynamic perception of the construction site by constructing a BIM construction simulation model and combining it with real-time construction data. It can reflect the construction progress and changes in the on-site environment in real time, and provide an accurate reference basis for drone path planning. It overcomes the limitations of traditional methods that rely on static models or preset routes, and improves the timeliness and adaptability of path planning.

[0032] S2: Develop an intelligent drone path planning system to generate the optimal flight path and automatically plan drone inspection paths.

[0033] Furthermore, the development of an intelligent UAV path planning system includes extracting the spatial layout data and construction stage information of the BIM construction simulation model, and converting the spatial layout data and construction stage information into the format required for UAV path planning.

[0034] It should be noted that the generation of the optimal flight path includes generating the optimal flight path based on the intelligent path planning algorithm, the construction scenario of the BIM construction simulation model and the real-time data of the construction site sensor network, introducing a heuristic method to optimize the UAV's flight path, and intelligently generating and adjusting the UAV inspection path. The heuristic function is expressed as:

[0035] ;

[0036] in, Indicates the flight node from the current drone The estimated total cost to the target node. The smaller the estimated total cost value, the better the path. Represents a node of the drone, The current drone is at the node The comprehensive environmental risk assessment values ​​are normalized to a range of 0 to 1 and are expressed as:

[0037] ;

[0038] in, represents the risk factor index, represents the total number of risk factors, Indicates the Risk factors in Real-time normalized perception value on the node, Indicates the The fusion weight of the section construction risk factor, Indicates the current node The normalized Euclidean distance to the target node, normalized to 0 to 1, is expressed as:

[0039] ;

[0040] in, Indicates the current node The geometric distance to the target node, Indicates the maximum flight distance in the BIM construction simulation model. Represents the distance score weight parameter, which controls the influence of geometric distance on the total cost. Represents the risk score weight parameter, which controls the proportion of security risk in the total cost. and The two weight parameters can be flexibly configured according to different flight strategies: in high-risk construction areas, Higher, prioritize risk avoidance; set when the task is urgent Higher, priority is given to speeding up. The system sets a heuristic threshold Used to determine whether the current path meets the planning requirements:

[0041] If all nodes in the current path ≤ , the path is considered feasible; if there are continuous nodes > , then call the local A* algorithm or intelligent path planning algorithm to replan the path.

[0042] It should also be noted that based on The calculation results show that an optimal solution for adjusting the inspection path of the UAV includes path cost clustering analysis: clustering the cost of each node in the initial planning path. Perform cluster analysis to identify “high-cost segments” (i.e., continuous high Interval), usually means that the area has high risk or low flight efficiency; Local path reconstruction mechanism: For the identified high-cost section, the system triggers the local path replanning module (local A* algorithm), limiting the search range between the current location node and the target point to find a feasible low-risk alternative path segment; Path optimization strategy (minimum total cost selection): Multiple candidate paths are compared for the total cost function:

[0043] ;

[0044] in, represents the sum of the total proxy value of the UAV flight path, Indicates the path The normalized flight time of all flight segments in seconds, It represents the additional time constraint, i.e. the maximum flight time, and selects the path with the smallest total cost and that meets the constraints as the preferred option; the path memory mechanism is combined with reinforcement learning: the system records the effect and flight performance of each candidate path during the path planning process, and feeds it back to the BIM construction simulation as a training sample, gradually forming a strategy library for path optimization and realizing adaptive path evolution.

[0045] It should also be noted that the intelligent path planning algorithm includes the intelligent path planning algorithm that implements the A* algorithm and the Dijkstra algorithm. Based on the BIM construction deduction model, the starting position of the drone is marked as the starting point, the key checkpoints that the drone needs to inspect are marked as target points, buildings, equipment, and people are marked as static obstacles as map information in the algorithm, and the positions of dynamic obstacles in the real-time sensor data are marked as dynamic obstacles and added to the map.

[0046] It should also be noted that the introduction of heuristic methods to optimize the flight path of drones includes using genetic algorithms and ant colony algorithms to optimize the flight path of drones, using adaptive crossover rate and mutation rate, adjusting according to the fitness of the population, and defining the fitness function:

[0047] ;

[0048] in, Represents candidate paths The total cost of the path is better, the smaller the value is, Candidate path The sum of the unit energy consumption normalized flight distances of all flight segments, in joule equivalent meters, is used to reflect the distance burden caused by flight paths in different energy consumption density areas, expressed as:

[0049] ;

[0050] in, Indicates the path segment number index, 'Indicates the path segment index, express Euclidean distance of the path segment, in meters, Indicates the Energy consumption coefficient per unit distance of segment space area, set open space area ∈[8,10], densely structured area ∈[11,13], construction high interference area ∈[13,16], set open empty area ≥17, unit joule, Indicates the path The normalized flight time of all the segments above, in seconds, is normalized to a weighted dimension by adjusting the actual time units, expressed as:

[0051] ;

[0052] in, Indicates the path segment number index, 'Indicates the path segment index, express Euclidean distance of the path segment, in meters, Indicates that the drone is Estimated flight speed along the flight path, in meters per second, Indicates the The execution delay of the segment task trigger, in seconds, is the construction risk factor of the area through which the path passes, and the sum of the environmental risk intensity assessment values ​​of each node on the path, reflecting the complexity and safety of the construction environment, expressed as:

[0053] ;

[0054] in, Indicates the path segment number index, 'Indicates the path segment index, Indicates the The comprehensive construction risk level score of the section is directly mapped and assigned based on the BIM construction deduction model and construction scene identification. Indicates the The fusion weight of the section construction risk factor is jointly assigned by the BIM construction simulation model and multi-source sensor data. 、 、 These are weight parameters that can be configured as needed or dynamically learned and adjusted. The sum of the three weight parameters can be normalized to 1. They are used to control the weight ratio of each factor during path optimization and provide real-time construction site data for path planning.

[0055] in, 、 、 Can be configured based on different mission requirements: if flying at low altitude, high navigation accuracy is required, If the task is urgent and the wind speed is high, you can increase If you fly at night, the risk is high and you can increase , compare the fitness values ​​of all paths, if the optimal candidate path ≤ the set fitness threshold, indicating that the path meets the acceptable cost. Otherwise, the number of iterations is increased and the adjustment is made. 、 、 Weight parameters make the algorithm biased towards efficiency or risk aversion.

[0056] It should also be noted that A preferred solution is to apply the calculation results of the method, which specifically includes: in the iterative process, retain the path with the smallest fitness value as the current optimal path. If the fitness threshold is less than or equal to the set one, the path will directly enter the task delivery process; if it is not satisfied, the path re-optimization mechanism will be triggered to perform "local segment replacement" on the path segments with high cost value, and reconstruct the path segments with the help of the surrounding low-cost path points to reduce the total cost. If the construction environment changes drastically and the response demand is fast, the system can enable the "safety weighted fast mode", that is, directly select the path segments that meet the requirements. ≤ In the path of setting the construction risk factor threshold, The shortest one is the best, and the full evaluation of some cost items is skipped to speed up the decision.

[0057] The heuristic method Manhattan distance calculation formula is expressed as:

[0058] ;

[0059] in, Represents the Manhattan distance between the current drone node and the target inspection point, which is used for heuristic function evaluation in path planning. Indicates the current lateral position of the drone in the BIM construction simulation model space. Indicates the horizontal position of the target inspection point in the BIM construction simulation model. Indicates the current longitudinal position of the drone in the BIM construction simulation model. Indicates the vertical position of the target inspection point in the BIM construction simulation model.

[0060] It should also be noted that the present invention has developed an intelligent drone path planning system that integrates the A* algorithm, Dijkstra algorithm, genetic algorithm, and ant colony algorithm. It can generate efficient and safe flight paths based on the BIM construction deduction model and real-time sensor data, and dynamically adjust to adapt to changes in the construction site, realizing the intelligence and automation of path planning and improving inspection efficiency and accuracy.

[0061] S3: Based on SLAM technology and multi-sensor fusion, drones coordinate control to dynamically adjust paths, use deduction to verify intelligent obstacle avoidance, and process inspection data in real time.

[0062] Furthermore, the UAV collaborative control dynamically adjusts the path, including the use of real-time positioning and SLAM technology to enable the UAV to perform self-positioning and path adjustment during flight.

[0063] It should be noted that the use of deduction to verify intelligent obstacle avoidance includes real-time detection of obstacles ahead based on multi-sensor fusion technology, combined with SLAM technology, and detection and dynamic obstacle avoidance of obstacles ahead of the drone in combination with real-time data from the sensor network.

[0064] It should be noted that the detection and dynamic obstacle avoidance of the UAV's front obstacles include the UAV running SLAM through lidar or binocular camera, building a construction site map in real time, performing image recognition, calibrating and classifying the detected obstacles, and introducing a dynamic interactive obstacle avoidance evaluation model. The obstacle set perceived by the UAV during the mapping process can be a set of multiple obstacle point clouds and contours. The dynamic interactive obstacle avoidance evaluation model is expressed as:

[0065] ;

[0066] in, The function value that represents the degree of risk of obstacles faced by the current environment, Indicates the current candidate path of the UAV, Indicates the number of obstacles, Indicates the current number of obstacles. Indicates that the drone reaches The distance measurement of obstacles, Indicates the The probability of whether an obstacle has dynamic characteristics. If the obstacle is in a continuous motion trend, the value is greater than 0.7. If it is in a static state, the value is 0. Indicates the If an obstacle has been marked in the current BIM construction simulation model, it is 1, otherwise it is 0. It represents the intersection probability within the time window. If the intersection time point is close, it is 1; if the obstacle is far away from the path, it is 0. 、 、 、 Indicates dynamically adjustable parameters, which are assigned values ​​through inspection history data optimization. Indicates a constant value.

[0067] It should also be noted that real-time processing of inspection data includes drones transmitting inspection videos and images to the control center in real time via wireless networks, using 4G / 5G and Wi-Fi high-bandwidth wireless communication protocols to receive data, automatically comparing it with the BIM construction simulation model, and using computer vision image processing algorithms to identify construction deviations, defects, and potential risks; data analysis results are used to generate automatic inspection reports, including problems found, inspection route maps, and construction status summaries, and feedback is generated based on the analysis results report to update the BIM construction simulation model or adjust the sensor configuration, and to provide a three-dimensional display of the construction status, flight path, and problem areas for reference by construction management personnel.

[0068] It should also be noted that the present invention realizes real-time positioning and dynamic obstacle avoidance of drones through SLAM technology and sensors, transmits inspection data to the control center in real time through wireless networks, and uses image processing algorithms and computer vision technology to automatically identify construction deviations, defects and potential risks, and generate inspection reports, realizing full process automation from data collection to feedback, improving inspection efficiency and the accuracy of data analysis, and providing an intelligent solution for construction management.

[0069] Example 2 is an embodiment of the present invention, which provides a dynamic UAV path planning method based on BIM construction deduction. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0070] To validate the practicality and innovativeness of a dynamic drone path planning method based on BIM construction simulation, six experiments were designed across typical construction phases and scenarios, covering construction daytime, densely populated areas, and areas with high-activity activity. The experiments compared the performance of a traditional static-path drone inspection method with that of the proposed solution. The BIM construction simulation model used, built using Autodesk Revit and Navisworks, integrates a construction phase simulation sequence and synchronizes construction data with sensors deployed on-site in real time via the MQTT IoT platform, forming a dynamic perception network for construction status.

[0071] First, based on the BIM construction simulation model, the current stage's geometric structure, component status, and construction interference information are extracted, and spatial layout point cloud data is derived. This data is then structured into a three-dimensional topological map acceptable to the path planning algorithm. Regarding path generation, this method combines the A* algorithm, the ant colony optimization algorithm, and the construction risk cost function to automatically calculate the optimal flight path for the drone from its starting point to the inspection target. The cost model is then adjusted in real time based on construction risk factors, achieving dynamic adaptive optimization of the path.

[0072] During flight, the drone uses SLAM technology for high-precision real-time positioning and mapping. By fusing visual images with LiDAR data, it identifies obstacles ahead on the current path, dynamically assesses their risk level, and uses obstacle avoidance functions to replan the path accordingly. If the current path shows a high-risk trend, the updated path results are synchronously written back to the BIM construction simulation model, providing real-time feedback on the construction status space.

[0073] After the flight, the drone transmits images and point cloud data back to the control platform via a wireless communication network. The platform then uses image processing algorithms to automatically compare the data with the BIM component model, identifying construction deviations, defects, and risk factors. It then automatically generates an inspection report, achieving a closed-loop automation process from path perception to feedback and decision-making. The experiment collected data from six scenarios, analyzing multiple metrics such as flight path length, mission duration, obstacle recognition rate, path update frequency, inspection coverage completeness, and report output latency.

[0074] Table 1 Comparison of BIM UAV path planning and intelligent obstacle avoidance

[0075]

[0076] As shown in Table 1, the present invention demonstrates advantages in both path efficiency and planning intelligence. In terms of path length and flight time, compared to traditional static planning methods, the average path is shortened by approximately 23%, and flight time is compressed by over 20%. High flight efficiency is particularly maintained in densely populated areas, demonstrating the collaborative control capabilities of the heuristic function and the component risk cost model during path planning.

[0077] In terms of obstacle recognition capabilities, the multi-source perception fusion strategy introduced in this invention effectively improves dynamic recognition accuracy, raising the average recognition rate to over 94%. Traditional methods, limited by static layers and a single visual sensor, maintain an accuracy rate of around 80%. Experimental scenarios included areas with dense human traffic and mechanical intersections, verifying that the dynamic consistency mechanism between the SLAM map and the BIM construction simulation model supports the accuracy of the obstacle avoidance strategy.

[0078] In summary, the present invention constructs a BIM construction simulation model, integrates path intelligent optimization, obstacle avoidance dynamic modeling, SLAM collaborative control and visual intelligent recognition mechanism, and realizes a closed-loop dynamic path planning system for the entire process from construction status perception, path calculation, obstacle warning to data feedback. It overcomes the limitations of traditional methods such as path rigidity, feedback lag and insufficient recognition accuracy, and shows obvious novelty and practicality.

[0079] Example 3 is an embodiment of the present invention, which provides a dynamic UAV path planning system based on BIM construction deduction, including a data fusion module, a path planning module, a UAV control module, and an intelligent analysis module.

[0080] Among them: the data fusion module includes BIM construction simulation module, sensor data acquisition module, data preprocessing module, and data synchronization module.

[0081] It should be noted that the BIM construction simulation module is used to import the BIM construction simulation model into the system and extract the building structure, construction progress, and key checkpoints; the sensor data acquisition module is used to receive real-time data from sensors deployed at the construction site, including environmental parameters, personnel and equipment locations, and dynamic changes; the data preprocessing module is used to clean, format, and fuse the collected BIM construction simulation model data and sensor data; the data synchronization module is used to synchronize the preprocessed data to the database and update the BIM construction simulation model in real time to ensure that path planning and intelligent analysis are always based on the latest construction status information.

[0082] It should also be noted that the data fusion module is used for sequential execution. After deduction, collection, and preprocessing, it is finally synchronized to the path planning module. The data fusion module provides a data basis for the path planning module and the intelligent analysis module.

[0083] The path planning module includes a map construction module, a path generation algorithm module, a path optimization module, and a dynamic adjustment module.

[0084] It should be noted that the map construction module is used to construct a three-dimensional environment map based on the data transmitted by the data fusion module; the path generation algorithm module is used to implement the A* algorithm and Dijkstra algorithm intelligent path planning algorithm to generate the initial inspection path of the UAV based on the map information; the path optimization module is used to optimize the initial path using genetic algorithm and ant colony algorithm; the dynamic adjustment module monitors the changes in the construction site in real time based on sensor data and SLAM technology, and dynamically adjusts the flight path of the UAV.

[0085] It should also be noted that the path planning module generates the inspection path of the UAV based on the information provided by the data fusion module, and provides path planning for the UAV control module.

[0086] The drone control module includes a drone communication module, a drone control module, and a drone scheduling module.

[0087] It should be noted that the drone communication module is used to establish a wireless communication connection with the drone, send control instructions and receive flight status information; the drone control module is used to control the flight direction, speed and altitude of the drone according to the flight path and control instructions generated by the path planning module; the drone scheduling module is used to manage the collaborative work of multiple drones, avoid path conflicts, and realize automatic switching and scheduling of drones.

[0088] It should also be noted that the drone communication module is responsible for establishing a connection with the drone, the drone control module controls the flight of the drone according to the instructions of the path planning module, and the drone scheduling module manages the collaborative work of multiple drones.

[0089] The intelligent analysis module includes target detection module, data analysis module and report generation module.

[0090] It should be noted that the target detection module is used to identify buildings, equipment, and personnel in images based on computer vision technology, and to extract the location and feature information of the target; the data analysis module is used to compare the identified target information with the BIM construction simulation model to analyze construction deviations, quality problems, and safety hazards; the report generation module is used to generate inspection reports based on the analysis results for reference by construction management personnel.

Claims

1. A dynamic UAV path planning method based on BIM construction simulation is characterized by: include: Build a BIM construction simulation model, integrate real-time data, generate simulation sequences for construction phases, and perceive the status of construction scenarios in real time; Develop an intelligent drone path planning system to generate the optimal flight path and automatically plan drone inspection paths; Based on SLAM technology and multi-sensor fusion, drones can coordinate control to dynamically adjust paths, use deduction to verify intelligent obstacle avoidance, and process inspection data in real time. Integrating real-time data includes building real-time synchronization between the physical status of the construction site and the BIM construction simulation model, and establishing a bridge between the BIM construction simulation model and the Internet of Things platform; Generating a construction phase simulation sequence involves seamlessly integrating the static BIM construction simulation model with the dynamic construction plan to form a time-space integrated construction simulation system. Automated planning of drone inspection routes involves deeply integrating BIM construction information with drone route planning to build intelligent inspection routes; The use of deduction to verify intelligent obstacle avoidance includes the introduction of SLAM real-time mapping and obstacle avoidance mechanisms to control changes in the dynamic construction environment in real time; Building a BIM construction simulation model includes: Create a building information model based on BIM software, combine the BIM construction simulation model with the time dimension, and use construction simulation software to generate a simulation sequence of construction phases to predict construction progress and site changes; Generating the optimal flight path includes, Based on the intelligent path planning algorithm, the optimal flight path is generated according to the construction scenario of the BIM construction simulation model and the real-time data of the construction site sensor network. The heuristic method is introduced to optimize the flight path of the drone, and the drone inspection path is intelligently generated and adjusted. The dynamic adjustment path of UAV collaborative control includes: Using real-time positioning and SLAM technology, the drone can perform self-positioning and path adjustment during flight; The use of deduction to verify intelligent obstacle avoidance includes: Based on multi-sensor fusion technology, combined with SLAM technology, it can detect obstacles in front in real time. Combined with the real-time data of the sensor network, it can detect and dynamically avoid obstacles in front of the drone.

2. The dynamic UAV path planning method based on BIM construction deduction according to claim 1 is characterized in that: The integrated real-time data includes: Build a sensor network, synchronize with the BIM construction simulation model in real time through the IoT platform, and dynamically perceive and update the construction scene; Based on API plug-ins, BIM construction simulation models are seamlessly integrated with real-time data from the construction site sensor network.

3. The dynamic UAV path planning method based on BIM construction deduction according to claim 1 or 2, characterized in that: The development of the intelligent UAV path planning system includes: Extract the spatial layout data and construction stage information of the BIM construction simulation model, and convert the spatial layout data and construction stage information into the format required for drone path planning.

4. A dynamic UAV path planning system based on BIM construction deduction, which adopts the dynamic UAV path planning method based on BIM construction deduction according to any one of claims 1 to 3, characterized in that: Including data fusion module, path planning module, drone control module, and intelligent analysis module; The data fusion module is used to integrate the BIM construction deduction model with real-time sensor data to build a dynamically updated construction scene model; The path planning module is used to generate and optimize the inspection path of the UAV based on the construction scene model provided by the data fusion module using an intelligent algorithm to adapt to the dynamic changes of the construction site; The drone control module is used to control the drone to conduct inspections along the path generated by the path planning module, dynamically adjust according to real-time data, collect images, videos and sensor data, and transmit them to the control center in real time; The intelligent analysis module is used to pre-process and format the inspection data collected by the drone, compare and analyze it with the BIM construction deduction model, identify construction deviations, defects and potential risks, and generate a visual report.

5. 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 dynamic drone path planning method based on BIM construction deduction described in any one of claims 1 to 3 are implemented.

6. 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 dynamic drone path planning method based on BIM construction deduction described in any one of claims 1 to 3 are implemented.

Images