Intelligent control method and system for ALC panel wall transportation and installation based on robot collaboration

Abstract

The present invention discloses an intelligent control method and system for transporting and installing ALC panel walls based on robot collaboration, which relates to the technical field of collaborative construction robot operations. The method includes collecting global data from the construction site, extracting information on the location, obstacle distribution, and installation site of the ALC panels, building a comprehensive path evaluation model, and selecting the optimal transport operation path; determining the gripping points and gripping parameters to identify and grip the target ALC panels; continuously collecting the robot's movement posture and the force changes on the ALC panels; after alignment and installation, the robot uses sensors to collect the posture, force, and fixed state data of the installed ALC panels for quality assessment. The method of the present invention optimizes the transport path planning of the ALC panels through global construction site modeling and comprehensive path evaluation, achieving high-precision operations throughout the entire process of panel handling and installation, improving construction efficiency and installation quality, and having good intelligence, adaptability, and engineering application value.

Description

Technical Field

[0001] The present invention relates to the technical field of collaborative operations of construction robots, and in particular to an intelligent control method and system for transporting and installing ALC panel walls based on robot collaboration. Background Art

[0002] With the continuous advancement of building industrialization, prefabricated construction technology has been widely promoted and applied worldwide. As a key component of prefabricated buildings, ALC (Autoclaved Lightweight Concrete) panels are widely used in wall systems of industrial plants, residential buildings, and public buildings due to their light weight, high strength, and excellent thermal and sound insulation properties. To improve the construction efficiency of ALC panels, traditional manual handling and installation methods have gradually been replaced with mechanical auxiliary equipment and semi-automated operation processes. In recent years, the exploration of panel handling and installation combined with robotic technology has accelerated. Some research has begun to explore the intelligent and automated construction process through methods such as path planning, visual recognition, and collaborative control, thereby reducing labor intensity, shortening construction cycles, and improving installation quality.

[0003] Although existing technologies have initially introduced robots to assist in the handling and installation of ALC panels, there are still many shortcomings overall. First, current construction site spatial modeling is mostly based on static point clouds, lacking the ability to update and align space in a dynamic environment. This makes it difficult for robot path planning to adapt to changes in the on-site environment, and the flexibility and accuracy of transportation path planning are insufficient. Secondly, existing robot handling operations are usually based on stand-alone mode or simple follow-up collaboration. The number of robots and coordination strategies are not dynamically adjusted according to the size, weight and handling path of the panels, which can easily lead to uneven force or posture instability of the panels, thereby increasing the risk of damage. In addition, existing path offset compensation technologies are mostly limited to single-point deviation correction, lacking a dynamic compensation mechanism based on continuous posture acquisition and joint analysis of force changes, making it difficult to achieve real-time posture optimization control during the handling process. During the panel installation stage, traditional alignment and inspection processes mostly rely on single positioning and manual verification, lacking automated and refined local correction strategies, and cannot effectively guarantee the consistency, verticality and fixation quality of the joints after installation. In contrast, the present invention, by constructing a standardized work scenario data set, introducing a comprehensive path evaluation model, implementing dynamic robot quantity matching and real-time compensation for posture offset, and combining multi-dimensional data detection and local fine-tuning mechanisms, can achieve overall optimization of construction site environment adaptation, continuous and stable handling posture, and high-precision controllable installation quality, which significantly overcomes the limitations of existing technologies in construction flexibility, transportation stability and installation accuracy. Summary of the Invention

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

[0005] Therefore, the technical problems solved by the present invention are: the existing ALC panel transportation and installation robot control method has the problems of poor real-time construction site modeling resulting in inaccurate path planning, lack of dynamic posture offset compensation during the handling process resulting in poor transportation stability, lack of high-precision quality inspection and local correction mechanism after installation, and how to realize integrated ALC panel wall transportation and installation intelligent control based on on-site modeling, robot collaboration and dynamic posture optimization.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent control method for the transportation and installation of ALC panel walls based on robot collaboration, comprising collecting global data of the construction site, constructing a standardized operation scene data set after spatial registration and semantic segmentation processing, extracting the position of ALC panels, obstacle distribution and installation site information, constructing a comprehensive path evaluation model based on the panel number and installation sequence, combining the feasibility of the transportation channel and the complexity of the operating environment, quantitatively analyzing the candidate transportation paths, and screening the optimal transportation operation path; guiding the robot to the target panel position based on the optimal transportation operation path, locating the actual position and posture information of the panel through visual recognition and posture perception, determining the grasping point and grasping parameters, and Information is collected, the number of handling robots is dynamically determined, and the target ALC plates are identified and grasped. During the identification and grasping stage of the target ALC plates, the robot's movement posture and the force changes of the ALC plates are continuously collected. If a posture offset is collected, the position and posture of each robot are adjusted based on the path offset compensation algorithm until the installation position of the optimal transportation operation path is reached. After arriving at the installation position of the optimal transportation operation path, the robot is aligned with the installation surface calibration point and the sensor information of the ALC plate end. After the alignment and installation, the robot collects the posture, force and fixed state data of the installed ALC plate through the sensor to make a quality judgment. According to the current operation progress, the robot status and the changes in the construction site environment, the subsequent ALC plate handling sequence and path planning are dynamically adjusted.

[0007] As a preferred solution of the intelligent control method for ALC panel wall transportation and installation based on robot collaboration described in the present invention, the construction of a comprehensive path evaluation model includes jointly evaluating the path length, obstacle density, path curvature change rate and panel extraction priority of the candidate transportation path, and screening the optimal transportation operation path based on the comprehensive evaluation score.

[0008] As a preferred solution of the intelligent control method for ALC panel wall transportation and installation based on robot collaboration described in the present invention, the dynamic judgment of the number of transport robots includes dynamically matching the number of robots according to the size, weight and initial posture information of the ALC panels, establishing a unified reference coordinate system, and controlling each robot to perform synchronous collaborative grasping and transporting actions.

[0009] As a preferred solution of the intelligent control method for transporting and installing ALC panels based on robot collaboration described in the present invention, the identification and grasping of the target ALC panels include continuously collecting information on the robot's movement posture and the force changes on the ALC panels;

[0010] If it is detected that the posture deviation exceeds the threshold, the position, clamping angle and handling posture of each robot are adjusted in real time.

[0011] As a preferred solution of the robot-cooperative ALC panel wall transportation and installation intelligent control method described in the present invention, wherein: the alignment based on the installation surface calibration point and the ALC panel end sensor information includes comparing the alignment accuracy by comparing the installation surface calibration point and the ALC panel end sensor information;

[0012] If the alignment deviation is detected to exceed the threshold, adjust the splicing gap width, the vertical perpendicularity of the ALC board and the flatness of the installation surface.

[0013] As a preferred embodiment of the robot-coordinated intelligent control method for transporting and installing ALC panel walls of the present invention, the quality assessment includes the following steps: after the panel is aligned and installed, the robot collects data on the attitude angle, force balance state, and preliminary fixation state, and performs inspections based on set quality assessment criteria;

[0014] If the detection indicators do not meet the standards, a correction path is automatically generated to control the robot to perform adjustments, clamping force adjustments or compaction operations.

[0015] As a preferred solution of the intelligent control method for ALC panel wall transportation and installation based on robot collaboration described in the present invention, the dynamic adjustment of the subsequent ALC panel transportation sequence and path planning based on the current operation progress, robot status and construction site environment changes includes real-time dynamic adjustment of the subsequent transportation sequence and transportation operation path according to the numbering sequence of the remaining panels, the current robot load status, construction site environment changes and path smoothness.

[0016] Another object of the present invention is to provide an intelligent control system for ALC panel wall transportation and installation based on robot collaboration, which can quantitatively analyze candidate transportation paths and screen the optimal transportation operation path by constructing a comprehensive path evaluation model, thereby solving the problem that the current ALC panel transportation and installation robot control method contains poor real-time modeling at the construction site, resulting in inaccurate path planning.

[0017] As a preferred solution of the ALC panel wall transportation and installation intelligent control system based on robot collaboration described in the present invention, it includes: a construction site operation environment modeling and optimal transportation operation path planning module, a target panel identification and dynamic handling posture control module based on path guidance, and a panel alignment installation, quality inspection and subsequent operation scheduling optimization module; the construction site operation environment modeling and optimal transportation operation path planning module is used to collect global spatial data of the construction site, establish a comprehensive path evaluation model, quantitatively analyze candidate transportation paths, and screen and generate the optimal transportation operation path; the target panel identification and dynamic handling posture control module based on path guidance is used to guide the robot to reach the target panel position, determine the optimal grasping point and parameters, and implement collaborative grasping and handling; the panel alignment installation, quality inspection and subsequent operation scheduling optimization module is used to collect the posture, force and fixed state data after installation in real time for quality judgment, and dynamically adjust the handling sequence and transportation path of subsequent panels after completing the installation of the current panel.

[0018] 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 an intelligent control method for ALC panel wall transportation and installation based on robot collaboration.

[0019] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of an intelligent control method for transporting and installing ALC panel walls based on robot collaboration.

[0020] Beneficial Effects of the Present Invention: The proposed intelligent control method for transporting and installing ALC panels based on robot collaboration collects global construction site data and performs spatial registration and semantic segmentation to construct a standardized work scenario dataset. It then extracts information on ALC panel location, obstacle distribution, and installation site. Combining panel numbering, installation sequence, transport channel feasibility, and work environment complexity, it establishes a comprehensive path evaluation model, enabling quantitative screening of candidate transport paths and optimal path planning, effectively improving the rationality of robot transport paths and operational continuity. By guiding robots to identify and grasp target panels based on the optimal transport operation path, and dynamically determining the number of transport robots and gripping parameters, the adaptive nature of the grasping action and posture stability during the initial transport phase are enhanced. During transport, the robot continuously collects data on movement posture and panel force changes, and uses a path offset compensation algorithm to adjust the robot's position and posture in real time, achieving full control of panel stability during transport, significantly reducing the risk of transport instability and damage. Upon arrival at the installation site, high-precision alignment is performed based on installation surface calibration points and sensor data from panel ends. Post-installation quality inspection and local correction actions ensure panel verticality, joint consistency, and secure fixation during installation. By combining post-installation progress with dynamic on-site changes, the system can optimize subsequent handling sequences and path planning in real time, achieving intelligent scheduling and load balancing. Overall, this invention effectively improves the automation level, construction efficiency, and installation accuracy of ALC panel handling and installation, significantly reducing the need for manual intervention and uncertainty in construction quality, and possesses promising engineering application prospects and promotional value. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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.

[0022] Figure 1 This is an overall flow chart of an intelligent control method for ALC panel wall transportation and installation based on robot collaboration provided in the first embodiment of the present invention.

[0023] Figure 2 A method logic diagram of an intelligent control method for ALC panel wall transportation and installation based on robot collaboration provided in the first embodiment of the present invention.

[0024] Figure 3 This is an overall flow chart of an intelligent control system for ALC panel wall transportation and installation based on robot collaboration provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] Example 1, reference Figure 1-Figure 2 , as one embodiment of the present invention, provides an intelligent control method for ALC panel wall transportation and installation based on robot collaboration, comprising:

[0027] S1: Global construction site data is collected and processed through spatial registration and semantic segmentation to construct a standardized operation scenario dataset. The ALC plate location, obstacle distribution, and installation site information are extracted. Based on the plate number and installation sequence, combined with the feasibility of the transportation channel and the complexity of the operating environment, a comprehensive path evaluation model is constructed to quantitatively analyze the candidate transportation paths and select the optimal transportation operation path.

[0028] Furthermore, a 3D laser scanning system and high-resolution visual recognition technology are used to collect global data from the construction site, creating a dynamic 3D operation model in real time, including the plate stacking area, feasible transportation channels, obstacle distribution, and target installation surface. The collected data undergoes spatial registration and semantic segmentation to form a standardized operation scene dataset.

[0029] It should be noted that based on the standardized operation scenario data set, combined with the number information of each ALC plate and the predetermined installation sequence requirements, a list of priority operation plates is screened out, and a set of candidate transportation operation paths is generated in real time according to the construction sequence and the dynamic environment of the site. For each candidate path, a comprehensive path evaluation model is used to evaluate the path. , the path length, obstacle density along the way, curvature change rate of the transportation process, and the extraction priority and desirability index of the target plate are comprehensively calculated to quantify the overall transportation quality of each path, which is expressed as:

[0030]

[0031] in, Expressed as a comprehensive evaluation function of the transportation path, Indicates the transport path, Indicates the first nodes, Indicates the first nodes, Representation node arrive The Euclidean distance, Representation node The density of obstacle points within the surrounding unit volume, Representation node The rate of change of curvature of the path at Represents obstacle avoidance adjustment parameters, represents the path curvature penalty adjustment parameter, Indicates the first Plate number, Indicates plate The corresponding installation priority factor, Represented as a plate The actual desirability factor of Expressed as Segment path segment evaluation weights, Expressed as The assessment weight of the board, Indicates the number of path nodes, Indicates the number of plates;

[0032] By sorting and screening the evaluation values ​​of candidate paths, the transport path with the best comprehensive score is finally determined as the basic path for executing the robot's handling task. Key nodes and fine-tuning points are dynamically marked on the path to support posture control and path optimization during subsequent handling operations.

[0033] The value range is ,The smaller the value, the better the path, the smoother the transportation, and the more reasonable the installation task matching;

[0034] like , indicating that the path is extremely optimal and the handling and installation efficiency is extremely high;

[0035] like , indicating that the path is good and can ensure normal construction efficiency; if , indicating that the path is obviously lengthy, has many obstacles, or has poor priority matching, and needs to be replanned.

[0036] S2: Based on the optimal transport operation path, the robot is guided to the target plate position, the actual position and posture information of the plate are located through visual recognition and posture perception, the grasping point and grasping parameters are determined, and the number of handling robots is dynamically determined according to the size, weight and posture information of the ALC plate to identify and grasp the target ALC plate.

[0037] Furthermore, after completing the optimal transport operation path planning, the system uses the comprehensive path evaluation model The determined optimal transport path guides the robot to move along the predetermined trajectory to the area where the target plate is located. During the journey, the system monitors the distribution of obstacles along the way, changes in local path curvature, and path smoothness in real time to ensure that the robot can successfully reach the target area in a dynamic construction environment. After arriving at the target area, the robot uses the integrated visual recognition module to perform image recognition and positioning of the plate, and combines posture perception methods to obtain the spatial posture information of the plate, including multi-dimensional parameters such as position coordinates, pitch angle, roll angle, and yaw angle. Based on the actual size, weight distribution characteristics, and posture parameters of the plate, the system comprehensively evaluates the optimal area and clamping direction for plate grasping, and determines the optimal grasping point and grasping parameters for ALC plate positioning and grasping, including clamping position, clamping angle, and clamping force, to ensure that the plate is evenly stressed and has a stable posture during transportation.

[0038] It should be noted that the system dynamically determines the number of handling robots required and the coordination method based on the plate's geometric characteristics, quality parameters, and path characteristics. For large, heavy, or complex plates, it automatically matches multiple robots for collaborative operation and plans the relative gripping positions and synchronized motion requirements between the robots within a unified reference coordinate system. This process enables the robots to achieve high-precision identification of target ALC plates, adaptive grasping, and dynamic allocation of handling resources. This not only improves the safety and stability of grasping and handling actions, but also provides a solid foundation for posture control and overall transportation efficiency in subsequent handling paths.

[0039] S3: During the identification and grasping stage of the target ALC plate, the robot's movement posture and the force changes of the ALC plate are continuously collected. If posture deviation is collected, the position and posture of each robot are adjusted based on the path deviation compensation algorithm until they reach the installation position of the optimal transportation operation path.

[0040] Furthermore, after completing the positioning and grasping of the target ALC plate, the robot enters the handling phase according to the optimal transport operation path. To ensure that the plate is stable and the force is balanced during the handling process, the system continuously collects the robot's movement posture parameters and the force changes of the plate during the entire handling process, focusing on monitoring the posture angle changes at the nodes along the path, local force offsets and dynamic changes in the transportation environment. Based on the comprehensive path evaluation model During the handling process, the robot dynamically adjusts its travel speed, gripping posture and synchronous collaboration strategy by referring to the obstacle distribution density, local curvature change rate and preset channel patency indicators along the path in real time.

[0041] When the robot's movement posture or the plate's force state is detected to be abnormally offset, and the offset exceeds the posture stability threshold set by the system, the system's path offset compensation algorithm is expressed as follows:

[0042]

[0043] in, Expressed as a time parameter The comprehensive offset compensation control index under Represents the current actual position vector, represents the robot's target desired position vector, Indicates the ground disturbance intensity factor per unit area around the robot’s current position, Indicates the robot at time The local force imbalance under represents the robot offset control weight, represents the synchronization error of the collaborative robot, Indicates the acceleration change during the robot's synchronous motion. It represents the rate of change of path curvature per unit time during the robot's handling process. represents the weight coefficient of robot collaborative operation, Indicates the total number of robots involved in the transport, Indicates the number of collaborative groups.

[0044] The system sets a posture stability threshold as a basis for determining whether there is abnormal deviation in the plate posture during the robot's movement. This threshold takes into account the following two core indicators:

[0045] The attitude angle change threshold (Δθ threshold) collects changes in the robot's pitch, roll, and yaw angles during plate handling. The attitude angle change threshold is set within ±2°. If the angle change in any single direction exceeds ±2°, the robot is considered unstable and the dynamic compensation mechanism is triggered.

[0046] The plate force imbalance threshold (ΔF threshold) monitors changes in plate force at the robot's gripping or support points. When the force deviation is within ±10% of the initial equilibrium state, normal handling is determined. If the deviation exceeds 10%, it is considered abnormal, potentially leading to localized stress concentration or positional deviation in the plate, triggering position and gripping force compensation.

[0047] The path offset compensation algorithm comprehensively evaluates the current position deviation and path curvature characteristics, quickly generates a set of local compensation action instructions, and controls each robot to coordinate and execute actions such as position fine-tuning, grip angle correction, and force balance optimization. This allows for real-time correction of the transport posture while ensuring the overall stability of the sheet. The compensation action is tightly coupled with the original transport path, eliminating drastic trajectory disturbances and ensuring continuous handling and a stable operation rhythm.

[0048] The value range is ;

[0049] like When ≤0.8, it means that the deviation during the handling process is extremely small and the posture is highly stable;

[0050] If 0.8< When ≤2, it means the offset is controllable and requires small dynamic fine-tuning;

[0051] like When the value is >2, it indicates that there is a significant posture deviation or synchronization imbalance during the handling process, and local strong compensation or a temporary stop of the operation should be performed for correction.

[0052] After identifying the target plate's position and planning its gripping posture, the system dynamically estimates the required number of robots based on the plate's dimensional parameters, weight distribution, and initial placement posture. It then establishes the relative positions of the robots within a unified reference coordinate system. Based on an analysis of the plate's force and center of gravity distribution models, the system optimizes the gripping point locations and force distribution strategies of each robot to address potential localized stress concentrations within the plate. This ensures uniform force distribution throughout the plate during handling, preventing distortion or breakage caused by unbalanced gripping torque. During the collaborative handling startup phase, each robot performs a synchronized start motion based on the initial node set of the planned path. They then share their position and posture information in real time according to a collaborative communication protocol, maintaining high consistency in speed, acceleration, and posture changes during the collaborative transport process. The system also monitors the synchronization error and handling force balance of each robot in real time. If the synchronization error exceeds a preset threshold, a local dynamic adjustment mechanism is triggered to rapidly correct the relative positions of the robots, ensuring the continuity and stability of the plate handling process.

[0053] S4: After arriving at the installation site of the optimal transportation operation path, the robot aligns the installation surface calibration point with the sensor information of the ALC plate end. After the alignment and installation, the robot collects the posture, force and fixed status data of the installed ALC plate through the sensor to make a quality judgment. According to the current operation progress, the robot status and the changes in the construction site environment, the robot dynamically adjusts the subsequent ALC plate handling sequence and path planning.

[0054] Furthermore, upon arrival at the target installation location, the robot first performs preliminary alignment of the sheet material with the installation reference surface based on real-time positioning and installation calibration data. Based on accumulated posture adjustment records and actual sheet force data during handling, the system predicts potential alignment deviation trends and prioritizes the path with the least disturbance to complete the placement start-up action. During the placement process, the robot continuously collects information on the three-dimensional position of the sheet material's ends, the flatness of the installation surface, and local clamping force changes. Through the coordinated perception of multiple posture sensors and a high-precision force control unit, the robot dynamically determines the alignment status of the sheet material with the installation surface. To improve installation accuracy, the system incorporates a dynamic correction mechanism based on a local posture micro-disturbance optimization strategy. After initial placement, the system automatically detects the sheet material's posture angle, gap width, and vertical perpendicularity. If any of these indicators deviate from a set threshold, a small local posture fine-tuning action is triggered. This includes multi-dimensional adjustments such as micro-shifting, rotation, and compaction to achieve refined correction of gap spacing, assembly fit, and overall flatness.

[0055] The set thresholds include the plate attitude angle change in any direction greater than ±1.0°; the difference between the minimum and maximum widths of the assembly gap is greater than 3mm; and the vertical deviation of the plate exceeds ±1.5mm / m.

[0056] Fine-tuning actions include but are not limited to: small translation along the local plane direction (no more than 5mm); small angle rotation around the center of mass (no more than 0.8°); small force compaction correction along the vertical direction (the clamping force increase does not exceed 20% of the initial force).

[0057] In addition, to avoid damage to the panel due to excessive adjustment, the system performs force balance detection and stability assessment before and after each fine-tuning action. If abnormal force on the panel is detected, the system will actively reduce the fine-tuning amplitude and prioritize the adjustment of force balance parameters to ensure the structural integrity and safety of the panel throughout the installation process.

[0058] It should be noted that after completing the initial installation and dynamic fine-tuning of the ALC panels, the robot immediately enters the quality inspection phase. Utilizing its built-in high-precision attitude sensor, force sensing module, and structural fixation status monitoring unit, the robot comprehensively collects data on the panel's three-dimensional attitude angle, force distribution, gap closure, and fixation stability. The system rapidly assesses this data based on dynamically set multi-dimensional eligibility thresholds, covering key indicators such as overall verticality, local force balance, gap uniformity, and the panel's initial fixation strength.

[0059] The multi-dimensional qualification threshold standard includes: during the quality inspection after the system is installed, if the test data meets the following conditions, the installation is judged to be qualified:

[0060] The overall vertical deviation of the plate is within ±2.0mm / m;

[0061] The force deviation of each clamping or supporting point is within ±8%;

[0062] The width difference of the gap between the panels should be within 3mm;

[0063] The initial fixing strength of the plate reaches more than 85% of the design requirements.

[0064] If all the test results meet or exceed the preset qualification standards, the system records the test data of the corresponding operation batch and marks the current plate installation status as "completed". If any test indicator exceeds the preset allowable deviation range, the system automatically deduces the local optimal correction path based on the test feedback, reasonably selects the nearest feasible micro-action instruction set, and guides the robot to perform targeted posture fine-tuning, clamping force compensation or local compaction operations until the corrected test data meets all qualification standards. The entire detection and correction process adopts a dynamic fault-tolerant mechanism, and introduces multiple rounds of continuous fine-tuning and verification cycles in the judgment process to ensure that the installation accuracy and structural reliability are maximized without causing excessive work or damage to the plate structure, while reducing the probability of rework due to installation errors.

[0065] It should also be noted that after the panel installation quality is qualified and final records are completed, the system activates an intelligent dynamic scheduling mechanism based on the current construction progress, robot operating status, and changes in the construction site environment. This mechanism allows for real-time rescheduling and route optimization of subsequent ALC panel handling and installation tasks. The system first generates a preliminary task sequence based on the remaining panel list, installation priority, and structural correlation with already installed panels. It then calculates a handling priority index based on each robot's current remaining battery life, mechanical load status, path accessibility, and local construction environment complexity. Based on this priority index, the system dynamically adjusts the panel retrieval order, transportation route, and installation strategy, prioritizing the next task to be handled with the least resource consumption, lowest transportation route risk, and highest installation efficiency. Furthermore, in response to dynamic environmental changes (such as new obstacles, restricted existing routes, or changing weather conditions), the system can replan local route segments in real time and simultaneously adjust the robots' work plans to maximize the continuity of handling and installation operations and overall construction efficiency. Through this intelligent scheduling mechanism based on real-time feedback and multi-factor dynamic optimization, the robot cluster's load balancing, operation rhythm synchronization, and abnormal scenario adaptation are effectively achieved, ensuring the efficiency, stability, and quality control of the overall ALC panel wall construction process.

[0066] Example 2, an embodiment of the present invention, provides an intelligent control method for ALC panel wall transportation and installation based on robot collaboration. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0067] First, a construction site was selected as the experimental site, where a typical ALC panel handling and installation environment was set up. The experiment employed a 3D laser scanner (1mm resolution), a high-resolution industrial camera (20 megapixels), a 6-DOF multifunctional robotic unit (rated load capacity 300kg), a ground-based inertial measurement unit (IMU), and a multi-point force sensor array for on-site deployment.

[0068] First, a 3D laser scan of the construction area is performed to collect point cloud data of the entire site. This data is then processed using a registration algorithm and semantic segmentation module to form a standardized dataset of work scenarios. Subsequently, the system comprehensively evaluates candidate transport routes based on the plate number and construction sequence, combined with the obstacle density and curvature change rate of the transport corridor. The optimal path is selected as the robot transport route, and key nodes and fine-tuning points along the path are annotated.

[0069] The robot follows the optimal path to the target plate area, locks onto the designated plate using its visual recognition system, and determines the gripping point and clamping parameters based on posture perception data. Based on the plate's dimensions (3m long, 0.6m wide, 0.1m thick) and weight (approximately 200kg), the system determines that two robots are required to work together. They establish a relative position relationship within a unified reference coordinate system and set a synchronized starting motion.

[0070] During the handling process, the system continuously monitors the robot's posture and changes in the force applied to the sheet. If a pitch angle deviation exceeding ±2° or a local gripping force variation exceeding 10% is detected, the system invokes a path offset compensation algorithm in real time to dynamically correct the robot's position and posture, ensuring stable sheet transport. Upon arrival at the installation location, the robot performs alignment based on the installation calibration points and end-sensor data. After initial placement, the system automatically detects the posture angle, gap width, and verticality. If deviations exceed these limits, the system performs local micro-perturbation optimization adjustments, including micro-movement, rotation, and light pressure.

[0071] After installation is complete, the system quickly assesses panel quality based on multi-dimensional compliance thresholds, including overall verticality (required within ±2.0 mm / m), local force balance (force deviation ≤ 8%), gap uniformity (width difference ≤ 3 mm), and initial fixing strength (≥ 85% of the design standard). If any anomalies are detected, the system automatically generates local correction instructions to guide the robot to make the necessary fine-tuning. Finally, based on the installation completion status and construction site changes, the system dynamically optimizes the handling and installation sequence of the remaining panels to maximize construction efficiency.

[0072] Table 1 Experimental data table

[0073]

[0074] The experimental data shows that the plate handling and installation operations implemented using the method of the present invention exhibit good stability and high-precision control levels in multiple key performance indicators. The specific analysis is as follows:

[0075] In terms of transport route planning, the optimal route was screened through a comprehensive path evaluation model. The path length in the samples was generally controlled in the range of 14m to 19m, and the obstacle density was maintained between 0.06 and 0.15 obstacles per cubic meter. This shows that the path avoidance effect is good, the transport smoothness is excellent, and the transportation time wasted due to obstacle avoidance or path interference is reduced.

[0076] In terms of handling posture control, the clamping force deviation is less than 10%, and the posture angle change is kept within 1.6°, which is significantly lower than the ±2° stability threshold set by the system. This shows that during the handling process, the position and posture are adjusted in real time through the path offset compensation algorithm, which effectively prevents posture instability and force imbalance, and ensures the stability and safety of the plate transportation process.

[0077] In terms of installation quality, the vertical deviation of the panels finally tested was generally between 1.0 and 2.3 mm / m. Except for sample 4 which slightly exceeded the limit (2.3 mm / m, triggering a fine-tuning correction action), the remaining samples met the preset high standard of ±2.0 mm / m. The gap consistency and initial fixing strength also met the set thresholds, fully verifying the actual effect of the local micro-disturbance optimization strategy on improving installation accuracy.

[0078] Compared with the traditional method of relying on manual visual inspection and single-machine transportation and installation, the present invention not only achieves a qualitative improvement in the rationality of path planning, the stability of the transportation process and the control of installation precision, but also effectively reduces the rework rate caused by unstable plate transportation posture or poor initial installation through dynamic posture control and local correction mechanism, further improving the overall construction efficiency and the quality of the finished panel wall products, reflecting obvious creativity and novelty.

[0079] Overall, the data of this embodiment fully demonstrates that the method of the present invention has a high degree of feasibility and significant comprehensive advantages in actual construction environments, can meet the urgent needs of modern construction projects for intelligent, standardized, and efficient ALC board wall construction technology, and has good promotion and application prospects.

[0080] Example 3, reference Figure 3 , which is an embodiment of the present invention, provides an ALC panel wall transportation and installation intelligent control system based on robot collaboration, including a construction site operation environment modeling and optimal transportation operation path planning module, a target panel recognition and dynamic handling posture control module based on path guidance, and a panel alignment installation, quality inspection and subsequent operation scheduling optimization module.

[0081] Among them, the construction site operation environment modeling and optimal transportation operation path planning module is used to collect global spatial data of the construction site, establish a comprehensive path evaluation model, conduct quantitative analysis of candidate transportation paths, and screen and generate the optimal transportation operation path. The target plate recognition and dynamic handling posture control module based on path guidance is used to guide the robot to reach the target plate position, determine the optimal grasping point and parameters, and implement collaborative grasping and handling. The plate alignment installation, quality inspection and subsequent operation scheduling optimization module is used to collect the posture, force and fixed state data after installation in real time for quality judgment, and dynamically adjust the handling sequence and transportation path of subsequent plates after completing the installation of the current plate.

[0082] If a function is implemented as 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 portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0083] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0084] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be 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 and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0085] It should be understood that various aspects of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gates for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gates, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc. It should be noted that the above embodiments are intended only to illustrate the technical solutions of the present invention and are not intended to be limiting. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art will understand that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and such modifications are intended to be encompassed by the claims of the present invention.

[0086] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. 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.

Claims

1. An intelligent control method for ALC panel wall transportation and installation based on robot collaboration, characterized in that: include: Global construction site data is collected and processed through spatial registration and semantic segmentation to construct a standardized work scenario dataset. Information on ALC panel locations, obstacle distribution, and installation locations is extracted. Based on panel numbering and installation sequence, combined with the feasibility of transportation channels and the complexity of the work environment, a comprehensive path evaluation model is constructed to quantitatively analyze candidate transportation routes and select the optimal transportation operation path. Based on the optimal transport operation path, the robot is guided to the target plate position. The actual position and posture information of the plate are located through visual recognition and posture perception. The grasping point and grasping parameters are determined. According to the size, weight and posture information of the ALC plate, the number of handling robots is dynamically determined to identify and grasp the target ALC plate. During the identification and grasping phase of the target ALC sheet, the robot's movement posture and the force changes on the ALC sheet are continuously collected. If posture deviation is detected, the position and posture of each robot are adjusted based on the path deviation compensation algorithm until they reach the installation position; After arriving at the installation site of the optimal transportation operation path, the robot aligns the installation surface calibration point with the sensor information of the ALC plate end. After the alignment and installation, the robot collects the posture, force and fixed status data of the installed ALC plate through sensors to make a quality judgment. According to the current operation progress, robot status and changes in the construction site environment, the robot dynamically adjusts the subsequent ALC plate handling sequence and path planning.

2. The intelligent control method for ALC panel wall transportation and installation based on robot collaboration according to claim 1 is characterized in that: The construction of the comprehensive path evaluation model includes jointly evaluating the path length, obstacle density, path curvature change rate and plate extraction priority of the candidate transportation path, and selecting the optimal transportation operation path based on the comprehensive evaluation score.

3. The intelligent control method for transporting and installing ALC panels based on robot collaboration according to claim 2, characterized in that: The dynamic determination of the number of handling robots includes dynamically matching the number of robots according to the size, weight and initial posture information of the ALC plate, establishing a unified reference coordinate system, and controlling each robot to perform synchronous collaborative grasping and handling actions.

4. The intelligent control method for transporting and installing ALC panels based on robot collaboration according to claim 3 is characterized in that: The identification and grasping of the target ALC plate includes continuously collecting the robot's movement posture and the force change information of the ALC plate; If it is detected that the posture deviation exceeds the threshold, the position, clamping angle and handling posture of each robot are adjusted in real time.

5. The intelligent control method for transporting and installing ALC panels based on robot collaboration according to claim 4 is characterized in that: The alignment according to the mounting surface calibration point and the ALC plate end sensor information includes comparing the alignment accuracy by the mounting surface calibration point and the ALC plate end sensor information; If the alignment deviation is detected to exceed the threshold, adjust the splicing gap width, the vertical perpendicularity of the ALC board and the flatness of the installation surface.

6. The intelligent control method for transporting and installing ALC panels based on robot collaboration according to claim 5, characterized in that: The quality assessment includes the following steps: after the plate is aligned and installed, the robot collects data on the attitude angle, force balance state, and preliminary fixation state, and performs testing according to the set quality assessment criteria; If the detection indicators do not meet the standards, a correction path is automatically generated to control the robot to perform adjustments, clamping force adjustments or compaction operations.

7. The intelligent control method for transporting and installing ALC panels based on robot collaboration according to claim 6, characterized in that: The dynamic adjustment of the subsequent ALC plate handling sequence and path planning based on the current operation progress, robot status and construction site environment changes includes real-time dynamic adjustment of the subsequent handling sequence and transportation operation path according to the numbering sequence of the remaining plates, the current robot load status, construction site environment changes and path smoothness.

8. A system using the ALC panel wall transportation and installation intelligent control method based on robot collaboration according to any one of claims 1 to 7, characterized in that: It includes a construction site operation environment modeling and optimal transportation operation path planning module, a target plate identification and dynamic handling posture control module based on path guidance, and a plate alignment installation, quality inspection and subsequent operation scheduling optimization module; The construction site operation environment modeling and optimal transportation operation path planning module is used to collect global spatial data of the construction site, establish a comprehensive path evaluation model, perform quantitative analysis on candidate transportation paths, and screen and generate the optimal transportation operation path; The target plate identification and dynamic handling posture control module based on path guidance is used to guide the robot to the target plate position, determine the optimal grasping point and parameters, and implement collaborative grasping and handling; The plate alignment installation, quality inspection and subsequent operation scheduling optimization module is used to collect the posture, force and fixed state data after installation in real time to make quality judgments, and dynamically adjust the handling order and transportation path of subsequent plates after completing the installation of the current plate.

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 intelligent control method for ALC panel wall transportation and installation based on robot collaboration according to 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 intelligent control method for ALC panel wall transportation and installation based on robot collaboration according to any one of claims 1 to 7 are implemented.

Images