77 results about "Collaborative mapping" patented technology

The embodiment of the invention provides a multi-unmanned aerial vehicle cooperative surveying and mapping method and system for areas along a railway, and belongs to the technical field of railway surveying and mapping. The method comprises the steps that the unmanned aerial vehicle collects monitoring data in the flight process; the relative position and posture between the aircrafts are dynamically adjusted, and an observation configuration with variable baseline parameters is constructed; laser ranging modules carried by the unmanned aerial vehicles are controlled to execute synchronous ranging operation, and multiple sets of laser point cloud data covering the railway structure area are generated; performing coordinate registration and fusion on the collected laser point cloud data, and combining position information and attitude information of each unmanned aerial vehicle; and extracting geometric dimension parameters of the railway structure from the compensated three-dimensional model, and outputting the geometric dimension parameters as measurement results. According to the scheme, high-precision non-contact measurement of geometric dimension parameters such as the track gauge, the height difference and the roll angle of a railway track structure is achieved.

The invention relates to the field of geological surveying and mapping, and discloses a geological collaborative surveying and mapping operation control method and system based on an unmanned aerial vehicle, and the method comprises the following steps: S1, collecting environment dynamic data of a geological surveying and mapping region in real time through a sensor group carried by a plurality of unmanned aerial vehicles, and constructing a dynamically updated three-dimensional environment model; wherein the sensor group comprises a camera, a laser radar and an inertial measurement unit; s2, based on a preset surveying and mapping task target, initial surveying and mapping sub-regions are allocated to the unmanned aerial vehicles, and conflict-free flight paths are planned; s3, monitoring the flight state of the unmanned aerial vehicle and environment dynamic data in real time, and analyzing and processing to obtain a terrain sudden change index, a meteorological disturbance index and an unmanned aerial vehicle health index; and if any one of the following trigger conditions is detected: at least one of the geomorphic mutation index, the meteorological disturbance index and the unmanned aerial vehicle health index exceeds the respective corresponding preset threshold interval, dynamic task redistribution and path optimization are triggered.

The invention discloses a distributed multi-robot autonomous collaborative exploration and mapping method. Comprising the steps that in the exploration process, each robot explores and obtains a global subspace state map, if each robot does not communicate with other robots, the current robot conducts global exploration path planning and local exploration path planning according to the global subspace state map explored by the current robot, and if not, the current robot conducts local exploration path planning; furthermore, autonomous local exploration and global exploration are carried out; if each robot communicates with other robots, the current robot performs global exploration path planning according to the latest global subspace state map and performs local exploration path planning combined with loopback constraint, and further performs collaborative local exploration and global exploration; and after exploration is completed, distributed collaborative mapping is carried out, and a positioning mapping result is obtained. According to the method, autonomy and accuracy of multi-machine cooperative sensing work are improved, and the method has good guidance value for application of multi-machine cooperation in a real world scene.

The invention relates to the technical field of forest fire management, in particular to an integrated forest fire intelligent analysis method and system. The system comprises a background service system, a central intelligent analysis system and a mobile intelligent analysis system. The background service system is deployed in a cloud computing server cluster and is used for uniformly storing personnel information, fire scene information and geographic information data and realizing multi-source data fusion and authority management through a standardized API (Application Program Interface); the central intelligent analysis system is deployed in a high-performance computer, integrates a forest fire danger auxiliary decision-making model, a forest fire spreading trend prediction model, a force distribution dynamic display module and a collaborative plotting module, and supports fire spreading prediction and real-time decision-making instruction issuing based on multi-dimensional data such as weather, terrain and vegetation; the mobile intelligent analysis system realizes fire spreading trend analysis, mobile plotting and instruction receiving in an offline environment, supports offline data caching and calling in an emergency scene, and effectively improves forest fire emergency response efficiency and resource scheduling accuracy.

The invention provides a multi-machine distributed collaborative mapping method and system based on a laser radar and an IMU (Inertial Measurement Unit), relates to the technical field of automatic driving, and aims to solve the problem that in the prior art, dynamic point cloud can influence the accuracy of measured data; the head carrier is high in information processing capacity and high in calculation difficulty; communication and mapping of other single machines can be influenced by communication disconnection or load collapse of the single machines; the sensor is high in cost and is interfered by a complex closed environment. According to the method, after laser point cloud data and IMU information are received, key frame point cloud data and pose data are generated through first-time loop-back matching of single machines, messages are forwarded to a back-end server through a communication module based on ROS + UDP, second-time loop-back matching between different single machines is carried out through a server side, and a global map is constructed and optimized. According to the method, the problems in the prior art are solved, and the accurate global pose estimation and the optimized global map are obtained.

The invention provides an unmanned system cluster remote co-location and global map construction method and system. Firstly, a remote server determines an initial relative pose of a node according to point cloud data of each node and performs initial global point cloud map splicing; each node obtains a speedometer pose and transmits the speedometer pose to the remote server in real time, and then the global pose P1 of each node is updated in a global point cloud map of the remote server; each node calculates self displacement change according to the speedometer pose, and when the displacement change is greater than a set distance threshold value, a local point cloud d1 is extracted and transmitted to the remote server; the remote server locally extracts a local point cloud D1; and performing registration on the d1 and the D1 to realize updating of the global map by the local point cloud. By using the method, the matching efficiency and the collaborative mapping efficiency can be improved; and meanwhile, the single-node resource consumption is reduced, and the single-node cruising ability is improved.

The invention requests to protect a multi-vehicle unknown environment collaborative mapping method based on topological characteristics, and the method comprises the following steps: a plurality of vehicles establish local maps based on respective laser radars in different regions of an unknown environment, and share the local maps; the method comprises the following steps: performing preliminary fusion on a main vehicle through first-round feature matching, performing clustering analysis on boundary points in a preliminary fusion map to obtain to-be-explored points of the vehicle, and establishing an exploring point model containing topological features; the host vehicle establishes a to-be-explored point cost function, and allocates an appropriate exploration point for each vehicle; each vehicle updates a local map according to the allocated exploration task, and then shares the local map to the host vehicle; and finally, the host vehicle calculates pose transformation between the local maps according to the exploration point model, and local map fusion is carried out until no new exploration point appears, so that a global map is obtained. According to the method, the efficiency and the precision of multi-vehicle collaborative mapping in a large-range unknown environment can be effectively improved.

The invention provides a multi-legged robot collaborative mapping method and system based on RTK, and relates to multi-robot collaborative mapping, and the method comprises the steps: constructing a hybrid processing architecture; various sensor data of the foot type robot are obtained, and timestamp alignment is carried out on the various sensor data; calculating a rotation matrix in an initial pose homogeneous transformation matrix between the foot robots and X and Y axis values in a translation vector; the height of a robot body is obtained, and a complete homogeneous transformation matrix between the foot type robots is determined; laser SLAM real-time mapping is executed through the distributed sensing layer; transmitting the local point cloud map of each foot type robot to a data center processing host; performing coarse splicing on the local point cloud map; in the centralized decision-making layer, error compensation is carried out on drifting of the foot-type robot, then fine correction is carried out on the spliced point cloud map, and a global consistency point cloud map is output. According to the method, the accuracy of map splicing is effectively improved, and the calculation amount of mapping is reduced.

The invention discloses a facial acne grading method based on collaborative mapping multi-scale self-distillation, is applied to the field of computers, and aims to solve the problem of low accuracy of acne severity grading in the prior art. According to the method, the convolutional neural network model is trained by adopting a self-distillation architecture, and a novel distillation module optimization training process is provided in combination with the characteristics of acnes, so that the model can notice the uniqueness of acne images, and the severity grading precision of the model for facial acnes is improved. The method can automatically identify the acne features and grade the severity of the acne features, assists doctors in diagnosis and treatment, and accelerates the healing period of the acne.

The invention discloses a three-dimensional scene multi-dimensional instruction collaborative mapping method and system based on a multi-modal large model and a knowledge graph, and belongs to the technical field of artificial intelligence. The method comprises the following four steps: acquiring and preprocessing a multi-mode instruction; performing instruction analysis and element disassembly, calling a built-in pre-training large language model by the multi-modal large model, disassembling the instruction into appearance, scene and control interaction elements through customized Prompt, and processing logic and dependency relationships; multi-dimensional state driving is carried out, and appearance parameter mapping, action sequence generation and cross-modal conflict resolution and semantic-voice-expression linkage execution are achieved through appearance, action and language intelligent agents; and the central coordinator schedules agent parallel tasks based on the knowledge graph. The system correspondingly comprises a function module for executing four steps. According to the method, the multi-dimensional instruction cooperative control precision and response efficiency of the three-dimensional scene can be effectively improved, the labor cost is reduced, and the method is adaptive to diversified interaction scenes.

The invention relates to the technical field of artificial intelligence, and particularly discloses an interactive intelligent content generation method and system based on AIGC. The method comprises the steps that a user editing instruction is collected and analyzed to obtain a first semantic body, and meanwhile a target change vector is extracted; performing connectivity analysis on the high-response pixel points to determine a candidate linkage area; obtaining a candidate linkage area, judging whether a physical shielding or self-shielding effect exists or not, and screening an effective response area; performing attenuation correction on the target change vector, and deriving a collaborative mapping parameter; and constructing a light and shadow guide matrix based on the collaborative mapping parameters, and performing directional guide processing on the effective response area. The system comprises an intention analysis module, a communication analysis module, a region screening module, an attenuation correction module and a synchronous rendering module. According to the invention, synchronous rendering of semantic subject change and ambient light and shadow effects can be realized.

The invention provides an intelligent graph recognition method and device based on collaborative drawing, equipment and a storage medium. The method is applied to the technical field of computers, and comprises the following steps: acquiring a canvas for collaborative drawing, performing pattern recognition processing on a pattern in the canvas for collaborative drawing, determining a boundary of the pattern, and performing segmentation processing on the pattern according to the boundary of the pattern to obtain at least one pattern and a pattern block corresponding to the pattern; the canvas for collaborative drawing is a drawing result obtained by collaborative drawing of a plurality of users; performing intelligent pattern recognition processing on the pattern block, and determining a visual component corresponding to a pattern in the pattern block; pixel point pickup processing is carried out on the graphic block, and each pixel point of the graphic block is traversed to obtain a pixel color value of the graphic block; and the data board is generated according to the visual component corresponding to the graph in the graph block and the pixel color value of the graph block, so that the identification accuracy is improved, and the development efficiency is improved.

This invention discloses a ground-air collaborative mapping method based on semantic features and ground plane multi-constraint fusion. The method includes: generating sub-map sets from local point cloud data collected by fire trucks and drones; and generating rotation-invariant semantic descriptors using a maximum height value rasterization strategy and rotation group enhancement. By calculating geometric and semantic distances, and combining isomorphic and heterogeneous pattern weighted fusion, candidate sub-map pairs with loop closures are selected and geometrically registered to generate loop closure constraints. Simultaneously, ground point clouds are extracted using the RANSAC algorithm, and the ground plane model is smoothly updated using a sliding window to construct height and pose alignment constraints. The loop closure constraints, ground plane constraints, and pose information are input into the Ceres optimization framework for joint optimization to generate a globally consistent overall map, effectively improving the accuracy and robustness of ground-air collaborative mapping, and is suitable for emergency scenarios such as complex fire rescue.

The invention provides a method for improving the production efficiency of a high-efficiency spring steel wire, and relates to the technical field of spring steel wire production.The method comprises the following steps that multi-source physical quantities in the spring steel wire winding process are collected in real time, and the multi-source physical quantities comprise steel wire tension distribution, the bending rod curvature radius, a roller temperature field and an equipment vibration frequency spectrum; based on the obtained multi-source physical quantity, a torque instruction, a rotating speed instruction and a bending radius compensation amount are generated through a dynamic collaborative mapping function; according to the generated instruction, a servo motor set is driven to adjust the wire feeding speed and the angular speed of a roller, and meanwhile a piezoelectric trimmer is controlled to correct the bending radius; and adopting a reinforcement learning strategy to optimize control parameters on line, and dynamically updating a mapping function according to winding quality feedback. According to the method, the problem that the remodeling debugging time is long can be effectively solved, the wire breakage rate can be remarkably reduced, and the size consistency can be effectively improved.

The invention discloses a ground-air collaborative mapping method based on semantic feature and ground plane multi-constraint fusion, which comprises the following steps: generating a sub-map set through local point cloud data collected by a fire-fighting unmanned vehicle and an unmanned aerial vehicle, and generating a rotation-invariant semantic descriptor by utilizing a maximum height value rasterization strategy and rotation group enhancement; by calculating a geometric distance and a semantic distance and combining isomorphic and heterogeneous mode weighted fusion, loopback candidate sub-map pairs are screened, geometric registration is carried out, and loopback constraints are generated. Meanwhile, ground point cloud is extracted through an RANSAC algorithm, a sliding window smoothly updates a ground plane model, and height constraint and attitude alignment constraint are constructed. And the loopback constraint, the ground plane constraint and the pose information are input into a Ceres optimization framework for joint optimization, a globally consistent total map is generated, the precision and robustness of ground-air collaborative mapping are effectively improved, and the method is suitable for emergency scenes such as complex fire rescue and the like.

The application belongs to the technical field of three-dimensional reconstruction and intelligent agriculture, and particularly relates to a three-dimensional Gaussian multi-machine collaborative mapping and optimization method and system for complex agricultural and forestry scenes. In view of the problem of low reconstruction accuracy caused by inconsistent exposure, dynamic disturbance of vegetation and sparse multi-machine view angles in complex agricultural and forestry scenes, the application sequentially carries out multi-machine data preprocessing, spatiotemporal outlier elimination, intermediate frame generation based on FILM and DepthAnything, and 3DGS joint optimization. Dynamic masks are generated through spatiotemporal residual double modal judgment to block dynamic interference at the level of loss function; sparse view angles are completed by using virtual intermediate frames to expand the observation data set. The application can effectively eliminate dynamic artifacts and cavities, realize high-precision three-dimensional reconstruction of complex agricultural and forestry scenes, and be directly applied to digital operation scenes such as vegetation monitoring and automatic path planning of forest land and orchards.

The application relates to the technical field of operation and maintenance management, and discloses an operation and maintenance management method and system for process industrial equipment, the method comprising the following steps: coupling multi-modal features of time sequence operation parameters and field state information of the process industrial equipment to obtain a fusion feature set of the process industrial equipment; quantifying fluctuation trends of the fusion feature set to obtain a degradation feature index of the process industrial equipment; performing evolution evaluation on the degradation feature index to obtain a health quantitative value of the process industrial equipment; constructing operation and maintenance decision boundary conditions of the process industrial equipment; performing collaborative mapping on the fusion feature set and the health quantitative value to obtain an optimized operation and maintenance strategy of the process industrial equipment; and associating and integrating the operation and maintenance decision boundary conditions and the optimized operation and maintenance strategy to obtain an operation and maintenance management report of the process industrial equipment; and the application can improve the operation and maintenance management efficiency of the process industrial equipment.

The invention relates to the technical field of communication, in particular to a collaborative mapping method and device based on a node evaluation result, and the method comprises the steps: obtaining a virtual network topology structure corresponding to a current network slice demand; generating a node mapping sequence between the virtual nodes and the physical nodes in the virtual network topological structure based on all the virtual nodes and all the physical nodes in the current network slice requirement; generating a candidate physical node set and a candidate physical link set meeting certain conditions by combining network configuration information and a node mapping sequence required by the current network slice; and based on the candidate physical node set and the candidate physical link set, utilizing a certain optimization objective function to cooperatively map virtual nodes and virtual links in the virtual network topology structure. Therefore, the problems that in the related technology, the physical network resources cannot be utilized to the maximum extent while the network slicing requirement cannot be met, and load balancing and optimal path allocation cannot be achieved are solved.

The application discloses a kind of based on fuzzy adaptive PID's roll rolling force thickness collaborative control method, belongs to industrial control technical field field.It includes: deployment instrument is at mill press-down hydraulic cylinder, process data are collected and preprocessed;Online calculation rolling force-thickness coupling degree factor, coupling degree factor is used as input with thickness error, error change rate, constructs three-dimensional fuzzy reasoning engine and carries out fuzzy reasoning;Using the collaborative coefficient matrix based on coupling degree factor and adaptive domain scaling mechanism, parameter adjustment amount is decoupled distribution and dynamic mapping, generates the PID parameter adjustment value of rolling force and thickness double loop respectively coordinated;Drive hydraulic servo valve to carry out roll gap and rolling force collaborative control.The application aims to realize the collaborative control of rolling force and thickness by introducing coupling degree factor, constructing three-dimensional fuzzy reasoning engine and double loop collaborative mapping.

The invention relates to the technical field of positioning and mapping related to intelligent transportation and automatic driving / vehicle infrastructure cooperation, in particular to a city-level crowd-source cooperation mapping and real-time positioning method and system, and the method and system achieve the stable fusion of city-level crowd-source data through standardized multi-source observation data, space-time reference construction and cross-source registration. And loop constraint and graph optimization are optimized through dynamic regulation and control parameters, so that the stability and the expandability under the conditions of heterogeneous sensors and data quality fluctuation are improved. By adopting multi-dimensional credibility characterization and a dynamic gating mechanism, loopback starting conditions are effectively controlled, the situation that a global map is polluted by wrong loopback caused by semantic anchor drift is avoided, the risk that structured errors are solidified into global consistency is reduced, and map safety is improved. Through a layered map and dynamic regulation and control, parameters can be optimized according to positioning residual errors and regional risk statistics during real-time positioning, and a closed-loop updating mechanism is formed.

The present application relates to the technical field of data processing, and more particularly to a twin model construction method, system, device and medium for tank decommissioning, the construction method comprising the following steps: acquiring point cloud data, reconstructing a point cloud network, extracting size information, and constructing a twin model; real-time monitoring of sensor health status through time series feature analysis, capturing device degradation rules using a gated recurrent network, generating a hidden vector reflecting the degree of performance degradation, constructing a Poisson equation to describe the implicit surface, and using the finite element method to solve to obtain a continuous mesh model; and collaborative mapping of three-dimensional mesh and two-dimensional projection data, which not only preserves the overall topological form of the tank, but also extracts key size parameters, providing dual precision protection for path planning, and solving the problem of data drift in the model construction method of the prior art.

The invention belongs to the technical field of crossing of artificial intelligence and intelligent robots, and particularly relates to a ground-air robot storage environment intelligent sensing and anomaly detection system based on AI vision. The invention discloses an AI vision-based intelligent sensing and anomaly detection system for a storage environment of a ground-air robot, and aims to solve the problem of incomplete anomaly detection caused by isolated sensing and shallow data fusion of a ground-air platform. The system comprises a multi-modal acquisition unit, a ground-air collaborative mapping unit, a unified semantic cognition unit, a multi-scale anomaly detection unit and a dynamic task planning unit. Through fusion of air wide-area perception and ground fine observation data, a high-precision three-dimensional semantic map is constructed, comprehensive detection of macroscopic layout, microscopic state and time sequence logic abnormity is realized, and the ground-air robot is driven to cooperatively respond, so that the perception integrity and intelligent decision-making capability of a storage environment are improved.

This paper discloses a facial acne grading method based on collaborative mapping multi-scale self-distillation. This method, applied to the computer field, addresses the low accuracy of existing acne severity grading techniques. The method uses a self-distillation architecture to train a convolutional neural network model. Taking into account the characteristics of acne itself, a novel distillation module optimizes the training process, enabling the model to account for the uniqueness of acne images and improving the accuracy of facial acne severity grading. The method can automatically identify acne features and grade their severity, assisting doctors in diagnosis and treatment and accelerating the recovery period of acne.

The application discloses a kind of publishing field knowledge service construction methods based on knowledge graph, it is related to intelligent digital publishing technical field, including, according to publishing content structure node set, constructs publishing content structure diagram, and in combination with publishing original resource set executes publishing field semantic information extraction and semantic correlation analysis, obtains publishing semantic diagram;From the structural distribution characteristics and content anchoring characteristics of semantic node in publishing resource in publishing semantic diagram are extracted, and the anchor point edge between publishing semantic diagram and publishing content structure diagram is established, and the multi-granularity anchor point double diagram is formed;Based on graph service execution plan, execute double diagram collaborative retrieval and service path generation, obtain knowledge service candidate set, and carry out service ordering and arrangement, generate publishing field knowledge service content.The application realizes the collaborative mapping of semantic relationship and content bearing position, enhances knowledge organization precision and service direction.

The present invention belongs to the technical field of intelligent navigation, and particularly relates to a low-cost collaborative mapping method based on mutual observation of multiple robots. It is applied to a multi-robot formation. Each robot in the formation is equipped with sensors such as a low-cost single-line lidar, a camera, and an IMU or a wheel speedometer, and the multiple robots communicate through a Wi-Fi local area network. Each robot in the robot formation combines the point cloud data of the single-line lidar with the IMU attitude angle data and acceleration data to achieve its own pose estimation and local map construction; furthermore, taking the key frame poses of each robot itself as vertices and the mutual observations between robots and the poses of other robots estimated by themselves as measurement edges, each constructs a pose graph optimization model, and then uses the results of graph optimization for loop detection to further optimize the pose of a single robot; on this basis, each robot performs pose transformation on the point cloud shared by other observed robots, and then incrementally performs map merging to achieve map information sharing among multiple robots, and all robots can independently construct an accurate global multi-beam point cloud map.

The invention relates to the technical field of data mining, in particular to a patent-driven digital economic evaluation method and system, and the method comprises the following steps: based on a digital economic patent database, distributing innovation participation proportions, summarizing main body distribution characteristics, combing the complete-period changes of legal states and operation behaviors, and analyzing industrial classification codes and obligee distribution. And evaluating the innovation level in a zoning manner, and outputting a digital economic grading index. According to the invention, through hierarchical induction of a patent subject sorting structure and a contribution proportion, dynamic performance of innovation participation dominance is enhanced, and interactive tracking of operation behaviors of obligees and a legal state cycle is combined, so that structured integration of multiple types of events in a patent life cycle is realized; according to the method, content association in a patent cluster is identified by utilizing technical content fusion characteristics, a multi-level collaborative mapping unit is constructed in combination with obligee behaviors and innovation participation data under industrial coding, and innovation characteristics are displayed in a refined manner in graded archiving of innovation ability expression.

The invention relates to the technical field of data processing, in particular to a twin model construction method, system and device for storage tank decommissioning and a medium, and the construction method comprises the following steps: obtaining point cloud data, reconstructing a point cloud network, extracting size information, and constructing a twin model: monitoring the health state of a sensor in real time through time sequence feature analysis; the method comprises the following steps: capturing an equipment degradation law by utilizing a gated loop network, generating a hidden vector reflecting the performance degradation degree, constructing a Poisson equation to describe an implicit curved surface, solving by adopting a finite element method to obtain a continuous grid model, a three-dimensional grid and collaborative mapping of two-dimensional projection data, retaining the overall form topology of a storage tank, extracting key size parameters, and obtaining a three-dimensional grid model; double precision guarantee is provided for path planning, and the problem of data drift existing in a model construction method in the prior art is solved.

The invention relates to the technical field of image data processing, and discloses an image data adaptive enhancement method in a high-speed rail platform end complex environment, which comprises the following steps: acquiring an environment image and extracting a brightness component, and executing spatial sampling to construct a brightness distribution matrix; calculating a brightness gradient vector of a sampling node to determine a spatial weighting coefficient; performing spatial filtering on the preliminary mapping gain by using a spatial weighting coefficient, generating a weight component, and realizing gain correction; calculating a brightness change rate to determine a time sequence smooth step length, executing time sequence constraint adjustment on a mapping function control parameter, and determining a collaborative mapping function; according to the method, the slicing feeling caused by a strong-directivity light source is eliminated and video flicker is suppressed through spatial weight correlation and time sequence smooth constraint, and the track edge topological features are locked while noise is filtered out.

The invention discloses an intelligent food pesticide residue color reaction image analysis system, relates to the technical field of computer vision and image recognition, and realizes physical decoupling and accurate qualification of mixed color signals through collaborative mapping of blind source separation and a standard fingerprint database. The system models a mixed Lab color signal collected by a reaction hole into a linear mixture of a plurality of unknown source signals, and inversely solves an inverse matrix of a mixed matrix by taking maximization of non-Gaussian property as a criterion through a blind source separation analysis engine, so that the mixed signal is decomposed into a plurality of statistically independent source signal components, and a plurality of unknown source signals are obtained. According to the method, the characteristics of the separated pure components are subjected to similarity calculation with standard developing characteristic data of various single pesticides pre-stored in a standard pesticide developing fingerprint database, so that direct cross interference of mixed signals is avoided, and each component in a mixture can be accurately judged even under the condition that various pesticides coexist.

The embodiment of the invention provides a multi-sensing-node collaborative mapping method and system, electronic equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: constructing a local map taking a local node as a reference according to multi-frame point cloud data locally acquired by the node, discretizing the local map to obtain a plurality of subspaces, and performing geometric feature coding and intensity feature coding on each subspace to correspondingly obtain a geometric structure code and an intensity structure code; and feature description is carried out on the local map according to the strength structure codes and the geometric structure codes, a bimodal feature descriptor of the local map is obtained, the bimodal feature descriptor and node poses of the local map are interacted by multiple nodes, and a global map is constructed based on interaction information. According to the invention, the efficiency and accuracy of multi-node collaborative mapping can be improved.