38 results about "Semantic grid" patented technology

The invention discloses a high-precision laser positioning unpacking path planning system, and belongs to the technical field of robot automatic control and industrial automation. The system comprises a data synchronization module used for multi-sensor hardware synchronization and data alignment; the high-precision positioning module is used for outputting a precise pose based on environment skeleton characteristics and sliding window optimization; the semantic map construction module is used for fusing vision and laser data to generate a dynamic semantic grid map; the global path planning module is used for planning a smooth path in the skeleton channel by utilizing a mixed potential field improved A * algorithm; the motion control module is used for realizing closed-loop motion control and safety monitoring through model prediction and tracking; and the operation execution module is used for finishing millimeter-level precise stopping of an operation point by adopting visual servo and triggering unpacking operation. According to the method, the positioning robustness under dynamic shielding is improved through the environmental skeleton features, the safety and the high efficiency of the path are ensured by utilizing semantic understanding and intelligent planning, and the full-process automation from navigation to precise operation is realized.

A method performed by an apparatus for controlling autonomous driving of a vehicle is introduced. The method may comprise generating, based on a segmentation model processing point cloud data, a first semantic grid map, generating, based on an object detection model, a second semantic grid map, adjusting a probability regarding whether occupancy exists for an element included in each grid of the first semantic grid map and the second semantic grid map, and generating a fused grid map by determining, as a representative label, at least one label corresponding to a highest value among final probabilities of the at least one label, wherein the final probabilities are determined based on whether the at least one label matches the element, outputting, based on the fused grid map, a signal, and controlling, based on the signal, autonomous driving of the vehicle.

The invention discloses a multi-angle campus panoramic intelligent monitoring system, and relates to the technical field of security monitoring systems, and the system comprises a sensing module which is used for obtaining sensing data based on sensor networks deployed in all regions of a campus, and dynamically distributing sensing tasks according to region functions; wherein the sensor network comprises a camera, a millimeter wave radar, a pressure sensor, an environmental noise sensor and a Bluetooth device; the processing module is used for processing the sensing data in real time through the reconfigurable hardware nodes and generating compliance features and abnormal identifiers; the risk deduction module is used for constructing a semantic grid, associating regional function attributes, time authority and a historical risk thermodynamic diagram and executing global risk causal chain deduction based on the compliance features and the abnormal identifiers output by the processing module; and the response execution module is used for triggering a dynamic response according to the deduction result, and the dynamic response comprises hierarchical privacy protection and cross-campus coordination action.

The invention discloses a multi-unmanned aerial vehicle low-altitude service scheduling result generation method and device, equipment and a medium, and relates to the technical field of unmanned aerial vehicle scheduling, and the method comprises the steps: constructing a low-altitude service semantic grid, converting the service demand characteristics of each region of a city into a region semantic vector, and mapping an unmanned aerial vehicle task to the grid to generate a task semantic vector; a semantic enhancement mechanism is utilized to calculate the semantic association strength of a task and a region, a multi-dimensional fairness index system is constructed, and a dynamic fairness preference weight is generated through self-adaptive correction. And finally, task allocation and path planning are performed based on the dynamic weight and the semantic association strength, so that the dynamic balance service efficiency and fairness of multi-unmanned aerial vehicle scheduling are improved, regional service deviation is dynamically corrected, the service accessibility of vulnerable regions and crowds is ensured, and the method is adaptive to complex urban environments and abnormal scenes.

The invention provides a semantic grid map optimization method and system based on multi-task road surface information, and belongs to the technical field of automatic driving navigation, and the method comprises the steps: processing an obtained road environment image to obtain a lane line segmentation result and a drivable region segmentation result; establishing a coordinate projection relation from an OCC space to a pixel coordinate system based on a rotation translation matrix between the sensors; projecting a surface grid center point of the semantic grid map to a pixel coordinate system based on the coordinate projection relationship, and supplementing lane line information according to a projection result; performing semantic correction on the drivable area based on the coordinate projection relation and the drivable area segmentation result; performing instance extraction and semantic association processing on an unknown obstacle; and outputting the optimized three-dimensional semantic grid map. Based on the method, the invention further provides a semantic grid map optimization system based on the multi-task road surface information. According to the method, the quality and practicability of the semantic map are improved on the premise that the system burden is not obviously increased.

The application provides a semantic grid map optimization method and system based on multi-task road surface information, and belongs to the technical field of automatic driving navigation. The method comprises the following steps: processing a road environment image to obtain lane line segmentation results and drivable area segmentation results; establishing a coordinate projection relationship from an OCC space to a pixel coordinate system based on a rotation and translation matrix between sensors; projecting surface layer grid center points of a semantic grid map to the pixel coordinate system based on the coordinate projection relationship, and supplementing lane line information according to a projection result; performing semantic correction on a drivable area based on the coordinate projection relationship and the drivable area segmentation results; performing instance extraction and semantic association processing on unknown obstacles; and outputting an optimized three-dimensional semantic grid map. Based on the method, the application further provides a semantic grid map optimization system based on multi-task road surface information. The application improves the quality and practicability of a semantic map without significantly increasing the burden of a system.

The application discloses an indoor distribution cable path intelligent generation method combined with building environment characteristics, and comprises the following steps: constructing a semantic grid map capable of distinguishing different building function areas by performing layer identification, semantic annotation and space discretization on an input building plan design map; based on the semantic grid map, different basic passing generation values are given to different types of areas, and a dynamic engineering constraint function comprising a corner turning penalty and a wall sticking reward rule is defined; path search of an improved A* algorithm is performed, in an engineering constraint cost field fused with the basic passing generation value and the dynamic engineering constraint function, a heuristic search algorithm with a dynamic penalty term is used to calculate and generate a candidate cable path meeting engineering specifications; virtual convergence points are determined through node clustering, the path search algorithm is applied hierarchically, a backbone path limited in a public area is generated, branch paths entering rooms are generated, and a complete indoor distribution system cable path topology is generated by merging.

This invention relates to the fields of deep space exploration engineering planning and artificial intelligence technology, specifically disclosing a method for selecting a lunar south pole research station based on a multimodal large model. The method includes: constructing a site selection index toolkit containing various evaluation tools; acquiring and fusing multi-source data from the lunar south pole to construct a unified multimodal semantic grid and comprehensive cost model; encoding environmental features and mission objectives into cue vectors using an encoder; calculating the similarity between the cue vectors and tool capabilities based on the multimodal large model, dynamically filtering matching toolchains and generating adaptive weight parameters; iteratively optimizing the site selection evaluation results through a closed-loop optimization mechanism of "evaluation-feedback-adjustment" until convergence conditions are met; and finally outputting the optimal or near-optimal site selection scheme, supporting dynamic relocation under data and mission updates. This invention achieves intelligent fusion of multi-source data and multi-objective adaptive decision-making in complex environments, significantly improving the scientific rigor, objectivity, and efficiency of lunar research station site selection.

The invention belongs to the technical field of grid map construction, and discloses a multi-semantic grid map construction method fusing structured road topology. The method comprises the following steps: extracting a structured road region from a remote sensing image, constructing a topological network of the structured road region, and generating a road topology containing a center line and key road points; performing multi-category semantic segmentation on the same image, and endowing each semantic category with a weight according to the traffic capacity; rasterizing the weighted semantic segmentation result to form a multi-semantic grid map; and finally, projecting the road topology to a grid map, and performing weight enhancement on grids covering the topology to generate a grid map fused with topology guide information. According to the method, map support containing semantic trafficability and a road topological structure at the same time can be provided for an unmanned platform in a complex cross-country environment, and the efficiency and reliability of path planning are remarkably improved.

The present disclosure provides a point cloud noise identification method, device and unmanned vehicle, comprising: performing feature identification on the point cloud data of the current frame to obtain semantic point cloud; performing rasterization processing on the semantic point cloud, and removing the grid unit representing the dynamic target category according to the category to which each point in the semantic point cloud belongs, to determine the target semantic grid data of the current frame; fusing the target semantic grid data of the current frame with the target semantic grid data of the historical frame to generate terrain data; and checking the point cloud data of the current frame according to the terrain data to determine the noise of the point cloud data of the current frame.

A navigation system includes: a control circuit configured to: a control circuit configured to: capture a semantic frame from a sensor data stream for a region of interest, calculate a score (EQ1) for semantic points in the semantic frame, align the semantic points includes a pose error corrected, generate a semantic grid map of the semantic points including a high-level grid and a low-level grid, calculate grid map statistics by counting the semantic points in the low-level grid within the high-level grid, filter the semantic points in the low-level grid based on the grid map statistics of the high-level grid, and generate a semantic map from the low-level grid filtered and the high-level grid; and a communication circuit, coupled to the control circuit, configured to: process the semantic frame through a network, and process the semantic map through the network for displaying on a device.

The invention provides a deck surface treatment device for a ship, and relates to the technical field of ship maintenance, the deck surface treatment device comprises a carrier loader, a cleaning box, a high-pressure spray gun, a two-axis moving table, a scraping plate, a multi-stage water tank group, a filtering system, a water pump valve group, a flexible apron and a stabilizing block, and further comprises a controller, the pressure, flow and moving track of the spray gun are self-adaptively adjusted; laser scanning and Doppler radar are fused to construct a semantic grid map containing obstacle and stain states and flatness, and an A-Star Algorithm algorithm is adopted to automatically plan a'box falling point 'path; according to the conductivity, the oil concentration and the temperature, water is dynamically shunted and recycled, and graded reuse is achieved; according to the device, full-automatic, water-saving, shake-resistant and efficient cleaning of the deck is achieved, and the operation safety and the water resource utilization rate are remarkably improved.

The application discloses a kind of based on multi-sensor's grid map two-way asynchronous construction method and system, the method includes: obtaining three-dimensional point cloud data, RGB image and depth map;Based on the space corresponding relation of RGB image and three-dimensional point cloud data, three-dimensional point cloud data is semantically labeled;Three-dimensional point cloud data, RGB image and depth map are timestamped alignment, coordinate transformation and filtering processing, obtain final point cloud data, with semantic point cloud data point cloud data is spatiotemporal alignment generation fusion point cloud data as semantic grid map input;Construct semantic grid map, adopt the two division strategies of front view map and rear view map, by independent thread asynchronous update;Establish motion object database and predict dynamic object motion trajectory based on time sequence prediction algorithm, update in semantic grid map synchronously.The application effectively guarantees the intelligent device obstacle avoidance success rate and path planning rationality, guarantee the operation safety and efficiency under complex environment.

The application provides a navigation model training method, a navigation method and a device for fine alignment learning, and the navigation model training method comprises the following steps: weighting and fusing visual features, semantic features and spatial features extracted from unmanned aerial vehicle aerial images to obtain semantic grid features; performing display learning on fine alignment relationships between entities and landmark objects based on the semantic grid features according to multiple auxiliary prediction tasks to obtain visual representations; taking a fine aerial visual dialogue navigation data set as a training sample, taking the visual representations as input features, and taking a comprehensive loss as a loss function to iteratively train a navigation model to obtain an aerial visual dialogue navigation model; wherein the comprehensive loss is determined based on a navigation loss function and loss functions corresponding to the multiple auxiliary prediction tasks. The method comprehensively fuses multi-modal features, and improves the navigation accuracy, alignment capability and task execution efficiency of the unmanned aerial vehicle in a complex scene.

This application relates to a semantic grid map construction method, system, and medium with automatic obstacle removal function, belonging to the field of lawnmower technology. The semantic grid map construction method includes: acquiring original point cloud data and original image data of the lawn according to the target projection resolution, and converting them to the same view plane; temporally synchronizing the original point cloud data and original image data to obtain a three-dimensional point cloud and a two-dimensional image, and transmitting them to a data queue; spatially transforming the three-dimensional point cloud, and constructing fused image data by combining object semantic labels with the two-dimensional image in a layered fusion mechanism; generating a lawn grid based on the fused image data, and marking obstacle nodes using a ray tracing mechanism to obtain a lawn grid map; accurately distinguishing obstacle types (static / dynamic, passable / impassable) through category information; and dynamically clearing grids in obstacle-free areas through a ray tracing mechanism, reducing false positive obstacles caused by limited detection field of view.

The present disclosure relates to object relationship estimation from 3D semantic meshes. The implementations disclosed herein provide systems and methods for determining relationships between objects based on a raw semantic mesh representing vertices and faces of a 3D geometry of a physical environment. Such raw semantic meshes can be generated and used to provide input to a machine learning model that estimates relationships between objects in the physical environment. For example, the machine learning model can output a graph of nodes and edges that indicates that a vase is on a table or that a particular instance V1 of a vase is on a particular instance T1 of a table.

The invention relates to a ground unmanned platform intelligent sensing method for a field scene, and belongs to the field of automatic driving. According to the invention, a dynamic obstacle sensing flow based on geometric information is constructed through fusion of a laser radar and a millimeter-wave radar; utilizing visual semantic segmentation to construct a static environment taking semantic information as a main part and a special obstacle perception flow; and finally, through an innovative semantic raster map fusion mechanism, unifying the geometric raster map and the semantic raster map, and providing an environment model with both geometric accuracy and semantic richness for planning control. According to the invention, through laser radar-millimeter wave radar fusion and the SORT adaptive algorithm, the tracking accuracy of the dynamic obstacle is improved, the tracking delay is reduced, and the problem of changeable motion modes of the field target can be effectively solved. According to the method, the visual sensor data is collected, semantic segmentation and laser radar correction are performed, the misjudgment rate of special targets such as grasses and water pits is reduced, and the sensing reliability in a complex environment is guaranteed.

The invention discloses an optimization method for a cognitive disease nursing area, relates to the technical field of nursing and intelligent perception for the aged, and particularly discloses an optimization method for constructing a special nursing area for the old with cognitive diseases in a nursing institution for the aged. According to the method, a closed-loop information acquisition and output system consisting of five parts, namely a context embedded lattice method (CAGM), a multi-domain sensing-sensing coupling body (PCN), a heterogeneous sensing common-standard system (HSCM), a cognitive pressure load distribution spectrum (CLFS) and a care structure sub-element set (CSES), is constructed, wherein the five parts are as follows: the context embedded lattice method (CAGM), the multi-domain sensing-sensing coupling body (PCN), the heterogeneous sensing common-standard system (HSCM), the cognitive pressure load distribution spectrum (CLFS) and the care structure sub-element set (CSES). Semantic gridding division is carried out on a nursing space, multi-modal sensing nodes are deployed to collect environment dynamic data, and semantic tags of nursing personnel, experts and an AI model are fused, so that recognition of susceptible areas of the cognitive old people and quantitative modeling of cognitive risks are realized. And finally, outputting a structured design suggestion sub-element set, and directly supporting scientific layout and intelligent transformation of the nursing special area.

The application discloses a multi-angle campus panoramic intelligent monitoring system and relates to the technical field of security monitoring systems.The system comprises a sensing module, a processing module, a risk deduction module and a response execution module.The sensing module is used for obtaining sensing data based on a sensor network deployed in each region of a campus and dynamically distributing sensing tasks according to regional functions.The sensor network comprises a camera, a millimeter wave radar, a pressure sensor, an environmental noise sensor and a Bluetooth device.The processing module is used for processing sensing data in real time through a reconfigurable hardware node to generate compliance features and abnormal identifiers.The risk deduction module is used for constructing a semantic grid based on the compliance features and abnormal identifiers output by the processing module, associating regional function attributes, time permissions and historical risk heat maps and performing global risk causal chain deduction.The response execution module is used for triggering dynamic responses according to deduction results, including hierarchical privacy protection and cross-campus collaborative actions.

This invention discloses a method and system for analyzing the navigation behavior of ships in waterways based on big data, relating to the field of ship technology. This invention collects dynamic ship data and static waterway data, constructs an environmental semantic grid, and maps the dynamic data to generate semantic trajectory sequences. Based on the sequences, it calculates the basic spatiotemporal correlation value, extracts trajectory direction entropy using a local minimum spanning tree, and constructs a ship behavior feature vector. Based on physical limits, it constructs a dynamic pseudo-label dataset and uses an evolutionary algorithm based on a weighted ROC convex hull guidance strategy to iteratively optimize the parameters of the nonlinear classification decision function. Using the optimal parameter set, it constructs a decision function to identify abnormal ship behavior, calculates risk potential energy, and generates chain reaction warnings based on the risk transmission coefficient. This invention effectively integrates environmental semantics and entropy features, solving the problems of scarce abnormal samples and complex nonlinear feature identification without manual annotation, and achieving proactive and precise prevention and control of waterway collision risks.

The application discloses a transformer partial discharge positioning method based on a partial discharge wave speed adaptive compensation. The method comprises the following steps: converting a three-dimensional semantic grid model of a transformer into a three-dimensional semantic voxel matrix; determining a target sound speed tensor matrix corresponding to the three-dimensional semantic voxel matrix; determining a time-of-arrival strategy template of each voxel in the target sound speed tensor matrix according to a semantic label identified by the three-dimensional semantic voxel matrix; generating a plurality of three-dimensional time field matrices according to the respective corresponding time-of-arrival strategy templates based on the target sound speed tensor matrix; and in the case of detecting a partial discharge signal of the transformer, determining a partial discharge positioning result of the transformer based on the plurality of three-dimensional time field matrices and observed time difference data. The application solves the technical problem of low transformer partial discharge positioning accuracy in related technologies due to the neglect of the anisotropic propagation characteristics of sound waves of the transformer winding structure.

The invention discloses a water transportation channel ship navigation behavior analysis method and system based on big data, and relates to the technical field of ships. Ship dynamic data and channel static data are collected, an environment semantic grid is constructed, and the dynamic data are mapped to generate a semantic trajectory sequence; calculating a basic space-time correlation value based on the sequence, extracting a trajectory direction entropy by using a local minimum spanning tree, and constructing a ship behavior feature vector; constructing a dynamic pseudo-label data set based on physical limits, and performing iterative optimization on parameters of the nonlinear classification judgment function by adopting an evolutionary algorithm based on a weighted ROC convex hull guide strategy; according to the method, environmental semantics and entropy value features are effectively fused, the problems of abnormal sample scarcity and complex nonlinear feature recognition under the condition that manual labeling is not needed are solved, and the method is suitable for ship abnormal behavior recognition. And active and accurate prevention and control of the water area collision risk are realized.

A method performed by an apparatus for controlling automatic driving of a vehicle is provided. The method comprises the following steps: generating a first semantic grid map based on a segmentation model for processing point cloud data; generating a second semantic grid map based on the object detection model; adjusting the probability of whether elements included in each grid of the first semantic grid map and the second semantic grid map are occupied or not; a predefined label is put into the transformed point cloud; and generating a fused raster map by determining one or more tags corresponding to a highest value in final probabilities of at least one of the predefined tags as representative tags, where the final probabilities are determined based on whether the at least one tag matches the element; outputting a signal based on the fused grid map; and controlling automatic driving of the vehicle based on the signal.

The navigation of an AV in an environment may be planned based on a model of a restricted traffic zone in the environment. Information of the environment (e.g., a vector map, information of one or more objects, a temporal sequence of semantic grids, a query grid, etc.) may be input into a neural network. The neural network may include a CNN and a GNN. The map and tracks may be input into the GNN. The temporal sequence of semantic grids or query grid may be input into the CNN. The neural network may output edges of the restricted traffic zone. The neural network may output a grid of points representing locations in the environment and information indicating drivability of each respective point. The neural network may output one or more polylines dividing the environment into regions and information indicating whether the AV can drive to or in each respective region.

The present disclosure relates to a localization method and apparatus, an electronic device, and a storage medium. The localization method comprises: acquiring a target local semantic point cloud map, a global semantic grid map, and a laser point cloud map; performing pose identification on the basis of the target local semantic point cloud map and the global semantic grid map to obtain a set of candidate poses; and determining a target pose according to the laser point cloud map and the set of candidate poses.

The invention discloses a target prediction method based on an irregular semantic grid and a multi-modal network, and belongs to the technical field of space-time big data intelligent mining. The method comprises the following steps: firstly, carrying out adaptive division on DEM and optical remote sensing data in a region R range by adopting IAIGS to obtain a series of irregular semantic grids as basic calculation units, and then respectively calculating DEM / optical remote sensing slices and track segments corresponding to irregular semantic grid regions; and then semantic vector coding is performed on the DEM / optical remote sensing slice of each irregular semantic grid by adopting ISG-VAE-encoder, and finally, an MFN-RSS-ST model is trained by adopting data such as a track segment and semantic vector coding, and the irregular semantic grid output by the trained MFN-RSS-ST model is used as a prediction result of a target appearance position at the next moment. According to the method, the optical and DEM remote sensing data and the trajectory data are fused, so that the position distribution of the target at the future moment can be predicted on the premise of not depending on road network information.

The invention provides a semantic grid map generation method and system for an automatic driving vehicle, and belongs to the technical field of intelligent driving perception, and the method comprises the steps: obtaining a look-around image sequence of a target vehicle; performing feature extraction on the surround view image sequence to generate a multi-scale surround image feature pyramid; after feature embedding and position coding are carried out on each layer of surround image features, a cross-view attention mechanism is used for fusing multi-view features to convert two-dimensional surround image features into three-dimensional voxel features; through a three-dimensional shuffling attention mechanism, channel and spatial feature interaction is enhanced, and multi-resolution three-dimensional voxel features are generated by using depth separable three-dimensional convolution; and performing three-dimensional convolution feature interaction and deconvolution sampling on the three-dimensional voxel features to obtain a three-dimensional semantic grid map. Based on the method, the invention also provides a semantic grid map generation system for the autonomous vehicle. According to the method, the speed of generating the semantic grid map is increased, and the calculation overhead of automatic driving is reduced.

The application discloses a high-precision laser positioning unpacking path planning system, and belongs to the technical field of robot automatic control and industrial automation. The system comprises a data synchronization module, a high-precision positioning module, a semantic map construction module, a global path planning module and a motion control module. The data synchronization module is used for multi-sensor hardware synchronization and data alignment; the high-precision positioning module is based on environmental skeleton features and a sliding window to optimize output accurate pose; the semantic map construction module fuses visual and laser data to generate a dynamic semantic grid map; the global path planning module utilizes a hybrid potential field to improve an A* algorithm to plan a smooth path in a skeleton channel; the motion control module realizes closed-loop motion control and safety monitoring through model predictive tracking; and the work execution module adopts visual servoing to complete millimeter-level accurate parking at a work point and trigger unpacking work. The application improves the positioning robustness under dynamic occlusion through environmental skeleton features, ensures the safety and efficiency of the path through semantic understanding and intelligent planning, and realizes full-process automation from navigation to accurate work.

The application discloses a target prediction method based on an irregular semantic grid and a multi-modal network, and belongs to the technical field of intelligent mining of space-time big data. First, the IAIGS is used to adaptively divide the DEM and optical remote sensing data within the region R, so as to obtain a series of irregular semantic grids as basic calculation units. Then, the DEM / optical remote sensing slices and trajectory segments corresponding to the irregular semantic grid regions are calculated respectively. Next, the ISG-VAE-encoder is used to perform semantic vector coding on the DEM / optical remote sensing slices of each irregular semantic grid. Finally, the MFN-RSS-ST model is trained by using the trajectory segments, the semantic vector coding and other data, and the irregular semantic grid output by the trained MFN-RSS-ST model is used as the prediction result of the target position at the next moment. According to the application, the optical and DEM remote sensing data and the trajectory data are fused, so that the position distribution of the target at the future moment can be predicted without relying on road network information.

This invention provides a localization method and system based on semantic object size chains. The method includes: acquiring a dataset; constructing a semantic object size chain to establish a two-dimensional semantic grid map; initializing a particle set; updating the particle set, calculating robot motion, performing coordinate transformation, predicting the position of each particle in the particle set to obtain a predicted particle set; calculating the weight value of each particle, extracting environmental semantics, identifying objects, performing foreground / background segmentation and coordinate transformation mapping, determining the corresponding position of the object in the semantic object size chain, using the information of each object in the current frame to inversely solve the robot's position, updating the weight value of the obtained estimated position value set; resampling the particles, continuously updating in a loop until the particles converge, and completing the localization. Compared with mainstream relocalization algorithms, this invention has higher stability, provides richer and more reliable features for robot localization and navigation, and thus can complete more advanced and complex tasks.