28 results about "Map quality" patented technology

The invention provides a map data acquisition crowd sensing participant recruitment method and a related system, and relates to the technical field of intelligent traffic. According to the method, a vehicle dynamic perception utility evaluation mechanism and a vehicle historical task reputation reuse mechanism are combined under an edge calculation framework, and an actual map defect area existing in a target map construction area in charge of each edge node is constructed; intelligent vehicles with sufficient perception utility intensity and good reputation are recruited as required for collaborative perception mapping, so that the timeliness, the accuracy and the system robustness of map data acquisition operation in a complex dynamic traffic environment are effectively enhanced, and the overall timeliness, the overall efficiency and the map quality of crowd-sourcing collaborative perception mapping operation are improved; the problems of local area sensing redundancy, local area sensing deficiency, serious mapping communication delay and the like existing in an existing crowd-sourcing cooperative sensing mapping scheme can be further relieved.

Autonomous docking systems and methods receive asynchronous images from a vehicle-mounted camera and a plurality of infrastructure cameras and perform object mapping to determine candidate routes leading to a docking station. Candidate routes are divided into route segments for which disparity map quality scores are estimated to select a navigation route. Information from infrastructure cameras and vehicle-mounted cameras is used to generate a disparity map to perform object detection, distance measurement, or localization along the navigation route. The disparity map is used to communicate navigation commands to an HMI or a vehicle control system.

The application provides a multi-type map-based fusion positioning method and an electronic device. The method comprises: acquiring a target image to be positioned; acquiring a target position at which the target image is captured; determining a target map quality of a map located at the target position in a map database composed of multiple different types of map data; determining a target positioning mode from a plurality of different positioning modes preset according to the target map quality, the target positioning mode being composed of basic positioning modes corresponding to each map data included in the map database; and positioning the target image by using the target positioning mode to obtain 6DOF of the target image. Thus, when the image is positioned, a suitable positioning scheme can be selected from multiple positioning schemes according to different map qualities corresponding to positions of the image, a positioning effect with higher precision and stability is realized, map quality is upgraded without perception in time and space, and user experience is improved.

Provided in the embodiments of the present application are a map quality evaluation method and apparatus, and a device and a storage medium. The method comprises: acquiring a map on the basis of perception information collected by means of a perception device; and on the basis of the occurrence of a score deduction scenario in the map, determining a score of the map, wherein the score of the map is used for representing the quality of the map, and the occurrence of the score deduction scenario is inversely proportional to the quality of the map. In the embodiments of the present application, after studying and obtaining a map, a memory navigation system performs quality evaluation on the map, obtains the score of the map by means of the quality evaluation, and displays the score of the map to a driver, such that the driver can determine, by means of the score of the map, whether to use the map, thereby ensuring that each map used by the memory navigation system is a map of a relatively high quality, ensuring the use effect of a memory navigation function, and improving the user experience.

The embodiment of the invention provides a map quality detection method, electronic equipment and a storage medium, and the method comprises the steps: obtaining the trajectory data of a traffic participant in a preset scene, a predetermined true value map and a to-be-detected vectorized map, matching the trajectory data with a first map element in the true value map, obtaining labeled trajectory data, and storing the labeled trajectory data in a database; and determining a target trajectory where the first map element in the labeled trajectory data is matched with a second map element in the vectorized map, obtaining a trajectory subset of the second map element, performing space matching degree and time consistency detection on the trajectory subset of the second map element and the second map element, and obtaining a dynamic detection result of the vectorized map. And determining a quality detection result of the vectorized map according to the dynamic detection result. Quality detection is performed by integrating the dynamic characteristics of the map, and the accuracy of the map quality detection result is improved.

The application discloses a kind of fusion navigation and reliability quantitative evaluation system based on pre-set sparse map.The system is fused positioning module by multi-source sensor, and is fused vision, inertia and optical flow data based on pre-set sparse feature map;Reliability quantitative evaluation module is used to calculate feature distribution balance degree, trajectory coverage and feature stability index, and generate navigation map quality index;Decision control module divides reliability level according to navigation map quality index, dynamically adjusts unmanned aerial vehicle flight speed and task mode;Abnormal processing module triggers degradation flight and monitors pose uncertainty when signal source fails, executes return or hovering strategy when threshold is exceeded.The application realizes high robustness positioning and hierarchical safety control of unmanned aerial vehicle in complex environment.

The invention discloses a grid map processing method, related equipment and a computer program product, and the method comprises the steps: converting an original grid map into a tri-state graph, carrying out the binarization processing, and extracting the contour line of an obstacle from a binarized image; and based on the contour line of the obstacle in the binarized image, performing masking processing on the tri-state graph, and determining an editable gap region in the tri-state graph through a masking form. And screening a first gap region meeting a gap credibility condition, and editing a grid state corresponding to the first gap region in the tri-state graph into an idle state. According to the invention, the accuracy of identifying passable gap areas such as door slots, corridors, narrow channels and the like is improved, and the map quality is improved.

The disclosure relates to a method and an apparatus for generating a 3D signal quality map. According to an aspect of the disclosure, there is provided a method for generating a 3D signal quality map, performed by a computing device including at least one processor, the method including: initializing a signal quality map; collecting signal quality values from a plurality of points; estimating a map quality state using the collected signal quality values; determining a quality map parameter based on the estimated map quality state; and updating the signal quality map using the quality map parameter.

The invention provides an efficient map element quality inspection AI system and an implementation method, and relates to the field of map element quality inspection systems, and the system comprises a multi-source data access module which is used for importing multi-type map element data and unifying a spatial reference system; the AI quality inspection model training module comprises a spatial topological feature extraction network and a quality inspection rule self-learning sub-model and is used for generating a dynamic rule base; the multi-element intelligent verification module integrates a topology verification unit, an attribute verification unit and an incidence relation verification unit and is used for joint verification of multiple types of map elements; the visual report and rectification module is used for generating a structured quality inspection report and supporting one-key rectification; and the system management module is used for user authority management and model iteration maintenance. According to the method, eight common error types in map drawing can be automatically identified, and efficient, accurate and intelligent map quality inspection is realized through multi-modal data in combination with deep learning and knowledge reasoning.

The present application relates to the technical field of robot patrol surveying, in particular to a four-legged robot autonomous patrol navigation control and active three-dimensional mapping method, system and terminal. The robot of the present application explores environment data in unknown environment, and draws a map with the explored environment data, so as to realize the purpose of exploring and mapping at the same time, and evaluate the map quality in real time, and actively map the area on the map again whose quality does not meet the standard, so as to improve the quality of the final obtained map. And based on the map quality evaluation result, the path required for exploring the area again whose quality does not meet the standard is planned, so that the robot can accurately and efficiently move to the area whose quality does not meet the standard.

The invention discloses a map quality detection method, a control device, a mobile robot and a medium. The method comprises the following steps: acquiring a current map constructed by the robot; pixel matching is carried out on the current map and a historical map to obtain similarity, and / or feature point matching is carried out on the current map and the historical map to obtain feature point pairs, and the historical map is a map constructed according to historical environment data collected by a robot; determining a map folding condition of the current map according to the similarity and / or the feature point pairs; and determining the map quality of the current map according to the map folding condition. In the embodiment of the invention, the quality of the map can be improved, and the situation of map overlapping is avoided.

The present disclosure provides a model processing and high-definition map quality verification method and device and a storage medium, relating to the fields of artificial intelligence such as automatic driving, machine learning and computer vision, wherein the model processing method can comprise: constructing a Bayesian network model; determining the values of each variable in the Bayesian network model according to the obtained training samples; and determining the network parameters of the Bayesian network model according to the training samples and the values of each variable, wherein the network parameters are used to determine the quality verification result of the high-definition map to be verified, and the quality verification result is determined according to the input data and the network parameters determined based on the point cloud data corresponding to the high-definition map. The scheme disclosed in the present disclosure can save labor and time costs and improve the accuracy of the verification result.

The invention discloses a map updating method and device, an autonomous mobile device and a storage medium, and relates to the technical field of autonomous navigation. Acquiring a pre-constructed global map, a semantic map, a pose of the autonomous mobile device, and sensor data, in which a static region and a dynamic region in the global map are labeled in the semantic map (S110); according to the pose and the sensor data, periodically constructing a local map to limit the coverage area of the local map (S120); aligning the global map and the local map to obtain a target local map aligned with the global map (S130); and updating the global map according to the global map, the semantic map and the target local map (S140). The consistency of the global map can be ensured, the quality of the global map is improved, and the efficiency and accuracy of map updating are improved.

The application discloses a kind of vehicle autonomous return control method, device and medium without satellite navigation, the method includes the following steps: to unmanned vehicle executes before departure preparation inspection operation, obtains preparation inspection result;According to preparation inspection result, unmanned vehicle is controlled to carry out journey detection;According to the feedback data of unmanned vehicle in journey detection, obtain the driving vehicle condition data and environmental detection data of unmanned vehicle;According to driving vehicle condition data and environmental detection data, point cloud map is constructed;The map quality of point cloud map is judged, and according to map quality, unmanned vehicle is selected to execute self-driving return operation or phased return operation;The application can be when unmanned vehicle investigates and explores road, according to the vehicle condition data of unmanned vehicle, intelligently infers the location of unmanned vehicle, and when returning, according to the aforementioned vehicle condition data and inference data, intelligently control unmanned vehicle to enter adaptive return trajectory and autonomous return mode of environment, realizes the autonomous road exploration return of unmanned vehicle under satellite system and satellite signal without needing.

The invention relates to the technical field of computer vision and robotics, in particular to an SLAM point cloud map-oriented multi-index assessment method, which realizes accurate registration of a to-be-assessed map and a true value map by adopting a point-to-plane ICP algorithm, and further performs voxelization processing based on dynamic size on the registered point cloud, so that the accuracy of the SLAM point cloud map-oriented multi-index assessment is improved. And establishing a Gaussian distribution model in each voxel, finally evaluating global geometric consistency by calculating a voxelization average Wasserstein distance, and evaluating local structure consistency in combination with a spatial consistency score (SCS). A unified quality evaluation standard is established, so that the map quality of different SLAM algorithms has comparability; the adaptive capacity to noise, sparse point cloud and non-uniform sampling is improved, and the robustness of the method is enhanced; the calculation complexity is reduced, good balance between efficiency and precision is achieved, and the requirement for efficient evaluation of large-scale point cloud data in practical application can be met.

The invention discloses a hybrid map construction method and device for mobile robot navigation and a medium, and relates to the technical field of navigation hybrid map construction, and the method comprises the following steps: collecting a multi-modal sensor observation flow, constructing a measurement representation, a topological representation and a semantic representation, and generating a time version chain starting point time version; updating the metric representation, the topological representation and the semantic representation in a control period, generating a differential representation, writing the differential representation into a time version chain, and generating a continuously expanded time version chain; generating a structure stability degree, a semantic drift degree, a topological evolution consistency degree and an updating cost density quality curve, and obtaining a quality curve set; and selecting a current running hybrid map time version, performing local updating of measurement representation, semantic representation and topological representation, and adjusting a time window length and a time version switching strategy. The objectivity of map quality evaluation and the time version selection decision precision are improved, and the map updating efficiency and the overall operation efficiency are improved.

This disclosure provides a method, apparatus, and device for simulating and testing the quality of high-precision maps, relating to the field of autonomous driving technology, specifically the field of simulation testing technology. The specific implementation scheme is as follows: determining the simulation type corresponding to the map to be tested; generating a simulation scene corresponding to the map to be tested based on the simulation type; controlling the driving of a simulated vehicle in the simulation scene and collecting abnormal driving information of the simulated vehicle; and generating a quality detection result for the map to be tested based on the abnormal driving information. This implementation method can improve the accuracy of map quality detection.

The invention relates to the technical field of incremental point cloud map construction methods, particularly discloses an incremental point cloud map construction method, and aims at solving the problems that an existing mapping method is low in efficiency, large in repeated calculation amount and insufficient in fusion precision. The method comprises the following steps: constructing an initial reference map based on a laser radar and an inertial measurement unit; extracting edge and plane feature points of the current frame and the reference map through the smoothness parameter; carrying out registration on the feature point cloud by adopting voxelization Gaussian distribution modeling and maximum likelihood estimation to obtain a transformation matrix; unifying the newly constructed map to the reference coordinate system through the transformation matrix and carrying out preliminary fusion; and finally, searching and deleting repeated points by using a Kdtree radius, and outputting a simplified fusion map. According to the technical scheme, efficient and high-precision incremental point cloud map construction can be realized, the mapping efficiency and the map quality are remarkably improved, and the method is suitable for scenes with high real-time requirements such as automatic driving and the like.

The invention provides a map construction method, a cleaning robot and a storage medium. The method comprises the steps that in a target water area, environment distance information of at least two distance sensors arranged on the periphery of the robot is acquired; based on the environment distance information, motion parameters of the robot are adjusted through a feedback control algorithm, and the robot is made to advance along the boundary of the target water area or a preset path; in the advancing process, boundary position information is determined according to lateral distance information in the environment distance information and position information and an orientation angle of the robot; and constructing a map of the target water area according to the boundary position information. By using the method, the map quality can be improved.

The invention relates to the technical field of agricultural robots and intelligent agriculture, in particular to a multi-robot collaborative synchronous positioning and mapping method, system and device for facility agriculture environment application. The method comprises the following steps: deploying a multi-robot cluster to synchronously collect environment multi-modal data; each robot carries out front-end processing based on an improved feature extraction and matching network, a lightweight dynamic target detection model and a dual feature point elimination strategy, and combines particle filtering to fuse multi-source information to obtain a rough pose; uploading the data to an edge computing terminal through a 5G and intelligent reflecting surface fused communication network; global optimization based on a pose map is carried out on the edge computing terminal to obtain a high-precision pose, and a panoramic three-dimensional map is generated through neural radiation field training rendering; and finally, unified storage, visualization and task scheduling are carried out through the cloud intelligent coordination platform. According to the method, the positioning precision, the map quality, the cooperation efficiency and the system robustness of the multi-robot system in the complex environment of facility agriculture are effectively improved.

The invention discloses an evaluation method and system for plane precision of a non-directional digital line map, and relates to the technical field of digital line map quality evaluation, and the method comprises a collection unit which is used for obtaining a field undirectional ground feature check point, a positioning unit which is used for obtaining the real-time coordinate of an observation station and the initial azimuth angle of the observation station when the ground feature check point is measured, and a processing unit which is used for processing the real-time coordinate. The processing unit is used for correcting the coordinates of the ground feature check points acquired for the first time in a non-directional manner, so that the quadratic sum of a plane difference value between the corrected coordinates of the ground feature check points and the coordinates of the homonymy points on the digital line graph is minimum, and the quality management system is used for receiving the corrected coordinates of the ground feature check points, and managing the quality of the ground feature check points. Carrying out precision evaluation on the corrected coordinates of the ground feature check points; through the device, inspection data under a free coordinate system is directly collected without orientation, the obtained data is sorted and analyzed, the plane precision of a digital line drawing is evaluated, manpower resource allocation is reduced, precious field operation time is saved, and then working efficiency is improved.

The invention relates to the technical field of map quality auditing, in particular to an intelligent map quality auditing method based on big data, and the method comprises the steps: obtaining user navigation path data, extracting all navigation points, carrying out map matching verification, recognizing unmatched points, and merging the unmatched points into track offset fragments; spatial coincidence verification is carried out on the data, non-coincidence coordinate segments are extracted to form a road missing section list, a road endpoint and boundary position relation is analyzed based on missing section boundaries, edge road description deviation is recognized, an interest point target path termination section is extracted, a termination point and a marking point position are compared, and an entrance offset result is constructed; and summarizing multi-source anomalies according to space grids to generate a map quality auditing result. According to the method, unmatched points of a navigation path are aggregated to construct a track offset segment, road coverage missing sections are identified, edge abnormal road positions are extracted, interest points are compared to terminate offset, quality problems are aggregated according to grids, a multi-dimensional marking state is established, and the anomaly identification precision and attribution definition are improved.

The invention discloses a radar odometer dynamic point elimination method based on associated visual semanteme, and relates to the field of synchronous positioning and map building.The method comprises the steps that LVI-SAM serves as a basic framework, a visual end adopts YOLOv8 to detect a dynamic object, and dynamic features are extracted and triangularized into three-dimensional visual dynamic points; the radar end receives visual dynamic points and pose information, dynamic semantics are spread to the radar point cloud through an expansion algorithm, a boundary attenuation model is introduced to adjust the expansion range of the visual dynamic point cloud boundary, and static radar point misjudgment is avoided; and finally obtaining a pure static point cloud which is used for feature extraction, matching and pose map optimization of a radar inertial system. The robustness of a complex scene is enhanced through multi-sensor cooperative calibration, scene-based parameter configuration can be flexibly applied to multiple scenes, SLAM mapping'ghosting 'is effectively eliminated, the pose estimation precision is improved, and the requirements of downstream tasks of a robot for map quality and positioning reliability are met.

The application discloses a high-precision map updating method and device. The method comprises the following steps: acquiring first pose information of a vehicle at a first acquisition time, and acquiring a local high-precision map corresponding to the first pose information from a cloud module, wherein the local high-precision map comprises road vector feature information; acquiring a plurality of road images and vehicle navigation information collected in a preset time period, and determining fused observation feature information according to the plurality of road images and the vehicle navigation information, wherein the vehicle navigation information is used for dead reckoning; registering the road vector feature information and the fused observation feature information to obtain registration pose information of the vehicle; and when the registration pose information meets a preset condition, uploading the fused observation feature information to the cloud module to update the local high-precision map. The application solves the technical problems of high cost or poor map quality in related art when updating a high-precision map.

The application provides a map data collection crowd-sensing participant recruitment method and a related system, and relates to the technical field of intelligent transportation. The application combines a vehicle dynamic sensing utility evaluation mechanism and a vehicle historical task reputation reuse mechanism under an edge computing framework, recruits intelligent vehicles with sufficient sensing utility intensity and good reputation for collaborative sensing mapping according to actual map defect areas existing in a target map construction area responsible by each edge node on demand, so as to effectively enhance the timeliness, accuracy and system robustness of map data collection operations in a complex dynamic traffic environment, improve the overall timeliness, overall efficiency and map quality of crowd-sensing collaborative mapping operations, and further alleviate problems such as local area sensing redundancy, local area sensing deficiency and serious mapping communication delay existing in existing crowd-sensing collaborative mapping schemes.

This application discloses an OpenDrive map quality detection method, apparatus, device, and storage medium, relating to the field of high-precision map technology. It enables automatic detection of OpenDrive map quality, preventing quality issues from affecting autonomous driving accuracy. The specific scheme includes: obtaining the first coordinates of multiple target points on a target reference line in a discrete map, and obtaining the angle value between the second and second coordinates of each target point in the OpenDrive map; the angle value is the angle between the tangent direction of the target reference line at the second coordinate and the horizontal direction in the OpenDrive map; determining the angle change value of each target point relative to the starting target point based on each angle value; and determining the third coordinate of each target point based on the starting angle value corresponding to the starting target point, the angle change value of each target point, and the first coordinate of the starting target point; and determining whether the target reference line in the OpenDrive map is qualified based on the spatial distance between the first and third coordinates of each target point.

The invention relates to the technical field of robot inspection and detection mapping, in particular to a quadruped robot autonomous inspection navigation control and active three-dimensional mapping method, system and terminal. The robot explores environmental data in an unknown environment and draws a map by using the explored environmental data so as to realize the purpose of mapping while exploring, and meanwhile, the map quality is evaluated in real time, and the area with substandard quality on the map is actively mapped again so as to improve the quality of the finally obtained map. And based on a map quality evaluation result, a map is planned to explore a path required by the substandard area again, so that the robot can accurately and efficiently move to the substandard area.