40 results about "Distance based" patented technology

The application belongs to the technical field of load identification of structural health monitoring, and provides a concentrated load positioning method based on principal stress constraint and strain gradient trajectory identification, which comprises the following steps: arranging strain sensors in a monitoring area of a planar structure plate and collecting strain data of measuring points, constructing a strain field inversion function based on a radial basis function and establishing an error optimization function containing a fitting error term and a smooth constraint, introducing a principal stress direction constraint and a gradient projection smooth constraint to form a comprehensive error function and solving to obtain an optimal strain field distribution, then calculating strain gradient vectors of each grid node and tracking a gradient trajectory through a gradient descent method, and finally performing an iterative clustering analysis based on distance statistics on a trajectory end point to output a cluster center as a concentrated load application position identification result. The application can improve the concentrated load positioning accuracy, enhance the anti-noise capability, and realize fast, stable and large-sample-free load position identification.

In the motion state detection method and self-moving cleaning device disclosed in this invention, when the self-moving cleaning device determines that it has moved a certain distance based on internal parameters, if the distance measurement value detects a small change in the relative distance between the self-moving cleaning device and objects in the environment, and the data state at this time matches the data state when slipping occurs, it can be directly determined that slipping has occurred. By combining the original hardware configuration of the self-moving cleaning device with relevant data statistics, it is possible to determine whether slipping has occurred. The hardware and software costs for slipping detection are extremely low, and the detection results are accurate. Even self-moving cleaning devices with lower hardware configurations can achieve slipping detection through software upgrades; without increasing purchase costs, users of self-moving cleaning devices with lower hardware configurations can also enjoy a good user experience.

The application discloses a kind of attention mechanism trajectory generation and simulation methods for sparse data completion, belong to intelligent transportation and trajectory prediction field.The application fills in trajectory missing value using high-precision sensor and map information, combines graph attention network (GAT) and multi-modal fusion technology;Adopt the attention module based on distance (D-GAT) and based on view (V-GAT), capture the interaction between vehicles, improve the understanding of complex traffic scene;Through prediction supervision generator and multi-modal trajectory generator, combine LSTM and Gaussian mixture model (GMM) to generate multiple possible trajectories, and use Kalman filter for online adjustment, ensure the accuracy and real-time of trajectory.The application realizes the intelligent completion of sparse traffic data and the accurate generation of trajectory, provides reliable data support and decision basis for intelligent transportation system, helps the efficient operation and sustainable development of urban traffic planning and management.

This invention relates to the field of mining area traffic planning and discloses a method for planning vehicle speed in mining areas that integrates AI algorithms and multimodal data. The method includes the following steps: S1, determining that the current vehicle is in a following state and collecting the current vehicle's driving parameters, the position of the leading vehicle, and the distance between the two vehicles; S2, based on the positions of the current vehicle and the leading vehicle, determining whether the leading vehicle is traveling on a slope or about to leave the slope; S3, if the leading vehicle is on a slope or about to leave the slope, determining a safe following distance based on the distance between the two vehicles and the leading vehicle's slope travel distance; S4, planning the current vehicle's driving speed. This invention identifies vehicle following patterns and collects multimodal data in real time and comprehensively. It utilizes AI algorithms to perform high-precision perception and forward-looking prediction of the leading vehicle's slope travel status, enabling the solution to fully understand the complex terrain environment currently and in the future, thus allowing for pre-emptive risk assessment.

This invention relates to the field of quadruped robot navigation technology and discloses an intelligent navigation system for quadruped robots that combines behavior tree and visual recognition. The system includes modules for path processing, turn prediction, behavior tree decision-making, obstruction judgment, visual recognition and language evaluation, and navigation decision-making. The path processing module integrates multi-sensor data to acquire pose and gait state; the turn prediction module calculates safe turning speed and trigger distance based on a gait phase sliding window; the behavior tree decision-making module dynamically adjusts node priorities according to trigger intensity, and the switching timing is controlled by a gait phase arbiter; the obstruction judgment module generates path obstruction flags; the visual recognition module adopts a two-level architecture, calling a visual language model to evaluate the landing area for static traversable obstacles; and the navigation decision-making module integrates landing semantic confidence and outputs commands to cross, detour, wait, or return. This invention enables quadruped robots to achieve proactive predictive navigation and intelligent obstacle avoidance decision-making in complex industrial environments.

A machine-learning based (ML-based) system and method for automatically extracting one or more data fields from one or more documents, are disclosed. The ML-based system includes a document obtaining subsystem to obtain documents, a document pre-processing subsystem to generate pre-processed data, a field identifying subsystem to identify data fields using a trained ML model, and a field extracting subsystem to extract financial information. The ML-based system also comprises an output subsystem to deliver the extracted data to end users via user interfaces. The ML model is trained using historical documents, labelled data fields, and features such as distance-based features, direction-based features, dimension-based features, positional features, and value-based features. The M-based system employs hyperparameter optimization, noise removal, and accuracy assessment mechanisms to enhance performance. This ML-based system provides a scalable, accurate, and automated solution for financial information extraction, ensuring efficiency, adaptability, and seamless integration with enterprise systems.

The application discloses a visual language navigation method based on distance perception of a Transformer, and belongs to the technical field of visual language cross-modal technology.The algorithm is realized in the following manner: firstly, visual information, instruction information and memory structure of a perceivable region of an intelligent agent are initialized, then a scene memory updating module based on a graph data structure is provided, and exploration information in a navigation process is further fused by combining a language visual multi-modal pre-training model, so that the perception ability of the intelligent agent to the environment is strengthened; a distance-based progress monitor is provided to compress the action space of each step decision in the navigation process, so as to reduce the operation resources and speed up the model training; a dynamic distance fusion module is provided to integrate distance information into action decision, so that the algorithm can perform global exploration while taking into account the exploration path length, and the efficiency of the navigation task is improved.The visual language navigation method based on distance perception of the Transformer provided by the application can obviously improve the exploration efficiency of the scene memory algorithm while ensuring a good navigation success rate.

The abnormality determination device includes a time series signal extraction unit, a normal vector registration unit, an abnormality determination model registration unit, and an abnormality determination unit. In a case where the abnormality determination flag is the first type, the abnormality determination unit calculates distances from the registered normal vectors, extracts a predetermined number of normal vectors as neighboring data in order of the distances from small to large, calculates a distance between a center of gravity vector of the neighboring data and an M-dimensional vector of an object of abnormality determination, and performs abnormality determination of the device based on the distance. In a case where the abnormality determination flag is the second type, the abnormality determination unit calculates a deviation from principal components based on transformation coefficients of the principal components calculated in advance, and performs abnormality determination of the device based on the deviation.

A data processing apparatus (100) and method for efficiently and accurately determining a relative pose (160) of a mobile agent such as a vehicle are disclosed. The apparatus (100) comprises processing circuitry (110) configured to determine a feature vector and a score for each point in a source point cloud (140) and a feature vector for each point in a target point cloud (150), and to transform a plurality of key points of the source point cloud (140) from a first pose to an unknown second pose for a plurality of relative pose candidates. The processing circuitry is further configured to pair each transformed key point with a target point in the target point cloud (150) based on distance, and to determine the relative pose of the mobile agent based on the plurality of feature vectors and positions of the plurality of transformed key points and target points.

This invention relates to the field of deep space exploration technology, and particularly to a real-time distance determination method and apparatus based on heterogeneous information compensation. The method includes: determining first distance data obtained by a dynamics computer within each preset exploration cycle; if the dynamics computer receives second distance data sent by a ranging simulator, obtaining distance compensation data based on the second distance data and the first distance data of the exploration cycle in which the ranging command was sent; in all subsequent exploration cycles in which no new second distance data is received, obtaining target distance data for the exploration cycle based on the distance compensation data and the first distance data corresponding to each exploration cycle; if the dynamics computer receives second distance data sent by the ranging simulator again, repeating the above process to obtain the target distance data corresponding to each exploration cycle. The technical solution of this invention can improve the accuracy of distance data between the probe and the lunar surface.

To improve the accuracy of distance estimation. [Solution] The distance estimation system 1 comprises a reference communication terminal 100 and a target communication terminal 10, each performing multi-carrier transmission, and an information processing device 500 that estimates the distance between the reference communication terminal and the target communication terminal according to the communication results between the reference communication terminal and the target communication terminal. The information processing device identifies a provisional distance estimate based on the received signal of the reference communication terminal transmitted and received between the reference communication terminal and the target communication terminal, removes the long-time delayed wave component from the received wave of the received signal based on the received signal from which the long-time delayed wave component has been removed, and estimates the distance based on the intensity of the distance spectrum within a predetermined search range of the distance including the provisional estimate.

The application relates to the field of intelligent electric meter detection, in particular to an intelligent electric meter power consumption anomaly detection method and system based on mode classification, which comprises the following steps: obtaining historical current sequences and to-be-detected current sequences of each user, performing multi-scale equal-length adaptive segmentation and frequency band division on the historical current sequences, combining user intra and inter power consumption mode differences to calculate power consumption tolerance of each frequency band, performing EMD decomposition and feature extraction on the historical current sequences, calculating mode classification distances based on power consumption tolerance and clustering to obtain power consumption mode clusters, and finally comparing distances between the to-be-detected sequences and the mode clusters, calculating anomaly scores and determining power consumption anomaly states. Through multi-scale equal-length adaptive segmentation, frequency band differential analysis on the historical current sequences, and combination of user intra and inter power consumption mode differences, tolerance and anomaly scores are constructed, precise and personalized anomaly detection of user power consumption is realized, and detection accuracy and efficiency are improved.

The application discloses a kind of motion planning method of inspection robot based on hybrid A* and model predictive control, constructs grid map and carries out obstacle inflation processing;By constructing continuous state discretization method, initialize data structure, vectorize motion mode and introduce direction change and reverse penalty term definition motion mode consistency penalty, dynamically adjust heuristic weight based on search progress;Calculate the actual cost including path length, consistency penalty and heading angle smoothing penalty, generate initial global path;Path is smoothed using B-spline;Establish discrete-time prediction model of differential robot, introduce progress variable to quantify task completion, dynamically adjust look-ahead distance based on path curvature, dynamically calculate reference state within the constraint forward window;Construct MPC objective function, solve optimal control sequence by rolling optimization and execute.The method can realize kinematically feasible, geometrically smooth global path generation and high-precision, strong robustness local trajectory tracking.

Systems and methods are described for distance-based user interfaces. A distance between a user and a display can be determined. The distance between the user and the display can be determined based on a signal strength of a signal from a remote control. The distance between the user and the display can be determined based on audio signals received by a control device. A user interface can be modified based on the determined distance.

This invention provides a method, system, device, and medium for constructing a multi-level detailed MR model, belonging to the interdisciplinary field of MR technology and computer graphics technology. The method includes: acquiring the geometric data of each component in the BIM model; converting the folding relationship of the facets into curvature correction terms and performing a nonlinear transformation to obtain the edge angle cost component; performing a nonlinear transformation on the edge length to obtain the edge length cost component; acquiring the distance from the device to the center of the component; scoring based on the distance, a preset maximum rendering distance, and structural importance; taking the highest score as the final level score of the component; determining the folding priority of each edge based on the edge angle cost component and the edge length cost component; and then performing folding processing on the edges to generate a multi-level detailed MR model. This invention, through a nonlinear cost function and two-dimensional hierarchical partitioning, effectively protects geometric features and engineering semantics during model simplification, dynamically adapts to changes in the MR viewpoint, and significantly improves rendering smoothness and resource utilization.

The application discloses a distribution network non-power-off operation scheme generation method, system, device and medium based on fuzzy matching, and belongs to the technical field of intelligent operation and maintenance of distribution networks. The method comprises the following steps: constructing a four-layer intelligent architecture of "perception-cognition-decision-learning", realizing fuzzy clustering and profiling of a mixed feature scene through an improved DBSCAN algorithm based on Gower distance; establishing a multi-dimensional expert knowledge system, integrating three-dimensional knowledge of rules, cases and parameters; designing a knowledge matching mechanism based on fuzzy comprehensive evaluation, realizing the cooperation of accurate label matching and fuzzy feature similarity matching; introducing a dynamic multi-objective optimization model, and combining real-time working conditions to realize personalized adjustment of the scheme. Finally, the self-learning evolution of the knowledge system is realized through execution feedback. The application realizes the fast, accurate and self-adaptive generation of the operation scheme, and improves the intelligent level and safety of the distribution network non-power-off operation.

The application relates to a flight plan generation method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: determining a divertable point meeting a diversion condition of a standby airport from a waypoint; determining a leg distance based on a leg between the divertable points; determining a segmentation point of the leg in a segmentation step based on a segmentation step corresponding to the leg distance; and changing the standby airport of the leg if it is determined that there is a target segmentation point not meeting the diversion condition of the standby airport in the segmentation points of the leg in the segmentation step. The method can determine the reachable standby airport for more positions in a leg.

The adaptive distance detection method, system and medium based on the TOF sensor include obtaining an original slant range measurement value and an original attitude angle measurement value; correcting the original slant range measurement value to obtain an effective slant range value; performing attitude solving processing on the original attitude angle measurement value to obtain an attitude angle component; performing time alignment processing based on the effective slant range value and the attitude angle component to obtain a correlated data tuple; calculating a calibrated straight-line distance based on the data tuple and a preset formula; performing effectiveness verification on the calibrated straight-line distance to obtain an effective straight-line distance; calculating a time sequence statistic based on a plurality of continuous effective straight-line distances, and calculating a time sequence change based on a plurality of continuous attitude angle components; comparing the time sequence statistic with a first static threshold value, and comparing the time sequence change with a second static threshold value; and adjusting a ranging frequency of the TOF sensor according to a comparison result.

This application discloses a product defect detection method and related apparatus. The product defect detection method includes: extracting features from an actual product image and a standard product image respectively, obtaining actual product features and standard product features, where the actual product image is taken of the target product in its actual state, and the standard product image is taken of the target product in its standard state; stitching the actual product features and standard product features along the channel direction to obtain stitched product features; using a distance metric model based on the stitched product features to obtain a distance map between the actual product image and the standard product image; and determining whether the target product in its actual state has a defect based on the distance map. This solution can improve the accuracy of product defect detection results and save storage space and computational overhead.

The present disclosure concerns a method of measuring the distance between a device and an object comprising the steps of determination of a first estimated distance based on the time of flight of first light pulses having a first period; determination of a second estimated distance based on the time of flight of second light pulses having a second period different from the first period; determination based on the interval between the first and second estimated distances of whether the device is in a wraparound area among wraparound areas; and if the device is in a wraparound area among wraparound areas, adding to the first estimated distance a compensation having its value depending on the wraparound area.

This invention discloses a robot path planning method and system based on tunnel feature constraints, belonging to the field of autonomous navigation for tunnel robots. The method involves acquiring 3D point cloud data of the tunnel to generate an initial 3D tunnel map model; acquiring tunnel surface images and inputting them into a YOLOv5 deep learning model for identification to obtain damaged areas; mapping these damaged areas onto the initial 3D tunnel map model; defining impassable areas and safe distances based on the damaged areas; generating a 3D safety map based on the impassable areas and safe distances; obtaining a 3D tunnel map with superimposed multi-constraint fields based on multi-feature constraint joint modeling and the 3D safety map; generating a global time field from the starting point to each grid based on the superimposed multi-constraint field 3D tunnel map; generating path points from the endpoint backward along the time field gradient; verifying the distances of the path points; and outputting the planned path if the distance exceeds a set limit. This ensures that the tunnel robot can complete its task safely and efficiently.

The application discloses a kind of stereoscopic SAR geometric calibration methods based on alternating direction multiplier method, comprising: obtaining multiple SAR images covering the same area, extracting satellite ephemeris parameters, observation slant range and Doppler center frequency, and obtaining elevation model data as prior elevation information;Based on the range-Doppler model, the range equation and Doppler equation containing the estimated parameter vector are established;Joint adjustment global optimization objective function with L2 regularization constraint is constructed;Auxiliary variables are introduced to convert the objective function into an equality constrained optimization problem, and an augmented Lagrangian function is constructed;Iterative solution is carried out using alternating direction multiplier method, and the estimated parameter vector, auxiliary variable and dual variable are updated alternately;After meeting the convergence condition, the optimal estimate of ground point three-dimensional coordinates and slant range system error is output.The application can realize high-precision and high-stability three-dimensional geometric calibration without ground control points.

The present application relates to the technical field of fire-fighting robot navigation and environment modeling, and particularly relates to a dynamic deduction method and system for a multi-dimensional semantic map of a fire-fighting robot. The present application comprises: obtaining a current world coordinate system pose of the robot, and establishing a voxel map with voxels as basic spatial units; obtaining multi-dimensional perception data, and calculating obstacle factor information, trapped person factor information and fire source factor information for each voxel; calculating temperature factor information and harmful gas factor information corresponding to voxels within a set distance value range from the location of the robot, and using a distance-weighted derivative deduction algorithm to complete the temperature factor information and harmful gas factor information for voxels in the voxel map that are not directly reached by sensors; and updating risk factor information corresponding to each voxel in real time, and generating a risk factor map. The present application can integrate multi-dimensional risk factors, and achieve dynamic deduction and semantic labeling.

We provide the system. [Solution] A device that acquires the user's location information, A server that calculates the distance based on the location information received from the aforementioned terminal and detects deviation from a predetermined safety range, Means having a generation model that generates and sends an interactive message to the user when the aforementioned deviation is detected, A means of calculating the route from the current location to the destination and instructing the user on the route, A system to prevent children from getting lost, including a lost child prevention system.

This application relates to a method, apparatus, and computer equipment for adding stakes in obstacle areas during road layout. The method includes: determining the construction centerline model and longitudinal profile elevation information of the road based on the original design data; determining an integrated centerline model of the road based on the construction centerline model and the longitudinal profile design elevation information; constructing a distance objective function between mileage parameter points on the integrated centerline model and corresponding reference objects in each obstacle area based on the integrated centerline model and pre-collected feature points; determining the stake points to be added based on the distance objective function; determining the engineering standard station number of each stake point based on the integrated centerline model and the location information of each stake point; and performing stake addition processing on each stake point based on the engineering standard station number of each stake point and the design elevation of each stake point determined by the longitudinal profile design elevation information. This method can reduce stake addition errors, thereby improving stake addition accuracy and efficiency.

This invention belongs to the interdisciplinary field of medical devices and artificial intelligence, and discloses a method and system for measuring the size of intestinal polyps based on monocular depth vision. The method includes: preprocessing endoscopic keyframe images; sequentially generating a depth map using a monocular depth estimation model; locating the polyp using a target detection model; and generating a pixel-level segmentation mask using an instance segmentation model. Next, the polyp body and tail are separated based on the distance distribution analysis from the contour points to the centroid, and the pixel diameter is obtained by geometric fitting of the body contour. Then, edge depth values ​​are sampled in the target's internal region using a contour inward contraction method based on distance transformation. Finally, the edge depth and pixel diameter are used as features input to a pre-trained machine learning regression model to predict the millimeter / pixel ratio and calculate the physical size of the polyp. This invention achieves fully automated and high-precision measurement of polyp size, effectively solving the problems of high subjectivity and low accuracy in existing technologies.

This invention relates to the field of network information security technology and discloses a method and system for continuous learning and detection of malicious code that adapts to memory budget. The method includes: acquiring and classifying newly added malicious code data for the current incremental task, and allocating a memory budget to each family; when the number of family samples exceeds the budget, dynamically selecting a processing mode based on the budget range: under a small memory budget, disabling PCA dimensionality reduction and enabling local density weighting, and fusing Mahalanobis distance and local sparsity to determine the comprehensive weight distance; under a large memory budget, enabling PCA dimensionality reduction and disabling local density weighting, and calculating the comprehensive weight distance based on Mahalanobis distance; constructing a replay sample set accordingly, and incrementally training the classification model after concatenating it with the newly added data. This invention achieves adaptive sample selection under different memory budgets, taking into account both global deviation and the capture of locally sparse samples, effectively mitigating catastrophic forgetting, and improving the accuracy and computational efficiency of malicious code family classification.