71 results about "State covariance" patented technology

The invention discloses a UE4-based digital twin model construction system and method, and relates to the technical field of computer vision, and the system comprises a geometric modeling unit which generates three-dimensional model data based on geometric modeling data of a target physical entity, and achieves dynamic LOD rendering level switching through virtualization processing; the real-time data interaction unit is used for analyzing the real-time sensor data flow and generating equipment state data in combination with a transmission operation and maintenance instruction; the simulation engine unit is used for executing rigid body motion and collision simulation based on the equipment state data and outputting a collision event sequence and state transition data by utilizing an event trigger; the machine learning unit is used for training an LSTM (Long Short Term Memory) model based on the collision event sequence and the state transition data, and optimizing state covariance parameters through adaptive Kalman filtering; and the visual interaction unit is used for realizing data synchronization of the command large screen and the mobile terminal through multi-screen collaboration. According to the method, the digital model capable of accurately reflecting physical entity behaviors and characteristics is constructed.

The invention relates to the technical field of new energy battery management, and discloses a sodium ion battery state-of-charge and state-of-health joint estimation method, which comprises the following steps: acquiring a state equation and an observation equation of a sodium ion battery; initializing a state estimation value, a state covariance, a capacity estimation value and a capacity covariance; performing unscented transformation on the state equation to obtain a plurality of key points and weights; a state equation and an observation equation are utilized to spread key points at the # imgabs0 # moment, the state at the # imgabs1 # moment, an observation nonlinear transmission result, a prediction state, an observation estimation value, a corresponding prediction state covariance and a corresponding prediction observation covariance are obtained, Kalman gain at the # imgabs2 # moment is constructed, and an extended Kalman gain matrix is obtained; presetting an innovation length, calculating a historical observation residual error, and constructing a multi-innovation matrix; and based on the extended Kalman gain matrix, the multi-information matrix and the actual observation value at the # imgabs3 # moment, correcting to obtain the sodium ion battery charge state and the battery health state at the # imgabs4 # moment.

The invention relates to an information fusion method and device of a multi-source navigation system, computer equipment and a computer program product. The method comprises the following steps: constructing a preset number of sub-models according to sensor systems in the multi-source navigation system, taking the product of the expected credibility and the real-time credibility of the performance of each sensor system as the comprehensive credibility of each sensor system, and determining a state transition probability matrix of the sub-models according to the comprehensive credibility; state prediction updating and measurement updating are carried out on each sub-model, and a system error state and a system state covariance are calculated; and calculating a predicted posterior probability of each sub-model, determining an interactive weight between the sub-models according to the predicted posterior probability and the state transition probability matrix, and correcting and updating the system error state and the system state covariance according to the interactive weight to obtain a final system error state and a final system state covariance. By adopting the method, the robustness of information fusion can be effectively improved.

The invention discloses an unmanned aerial vehicle state estimation method, a readable storage medium and a navigation device, and belongs to the technical field of unmanned aerial vehicle navigation. The method comprises the following steps: establishing a linear state space model with multi-cluster measurement noise, modeling the measurement noise as multivariate Gaussian distribution, and introducing a measurement noise covariance matrix coefficient; joint prior updating is carried out based on posterior information of a previous moment, and prior estimation of a state, a state covariance, a measurement noise covariance matrix coefficient and a generalized inverse Gaussian (GIG) distribution parameter is obtained; performing pre-clustering on the measured values; online adaptive clustering is realized by using an EM algorithm, and unknown outdoor scene noise can be dynamically identified and divided; joint posterior updating is carried out, fixed point iteration is not needed, and therefore an updated measurement noise covariance matrix is obtained; updating the state and outputting the unmanned aerial vehicle state. According to the invention, through precise noise modeling, online clustering and adaptive adjustment of the measurement noise covariance matrix, the positioning precision and system robustness of the unmanned aerial vehicle are significantly improved.

The invention relates to the technical field of medical robots, in particular to a surgical robot and a remote motion center dynamic adjustment method for the surgical robot, and the method comprises the steps: building a kinematics constraint model between a tool axis of a surgical tool and a robot base coordinate system; on the basis of a visual sensor and a hand-eye transformation matrix, a pose measurement value of the remote motion center point under a robot base coordinate system is obtained in real time; fusing a pose state prediction quantity driven by a robot motion instruction and the pose measurement value, and generating an optimal estimation pose and a state covariance matrix of the remote motion center point; according to the state covariance matrix, determining whether the remote motion center point has a large offset; when it is judged that the large-amplitude offset occurs, a safety strategy is triggered to control the surgical robot. According to the technical scheme, dynamic tracking and real-time adjustment of the remote motion center point in the operation are achieved, and the problems that a traditional scheme is insufficient in flexibility and poor in safety are solved.

The invention discloses a method and a system for enhancing the robustness of a multi-source data fusion algorithm, and aims to improve the adaptability to noise and outliers in a multi-sensor data fusion process. According to the method, an adaptive noise mechanism and an outlier detection mechanism are introduced, so that the influence of abnormal observation data is effectively suppressed, and the fusion precision and the system stability are improved. The method comprises the following steps: firstly, a system carries out preliminary state prediction by initializing a target state, a covariance matrix and observation noise; then, the mahalanobis distance of each observation data is calculated based on chi-square test through an outlier detection mechanism, if the observation data deviates greatly, the observation data is judged as an outlier, and the influence of the observation noise matrix on a fusion result is reduced by increasing the observation noise matrix of the observation data; then, an adaptive noise adjustment method is adopted, adaptive factors are calculated in real time according to observation data of each sensor, and observation noise is dynamically adjusted to adapt to changes of the noise level; and finally, state estimation and covariance updating are carried out in combination with fusion algorithms such as Kalman filtering, and data fusion and system feedback are completed. According to the scheme, noise interference and abnormal values in multi-source data can be effectively dealt with, the robustness and the real-time response capability of the system are improved, and the method has wide application prospects.

The invention provides an IMU sensor space-time fusion industrial defect detection system and method based on an SORT algorithm. The method comprises the steps that S1, system initialization and space-time calibration are carried out, a time synchronization model is established, the single pixel size dpixel is calculated, and IMU and camera coordinate system registration is completed; s2, collecting asynchronous data, and obtaining working parameters of a camera and the speed vt of a conveyor belt; s3, constructing an SORT state vector and predicting an IMU enhancement state, detecting defects of a current frame by adopting YOLOV8, and generating a detection set Dt; s4, executing EKF space-time fusion, and predicting and updating a defect state covariance and a position; s5, quantifying the position uncertainty sigma pos, calculating an optimal acquisition period Topt, controlling the line frequency of the camera, and carrying out confidence verification and misjudgment elimination; s6, cloud federated filtering fuses the edge and the cloud state, IMU zero offset is estimated, and cooperation of multiple detection devices and system expansibility enhancement are achieved.

The invention discloses a least square covariance dynamic weighting satellite inertial navigation combined attitude determination method, which belongs to the technical field of combined navigation and mobile carrier attitude determination, is used for satellite inertial navigation combined attitude determination, and comprises the following steps: obtaining and preprocessing original data, constructing a nonlinear observation model, linearizing by using a Gauss-Newton iterative algorithm, and solving; performing time updating of an error state vector and a state covariance based on inertial navigation system mechanical arrangement; and reconstructing a measurement noise covariance matrix of extended Kalman filtering, constructing a measurement information vector, calculating Kalman gain, performing state updating, and outputting an attitude determination result. According to the method, the current epoch least square posterior covariance is introduced for dynamic weighting, so that instantaneous delay-free adaptive fusion is realized, the short baseline noise amplification effect is remarkably inhibited, and the attitude estimation precision, the statistical consistency and the real-time observation quality self-diagnosis capability under the complex sea condition are improved.

The invention relates to the technical field of unmanned aerial vehicle flight control and intelligent navigation, in particular to an unmanned aerial vehicle low-altitude obstacle avoidance route planning method and system, and the method comprises the steps: firstly fusing three-dimensional space data and airspace rules, constructing a signed distance field, a capacity field and a state covariance, generating a channel graph, and calculating a door time lattice capacity upper limit; establishing joint trajectory optimization in the channel graph, combining geometric feasibility, dynamics reachable and covariance-based opportunity constraint separation, outputting a nominal trajectory, and controlling input and door crossing time; aligning the door penetrating time with the door time grid flow by a unification method to obtain the door time slot flow and the dual price; airborne control is executed according to a nominal trajectory and a time sequence constraint closed loop, and capacity change and price change are re-optimized and fed back in a time window under a triggering condition. According to the invention, the safety interval, the punctuality rate and the traffic efficiency are improved.

The invention discloses a target tracking method, active radar equipment and a storage medium. The tracking method comprises the following steps: acquiring a radar echo signal; performing target detection on the radar echo signal, and calculating a current state parameter of a target; based on the current state parameter of the target, calculating the next state optimal prediction value of the target by using an extended Kalman filtering algorithm, and updating the state covariance matrix; and controlling the radar orientation according to the optimal predicted value of the next state of the target to realize target tracking. According to the method, the azimuth angle and the pitch angle of the target at the next moment are predicted by using the extended Kalman filtering algorithm with higher precision, and the radar orientation is controlled through the servo turntable according to the prediction result, so that the radar faces the target direction to realize tracking, the tracking performance of the high-speed radar on the high-speed target is effectively improved, and the tracking efficiency is improved. And the high-speed target tracking accuracy is improved.

The invention discloses a low-orbit Doppler positioning method and device for dynamically weighting epochs based on an intelligent agent, and belongs to the technical field of satellite navigation positioning. According to the method, an initial position and an initial state covariance matrix of a receiver are determined based on an initial accumulation low-orbit non-cooperative signal of the receiver, an initial point location of a current epoch signal is determined when a new low-orbit non-cooperative signal is received so as to realize time frame synchronization, and a state characteristic of the current epoch signal is determined at least based on the initial point location. The state features at least comprise satellite features, epoch state features, signal state features and positioning state features, determining a weight of a current epoch signal based on the state features using a pre-training agent, and determining a real-time position of the receiver based on the current epoch signal and the weight of the current epoch signal using a recursive algorithm, according to the invention, adaptive empowerment based on the multi-dimensional features of the epoch signal is realized, the accuracy of the determined epoch signal weight is improved, and the positioning precision is improved.

The invention belongs to the field of multi-agent co-localization, and provides a manifold-null space constraint-based co-localization state estimation method and system, and the method comprises the steps: carrying out the state prediction of multiple agents based on the data of an inertial measurement unit at a current moment, and obtaining a prediction reference state and a prediction error state covariance matrix; performing adaptive non-line-of-sight processing according to the actual distance measurement value and the predicted distance measurement value to obtain a measurement noise covariance matrix; performing consistency monitoring on the prediction error state covariance matrix according to the measurement noise covariance matrix to obtain an expanded prediction error state covariance matrix; performing state updating on each agent to obtain an updated reference state and an updated error state covariance matrix; and performing null-space projection on the global covariance matrix by using a projection operator to obtain an updated global covariance matrix. According to the method, the problem of numerical instability caused by inconsistent covariance propagation and unobservable degree of freedom in a multi-agent system is solved.

Certain aspects of the present disclosure provide techniques for uncertainty estimation, such as for deep learning (DL)-based object tracking systems. A method generally includes processing, with a deep learning network, an input state associated with an object to predict an output state for the object, wherein the output state comprises a plurality of state estimates for a first time period; and generating a state covariance based at least in part on estimated covariance between at least two state estimates of the plurality of state estimates, wherein the state covariance represents an estimated uncertainty associated with the output state.

This application provides a GNSS, 5G, and IMU fusion positioning method and electronic device. The method includes: constructing an event queue based on the reception times of GNSS observation data, 5G observation data, IMU measurement data, and SSR enhancement information; performing timeliness modeling on the SSR enhancement information to obtain SSR correction packets; generating a parameter set based on a preset encoder and a hybrid expert model; performing asynchronous fusion updates according to the time sequence of the event queue, using IMU measurement data to drive state prediction, to obtain a fused state vector and a state covariance matrix; outputting the position state vector in the fused state vector as the fused positioning result; and outputting the sub-block in the state covariance matrix corresponding to the position state vector as the uncertainty of the fused positioning result. This application can solve the problem that existing methods are unable to maintain positioning accuracy, continuity, robustness, and system stability in the long term.

The application relates to the technical field of control, in particular to a kind of excimer lamp cooperative control method based on multi-source data fusion.The method comprises the following steps: obtaining the multi-source sensing data of excimer lamp system, initializing system state vector, state covariance matrix and the inverse Wishart distribution prior parameter of process and measurement noise covariance matrix, obtaining predicted state mean and predicted covariance matrix based on posterior state estimation, calculating innovation, updating process and measurement noise covariance matrix, calculating state-measurement mutual covariance matrix and measurement innovation covariance matrix, determining optimal gihonov regularization parameter and calculating kalman gain, updating state estimation and state covariance matrix, and generating operation instruction of each excimer lamp based on the updated state.The scheme of the application can overcome the limitations of standard unscented kalman filter, ensure the reliability of kalman gain, and thus improve the uniformity and stability of system output light field.

The invention belongs to the technical field of rigid body posture estimation, and discloses a rigid body posture estimation method, system and device based on generalized correlation entropy geometric filtering, and the method comprises the steps: obtaining target motion information, and building a discrete nonlinear kinematics model; the discrete nonlinear kinematics model is initialized; sigma points of a posterior state covariance matrix and a process noise covariance matrix are generated respectively, and the sigma points are propagated and updated through manifold fast unscented transformation; obtaining a prediction state mean value, a priori state covariance matrix and a square root of the priori state covariance matrix; updating the central parameters based on the information of the historical moments; calculating a pseudo measurement matrix and updating the gain; correcting the state estimation by using the gain; judging whether convergence occurs or not, and if not, continuing iteration; otherwise, outputting a posterior state estimation value as a final rigid body posture estimation result at the moment. According to the method, the problem that the robustness and precision of rigid body posture estimation in a non-zero mean value and non-Gaussian noise environment are reduced is effectively solved.

This paper proposes a method and device for adaptively modeling the uncertainty of LiDAR point, line, and surface features. This method constructs a maintainable parameterized local subgraph by parametrically extracting and tracking plane / line features. The uncertainty of the point cloud and parameterized plane / line features in the local subgraph is then modeled, thereby adaptively determining the observation covariance. By rationally modeling LiDAR variance, this method enables better integration with other sensors, effectively improving GNSS / INS / LiDAR positioning performance in various complex urban environments and addressing the inconsistency of LiDAR Inertial Odometry (LIO) state covariance.

The invention discloses a cross-water-area bridge deformation solving method based on Beidou No.3 / GNSS inversion, and particularly relates to the technical field of bridge monitoring. The method comprises the following steps: establishing an observation equation by combining all satellites based on satellites which can be observed by a bridge structure monitoring station; solving the observation equation by using a matrix method to obtain a prediction state vector of the deformation quantity of the bridge structure and a covariance matrix of the state vector; in consideration of the influence of gross error of a Beidou No.3 / GNSS observation value, a self-adaptive factor is provided to correct a predicted value of a state vector; obtaining a vector K and an updated state vector covariance; introducing a robust factor M to determine the weight of each type of observation values in consideration of gross errors in the Beidou No.3 / GNSS carrier phase observation values; updating the matrix K and the state covariance matrix by using the corrected measurement covariance matrix R; and calculating the updated state vector. According to the technical scheme, the problem that a conventional Beidou / GNSS data processing method is low in precision is solved, and the precision of bridge deformation calculation is improved.

The embodiment of the invention discloses a target tracking method for a low-altitude strong-maneuvering unmanned aerial vehicle, and relates to the technical field of target tracking, and the method comprises the steps: obtaining a measurement point set, and a state estimation value and a state covariance matrix of a previous moment, so as to obtain a state estimation value of the previous moment through a plurality of preset strong-maneuvering models; obtaining a current prediction index of the current moment corresponding to each strong maneuvering model; determining an elliptical correlation gate corresponding to each current prediction index, so as to determine a candidate measurement point set falling into the elliptical correlation gate according to the measurement point set; performing intra-model association and inter-model association through a preset hierarchical association strategy, and screening a global optimal measurement corresponding to the current moment and a corresponding matching strong maneuvering model; and according to the global optimal measurement corresponding to the current moment, performing Kalman filtering updating on the current prediction index of the matched strong maneuvering model to obtain an updated prediction index of the target at the current moment so as to realize target tracking.

The invention discloses a real-time optimization scheduling method for opposite conflict of long-tunnel single-lane construction vehicles, and the method comprises the steps: extracting a standard deviation corresponding to a state covariance matrix eigenvalue outputted by a UWB / IMU fusion positioning algorithm, and introducing the standard deviation into dynamic travel time prediction and dynamic safety boundary calculation. The interval prediction of the conflict probability and the self-adaptive adjustment of the security boundary along with the change of the positioning precision are realized; establishing a multi-objective optimization dynamic avoidance decision model which integrates multiple rigid constraints of vehicle staggering platform safety, transportation material timeliness, TBM key process progress, heavy-load vehicle starting and stopping and buffer area smoothness and comprehensively considers three objectives of minimization of construction progress influence, minimization of transportation total delay and maximization of load throughput; the problem that tunnel construction requirements cannot be dynamically met due to the fact that current tunnel vehicle scheduling research is limited in positioning precision, rigid in safety boundary, lack of probability-based conflict advanced early warning capability and dependence on fixed rules when facing a GNSS rejection environment is solved.

The invention belongs to the technical field of inertial measurement unit diagnosis, and particularly relates to an inertial measurement unit fault diagnosis method and system. According to the method, the innovation and the attitude difference are combined, and uncertainty weighting based on covariance is adopted, so that recognition of multiple types of faults is more reliable, the adaptive threshold value is automatically adjusted according to the state covariance and the motion change, the sensitivity and robustness can be balanced in static and dynamic scenes, false alarms and omission are reduced, and the fault diagnosis accuracy is improved. According to the method, the zero offset and the gravity component are removed through preprocessing, filtering is carried out, the attitude representation based on quaternion is matched, the estimation stability in a high-dynamic or complex vibration environment is improved, the zero offset of the gyroscope is used as a state quantity for estimation, slow-varying errors can be compensated in real time, and the accuracy of diagnosis and judgment is improved.

The present invention discloses a method for estimating dynamic targets of unmanned aerial vehicles (UAVs) in an information denial environment. The method comprises: obtaining three-dimensional angle information, the three-dimensional angle information including the angle of arrival from the UAV to a first anchor point, the angle of arrival from the UAV to a second anchor point, and the angle of arrival from the UAV to the target; filtering the three-dimensional angle information with an extended Kalman filter to obtain estimated UAV state information and corresponding state covariance information, the UAV state information being used to characterize the position and velocity of the UAV and the position and velocity of the target; and constructing a loss function using the UAV state information and the state covariance information to optimize the flight path of the UAV and achieve observation of the target. The present invention utilizes two anchor point information with known absolute positions to achieve position tracking of the UAV and the target.

The application provides a non-Gaussian noise suppression method and device with adaptive kernel width, and belongs to the field of inertial base combined navigation algorithm and state estimation. The method solves the problems that the robust filtering method based on fixed kernel width is difficult to adapt to time-varying noise characteristics, and the scheme depending on an optimization algorithm has the problem of insufficient real-time performance. The method comprises the following steps: initializing filter parameters according to a SINS / DVL combined navigation system; performing time updating to obtain a predicted state vector and a predicted state covariance matrix at the current moment; updating a measurement noise covariance matrix through a variational Bayesian method, wherein the measurement noise covariance matrix is modeled as an inverse Wishart distribution; adaptively updating a kernel width parameter according to a filter innovation at the current moment and the measurement noise covariance matrix; and updating a state quantity estimation value and a state covariance matrix at the current moment through a fixed-point iteration algorithm by using the updated kernel width. The method is used in the field of underwater resource exploration.

The present application belongs to the field of civil engineering safety monitoring and Internet of Things technology, and provides a deep and large foundation pit safety monitoring method based on cloud edge collaboration and digital twinning, which comprises the following steps: an edge gateway dynamically and adaptively adjusts the sensor sampling frequency and compressed sampling mode according to the foundation pit deformation; an edge computing server performs real-time anomaly detection by using a lightweight deep learning model; an extended Kalman filter is used to fuse multi-source data and dynamically adjust the warning threshold based on the state covariance; a cloud platform constructs a digital twinning model, inverses soil parameters by using a genetic algorithm, and predicts the deformation trend; and the cloud edge collaboration optimizes the sampling strategy and warning parameters in a closed loop; the present application realizes real-time warning of deep and large foundation pit monitoring, greatly reduces network bandwidth consumption, effectively reduces the false alarm rate, significantly prolongs the endurance time of the sensor node, and significantly improves the real-time performance, accuracy and energy efficiency of the monitoring system.

The embodiment of the specification discloses a target tracking method of a low-altitude strong maneuvering unmanned aerial vehicle, relates to the technical field of target tracking, and comprises the following steps: acquiring a measurement point set and a state estimation value and a state covariance matrix of a previous moment, so as to obtain a current prediction index corresponding to each strong maneuvering model at a current moment through a plurality of preset strong maneuvering models; determining an elliptical correlation gate corresponding to each current prediction index, so as to determine a candidate measurement point set falling into the elliptical correlation gate according to the measurement point set; performing intramodel correlation and intermodel correlation through a preset hierarchical correlation strategy, and screening a global optimal measurement corresponding to a current moment and a matching strong maneuvering model; performing Kalman filter updating on the current prediction index of the matching strong maneuvering model according to the global optimal measurement corresponding to the current moment, so as to obtain an updated prediction index of the target at the current moment, and target tracking is realized.

This invention belongs to the field of equipment control technology, specifically relating to a power equipment control method and system based on the Internet of Things (IoT), comprising the following steps: S1, acquiring real-time operating data of nodes of each power device in the IoT, constructing a second-order state tensor representing the operating state of each node; projecting the second-order state tensor onto a low-dimensional subspace defined by basis vectors to obtain a low-dimensional state descriptor, wherein the basis vectors are adaptively updated based on the historical state covariance matrix of all nodes; calculating the Wasserstein distance of the low-dimensional state descriptor sequences between nodes, and generating a weighted transition matrix for parameter aggregation between nodes by combining the communication link quality; S2, if the condition number of the local state covariance matrix of a node exceeds a first threshold, then local optimization is initiated. This invention improves the convergence speed and accuracy of the optimization algorithm, and achieves more stable collaborative control of power equipment groups through a two-level control mechanism combining local optimization and global correction.

The invention discloses a robot observation optimization target positioning method with sensor measurement drift. The method comprises the following steps: acquiring sensor measurement data; for the measurement data, an expansion Kalman filter is facilitated for filtering, current state information and corresponding state covariance information of the robot are obtained, and the state information comprises a measurement deviation angle; a gradient descent algorithm is adopted, the moving direction of the robot is optimized by minimizing a set loss function, so that the robot obtains an optimal observation path for a target when moving in the direction, the loss function is constructed by utilizing the robot state information and the state covariance information, and the loss function is constructed by utilizing the state covariance information. And the loss function reflects the cost value generated when the robot moves towards the positive and negative directions of three components of the X axis, the Y axis and the Z axis. According to the method, the error influence caused by measurement drift due to sensor installation errors is eliminated, and the problem of robot target positioning in a three-dimensional information interference environment is solved.

The invention provides a three-dimensional PFF beam tracking method and system for a millimeter wave communication platform of an unmanned aerial vehicle. The method comprises the following steps: S1, establishing a channel model for millimeter wave communication of the unmanned aerial vehicle; s2, initializing the motion state of the unmanned aerial vehicle, and generating an initial particle set; s3, updating the particle set through Gaussian process noise driving, and calculating a mean value of the particle set; s4, updating the particle set according to a logarithm homotopy function and an Euler integral method to obtain an updated state vector; s5, updating the state covariance matrix based on the UKF; and S6, repeating the steps S3-S5 to update the state vector of the unmanned aerial vehicle. According to the method, the particle flow filtering is utilized, the prior distribution of the motion state information is smoothly migrated to the posterior distribution by constructing the logarithmic homotopy function and the pseudo-time variable so as to realize efficient tracking, the particle degradation problem under the high-dimensional condition is avoided, and the robustness and the precision of beam tracking are improved.

The invention relates to the technical field of three-dimensional measurement and data processing, and discloses a three-dimensional measurement data fusion device and method based on Beidou positioning and laser scanning. The device comprises a Beidou positioning module, an inertial measurement unit, a laser scanning module comprising a holder scanner, a data fusion processing module, a data transmission module and a data storage and visualization module. The data fusion processing module estimates a state vector of the device and a state covariance matrix representing the uncertainty of the state vector based on a kinematic model; and when the uncertainty of the state vector exceeds a preset threshold value, the module actively generates a control instruction to drive the pan-tilt scanner to execute target scanning to obtain high-value observation data. The obtained high-value observation data passes through an observation noise covariance matrix and is used for updating a state vector, so that closed-loop control capable of rapidly converging uncertainty is formed. According to the invention, the fusion precision, the long-term stability and the reliability of a measurement system are improved through adaptive weighting and an on-line external parameter calibration technology.

The application discloses a pedestrian inertial navigation positioning method based on LSTM zero speed detection and EKF, wherein the LSTM is used to identify the pedestrian state as zero speed or walking state according to IMU data; an error state vector is constructed; an error differential propagation equation is constructed according to the error state vector; a state transition matrix is obtained by discretizing the continuous time state equation; the prior state estimation value and the prior state covariance matrix at the current time are calculated; zero is taken as a virtual absolute observation value; the difference between the actual observation speed and the current predicted speed is taken as the measurement innovation; the Kalman gain is calculated according to the measurement innovation; the error state vector is corrected by using the Kalman gain, and the posterior state covariance matrix is updated; the false positive label noise is eliminated from the source, the pure and high-fidelity observation update signal can be provided for the EKF filter, and thus the inertial navigation drift problem in a complex dynamic scene is greatly inhibited.