62 results about "Extended Kalman filter" patented technology

A high-precision positioning method based on multimodal fusion filtering, relating to the field of intelligent positioning technology, includes the following steps: acquiring sensor data collected in real time by a GNSS submodule, an IMU submodule, and a barometer submodule, and performing collaborative preprocessing on the sensor data; performing state estimation through an extended Kalman filter (EKF) and an adaptive particle filter (APF) to obtain the corresponding EKF positioning output and APF positioning output; calculating a multi-dimensional positioning reliability reflecting the geometric accuracy of the GNSS signal, the stability of the IMU data, and the high consistency between the barometer and GNSS; dynamically allocating fusion weights for the EKF positioning output, APF positioning output, and historical positioning data; and performing weighted fusion of the EKF positioning output, APF positioning output, and historical positioning data to output the final positioning result. This invention, through a three-layer architecture of collaborative data preprocessing, intelligent filtering, and dynamic decision-making, systematically improves the accuracy, continuity, and overall robustness of positioning in complex environments.

The application relates to the technical field of battery management systems, and discloses a battery pack fault diagnosis method and system based on physical enhancement and machine learning. The method is based on an interpolation parameter matrix to construct an improved extended Kalman filter model, to obtain state estimation, reference voltage and residual information of a battery monomer; a physical enhancement self-encoder is constructed, current, state estimation, temperature or equivalent environmental variables and monomer residuals are taken as context inputs, combined with consistency reference of other monomers, to reconstruct a health reference voltage response of a target monomer; dynamic impedance response, event locking features, local consistency features, sensor bias / noise features and aging persistence features are extracted to form a mechanism feature space facing connection faults, sensor faults and battery aging; a cascade random forest model is adopted to realize fault screening and fault type identification, and online diagnosis results are post-processed through current gating, sliding window lag and physical priority correction strategies.

The application discloses a double-fed induction generator rotor speed estimation method based on maximum cross-correlation entropy weighting, and belongs to the field of motor control. The method creatively applies cross-correlation entropy theory to noise covariance estimation of EKF, and designs a complete algorithm system containing dynamic weighting, adaptive kernel bandwidth, mixed robust weighting and numerical reinforcement. The progressiveness is reflected in that the method comprehensively solves the shortcomings of traditional methods in response speed, parameter disturbance resistance and non-Gaussian noise resistance. Theoretical proof and comprehensive simulation experiments prove that the method has better estimation accuracy, robustness and reliability in complex industrial environments such as wind power generation.

This invention discloses an AI-enhanced extended Kalman filter method and system, belonging to the field of Kalman filter technology. The method constructs an extended state including velocity and measurement bias, and performs prediction and linearization based on a dynamic model. The forward innovation and its variance are calculated using the minimum process noise of the fixed bias channel, and used for feature normalization. A sliding window feature sequence is constructed using the normalized innovation and velocity increment, and input into a one-dimensional convolutional neural network for multiple random deactivation inferences to obtain anomaly intensity scores and cognitive uncertainty. Based on this result, the process noise of the bias channel is adaptively adjusted to enhance bias tracking capability when anomalies are significant, and maintain estimation smoothness when normal conditions are normal. Finally, the extended Kalman filter update is completed, achieving robust joint estimation of velocity and bias. This invention improves the estimation stability and accuracy under strong noise and transonic conditions, and is applicable to velocity measurement of aircraft and ultra-high-speed motors.

This application relates to the field of Internet of Things (IoT) technology, and in particular to a method and system for personnel safety monitoring in chemical industrial parks based on dual-channel heterogeneous data transmission and multi-source fusion. The method synchronously collects environmental parameters and inertial data through mobile sensing terminals; constructs an extended Kalman filter model to tightly couple and fuse ultra-wideband positioning coordinates with inertial dead reckoning data to correct cumulative drift in predicted values; employs a vertical distance threshold trajectory compression algorithm at the edge to eliminate redundant positioning points on linear paths, reducing transmission load; dynamically adjusts the radius of the electronic fence based on gas concentration and determines fall events by combining acceleration amplitude temporal characteristics; and utilizes a dual-channel WiFi collaborative mechanism to normally upload lightweight data via a low-power channel, only activating the high-speed channel to upload on-site images when boundary crossings or fall anomalies are detected. This application effectively solves the technical problems of low positioning accuracy, multimedia data transmission bandwidth conflicts, and delayed safety warnings in industrial sites.

The invention relates to an SLAM back-end optimization method based on sparse matrix factorization and a hardware accelerator architecture, and the method comprises the steps: constructing a Hessian matrix through employing a binary sparse coding mechanism according to the actual observation coordinates of feature points on an image plane and the predicted coordinates of road sign points projected to a camera coordinate system; performing Schel elimination processing on the Hessian matrix based on binary sparse coding to obtain a linear equation set only containing a camera pose variable; and carrying out extended Kalman filtering on a linear equation set only containing a camera pose variable to realize incremental updating of a state pose and a road sign point coordinate. According to the method, the overall delay of SLAM rear-end optimization can be remarkably reduced, and the real-time requirement in a high-speed moving scene is met.

The application discloses a kind of mechanical arm motion trajectory determination method, belong to industrial robot control technical field.The method includes: through six-dimensional force sensor, current sensor, encoder, IMU and vision sensor and so on multisource sensor synchronous acquisition mechanical arm state and environmental data;Original data is filtered, interpolation and time alignment using FPGA, generates standardization synchronous data frame;MCU fuses pose data by extended Kalman filter, and checks load state by least square method;When detecting that load current or end force changes more than threshold value, trigger DSP to execute online inertia identification, based on recursive least squares method real-time estimates total inertia;Trajectory planner adjusts angular velocity and angular acceleration parameters of motion trajectory according to fusion pose, environmental information and inertia identification result, generates optimized trajectory adapted to current load.The application can significantly improve trajectory tracking accuracy, motion stability and system response speed under variable load conditions.

The application discloses a target tracking method and system adapting to scenes and cascading data, and related equipment, and relates to the field of automatic driving perception. The method comprises the following steps: collecting and synchronizing a laser radar, a millimeter wave radar, vehicle state data and a simultaneous localization and mapping pose; predicting a target motion state by using an extended Kalman filter, wherein the process noise and the observation noise matrix can be dynamically adjusted according to the degree of vehicle motion and the target blocking condition; performing data association on the predicted trajectory and the detected target by using a three-level cascading strategy, and decoupling the height and depth errors step by step; finally, updating the trajectory state according to the association result, performing whole life cycle management, and outputting a tracking result. The application can solve the problems of low tracking accuracy, unstable trajectory and high missing matching rate of traditional methods in the conditions of vehicle violent maneuvering, target blocking, road bumping and long-distance scenes, and significantly improves the tracking robustness and state estimation accuracy in complex dynamic environments.

The application provides a dynamic target optimization control method for a veterinary traditional Chinese medicine compound decoction process, and relates to the technical field of process control.The method comprises the following steps: constructing a fluid dynamics characteristic space, using a detrended and filtered pressure time series signal, calculating a pressure fluctuation variance index to represent the turbulence intensity; constructing a thermodynamic energy observation space, using an extended Kalman filter to solve the system thermal efficiency coefficient in real time; performing time domain lag compensation, calculating the partial derivative eigenvalue of the thermal efficiency relative to the turbulence intensity, and generating a fluid-thermal coupling sensitivity index; inputting the index into a dynamic extreme value search controller based on phase plane trajectory constraints to generate an adaptive power instruction. Through driving the sensitivity index to converge to a zero value dead zone, the application realizes dynamic impedance matching of physical disturbance and chemical endothermic of the medicine liquid, and solves the problems of energy efficiency feedback lag and extraction working condition mismatch in traditional control.

This invention discloses an underwater acoustic positioning sound velocity compensation method based on vertical total time delay random walk, belonging to the field of underwater acoustic navigation and positioning. The method includes: collecting two-way time delay observation data in underwater acoustic positioning; establishing an ocean sound velocity compensation formula; defining the vertical total time delay and establishing a conversion function between ocean sound velocity variation and vertical total time delay; calculating a coarse prior value of the vertical total time delay based on the conversion function, and using a first-order Markov process to calculate the random walk noise of the vertical total time delay; using the two-way time delay observation data, the coarse prior value, and the random walk noise, accurately estimating the vertical total time delay using an extended Kalman filter, and then substituting it into the conversion function to obtain the ocean sound velocity variation, thus achieving sound velocity compensation. This invention eliminates the need for additional sound velocity measurement equipment, enables real-time online compensation of ocean sound velocity variation errors, improves underwater acoustic positioning efficiency, and enhances the temporal resolution of ocean sound velocity variation detection.

The application discloses a kind of multi-radar resource management methods based on risk assessment, belong to radar signal processing technical field.First, the joint state space model of fusing motion state and classification state is constructed, state estimation is carried out using extended Kalman filter, and the misjudgment cost of target classification is modeled by introducing statistical risk function;Subsequently, the expected risk difference before and after observation is calculated, and the expected risk reduction value of the quantitative target current observation value is obtained;Boolean scheduling variable is introduced to construct scheduling optimization model, and the global ERR is maximized as objective function;Finally, local search and conflict resolution strategy are iteratively solved, and the optimal allocation result is quickly converged.The application realizes the scheduling target of key target priority observation, sensor resource efficient utilization and overall risk minimization.

This invention discloses a multimodal tightly coupled synchronous localization and mapping method and system with resistance to dynamic interference. The method simultaneously acquires images, point clouds, and inertial data. The visual front end combines a feature extraction network and a target detection model, using an adaptive extended Kalman filter to track dynamic targets and generate a mask for removing key points in dynamic regions. Dynamic feature points in these regions are removed, and the remaining static key points are used to complete inter-frame matching and relative pose estimation, forming visual odometry constraints. The laser front end uses inertial pre-integration to distort the point cloud and calculates laser odometry based on geometric feature registration. Loop closure detection performs candidate frame retrieval based on geometric descriptors and combines geometric consistency checks to generate loop closure pose constraints. The back end constructs a global factor graph and integrates visual odometry constraints, laser odometry constraints, inertial constraints, and loop closure pose constraints for joint nonlinear optimization. This invention effectively suppresses dynamic environmental interference and significantly improves positioning accuracy and robustness.

The application relates to an EM-EKF-based adaptive estimation method for a lunar satellite formation orbit, which comprises the following steps: based on the orbit state of a lunar satellite formation at the last moment, observation data at the current moment, and a process noise covariance matrix and an observation noise covariance matrix, an extended Kalman filter module of a navigation algorithm is used to predict the orbit state of the lunar satellite formation at the current moment; and based on a state sequence composed of a series of orbit states output by the extended Kalman filter module within a period of time, an expectation maximization module of the navigation algorithm is used to update the process noise covariance matrix and the observation noise covariance matrix. According to the method, the process noise covariance matrix and the observation noise covariance matrix can be dynamically estimated, and the online adaptive update of the extended Kalman filter parameters is realized.

The present application relates to the technical field of fusion positioning, and more particularly to a multi-sensor fusion positioning method based on extended Kalman filtering, which proposes the following scheme: by fusing the motion information obtained by a wheel speed encoder and an inertial measurement unit, a slip indicator reflecting the change of wheel-ground adhesion is constructed, and a plurality of motion modes and mode probabilities are introduced accordingly; a slip extension state is introduced in a unified state vector, and prediction updating and observation consistency evaluation are respectively performed under different motion modes; the observation noise parameters are adaptively adjusted in combination with observation innovation, and the multi-mode estimation results are fused and output based on the mode probabilities. The present application can improve the positioning stability and robustness under the conditions of load change and adhesion fluctuation.

The application relates to the field of digital signal processing, in particular to a digital signal processing system and method based on a dynamic clock anti-jitter algorithm, which comprises the following steps: collecting historical jitter data of a clock signal in real time through a clock data collection module; generating jitter statistical characteristic parameters by using a Gaussian mixture model dynamic modeling module; realizing sub-nanosecond level real-time phase compensation by means of an extended Kalman filter correction module; dynamically adjusting an I2S master clock phase in cooperation with a software programmable clock generation module; and realizing a prediction-compensation feedback mechanism to complete jitter suppression through a closed-loop control unit. The application achieves the technical effects of significantly reducing clock jitter, improving digital signal processing precision and stability, and especially showing excellent anti-jitter performance in a high-frequency signal processing scene.

The application discloses a kind of unmanned aerial vehicle cluster cooperative navigation methods based on NLOS environment, comprising: by the state parameter of unmanned aerial vehicle constructs the state model of unmanned aerial vehicle;Judge the communication NLOS environment between wingman and host;Based on the NLOS error compensation value and relative distance of calculating distance measurement, the NLOS error compensation value and relative distance are superimposed to obtain correction distance, and the correction distance and measured distance ρ li Construct initial observation model;Error covariance matrix R a→b Add to initial observation model to obtain position observation model;State model and position observation model are brought into extended Kalman filter formula and are iterated, and the final estimated position of host is obtained;Wireless communication is used to make host and wingman interact and adopt the way of wingman following host Cooperative navigation, the correction of navigation information, keep unmanned aerial vehicle cluster normal flight under NLOS environment.

The application discloses a stamping process intelligent decision-making method of man-machine cooperation, constructs a stamping forming prediction model based on a physical information neural network, embeds Hill48 yield criterion, Swift hardening model and friction law into a loss function in the form of a regular term, trains process sensitivity gradient by using small sample data and outputs the process sensitivity gradient, calculates information gain by using an expectation improvement or a confidence upper bound acquisition function and recommends a die trial point based on model cognitive uncertainty, triggers manual confirmation when uncertainty is higher than a threshold value, executes process parameters, collects a stamping force-displacement curve in an initial die trial stage, inverses sheet metal parameters by using an extended Kalman filter to correct model input, records results and feeds back and updates the model, solves a small sample learning problem by embedding physical constraints, reduces die trial times by active learning, realizes material self-adaptation by online inversion, and forms a closed-loop optimization of prediction-die trial-inversion-updating.

The application discloses a positioning installation method and device of a bird repelling device, terminal equipment and a computer readable storage medium, and belongs to the technical field of power line operation and maintenance and unmanned aerial vehicle intelligent control. The method comprises the following steps: acquiring GNSS, IMU and image data of an unmanned aerial vehicle; performing electromagnetic noise filtering on the GNSS data; calculating a signal-to-noise ratio and a feature matching degree to dynamically adjust a fusion weight, wherein the GNSS weight is positively correlated with the signal-to-noise ratio, the IMU weight is negatively correlated with the signal-to-noise ratio, and the visual weight is positively correlated with the matching degree; and outputting accurate coordinates and postures based on the adjusted weight by using an extended Kalman filter, and controlling the unmanned aerial vehicle to hover and the mechanical arm posture to complete installation. Through electromagnetic noise suppression and a multi-source weight adaptive compensation strategy, the application effectively solves the problems of low installation precision and high operation risk caused by positioning drift and mechanical shaking in a high-voltage line strong electromagnetic interference and signal fluctuation environment.

The application discloses an underground space unmanned aerial vehicle positioning system, method, equipment and medium, and belongs to the technical field of unmanned aerial vehicle positioning. The system comprises a sensor data input layer, which is used for acquiring multi-source sensor data of an unmanned aerial vehicle in real time; a network feature extraction layer, which is structured as a ResNet backbone network and a bidirectional long short-term memory network; a state estimation algorithm layer, which is based on a sliding window self-adaptive extended Kalman filter, utilizes the output of the network feature extraction layer to dynamically adjust filter gain and noise covariance, and combines a sliding window to perform batch state processing and backward smoothing processing; and an external observation interface, which is used for acquiring external positioning observation data, and performs adaptive weight distribution and non-line-of-sight interference suppression based on a motion mode output by the network feature extraction layer. The application solves the technical problem of inaccurate positioning of an unmanned aerial vehicle in an underground space.

This invention discloses a rubidium atomic clock discipline method and related products based on the fusion of BeiDou and longwave dual-source signals, belonging to the field of high-precision time and frequency synchronization technology. The method of this invention simultaneously measures the first time difference between the rubidium atomic clock and the BeiDou reference time signal, and the second time difference with the longwave reference time signal, fusing the short-term accuracy of BeiDou with the long-term stability of longwave. An extended Kalman filter model is constructed, whose state vector includes a first type of state variable representing the time-frequency characteristics of the rubidium atomic clock and a second type of state variable representing the fused time difference between BeiDou and longwave. The first and second time difference values ​​are used as observation inputs for iterative estimation, synchronously updating the optimal values ​​of the two types of state variables. A frequency adjustment is generated based on the optimal estimate, and closed-loop control is performed on the output frequency of the rubidium atomic clock. This invention can synergistically utilize the advantages of BeiDou and longwave dual-source signals to achieve time synchronization with high instantaneous accuracy and long-term reliability.

This application discloses a method and apparatus for thermo-coupling field state inversion in compressor hot-assembly processes, relating to the fields of intelligent manufacturing and digital twin technology. The method includes: offline modeling based on historical temperature and displacement data of key nodes of the compressor impeller to obtain a reduced-order model and a physics-data hybrid evolution model that meet preset conditions; using the reduced-order model to reduce the order of the observed state at the previous moment, obtaining a reduced-order state and a reduced-order orthogonal basis matrix; calculating the estimated state at the current moment using the physics-data hybrid evolution model based on the reduced-order state; calculating the target estimated state using the extended Kalman filter method based on the estimated state and the real-time acquired current observation data; and performing inversion using a preset projection function based on the target estimated state and the reduced-order orthogonal basis matrix to obtain the inversion result. This method improves the accuracy of the inversion results and can improve the assembly quality of high-end equipment.

The application discloses a kind of intelligent heat management method and system based on multi-sensor fusion, its method includes the following steps: S1: multi-point temperature array data acquisition: in radiator, power device, busbar, electromagnetic shield area layout N point temperature sensor array, temperature data is collected by temperature sensor.The application is by in key area layout multi-point temperature sensor array and combines electrical parameter, environmental parameter and the full dimension acquisition of heat dissipation component state, realizes multi-source data fusion by means of extended Kalman filter to accurately inverse device real-time junction temperature, again through RBF network reconstruction global thermal field distribution to locate hot spot and thermal gradient, simultaneously utilize LSTM neural network to predict future hot spot temperature variation, finally according to junction temperature, thermal gradient and prediction result dynamic adjustment fan speed, liquid cooling pump flow and cooling mode.

The present application relates to the technical fields of power system automation and intelligent safety monitoring, and discloses a substation operation space dynamic modeling and out-of-bound early warning method based on multi-sensor fusion, aiming at the cumulative deviation of space-time reference and the coupling amplification effect, the time deviation and space drift are included in the extended Kalman filter joint estimation and separated compensation, the mutual excitation loop of the two types of errors in the fusion algorithm is eliminated, the positioning error is still controlled within 5 centimeters after 8 hours of continuous operation, the problem that the real out-of-bound and reference dissonance cannot be distinguished at the key early warning moment is completely solved, aiming at the false out-of-bound false alarm caused by environmental mutation, the UWB signal-to-noise ratio and the cross-correlation function of the electric field output are calculated after the random forest identifies the electromagnetic interference state, the homology is judged based on zero time delay peak value and the alarm is suppressed, the wolf came type trust numbness of the operating personnel caused by frequent false alarm is avoided, and the reliability and response rate of 100% of the early warning signal in the safety critical area are ensured.

The application belongs to the technical field of deep exploration, and discloses a directional drilling intelligent drilling system and control method based on digital twinning and multi-source information fusion, which solves the problems of multi-source data heterogeneous island, parameter inversion multi-solution lag, passive risk evaluation and non-virtual and real closed-loop intelligent regulation in the existing directional drilling technology. The underground sensing and executing unit collects multi-source heterogeneous data and uploads them to the ground intelligent decision platform. The platform pre-processes the data, updates the digital twinning model based on the extended Kalman filter, and inverses the rock mass mechanical parameters and the geological state in front of the drill bit. The twinning model is used for multi-working-condition advanced deduction, so as to obtain the optimal drilling control strategy and issue it to the underground executing mechanism. The application can improve the safety, trajectory accuracy and drilling efficiency of directional drilling construction, and is suitable for deep exploration.

This application discloses a method and system for estimating the state of charge (SOC) of lithium-ion batteries, relating to the field of battery SOC estimation technology. The method includes: acquiring the terminal voltage, charge / discharge current, and open-circuit voltage of the lithium-ion battery under test at different SOC states; constructing a second-order Thevenin equivalent circuit model and identifying the parameters in the model; establishing a nonlinear mapping relationship between open-circuit voltage and SOC; denoising the acquired terminal voltage and charge / discharge current of the lithium-ion battery under test; estimating the SOC using an extended Kalman filter to obtain an estimated SOC value; constructing a backpropagation (BP) neural network and optimizing the initial weights and thresholds of the BP neural network using a sparrow search algorithm to obtain an optimized BP neural network; and fitting and compensating the estimated SOC value to obtain the final estimated SOC value. This application can improve the accuracy of lithium-ion battery SOC estimation.

The application discloses a kind of multi-modal solution methods of mobile target position under dynamic radiation environment, belong to indoor positioning technical field.The application first collects various positioning and environmental data, compensates the phase lag caused by humidity by means of data-driven method, calculates phase position reliability factor relying on channel waveform similarity, adaptively adjusts filter measurement noise matrix, then realizes PDR step closed-loop calibration and timing smoothing update by using sliding window combined with high-precision positioning result, and finally completes two types of positioning information fusion output position result by extended Kalman filter.The application effectively solves the problems of systematic ranging deviation caused by humidity, low multi-path interference recognition accuracy, fixed filter weight and easy accumulation of pedestrian dead reckoning error in the prior art, can significantly improve the positioning accuracy, anti-interference ability and long-time running stability in complex indoor scene, has wide application range and high engineering practical value.

The present application relates to the field of communication technology, especially to a kind of multi-modal data transmission method and system for unmanned area operation.The method comprises the following steps: firstly, a virtual fluid model of multi-modal data is constructed, and virtual viscosity coefficient and virtual compression coefficient are calculated respectively;Secondly, using adaptive extended Kalman filter, combining signal-to-noise ratio and jitter change rate to dynamically correct process noise covariance matrix, real-time estimate channel effective bandwidth;Further, a normalized fluid potential field cost function is constructed, a viscous resistance matching term is constructed using the virtual viscosity coefficient, and the optimal flow rate is solved under the premise of meeting the bandwidth constraint;Finally, combined with virtual compression coefficient and flow rate deficit ratio, the quantization parameter is adaptively calculated through nonlinear mapping.The present application realizes rigid data fidelity and flexible data shock absorption by using data physical properties, which significantly improves the service reliability in extreme environment.

The application relates to the technical field of intelligent control of bridge construction, and discloses a cantilever beam builder multi-source data fusion control and intelligent monitoring method based on digital twinning, which comprises the following steps: collecting the displacement, pressure and construction vibration intensity of each oil cylinder in real time; adopting attenuated memory improved extended Kalman filtering with unknown input decoupling estimation to jointly estimate the oil cylinder displacement, speed, pressure and unknown disturbance force, and outputting a multi-dimensional fusion feature vector containing fusion state estimation value, unknown disturbance force estimation value, health index and displacement estimation standard deviation; adopting an improved isolated forest based on a segmented cumulative probability density function to perform abnormal scoring and early warning; performing multi-cylinder load balancing adjustment and PID synchronous control based on the unknown disturbance force estimation value; and mapping the estimation result, abnormal score and early warning level to a digital twinning platform in real time, driving a three-dimensional model to perform state synchronization and visualized monitoring. Therefore, the multi-oil-cylinder collaborative control precision and abnormal detection capability of the cantilever beam builder are improved.

The application relates to the technical field of rail transit, and discloses a rail transit contact line abrasion detection device and method, which comprises a device platform, an intelligent light supplementing module, an acquisition module, a pose compensation module, an image processing module and a warning module, the device platform integrates various function modules; the intelligent light supplementing module adaptively adjusts light source parameters according to environmental illumination; the acquisition module acquires high-resolution optical images; the pose compensation module realizes real-time sensing of spatial pose and distortion correction; the image processing module realizes profile extraction, three-dimensional reconstruction and abrasion feature calculation; and the warning module realizes graded warning according to abrasion data. The application realizes multi-sensor fusion by adopting an extended Kalman filter, adjusts a light source by a PID control algorithm, and realizes high-precision and high-robustness online detection of rail transit contact line abrasion by using an analysis method combining standard section template matching and deep learning, thereby providing reliable data support for contact network state repair.

This invention discloses a VR virtual-real fusion interaction system and method based on large-space positioning and dynamic rendering. The system includes: a physical space modeling module to generate a spatial risk field function; a hybrid positioning engine that uses tightly coupled extended Kalman filtering to fuse SLAM visual features and UWB / Bluetooth AoA data to calculate pose, and integrates a long short-term memory network for predictive compensation in case of visual failure; a spatial synchronization and dynamic scheduling module to allocate rendering and bandwidth resources; a virtual-real fusion rendering unit that dynamically generates a fused video stream containing virtual scenes and boundary warnings; a low-latency transmission network that distributes the video stream based on WiFi 7 with a latency of no more than 15ms; and a terminal presentation and closed-loop correction module that displays and transmits IMU data to correct pose. This invention achieves highly robust positioning, dynamic boundary warning, predictive resource scheduling, and multimodal interaction closed loop, significantly improving the immersion and safety of large-space multi-person VR experiences.