25 results about "Dead reckoning" patented technology

An autonomous drone swarm system and method for subterranean and GPS-denied operations utilizing artificial intelligence for coordinated operations comprises command drones equipped with large language model processors and subordinate drones coordinated through a hierarchical Queen-Worker architecture. The system processes natural language commands, generates autonomous mission plans, and coordinates multi-drone operations through an encrypted self-healing mesh communication network utilizing multiple modalities including radio frequency, optical, acoustic, and visual channels. A Unified Ground Frame with Surface-Referenced Z (UGF-SRZ) coordinate system provides signed vertical coordinates enabling seamless operation across surface and subterranean environments. GPS-denied navigation combines multi-sensor dead reckoning, collaborative positioning, and distributed mapping with fog-layer processing for enhanced accuracy. The system implements federated learning protocols for distributed AI improvement, fault-tolerant operation with automatic leader election, and specialized adhesion Workers functioning as persistent infrastructure nodes.

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.

This invention relates to a multi-sensor fusion positioning method for autonomous trucks in industrial parks, comprising: generating a high-precision point cloud map and a gridded high-precision positioning layer based on sensor data acquisition; acquiring positioning information from a laser positioning module, GNSS positioning module, 6G positioning module, and dead reckoning module in real time; performing single-source verification on laser positioning, GNSS positioning, and 6G positioning, marking each positioning source as valid, suspected invalid, or invalid; performing cross-source consistency verification based on 6G positioning as a benchmark to identify hidden faults; dynamically adjusting the weights of each positioning source according to the verification results; fusing positioning information through an error state Kalman filter to output a robust positioning result. This invention, by fusing 6G, GNSS, laser radar, and dead reckoning data, constructs a multi-source redundant positioning system, significantly improving the positioning robustness of autonomous trucks in complex park environments, accurately identifying and suppressing hidden faults, and ensuring reliable positioning results.

The application provides a kind of based on multi-source sensor fusion calibration and space constraint collaborative indoor positioning method, the method comprises the following steps: S1, a plurality of position known low-power Bluetooth anchor points are deployed in target indoor area, by utilizing the real physical displacement provided by IMU Pedestrian Dead Reckoning (PDR) as constraint reference, the RSSI compensation parameter of terminal special is dynamically deduced, this method can adaptively calibrate the antenna gain and receiving sensitivity difference of different models of mobile phone, realizes the wide compatibility of positioning algorithm to all brand mobile phones. Through the collaborative solution of weighted least squares method and Kalman filtering, while eliminating low quality signal interference, the trajectory is smoothed by using time sequence filtering, the positioning jump caused by environmental noise is significantly reduced, and the positioning stability is improved. In addition, the A* path planning algorithm is introduced for space topological constraint, and the positioning result is forced to be corrected to the walkable area of the map, effectively eliminating the phenomenon that the trajectory penetrates the wall or obstacle.

In some embodiments, a method comprises: receiving acceleration data from a motion sensor of a mobile device carried by a user, the acceleration data represented by a space curve in a three-dimensional (3D) acceleration space, the space curve indicative of a cyclical vertical displacement of the user's center of mass accompanied by a lateral left and right sway of the center of mass when the user is stepping; computing a tangent-normal-binormal (TNB) reference frame from the acceleration data, the TNB reference frame describing instantaneous geometric and kinematic properties of the space curve over time; and computing a direction of travel of the user based on an orientation of a unit binormal (B) vector of the TNB reference frame in the 3D acceleration space, and computing a speed of the user based on a linear regression model applied to the kinematic properties of the TNB reference frame.

The application discloses an orchard spraying machine automatic navigation method, system, device and product, relates to the automatic navigation field, and the method comprises the following steps: collecting orchard environment information and orchard spraying machine state information; when the orchard spraying machine travels between the fruit tree rows, the fruit tree target is identified based on the image between the fruit tree rows, the navigation center line is extracted, and visual navigation is carried out; when it is determined that the end of the fruit tree row has been reached through the image between the fruit tree rows, the visual navigation is switched to the dead reckoning mode; in the dead reckoning mode, the real-time position is calculated through dead reckoning, and the orchard spraying machine is controlled to travel from the end of the fruit tree row to the head turning point; when it is determined that the orchard spraying machine has reached the head turning point, the orchard spraying machine is controlled to turn at the head; after the orchard spraying machine completes the head turning, the visual navigation is restored, and the technical problem that the anti-interference ability is weak and the signal is unstable when a single sensor is used for navigation in the prior art can be solved.

This invention discloses a real-time anomaly detection method for sanitation operations based on edge computing, belonging to the field of smart city technology. The invention includes deploying edge computing nodes and configuring multimodal sensors to collect positioning, vibration, operation commands, and actuator feedback data; performing time synchronization, filtering, and feature extraction preprocessing on the multi-source sensor data; fusing vibration spectrum features and actuator feedback to determine the vehicle's continuous operation status; compensating for vehicle position by dead reckoning based on operation status when GPS signal is lost; associating the compensated position with the operation status to form an operation chain and detecting three types of abnormal events; uploading summary data only when an abnormal event is uploaded, and generating a work order from the cloud. This invention, by fusing chassis vibration features and the status of the operation actuator at the edge computing node, can infer the continuity of operations and perform position compensation based on the vibration spectrum when the GPS signal is lost.

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 electric power robot navigation positioning technical field, specifically to a kind of transformer internal inspection robot navigation method based on drawing and internal anchor point constraint, comprising: the real-time image of robot collected to the oil tank inside is repaired with image enhancement processing to the environment feature under oil;The visual semantic features extracted are matched with multi-modal navigation anchor point knowledge base, and navigation anchor point is identified;Based on the navigation anchor point identified by feature matching, the real-time pose of robot relative to navigation anchor point is calculated;The current dead reckoning data of robot is obtained, and robot global pose correction is carried out;With the global pose after correction as reference, path planning based on structural design drawing constraint is carried out.The method continuously fuses the dead reckoning data of inertial navigation unit and high-confidence anchor point absolute coordinate observation value, drives robot to autonomously, safely and accurately reach preset inspection point, and completes close observation task.

This invention discloses a navigation method suitable for field geological surveys, specifically relating to the fields of geological exploration and navigation positioning technology. It involves collecting three-component geomagnetic field data to calculate rotational angular velocity and extracting travel cycles to calculate triaxial cross-correlation coefficients. When both rotational and correlation anomalies occur simultaneously, a geomagnetic anomaly zone is identified, and the mechanical and electronic compasses are forcibly shut down. The accurate magnetic azimuth and satellite coordinates before entering the anomaly zone are extracted as initial references. Inertial dead reckoning is initiated, and the heading change or absolute heading angle is obtained. Periodic drift corrections are performed on the dead reckoning to correct the navigation heading. This invention accurately identifies geomagnetic anomaly zones using dual anomaly detection based on geomagnetic field vector rotational angular velocity and triaxial correlation coefficients, forcibly shutting down compass output to avoid misleading information. Furthermore, by integrating inertial dead reckoning with visual or polarized light heading correction, a corrected navigation heading independent of the geomagnetic field is output, ensuring the accuracy and safety of field geological surveys.

This application relates to the field of dead reckoning correction technology, and discloses a dead reckoning correction system and method based on RFID zero-point reset. The method includes: performing dead reckoning on the angular rate and acceleration from the inertial measurement unit to generate a first predicted pose of the vehicle; in the interval where no RFID reader reads the RFID tag along the track, continuously correcting the first predicted pose based on the lateral distance collected by the lateral ranging sensor and preset track geometry information to obtain an intermediate pose; when a read event signal is received, resetting the track position state of the intermediate pose to the track position corresponding to the read RFID tag to obtain a reset pose; outputting the reset pose and using the reset pose as the initial pose for the next dead reckoning; this application realizes full-range pose estimation of rail vehicles in long-distance tagless intervals without satellite positioning, improving the pose estimation accuracy.

This invention discloses a dead reckoning system and method for a dual-wheel differential AGV, belonging to the field of dead reckoning technology. The system employs a data acquisition module to acquire multi-source operating data of the AGV and preprocess it to generate a standardized data stream; a mileage calculation module to generate the original mileage increments for the left and right wheels; a heading fusion module to fuse the standardized data stream and the original mileage increments through a filter to generate a fused heading angle; a motion control module to generate motor drive commands based on the fused heading angle and target commands; a memory optimization module to identify scenarios and match historical strategies, dynamically adjusting relevant calculation parameters; and a visualization module to visualize the operating data and control process and generate a trajectory report. This invention, by fusing multi-source sensor data and intelligent memory optimization, achieves adaptive parameter adjustment and scenario-based strategy reuse in dead reckoning, effectively suppressing accumulated errors and improving the motion control accuracy and robustness of the AGV in complex environments.

The application discloses a kind of vehicle positioning methods based on Pareto and Lyapunov, by obtaining multiple sensor data of vehicle, and according to multiple sensor data constructs positioning model, according to speed and direction constructs vehicle's dead reckoning model, and the position estimation of the dead reckoning model is fused and estimated to obtain vehicle state information, error state constraint Pareto algorithm is used to optimize and analyze vehicle state to determine constraint optimization problem, and according to Pareto front algorithm, the optimal solution of constraint optimization problem is determined, according to optimal solution, the state space model of fusion estimation process is constructed, and Lyapunov and state space model are used to analyze the stability of vehicle positioning to obtain stability evaluation result, the stability of fusion estimation is analyzed using state space model, realizes robust fusion estimation process, and enhances the ability of vehicle positioning in dynamic environment and the ability of reliable operation under changing conditions.

This application provides a method, apparatus, electronic device, storage medium, and program product for calibrating dead reckoning information. The method includes: acquiring first dead reckoning information and pseudo-measurement information of a vehicle, wherein the first dead reckoning information is determined by the vehicle's inertial measurement unit (IMU), and the pseudo-measurement information is represented in the vehicle coordinate system; transforming the first dead reckoning information to the vehicle coordinate system to obtain second dead reckoning information of the vehicle; determining the measurement error of the IMU based on the second dead reckoning information and the pseudo-measurement information; acquiring noise parameters of a data filter, wherein the noise parameters describe the noise of the data filter; and calibrating the first dead reckoning information of the vehicle through the data filter based on the measurement error and the noise parameters to obtain third dead reckoning information of the vehicle. This application can effectively improve the accuracy of calibrated dead reckoning information.

The application discloses a milestone positioning method and device based on multi-modal fusion, equipment and medium, relates to the field of image recognition technology, and the method comprises the following steps: firstly, acquiring the left and right views of the front road, the instantaneous speed, the absolute geographical coordinates and the vehicle heading angle collected by the inspection vehicle; secondly, calculating the real-time pitch angle of the camera relative to the road surface according to the left and right lane line vanishing points; simultaneously, performing time integration on the speed and combining historical data to obtain the dead reckoning mileage value; when the target milestone is detected, performing inverse distortion processing on the initial three-dimensional coordinates by using the pitch angle and verifying the identification value; if the target milestone is not detected and the theoretical mileage position is reached, generating a virtual anchor point coordinate based on the geographical coordinates, the heading angle and the preset lateral offset; mapping the calculated value to the milestone and combining the anchor point to obtain the final positioning result. The application can realize high-precision positioning of the road mileage milestone under the actual inspection working conditions of vehicle dynamic driving, target identification misjudgment or missed detection.

The application relates to the technical field of electric vehicle track recording, and discloses a track deviation correction method based on electric object double-domain causality enhancement. The method collects multi-modal synchronous data through the establishment of a cross-device communication link, identifies the human-vehicle coupling state by using the time sequence causality relationship between the electric signal state change and the acceleration response, obtains the calculated speed through the internal resistance conversion coefficient decoupling mechanism and Kalman filtering online learning, identifies the GPS drift point based on the double-layer causality determination of the ripple driving state and the bus voltage deviation direction, restricts the dead reckoning through the voltage waveform mode in the GPS blind area, and performs uncertainty weighted error distribution, and finally backtracks and refines the parking point coordinates at the ripple zero time. The application can accurately identify the human-vehicle coupling state and the GPS drift under the low-cost hardware architecture without a current sensor, realize the full-scene continuous track recording and accurate positioning of the parking point.

This disclosure provides "Mobile Device Connectivity for Vehicle Systems Based on Variable Time of Flight and Dead reckoning". A method and apparatus for mobile device connectivity for vehicle systems based on variable time of flight and dead reckoning are disclosed. An example vehicle includes a communication module that communicates with a mobile device using multiple frequency bands and a vehicle body control module. The vehicle body control module estimates the position of the mobile device relative to the vehicle at time intervals based on time-of-flight measurements using one of the multiple frequency bands selected based on a previous position estimation. Between the time intervals, the vehicle body control module uses dead reckoning to track the position of the mobile device. Furthermore, the vehicle body control system controls the vehicle's subsystems based on the position of the mobile device.

The application provides a method for realizing high-precision underwater integrated navigation by fusing AUV kinetic velocity and single-beacon acoustic data, and belongs to the technical field of underwater navigation and positioning. The method comprises the following steps: estimating the speed against water in the carrier coordinate system by using the propeller rotating speed and the motor current, decomposing the speed against water to the navigation coordinate system by fusing the SINS attitude, obtaining the three-dimensional motion velocity of the AUV, and obtaining the preliminary position based on the dead reckoning; adaptively selecting the navigation strategy according to the operation time length and acoustic availability: the pure kinetic dead reckoning is adopted for the medium-short time task, and the single-beacon distance information is introduced for the long time operation, the navigation position after correction is obtained by periodically constraining the dead reckoning result through the geometric projection filtering algorithm of resetting the starting point. Compared with a single data source, the application significantly improves the navigation precision and reliability, and effectively solves the technical problem that the application of the acoustic sensor is limited in the deep sea environment.

A method for controlling autonomous mine vehicle operations includes the steps of detecting a dust condition for an autonomously operating mine vehicle performing optical environment scanning for positioning the mine vehicle at a worksite, transitioning the mine vehicle operating in an automatic driving mode to a dust driving mode in response to detecting the dust condition, the dust driving mode being associated with one or more control actions for autonomous operation of the mine vehicle, controlling dead-reckoning based positioning for updating the position of the mine vehicle during the dust driving mode, monitoring of a dead-reckoning error parameter during the dust driving mode, and in response to the dead-reckoning error parameter reaching an error threshold, controlling the mine vehicle to stop or reduce speed.

The application discloses a kind of sanitation worker operation track self-adaptive collection method and system based on gesture recognition, it is related to wisdom city management technical field.The method includes: synchronous acquisition IMU inertial data and positioning module position data;Current operation posture category is identified based on inertial data, including bending to clean, arm picking up etc.;According to posture category, dynamically adjust track collection strategy, including positioning data reporting frequency and positioning module work power consumption state;According to strategy, target position data is obtained and is associated with posture label upload;The operation track with state label is generated.The application is linked by posture and power consumption strategy, significantly reduces terminal power consumption, enriches track information dimension, and guarantees blind area track continuity by gesture perception dead reckoning.

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

This invention discloses an autonomous AGV (Automated Guided Vehicle) suitable for confined spaces and its scheduling method, relating to the field of transport vehicle technology. The autonomous AGV includes a vehicle body, a drive module, a control module, a telescopic sensing mast, a bottom sensing unit, and a fusion positioning and navigation module. By integrating the telescopic sensing mast and the bottom sensing unit, and combining the adaptive mode switching of the fusion positioning and navigation module, the AGV achieves seamless autonomous navigation between open spaces and low-ceilinged, confined spaces. In open spaces, the telescopic sensing mast is raised, and the first sensing unit uses lidar and a visual camera for global SLAM navigation. When entering or about to enter a confined space, the telescopic sensing mast is lowered, and the system switches to dead reckoning navigation based on the bottom sensing unit.

The application discloses a kind of based on multi-sensor fusion and double neural network's pedestrian motion state identification and trajectory calculation method, comprising the following steps: collecting accelerometer, gyroscope, barometer, magnetometer data of portable electronic device, filtering and sliding window segmentation preprocessing are carried out;Extract 16-dimensional feature vector for motion state identification and 18-dimensional feature vector for holding state identification;Motion state and holding state are identified in parallel by double neural network;According to holding state, adaptively select coordinate conversion function, and unify sensor data to world coordinate system;Adopt vector method to solve heading angle, combine step frequency detection and step length estimation, and generate motion trajectory by pedestrian dead reckoning.The application effectively eliminates device posture change interference through holding state adaptive coordinate conversion and double neural network collaborative identification, significantly improves the precision, robustness and real-time performance of pedestrian trajectory calculation in complex environment.

This invention discloses a TridentNet-LSTM pedestrian dead reckoning method based on prior physical model constraints, comprising: constructing a TridentNet-LSTM model to combine multi-scale feature extraction with time series modeling; constructing a loss function consisting of three parts: a basic loss function based on weighted mean square error loss, a sequence consistency loss function, and a Physical Information Neural Network (PINN) loss function; during model training, data preprocessing is first performed, and the training and validation sets are divided and initialized; the Adam optimizer is selected for end-to-end training, and the ReduceLROnPlateau learning rate scheduling strategy is adopted; the PDR algorithm is used for trajectory reconstruction, and RMSE is used as the error analysis metric. This invention, through the TridentNet-LSTM model based on prior physical model constraints, can achieve end-to-end pedestrian trajectory reckoning and can adapt to walking, running, and mixed walking-running gaits. It does not rely on the strong periodic signals of foot IMUs and can also handle shoulder IMU data with relatively ambiguous gait characteristics.

A vehicle position estimation device includes an external information acquisition unit, a vehicle parameter acquisition unit, a map data acquisition unit, a lane change determination unit, and a position estimation unit. The external information acquisition unit acquires external information. The vehicle parameter acquisition unit acquires a vehicle parameter related to traveling. The map data acquisition unit acquires map data. The lane change determination unit determines whether the vehicle is changing lanes. The position estimation unit estimates a self-position of the vehicle on a map. When the lane change determination unit determines that the vehicle is changing lanes, the position estimation unit estimates the self-position using dead reckoning. When the lane change determination unit determines that the vehicle is not changing lanes, the position estimation unit estimates the self-position based on the external information and the map data.