151 results about "Sensor fusion" patented technology

The application discloses a kind of based on sensor fusion's full-automatic dam slag salvaging pipe control system, belong to the technical field of intelligent operation and maintenance of hydropower station.System includes multi-source perception module, fusion decision module, integrated execution module, safety protection module and man-machine interaction module.Through water level, load, attitude, vision, wind speed, anti-collision multi-sensor fusion, realize environmental full-factor perception, automatically identify floating object type and adapt to water level and attitude balance, complete slag, log cutting, grappling hook salvage, automatic dumping, electric extension and manned safety operation, can realize eight-way movement with dam crane, one machine multiple hole operation.System has multistage safety protection, salvage load is greater than or equal to 1.5t, vertical stroke is greater than or equal to 9m, uses 380V industrial power supply, durable and reliable structure.The application realizes dam slag unmanned, intelligent, integrated operation, high efficiency, strong safety, low modification cost, suitable for various hydropower station floating object cleaning operation and maintenance.

The invention discloses an intelligent automobile active obstacle avoidance control system and method suitable for complex road conditions. The system comprises a multi-source road condition sensing fusion module, a dynamic risk assessment and decision module, an obstacle avoidance path planning module, a vehicle dynamics control module, a man-machine interaction and emergency takeover module and a system state monitoring and fault diagnosis module. According to the invention, the problem of unreliability of a single sensor in rainy days, congestion and other scenes is solved through multi-source sensor fusion, and the sensing precision is ensured; a multi-factor risk assessment model avoids misjudgment of single distance judgment, and the decision more conforms to actual safety requirements; path planning is combined with vehicle dynamics constraint, closed-loop control ensures accurate path tracking, and the vehicle is prevented from being out of control.

This application relates to the field of charger power environment monitoring technology, specifically to a charger power environment monitoring system based on multi-modal sensor fusion. The system includes: a data sensing module, used to synchronously acquire current, voltage, and temperature data of each charging module operating in parallel within a transient window, generate thermal response delay current, and reconstruct the heat generation rate and temperature rise rate of the charging modules; a feature extraction and diagnosis module, configured to screen effective charging modules based on the heat generation rate and generate a thermal resistance characteristic index to quantify thermal resistance anomalies caused by microchannel fouling or air resistance; and a control decision module, used to classify the health status of each effective charging module according to the thermal resistance characteristic index and adjust the command current allocation weight of each effective charging module to achieve thermal stress balance within the group. This application aims to eliminate common-mode interference and achieve accurate identification in the early stages of fouling through soft-measurement monitoring.

The application provides a millimeter wave radar and video fusion tower clearance real-time monitoring method, which comprises a video monitoring camera system and a millimeter wave radar system; first, the two systems are installed at the bottom of the cabin and rotated to point to the blade clearance area, realizing image acquisition and radar reflection point data acquisition in the blade movement cycle; then the controller system calculates the blade tip clearance value according to the collected image data and radar reflection points, qualitatively evaluates the deviation of the two according to the spatial relationship between the blade tip trajectory line and the blade tip reflection point, and ensures the high-precision clearance monitoring of the blade tip and the tower. The clearance monitoring method of the fusion of the two sensors can realize the functions of mutual checking of the accuracy between the systems in normal weather, selection of the clearance for unit control in severe weather, stronger environmental adaptability and working condition adaptability, and avoids the problems of failure of a single sensor due to environmental influence or low clearance accuracy.

This invention provides a 4D radar odometry method for high-dynamic scenarios, relating to the field of autonomous driving perception and sensor fusion technology. The method includes: acquiring raw point cloud data using a 4D millimeter-wave radar-based perception system; extracting corresponding clustering parameters from the raw point cloud data, wherein the clustering parameters include search radii in different directions and minimum neighborhood density; clustering the raw point cloud data using the DBSCAN clustering method based on the clustering parameters to obtain different point cloud clusters; extracting static points from the different point cloud clusters; and calculating the vehicle speed based on the static points using an angle-distance weighted least squares method. This technical solution effectively improves the accuracy of vehicle speed measurement.

The application provides a kind of attack detection method, system and medium for sensor fusion system, it is related to communication security technical field, the method includes obtaining control input and each sensor measurement information, according to this, divide credible and suspicious sensor set and establish attack hypothesis set.By injecting bounded exposure input to control input, construct sensor layer, hypothesis layer and attack output set, use rolling time optimization to increase the separation trend between hypothesis layer and attack output set, while carrying out sensor layer detection.Based on the detection result and separation trend value, iteratively update the attack hypothesis set, repeat the active exposure detection until the stop condition is met, and finally identify the attack and the attacked sensor.The method expands the gap between normal output and attack output by actively injecting bounded exposure input and rolling time optimization, thereby achieving active exposure of covert deception attack and accurate identification of attacked sensor without modifying sensor interface and communication link.

The present application belongs to the technical field of robot control, and specifically discloses a railway inspection robot laser radar anti-collision and remote video linkage control method, aiming to solve the problems of low inspection efficiency, low sensor fusion degree and missing linkage mechanism in industrial scenarios. The method comprises: performing benchmark calibration and entering inspection line data through system initialization and parameter configuration; acquiring point cloud data by high-frequency dynamic scanning using a laser radar, and real-time matching of multi-level early warning thresholds to trigger linkage response; the power control unit executes brake or speed reduction operation according to the instruction, and resets the mode to resume work after confirming safety; the system also archives the full data of linkage events to support continuous optimization of the inspection plan. Through the deep coupling linkage of the laser radar and the video imaging module, the present application can realize all-weather, high-precision and high-safety autonomous operation of the inspection robot in complex high-dynamic environments, significantly improving the inspection efficiency and risk control level.

This invention discloses a safe navigation and localization method for bipedal robots based on discrete control barrier functions and a hierarchical architecture, belonging to the field of robot control technology. The method employs the Relative Dynamics Test (RRT) algorithm to generate a global path and combines it with a Linear Inverted Pendulum Model (LIPM) to generate a stable gait. A discrete control barrier function (D-CBF) is used to ensure obstacle avoidance in dynamic environments, and the safe control input is solved through an optimization problem. Sensor fusion technology is used for real-time localization, and moving average filtering is applied to eliminate oscillation errors caused by gait. This invention, by combining discrete control barrier functions (D-CBF) with hybrid zero dynamics (HZD), achieves high-precision navigation and safe obstacle avoidance for bipedal robots in complex environments, effectively solving the problems of insufficient stability and lack of safety in traditional methods.

This invention discloses an intelligent interlocking and audible-visual early warning system for cantilever tunneling machines based on sensor fusion. This invention relates to the field of safety technology for mining tunneling equipment, solving the technical problem that existing mining tunneling equipment often uses manual three-way ball valves for hydraulic interlocking to switch oil circuits. This invention uses a three-position four-way valve in conjunction with various hydraulic valves to achieve forced hydraulic interlocking of the three major operating oil circuits: tunneling, anchor cable tensioning, and support. Only one operating circuit is energized at a time, completely avoiding the problem of simultaneous malfunction of multiple mechanisms caused by accidental operation of the control handle or failure to lock the hydraulic circuit, effectively reducing equipment collision damage and personnel safety hazards. By using pressure sensors to collect oil circuit load pressure signals in real time, it achieves audible-visual and voice early warning, emergency stop interlocking for cutting motor power failure, and intelligent on / off control of electronic fences. This not only warns on-site workers to stay away from dangerous areas in advance but also eliminates the risk of accidental start-up of the cutting motor during support and anchor cable operations.

This invention discloses a multi-sensor fusion-based fiberboard hot pressing control method, belonging to the field of equipment control technology. The invention monitors the displacement and pressing speed of each layer of the hot pressing platen using sensors, analyzes the pre-pressing time of each layer in real time, and adjusts the pressing speed of each layer during pre-pressing accordingly. Before formal compression, it analyzes the estimated time for each layer to reach the corresponding target thickness, obtains an intermediate value as the target time, and adjusts the preset pressure of each layer according to the target time, allowing each layer to be compressed to the target thickness simultaneously. During the holding pressure stage, it analyzes the estimated holding pressure time of each layer, obtains an intermediate value as the target holding pressure time, and adjusts the preset holding pressure of each layer according to the target holding pressure time, allowing each layer to complete holding pressure simultaneously. This ensures the quality of the hot-pressed finished product while ensuring that each layer completes the process synchronously at each stage.

This application discloses an AGV multi-sensor tightly coupled positioning method and system based on adaptive factor graph optimization, relating to the field of AGV navigation technology. By quantitatively evaluating the real-time positioning quality of LiDAR and GNSS, and dynamically adjusting the Gaussian noise covariance matrix and sensor fusion weights, it achieves intelligent switching of the dominant positioning sensor. It can accurately identify anomalies such as satellite signal failure and decreased LiDAR matching accuracy, quickly switching to a stable sensor to avoid positioning jumps, drift, and interruptions. This enhances the anti-interference capability of the positioning system, ensures the continuity of AGV autonomous navigation and operational safety, and facilitates the penetration of AGVs into high-end industrial scenarios, improving their adaptability and operational efficiency in flexible manufacturing, intelligent warehousing, and other scenarios. It effectively solves the technical problem of existing multi-sensor fusion positioning using fixed weights and being unable to dynamically adapt to environmental changes, significantly improving the positioning performance of AGVs under complex working conditions.

This invention discloses a multi-layer, three-dimensional cleaning robot that integrates multimodal information. Belonging to the field of poultry industry robot technology, this invention combines data from lidar and ultrasonic sensors to achieve dynamic obstacle avoidance for the cleaning robot. By combining data from optical sensors, when the robot is suspended in mid-air, if the receiver tube does not receive a signal or the received signal is below a set threshold, the cleaning robot directly determines that the area below is empty, immediately stops moving, and reverses. This multi-sensor fusion poultry house cleaning robot aims to autonomously map, autonomously avoid obstacles, autonomously plan cleaning routes, autonomously complete cleaning tasks, and autonomously return to its charging station for recharging.

The application discloses a multi-sensor fusion aerial operation hook three-dimensional posture monitoring and early warning method, and relates to the technical field of aerial operation safety monitoring. The method comprises the following steps: acquiring a locking state signal of a hook of a speed difference self-locking device, a load bearing connection state signal and real-time inertial measurement data; performing Kalman filtering on the real-time inertial measurement data to generate hook three-dimensional posture data; performing first-level risk analysis on the hook three-dimensional posture based on the locking state signal to generate a first priority early warning instruction representing a hook locking failure; performing second-level risk analysis on the hook three-dimensional posture according to the load bearing connection state signal to generate a second priority early warning instruction representing a hook hooking failure; analyzing the change characteristics of the hook three-dimensional posture data, and performing third-level risk analysis on the hook three-dimensional posture according to the change characteristics to generate a third priority early warning instruction representing an abnormal spatial position of a hook anchor point. The application improves the accuracy of aerial operation hook three-dimensional posture monitoring and early warning.

The present application relates to the technical field of navigation positioning, and in particular to a multi-source sensor adaptive weight fusion positioning method and related equipment, which comprises the following steps: collecting multi-source positioning sensor observation data, calculating corresponding health degree factors according to the data characteristics of each sensor, which are used to represent the data quality at the current time; inputting the health degree factors into a pre-trained reinforcement learning model, the model taking the maximization of the reward function constructed by the positioning error and the sensor health degree as the goal, and outputting the fusion weight of each sensor. According to the output weight, the multi-source observation data is fused and solved through factor graph optimization, and the final positioning result is output. This method can dynamically adapt to the differences in sensor working conditions and environmental disturbances, suppress the influence of abnormal data, realize the collaborative improvement of positioning accuracy and system reliability, and is suitable for multi-source fusion positioning scenes such as automatic driving, robots, intelligent navigation, etc.

The utility model provides a kind of multi-sensor fusion identification goods sorting device, including sorting trolley, the sorting trolley includes chassis, infrared obstacle avoidance sensor located at the outer periphery of chassis, infrared tracking sensor located at the bottom of chassis, weighing platform located above chassis and microcontroller located on chassis, the chassis upper end surface is fixedly connected with the guide frame located in the both sides of weighing platform, the guide frame top is slidably connected with the protective sleeve of the weighing platform outside.In the utility model, by the outer periphery of weighing platform is equipped with protective sleeve, when sorting trolley moves fast and turns, goods will be blocked by protective sleeve, so that sorting trolley moves fast, and goods will not appear the problem of sliding due to inertia force, and compared with prior art, the efficiency of goods sorting and distribution is greatly improved.

This invention relates to the field of waste heat recovery technology in textile machinery, and more particularly to a multi-sensor fusion monitoring method and system for waste heat recovery systems in stenters. The method acquires data from multiple sensors and performs spatiotemporal alignment and fusion calculations to obtain a comprehensive system status assessment result. Based on this result, anomaly identification and multi-objective optimization are performed to generate a control execution scheme. After the scheme is executed, response data is collected to analyze control effect deviations, and relevant parameters are adaptively adjusted accordingly. This invention achieves precise monitoring and intelligent control of the waste heat recovery system status, improving system operational stability and energy efficiency.

This document describes techniques, systems, and methods for multi-scan sensor fusion for object tracking. Sensor fusion systems can acquire radar and visual tracking data generated for a vehicle's environment. The system maintains a set of hypotheses about the association between visual and radar tracking based on multiple scans of radar and visual data. This set of hypotheses includes quality values ​​for the associations. The system determines a probability value for each hypothesis. Based on these probability values, a match is determined between radar and visual tracking. The system then outputs the match to a semi-autonomous or autonomous driving system to control the vehicle's operation. In this way, the described techniques, systems, and methods can provide high-precision object tracking with quantifiable uncertainty.

The application provides a feedback control method based on sensor fusion and operation intention recognition, and relates to the technical field of intelligent sensors, which comprises the following steps: acquiring inertial measurement data, pressure sensing data and external visual pose data arranged in a target interactive carrier, and performing preprocessing to form a multi-modal operation data sequence; performing sliding window segmentation processing based on the multi-modal operation data sequence, and extracting multi-dimensional feature parameters reflecting operation intensity, change trend and periodic characteristics to construct a feature vector; performing multi-dimensional decision mapping on the feature vector to identify the corresponding operation intention category; generating an interest weight coefficient according to the operation intention category and its continuous distribution characteristics in the time dimension; constructing a feedback control strategy based on the interest weight coefficient and the operation intention category, and driving an execution unit to output a response signal. The application can fuse multi-source data of an interactive device, and improve the timeliness of dynamic adjustment of a feedback strategy in combination with operation intention recognition.

This invention provides an intelligent anti-extubation vest and its application control method. Through sensor fusion and intelligent control technologies, it upgrades traditional passive fixation to an active protection system, shifting from "post-event handling" to "pre-event warning." Clinical trials show that it can reduce unplanned extubation rates, shorten nurse response times, and significantly improve the safety and quality of care for thoracic surgery patients. This invention achieves active protection through a closed-loop control system of "real-time monitoring - automatic clamping - multi-level alarms," ​​realizing an active anti-extubation mechanism and improving fixation reliability.

The application discloses a kind of real-time flow deviation compensation control methods of multi-sensor fusion, comprising the following steps: S1, obtain set flow;S2, the actual flow of current header is obtained by flowmeter, and the deviation between actual flow and set flow is calculated;S3, the header number of deviation exceeding pre-set range is identified, and the valve positioner is dynamically adjusted until the actual flow is stable, and the actual valve opening degree and actual flow are recorded;S4, according to the actual valve opening degree and actual flow recorded, the data points in flow-valve opening degree corresponding relationship are reversely calculated and updated using traversal method.The application identifies the header with deviation and automatically corrects flow-valve opening degree corresponding relationship, so that the system can directly obtain actual flow meeting set flow requirement when next valve action, reduces the repeated adjustment of proportional regulator, and significantly reduces flow fluctuation.

Various embodiments relate to a method, apparatus, and machine-readable storage medium for simulating a sensor value including one or more of the following: receiving a real sensor value from a sensor device at a first location within a system; propagating the real sensor value through a digital twin simulation of the system from a first simulated location associated with the first location to a second simulated location associated with a second location within the system, wherein propagating comprises applying at least one physics-based transfer function to the real sensor value; determining that a virtual sensor value should be generated for the second location within the system; and extracting the virtual sensor value from the second simulated location of the digital twin simulation.

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

The utility model discloses a kind of oil pillow type borehole stress measuring devices of multi-sensor fusion in the technical field of mine borehole stress monitoring, including oil bladder, first pressing plate component, second pressing plate component, third pressing plate component, fourth pressing plate component and plastic package cover, the oil bladder is hollow flat cavity, two ends are set exhaust component and oil inlet pipe respectively, first pressing plate component and second pressing plate component are set in the upper and lower ends of oil bladder, the third pressing plate component and fourth pressing plate component are set in the left and right ends of oil bladder, the two ends of first pressing plate component and second pressing plate component are connected with third pressing plate component and fourth pressing plate component respectively through linkage structure, and the plastic package cover is covered in the outside of each pressing plate component.The oil pillow type borehole stress measuring device of utility model patent design can realize the monitoring of borehole multidirectional compression, and improve monitoring quality.

In order to solve the problem that the road marking device is low in automation degree and pipeline is easy to be blocked, the utility model provides a kind of traffic marking unmanned vehicle of multi-sensor fusion, comprising: unmanned vehicle main body, steering wheel and driving device are arranged on unmanned vehicle main body;Marking device, by setting up paint tank, paint pump and spray gun on unmanned vehicle main body, paint pump and inlet and outlet are connected with paint tank and spray gun respectively;Control system, by controller, camera, positioning module, IMU linear measurement unit, laser ranging unit is formed, camera, positioning module, IMU linear measurement unit, laser ranging unit are connected with controller signal input end, paint pump, driving device are connected with controller signal output end, by installing laser radar, camera and other sensors are combined, complete surrounding environment modeling and perception, high-precision automation completes marking work.

Generally, the disclosed systems and methods implement improved detection of objects in three-dimensional (3D) space. More particularly, an improved 3D object detection system can exploit continuous fusion of multiple sensors and / or integrated geographic prior map data to enhance effectiveness and robustness of object detection in applications such as autonomous driving. In some implementations, geographic prior data (e.g., geometric ground and / or semantic road features) can be exploited to enhance three-dimensional object detection for autonomous vehicle applications. In some implementations, object detection systems and methods can be improved based on dynamic utilization of multiple sensor modalities. More particularly, an improved 3D object detection system can exploit both LIDAR systems and cameras to perform very accurate localization of objects within three-dimensional space relative to an autonomous vehicle. For example, multi-sensor fusion can be implemented via continuous convolutions to fuse image data samples and LIDAR feature maps at different levels of resolution.

(Main claim) Mobile system for defense against unmanned aerial vehicles, comprising: • a radar system for target detection, • an electro-optical and / or infrared-based observation system, • an extendable or foldable mast platform, • a directional jammer with at least one directional antenna on a stabilized platform, • a central control unit, and • an operating and display unit, characterized in that the central control unit calculates a dynamic jamming vector from the sensor data, which determines both the orientation of the directional antenna and the spectral distribution of the jamming signal.

The application provides a fire-fighting robot intelligent control system based on intelligent sensing and aiming decision, and fundamentally solves the pain points of low positioning accuracy, poor reliability and insufficient intelligence of traditional mobile fire-fighting devices by deeply integrating advanced computer vision, nonlinear state estimation, multi-sensor fusion and intelligent control algorithm into the fire-fighting equipment. It represents a new generation of intelligent fire-fighting infrastructure development direction of algorithm empowerment hardware and software defined system, and has wide application prospect and high popularization value in the field of large space fire-fighting support. Through the AI vision self-calibration algorithm, the accurate mapping between the slide rail coordinate system and the ground real world coordinate system is dynamically established and maintained, so that low-cost, high-reliable and self-adaptive high-precision positioning and fire extinguishing are realized.