78 results about "Augmentation system" patented technology

Methods and systems for training an end-to-end autonomous driving system using a vision-language planning (VLP) machine learning model in a closed-loop environment. Images associated with an environment about a vehicle are generated, and a BEV model is executed to generate a BEV view based on the images. A planning model predicts navigation trajectories based on the BEV. The VLP model enhances the system by extracting vision-based planning features, generating text prompts, and employing a language encoder to create text-based expectation features. A contrastive learning model identifies similarities between vision and text features, boosting the performance of the BEV and planning models. The system undergoes closed-loop evaluation in a simulated environment, capturing metrics to refine the autonomous driving system.

The invention relates to the technical field of multi-vehicle cooperative control, and discloses a multi-AGV distributed cooperative path planning method and system, and the method comprises the steps: carrying out the task distribution based on the AGV state and position distance after receiving the order picking wave issuing; performing global path planning on the selected AGV, and determining continuous path points to be driven; the AGV dynamically blocks a front path point to form a temporary exclusive channel; detecting conflicts among the AGVs through a double conflict judgment mechanism based on timestamps and direction representation; if no conflict exists, the task is executed, and if the conflict exists, deadlock judgment is carried out firstly; if deadlock occurs, a heuristic avoidance strategy is adopted to search temporary obstacle avoidance points, and a path is re-planned through an A * algorithm in combination with a direction priority principle; and if the deadlock does not exist, directly carrying out path adjustment. According to the scheme, through dynamic blocking and double conflict judgment, waiting and collision are effectively reduced, and the passing efficiency and safety are improved; and in combination with a heuristic avoidance method based on a ternary search tree, the scheduling flexibility and intelligence of the system in a deadlock scene are enhanced.

The invention discloses a hierarchical visual language navigation memory enhancement system in a cross-floor scene, relates to the technical field of intelligent navigation, and adopts the technical scheme that the hierarchical visual language navigation memory enhancement system comprises three core parts, namely a hierarchical visual semantic model construction module, a memory enhancement algorithm module and a navigation system integration module. The hierarchical visual semantic model construction module is used for constructing a basic visual feature layer, a floor semantic layer and a cross-floor semantic association layer; the memory enhancement algorithm module comprises a short-term memory module, a long-term memory module and a memory fusion and update strategy module; and the navigation system integration module is used for integrating the hierarchical visual semantic model and a memory enhancement algorithm into the system. Three-dimensional space characterization misalignment and path planning error accumulation can be effectively avoided, the accuracy, environment adaptability and decision-making efficiency of cross-floor navigation of the intelligent agent are remarkably improved, and the method has important technical innovation value and application prospects.

The invention relates to the technical field of industrial automation, in particular to an inspection path generation method and device, a storage medium and computer equipment, when an inspection path is generated, time-space synchronization can be carried out on data collected by different sensors, geometric and physical consistency of a motion track is ensured, the dynamic positioning precision is further improved, and the accuracy of the inspection path is improved. Moreover, when part of the sensors fail, the robustness of the system can be effectively enhanced through a synchronized redundant data maintenance function, and the data processing delay can be reduced through time-space synchronization, so that the real-time control requirement of a dynamic scene is met, and a map can be updated in real time according to the current environment to improve the accuracy of navigation and positioning. The method adapts to complex environments; in addition, the current positioning error can be corrected according to the target point cloud data and the target image data so as to further improve the positioning accuracy, and the relatively accurate inspection path and control instruction can be generated based on the corrected positioning result and the target map.

The invention relates to the field of field groundwater magnetic resonance detection methods, in particular to an augmentation system and method for field groundwater magnetic resonance detection small sample data. Comprising a generation network configured to receive random noise and generate augmented data based on the random noise; the discrimination network comprises a time domain discrimination network and a frequency domain discrimination network; the generative network and the time domain discrimination network form a first discrimination channel, the generative network and the frequency domain discrimination network form a second discrimination channel, and in the second discrimination channel, augmented data generated by the generative network and the noisy data are jointly input into the frequency domain discrimination network; the frequency domain discrimination network is used for discriminating whether the source of input data is a generation network or noisy data in a frequency domain. According to the method, a magnetic resonance detection small sample noisy data set is established, and multi-scale features in an amplitude spectrum and a phase spectrum are captured through the frequency domain discrimination network; the collaborative driving generation network generates a high-quality sample which is close to small sample noisy data in waveform form and spectral characteristics.

The invention discloses a positioning method and device and electronic equipment. The method comprises the following steps: receiving original satellite-based service data accessed by terminal equipment, the original satellite-based service data comprising original correction data which is acquired by the terminal equipment from a satellite-based enhancement system and is used for correcting a positioning error; an analysis strategy corresponding to the terminal equipment is determined, and the analysis strategy is used for extracting error correction parameters of a preset type in the original correction data; an analysis strategy is adopted to analyze the original satellite-based service data, target correction data are obtained, and the target correction data comprise error correction parameters of a preset type; and determining a positioning result of the terminal equipment according to the target correction data and navigation satellite data of the terminal equipment. The technical problem that a terminal user cannot autonomously adjust an analysis strategy or a positioning algorithm due to the fact that a satellite-based enhanced positioning algorithm adopted in the related technology integrates a data analysis algorithm and a positioning algorithm is solved.

The invention relates to the technical field of industrial automation, in particular to an automatic inspection method and device in a complex environment, a storage medium and related equipment, data acquired by different sensors can be subjected to space-time synchronization to improve dynamic positioning precision, and when part of the sensors fail, a function can still be maintained through synchronized redundant data, so that the reliability of the system is improved. The robustness of the system is effectively enhanced, and the data processing delay can be reduced through space-time synchronization, so that the real-time control requirement of a dynamic scene is met; locally updating the newly acquired global map according to the static characteristics and the target attitude data, thereby reducing the calculation amount, improving the accuracy of navigation positioning, and adapting to a complex environment; the current positioning error is corrected according to the target point cloud data and the target image data, so that the positioning accuracy is further improved, and the inspection path and the control instruction are generated based on the corrected positioning result and the target map, so that the operation risk is effectively reduced while automatic inspection is realized.

The invention provides a multi-source heterogeneous sensor adaptive fusion positioning and mapping method and device, and relates to the technical field of automatic driving and mobile robots. The method comprises the following steps: for a mobile robot in an indoor environment, acquiring sensor data through a sensor data acquisition module, inputting the sensor data into a front-end data processing module to obtain processed sensor data, and inputting the processed sensor data into an environment scene recognition module to obtain an environment scene type recognition result; and inputting the result into a back-end state estimation and optimization module to obtain a map construction and pose estimation result. Through innovative front-end feature extraction, a rear-end optimization mechanism and a multi-sensor fusion strategy, the problems in the prior art are solved. By introducing a low-cost magnetometer, the robustness of the system in a GPS signal missing or complex electromagnetic environment is enhanced, meanwhile, the calculation efficiency and precision in different environments are improved through a self-adaptive optimization mechanism, and finally, high-precision and high-robustness autonomous positioning and mapping functions are achieved.

The embodiment of the invention provides a satellite navigation ranging link integrity monitoring method and device, a computer readable storage medium, an electronic device and a computer program product, and the method comprises the steps: screening out at least one first satellite meeting a preset monitoring condition from a preset satellite set according to satellite data broadcasted by a satellite-based augmentation system; calculating a first deviation of a satellite signal of the first satellite at the first site according to the satellite data; calculating a second deviation of the satellite signal of the first satellite at the first station according to the actual observation data of the first station; and determining a consistency index of the first satellite according to the first deviation and the second deviation, and determining whether the integrity of the navigation ranging link of the first satellite reaches the standard based on the consistency index. Therefore, signal anomalies are captured on different scales, limitation of a single monitoring method is avoided, monitoring precision is improved, and accurate monitoring of integrity of a satellite navigation ranging link is realized.

Methods and systems for training an end-to-end autonomous driving system in a closed-loop environment using a Visual Language Planning (VLP) machine learning model. An image associated with a vehicle surroundings is generated, and a BEV model is executed to generate a BEV view based on the image. The planning model predicts a navigation trajectory based on the BEV. The VLP model enhances the system by extracting vision-based planning features, generating text cues, and employing a language encoder to create text-based expected features. And comparing a learning model to identify the similarity between visual and text features, and enhancing the performance of the BEV and the planning model. The system experiences closed-loop evaluation in a simulated environment, obtaining metrics to improve the autonomous driving system.

This invention proposes a method for real-time pseudorange quality control in the BeiDou satellite-based augmentation system, comprising: calculating n pseudorange residuals at time t; determining whether the number of original pseudorange residuals n is greater than or equal to a preset parameter; subtracting the mean residual from the original pseudorange residual of each satellite; dividing the centered pseudorange residual of each satellite by the dual-frequency pseudorange noise; calculating the test statistic X; determining whether the test statistic X is less than the 95th quantile of the chi-square distribution with n-4 degrees of freedom; removing the satellite with the largest absolute value of the normalized pseudorange residual; completing the removal of pseudorange outliers; and obtaining the current pseudorange residual. This invention is real-time, meeting the high real-time requirements of differential integrity processing in the BeiDou satellite-based augmentation system. The embodiments of this invention can identify and remove small abnormal pseudoranges in the BeiDou interplanetary augmentation system, achieving good pseudorange quality control.

The invention provides a satellite-based ADS-B (Automatic Dependent Surveillance-Broadcast) multi-beam dynamic optimization method based on deep reinforcement learning, which is applied to a satellite receiving end and comprises the following steps: acquiring current state information in a multi-beam dynamic optimization scene; outputting a target action from a preset action space based on the current state information and a decision strategy iteratively optimized by a reward value in the last round, the preset action space being a complex increment of the beam weight matrix; adjusting the complex increment of the beam weight matrix based on the target action, and generating new state information; based on the new state information, determining a reward value under the multi-beam dynamic optimization scene of the round; and the step of obtaining the current state information in the multi-beam dynamic optimization scene is repeated until the reward value in the multi-beam dynamic optimization scene in the current round is determined based on the new state information until the decision strategy meets a preset convergence condition. According to the invention, the adaptability of the system under diversified airspace conditions can be enhanced.

The invention relates to the field of unmanned aerial vehicle data link communication, in particular to a satellite and data link communication MAC (Media Access Control) layer resource scheduling method, which adopts the technical scheme that a plurality of master devices maintain a neighbor relation through heartbeat and mutually report the number of connected slave devices and congestion conditions, and the slave devices to which the master devices belong report signal quality in real time; when the service volume of a certain master device exceeds a threshold, service negotiation with a neighbor master device is carried out, and part of slave device services are redirected to other idle master devices; real-time information sharing and signal quality feedback are realized, so that the transparency of the overall operation state of the system is improved; service volume monitoring and response are also realized, and the expandability of the system is improved, so that balanced distribution of service loads is realized; and moreover, the fault handling capacity is improved, the single-point fault risk is reduced, and the reliability and stability of the system are enhanced.

The invention discloses a multi-source data fusion implementation method for flight control, which is used for accurately navigating and controlling an aircraft, realizing high-precision navigation and control and enhancing the anti-interference capability of a system. According to the method, inertial navigation is adopted for high-precision navigation, GNSS data can be corrected, Kalman filtering is adopted for integrated navigation fusion, data chain data fusion is carried out on target object information in the middle flight stage, and visual information data fusion is carried out in the final flight stage. And finally, full-process information fusion coverage is realized.

The present application relates to the technical field of nondestructive testing, and provides a kind of dynamic characteristic eddy current detection system and method of scraper chain to solve the problems of low detection efficiency, unable to measure tension and speed synchronously, and probe is easily damaged in harsh environment and inconvenient to maintain, etc.The technical scheme of the system mainly includes: probe detection unit, adopts built-in iron core array coil layout, synchronously induces dynamic eddy current determined by chain speed and induced eddy current caused by tension change;Detection protection unit is provided with upper and lower open and close maintenance opening for quick maintenance;And detection lift-off regulation unit can accurately adjust the distance between probe and chain.The present application can realize the online synchronization, high-precision monitoring of scraper chain tension and speed, significantly improve the detection efficiency and reliability, and at the same time enhance the environmental adaptability and maintenance convenience of the system, and provide effective support for intelligent operation and maintenance of scraper conveyor.

The invention provides a suspension hovering fast part electromagnetic signal monitoring system which comprises a ground station, a suspension device assembly and an electromagnetic induction assembly, and the suspension device assembly is connected with the ground station through a composite transmission line. The suspension device assembly comprising the air bag is arranged, the electromagnetic induction assembly lifts off through buoyancy, energy consumption is reduced, the orientation correction mechanism is in a power-off and non-working state when no wind exists in the air or system coordinates do not need to be adjusted and corrected, power management is effectively carried out, and system energy consumption is reduced; the effective hang time of the system is prolonged, a suspension device cavity and an inflation and exhaust port are arranged, an air bag can be stacked in the suspension device cavity after being exhausted, the quick requirement is better met, the longitude and latitude of equipment are obtained through a positioning module, and the aerial posture of the system is adjusted based on an orientation correction mechanism; meanwhile, when the air pressure sensor detects insufficient air pressure alarm, the orientation correction mechanism can provide power to assist descending, and the safety of the system is enhanced.

The application discloses a positioning method, system, device and medium, and belongs to the technical field of satellite positioning, and the method comprises the following steps: determining a plurality of target base station sets from all first base stations of a Beidou ground-based augmentation system based on initial position information of an off-network user; determining an ionosphere correction model for observation data of all target base stations in each target base station set, and then determining initial ionosphere correction numbers; calculating the difference between each two ionosphere correction numbers, obtaining a maximum difference value, and comparing the maximum difference value with a preset threshold value; if the maximum difference value is less than or equal to the preset threshold value, fusing the initial ionosphere correction numbers to obtain a target ionosphere correction number, and sending the target ionosphere correction number to the off-network user, so that the off-network user performs positioning calculation based on the target ionosphere correction number and original observation data of the off-network user to obtain target position information, and therefore, high-precision positioning of the off-network user can be realized by implementing the application.

The application provides a multi-layer satellite network distributed routing method and system, the method comprising: dividing a low-orbit satellite set into multiple low-orbit satellite regions, each low-orbit satellite region corresponding to at least one medium-high-orbit satellite as a regional control node; multiple medium-high-orbit satellites cooperatively generating an exit selection strategy for each low-orbit satellite region and issuing the exit selection strategy to the corresponding low-orbit satellite region; low-orbit satellites in a low-orbit satellite region taking the corresponding exit selection strategy as an inter-regional forwarding constraint and performing hop-by-hop autonomous forwarding in the low-orbit satellite region; and multiple medium-high-orbit satellites updating the exit selection strategy for each low-orbit satellite region based on updated regional network state. The multi-layer satellite network distributed routing method and system of the application can reduce the frequency of cross-region path reconfiguration while retaining the real-time response capability of hop-by-hop routing, thereby enhancing the overall stability and scalability of the system.

The invention relates to a hybrid eVTOL energy optimization management and fault-tolerant control system. The hybrid eVTOL energy optimization management and fault-tolerant control system comprises a data sensing layer, an upper macroscopic decision-making layer, a lower rule implementation layer, a fault-tolerant control layer and a final actuator layer. The data sensing layer preprocesses sensor data; the upper macroscopic decision-making layer and the lower rule implementation layer are used for realizing energy optimization management based on sensor data; the fault-tolerant control layer affects the decision-making layer to realize fault-tolerant control through fault diagnosis and fault-tolerant arbitration; and finally, the control instruction is sent to the actuator layer. The system aims at achieving optimal and reliable energy control of a hybrid power system under the complex flight working condition, improving the dynamic response speed and the multi-target optimization capacity of an energy management system, enhancing the survivability of the system under key component faults and ensuring manned safety, is particularly important for manned eVTOL, and has wide application prospects.

The invention discloses a port ship traffic organization optimization and regulation and control method, which belongs to the technical field of waterway traffic optimization and intelligent management and control, and comprises the following steps: collecting port data, constructing an information physical system framework, and dynamically managing a port by using the port data through the information physical system framework. The method comprises the following steps of: extracting and quantizing, performing uniform feature fusion, obtaining a judgment result by utilizing an event triggering mechanism, updating a system state, predicting the updated system state by utilizing a model prediction control algorithm to obtain a system step length, predicting the system step length in real time by utilizing a self-adaptive vision field mechanism to obtain a real-time step length, and calculating the real-time step length according to the real-time step length. And solving by utilizing a multiplier alternating direction method according to the judgment result and the real-time step length to obtain a port ship traffic scheduling control strategy. According to the invention, high-efficiency ship traffic scheduling and resource optimization can be realized in a complex and changeable port environment, the port transportation efficiency is obviously improved, traffic congestion is reduced, and the self-adaptive capability of the system is enhanced.

The present application relates to the field of power system testing, and more particularly to a method and system for testing a backup power automatic switching device under simulated power system operating conditions. The method comprises the following steps: S1: collecting operating parameter data of the backup power automatic switching device in a high-altitude, low-pressure environment through a data acquisition system, and performing strict data cleaning, feature extraction and standardization processing using a Z-score method; the operating parameter data is divided into key feature data and auxiliary feature data; the key feature data specifically refers to parameters directly related to lubricating oil viscosity changes causing faults. The present application accurately models lubricating oil viscosity changes in a high-altitude, low-pressure environment through comprehensive data acquisition and preprocessing, constructs a multi-layer simulation test model, optimizes data selection and dynamic adjustment mechanisms, significantly improves the performance evaluation and fault prediction capabilities of the backup power automatic switching device, reduces fault risks, ensures the safe and stable operation of the power system, and enhances system reliability.

Systems, methods, and devices for quantization parameter signaling for rank augmentation in wireless communications are described. According to an aspect of the present disclosure, a method performed by a user equipment (UE) comprises: receiving, from a network unit, a first control communication; transmitting, to a wireless communication device, a second control communication indicating one or more quantization parameters, wherein the one or more quantization parameters are based on the first control communication; receiving, from the network unit, a downlink data communication; and receiving, from the wireless communication device, a quantized downlink data communication, wherein the quantized downlink data communication is based on the one or more quantization parameters and the downlink data communication.

The invention relates to the technical field of computer vision and robots, and provides an integrated navigation method and system based on heterogeneous feature data association, and the method comprises the following steps: preprocessing visual sensor data to obtain a camera inter-frame rotation variation and a camera inter-frame translation variation; the method comprises the steps of preprocessing observation data to obtain acceleration variation and angular velocity variation, calculating a motion scale factor according to rotation variation and translation variation between frames of a camera, constructing motion constraints according to the motion scale factor, the acceleration variation and the angular velocity variation, and optimizing a key frame selection mechanism according to the motion constraints. And constructing a bimodal tight coupling objective function according to the key frame, and performing nonlinear optimization on the bimodal tight coupling objective function to obtain an optimized camera pose and map point. According to the method, the coverage capability of robust features is remarkably improved, the adaptability and stability of the system in a complex environment are enhanced, and accurate estimation of key state variables is realized.

This application provides a fire lane occupancy identification system and method using laser and radar collaboration, relating to the field of laser radar technology. The system includes: a point cloud generation module, used to emit laser beams to the target area using a solid-state laser radar, receive reflected signals, extract time difference and phase difference, convert them into polar coordinate data, and generate a point cloud dataset; a 3D spatial model construction module, used to perform point cloud filtering, clustering, and 3D reconstruction based on the point cloud dataset to construct a 3D spatial model of the target area; and an occupancy decision module, used to calculate the space occupancy rate based on the 3D spatial model, and when the detected space occupancy rate exceeds a preset dynamic threshold, to perform adaptive occupancy decision and push alarm information. This application can solve the technical problem of low occupancy detection accuracy in existing technologies, achieving the technical effects of improving detection stability, reducing false alarm rate, and enhancing system adaptability and linkage response capabilities.

This invention discloses a method and system for optimizing the aeroacoustic performance of a cooling fan system, relating to the field of data processing technology. The method includes: real-time acquisition of multi-dimensional dynamic data during the operation of the cooling fan system; construction of aerodynamic state feature vectors and identification of flow topology states; establishment of a mapping relationship between flow topology units and sound source contributions; calculation of sound source contribution weights to extract dominant sound source types; analysis of their aerodynamic excitation spectrum distribution characteristics; calculation of spectral coupling risk values ​​using acoustic modal risk channels; and finally, output of an optimized speed control strategy. This invention solves the technical problems of existing technologies, such as difficulty in adapting to complex dynamic conditions, inability to accurately identify and quantify multi-source aerodynamic noise sources in real time, and lack of dynamic monitoring of multi-physics field coupling resonance risks. It achieves the technical effects of improving the adaptive optimization capability of the fan system's aeroacoustic performance under dynamic operating conditions, significantly reducing broadband and discrete noise, and enhancing system operational reliability.

The invention relates generally to the radio navigation field and may be applied to design of Global Navigation Satellite System (GNSS) Receivers, and particularly of GNSS GPS (USA), Galileo (EU), Glonass (Russia), Beidou (China), QZSS (Japan), IRNSS (India), and augmentation systems SBAS (different states). In the invention, the function of generating various PRN codes is repositioned from numerous tracking channels of multi-frequency, multi-constellation GNSS receiver to a shared PRN code generator unit, which serves in series all tracking channels. Such centralization of the PRN codes generation function enables a significant complexity reduction when the GNSS receiver includes a great number of tracking channels. A sufficient speed performance of the shared PRN code generator is achieved due to transfer of the PRN code lines from the shared PRN code generator to the receiver tracking channels via a dedicated parallel bus. Speed performance requirements to the dedicated parallel bus of the shared PRN code generator is kept moderate by a special number of symbols choice of PRN code lines thus providing uniformity of tracking channels requests to get new code lines. Use of several alternate means of PRN code lines forming: PRN Code ROM, PRN Code RAM, LFSR-based and one-shot PRN code generators—permits choosing optimal generation means for each type of GNSS signals.

The invention provides a service message abnormity monitoring method and system based on a satellite-based augmentation system, and belongs to the field of satellite navigation and satellite-based augmentation. The method comprises the following steps: firstly, acquiring an enhanced message generated by a master control station based on observation station observation data calculation, and performing static inspection on the enhanced message; if the static check is passed, uploading an enhanced message; receiving the broadcasted enhanced telegraph text, sequentially comparing the satellite-ground consistency in real time, performing observation quality evaluation based on the O-C residual error to verify the enhancement effectiveness of the enhanced telegraph text, and performing PPP integrity test based on the monitoring station; if the test is passed, the service message is normal; and if the static check is not passed and static abnormity exists, or satellite-ground consistency comparison abnormity exists, or O-C residual verification is not passed, or positioning check is not passed and monitoring station PPP positioning abnormity is determined, fault association and positioning are carried out according to a determination result by constructing a rule base or an algorithm model. According to the invention, the abnormal monitoring capability of the telegraph text is enhanced.

The invention provides an air-sea cross-domain communication gateway energy optimization management system and method in a coupling environment, a closed-loop control mechanism is constructed by fusing data noise reduction of extended Kalman filtering and particle filtering and an LSTM power prediction and reinforcement learning scheduling algorithm, and fine regulation and control of whole sea conditions are realized by combining a multi-mode power supply network. Compared with a traditional static strategy, the energy use time is effectively prolonged; the environmental state judgment accuracy is improved through a nonlinear motion model and a trend prediction mechanism, a transition scene regulation blank is effectively filled up through a medium sea condition mode, the mode switching time delay is lower, and the adaptive capacity of the system to a complex and changeable marine environment is remarkably enhanced; through a surge suppression circuit, redundant power supply design and a hybrid communication link scheduling strategy, the success rate of coping with power supply fluctuation and hardware faults, the communication link switching accuracy and the cross-domain data transmission success rate of the system are all improved, and meanwhile the system has wide applicability and can be expanded to various mobile platforms such as unmanned aerial vehicles and unmanned ships.

A deep learning-based real-time maritime low-light video enhancement system belongs to the field of maritime image processing and ship-aided navigation technology. The system includes: a video acquisition module for real-time acquisition of sea surface video images; an edge computing enhancement module electrically connected to the video acquisition module, which has a built-in pre-trained deep learning image enhancement model for real-time enhancement processing of the video images; a display module electrically connected to the edge computing enhancement module for real-time display of the enhanced video images; and a power supply module to power all modules. This invention can enhance sea surface video in real-time under low-light conditions such as nighttime and foggy weather, clearly presenting wave details, assisting crew members in judging wind speed, and features high system integration, strong real-time performance, and convenient operation.