214results about How to "Increase autonomy" patented technology

The invention provides a robot alarm processing method and system based on a target detection algorithm and a cloud platform, and relates to the technical field of robot alarm processing, and the method comprises the steps: carrying out the detection of an abnormal target based on a convolutional neural network target detection model of the cloud platform in combination with a residual structure, a channel attention mechanism and an improved anchor-frame-free target detection algorithm, performing feature fusion through a feature fusion network guided by depth information to obtain accurate three-dimensional representation data, constructing a dynamic anomaly association graph by using an improved time sequence graph neural network, and generating a multi-level decision sequence in combination with an improved hierarchical reinforcement learning algorithm, and finally, collaborative task planning is carried out through a task decomposition network to obtain a task allocation scheme, and the robot carries out exception handling according to the optimal motion track, obstacle avoidance track data, real-time pose data, key operation sequence data and contact force feedback data.

The invention discloses an unmanned aerial vehicle group cooperative inspection control method for power station inspection, and the method comprises the steps: determining an unmanned aerial vehicle group according to a power station inspection task; performing task allocation of the heterogeneous unmanned aerial vehicle cluster by using a multi-objective optimization algorithm; performing unmanned aerial vehicle path planning by adopting an improved dynamic multi-population particle swarm algorithm; based on a graph theory and master-slave control, unmanned aerial vehicle group attitude consistency control is realized; integrating a target detection technology based on deep learning, and constructing an inspection anomaly detection model; performing remote fault diagnosis analysis on the real-time inspection data through an inspection anomaly detection model to obtain an inspection anomaly result; optimizing the inspection anomaly detection model according to the target condition of the real-time inspection data; and dynamically controlling task allocation and path planning of the unmanned aerial vehicle group according to an abnormal inspection result. Through the scheme, potential problems can be found and processed in time, the intelligent control level of power station inspection is improved, and the efficiency and accuracy of unmanned aerial vehicle group cooperative inspection are improved.

The invention discloses an on-satellite full-autonomous task planning system for an agile remote sensing satellite. Comprising an imaging target database module, a high-precision orbit prediction and orbit calculation module, a target visible arc section calculation module, an imaging task preprocessing module, a subsystem constraint model module, an imaging task planning module, a data transmission task planning module, a solid memory autonomous erasing module, an instruction data block generation module and a satellite state real-time monitoring module. By carrying out constraint modeling on subsystems or single machines such as load, data transmission, control and the like, an on-satellite full-autonomous operation process from receiving of subsystem or single machine instruction blocks from user requirements is established, satellite control is effectively simplified, and remote control uploading efficiency and on-satellite autonomous operation capacity are improved. And through a satellite state real-time monitoring module, the execution condition of tasks on the satellite, satellite state changes and the like are monitored in real time, task execution stopping, whole satellite sun-facing or re-planning are further triggered, task requirements and environment changes are quickly responded, task plans are formulated and adjusted in real time, and the task execution efficiency is improved.

The invention provides a construction method, a control method and a system of a flight control network, and the method comprises the steps: employing a depth deterministic strategy gradient algorithm, building an attitude control network of an unmanned aerial vehicle in a flight process based on the state information and a target flight value of the unmanned aerial vehicle in the flight process, employing a depth reinforcement learning algorithm, and carrying out the attitude control of the unmanned aerial vehicle in the flight process. Based on the state information and the information of the environment where the unmanned aerial vehicle is located, a path planning network and an intelligent avoidance network of the unmanned aerial vehicle in the flight process are built respectively; based on the attitude control network, the path planning network and the intelligent avoidance network, constructing a hierarchical deep reinforcement learning network of the unmanned aerial vehicle in the flight process; and training the hierarchical deep reinforcement learning network by adopting historical flight data of the unmanned aerial vehicle in different flight environments and a preset flight reward mechanism to obtain a flight control network of the unmanned aerial vehicle. According to the invention, the adaptability and flexibility of the unmanned aerial vehicle in the flight process can be improved.

The invention provides an unknown environment adaptive navigation control system based on deep learning, and aims to improve the autonomous navigation capability of a machine in a complex and unknown environment. According to the system, an advanced sensing module is adopted, multi-sensor data are combined, and a dynamic environment is quickly and accurately sensed through a deep learning algorithm. The online environment modeling mechanism can update the environment information in real time without depending on a pre-constructed map. And by utilizing a reinforcement learning algorithm, the system can autonomously learn and optimize path planning, and meanwhile, energy consumption, time efficiency and safety are considered. An innovative multi-mode obstacle avoidance strategy is adopted, and obstacle avoidance behaviors are dynamically adjusted according to environment complexity and machine states. The intelligent decision support system combines a decision tree and fuzzy logic, and provides fast and accurate decision ability. The adaptive motion control algorithm optimizes path tracking performance and adapts to dynamic characteristics and environmental conditions of a machine. In addition, the collaborative job mechanism supports efficient communication and task collaboration in a multi-machine system.

The invention discloses a liquid fertilizer application effect analysis method based on self-supervised learning. The method comprises the following steps: S1, generating initial feature data; s2, environment feature representation is generated based on a heterogeneous environment self-adaption module; s3, extracting short-term and long-term spatio-temporal characteristics of the liquid fertilizer application effect based on the dual spatio-temporal characteristic decoupling and dynamic fusion model, and generating comprehensive spatio-temporal characteristic representation; s4, generating fertilization characteristics in different situations by utilizing self-supervised learning, and eliminating environmental interference factors through a causal reasoning module; s5, generating a fertilization intention feature, and dynamically adjusting a fertilization strategy; s6, when the difference between the prediction result and the actual effect exceeds a threshold value, triggering a re-learning module to update model parameters; and S7, carrying out integrated optimization, realizing feature sharing and task coordination through multi-task collaborative learning, and carrying out automatic tuning by utilizing Bayesian optimization. The intelligent analysis of the liquid fertilizer application effect is realized through the self-supervised learning and multi-task collaborative optimization method.

The invention discloses a multi-agent cooperative control system based on multi-mode brain-computer interface-visual tracking, and the system comprises the following modules: a signal collection and processing module which employs an 8-lead electroencephalogram cap to collect electroencephalogram original data, selects occipital region parts (PO7, PO8, P3, P4, Pz, O1, O2 and Oz) as an electroencephalogram data collection region, and carries out the EEG data collection; the feature extraction and classification module is used for extracting SSVEP signal features by using a space-time convolutional network, optimizing classification precision in combination with an integrated learning strategy, extracting EOG signals based on a Transform model, integrating an LMS adaptive filter and denoising the EEG signals in combination with wavelet transform, expanding the frequency tracking range of the adaptive filter, and reducing signal loss to the greatest extent; the cooperative control strategy design module is used for mapping the electroencephalogram signals into control instructions of different intelligent agents, and cooperative control over the unmanned aerial vehicle and the trolley is achieved; and the target detection and tracking module is used for optimizing an unmanned aerial vehicle visual tracking system based on a PP-YOLOE model and realizing accurate tracking and automatic adjustment of the trolley.

The invention discloses a reinforcement learning automatic driving method and system based on man-machine cooperation, and belongs to the technical field of automatic driving. The method includes: acquiring a current state of the autonomous vehicle; inputting the current state of the automatic driving vehicle into the trained automatic driving network for processing so as to obtain a decision-making action of the automatic driving vehicle at the current moment; a reward-free strategy learning method is introduced, and an automatic driving network is trained through an explicit intervention mechanism and an implicit intervention mechanism by taking human takeover cost minimization and action distribution entropy and stability maximization as targets. An explicit and implicit intervention value function is designed, and an intelligent agent is trained to drive in an invisible traffic scene with minimum human takeover cost and comfort maximization as targets; the strategy optimization problem of an automatic driving automobile in a complex dynamic traffic environment is solved.

The invention provides a multi-robot cooperative control method and system based on edge computing, and relates to the technical field of multi-robot control, and the method comprises the steps: dividing a search and rescue region into a plurality of sub-regions, generating a sub-region search and rescue task, and carrying out the search and rescue of the sub-regions according to the sub-region search and rescue task and the capability parameters and current states of ground robots. An optimal matching scheme of ground robots and sub-region search and rescue tasks is generated, different search and rescue strategies are adopted for different types of ground robots, and a heterogeneous robot cooperative search and rescue strategy is generated by defining formalized languages and lexical methods for cooperative control of the ground robots; each ground robot executes a search and rescue task in the corresponding sub-region according to the heterogeneous robot cooperative search and rescue strategy, when it is detected that the resource use condition or the network condition meets the preset condition, a calculation unloading decision is started, part of the search and rescue tasks are unloaded to other calculation nodes according to the decision result, and the search and rescue action continues to be executed. And the search and rescue task is completed.

The invention discloses an unmanned loading vehicle autonomous loading and unloading method suitable for mining area bulk cargo transfer, and relates to the technical field of mining unmanned loading and unloading and transportation control, and the method comprises the following steps: S1, carrying out function division on an open-air mining area to obtain a corresponding bulk cargo stacking area, an unmanned loading vehicle waiting area and a truck waiting area; and S2, an autonomous loading and unloading system is integrated on the unmanned loading vehicle, mining area environment information is obtained through the autonomous loading and unloading system, a global map of an operation area is constructed, an operation path is planned, loading and unloading operation is completed, and in the autonomous loading and unloading system, a loading and unloading operation logic module serves as a main process. According to the unmanned loading vehicle autonomous loading and unloading method suitable for mining area bulk cargo transfer, all scenes in the mining area bulk cargo loading and unloading process are independently achieved through the unmanned loading vehicle, that is, the unmanned loading vehicle can accurately construct an operation environment map through an advanced sensor and an intelligent algorithm, and efficient autonomous loading and unloading are achieved.

The invention discloses a satellite navigation decoy detection method based on inertial navigation, and the method comprises the steps: carrying out the validity verification of received satellite navigation data before the alignment of equipment is not completed; once the data is valid, the equipment enters a combined navigation state, and in the state, the judgment threshold values of the satellite navigation position and speed are dynamically set by utilizing the characteristic that inertial navigation errors diverge along with time; position and speed information provided by satellite navigation and inertial navigation is compared in real time, and if the difference value of the two exceeds a preset dynamic threshold value, it is judged that the satellite navigation information may be decoy; once decoy is detected, the device exits the integrated navigation state; according to the invention, satellite navigation decoy detection is realized through a software algorithm, navigation data can be judged and processed autonomously and accurately in a complex and severe navigation environment, and navigation errors caused by signal decoy are prevented.

The invention relates to the technical field of flight control, in particular to a low-altitude traffic control method and system for an aircraft. The control method comprises the steps that a wireless communication network is built, data exchange between the aircrafts is ensured through a multi-layer topological structure and a dynamic spectrum management technology, and the wireless communication network adopts a channel evaluation mechanism to adapt to a changeable airspace environment and ensure stable high-bandwidth connection. According to the invention, a wireless communication network is established and a multi-level topological structure and a dynamic spectrum management technology are adopted, so that the problem of communication delay caused by dependence on ground infrastructure in a traditional system is solved. Through a channel evaluation mechanism, the network can adapt to a changeable airspace environment, stable and reliable data transmission between aircrafts is ensured, and the realization of high-bandwidth connection provides a solid guarantee for real-time monitoring and dynamic decision making.

The invention discloses a control system for a cooling fan, and relates to the technical field of cooling fan control systems. The temperature acquisition module is used for monitoring the temperature of a key heating part in real time by adopting a high-precision temperature sensor and converting an analog signal into a digital signal through a data acquisition card; the data processing module is used for receiving the data from the temperature acquisition module and analyzing the data by using an embedded processor; a self-adaptive filtering algorithm is built in the module so as to reduce the influence of environmental noise on temperature reading; and the core of the control algorithm module is a PID (Proportion Integration Differentiation) controller, and a hybrid control strategy is formed by combining fuzzy logic control. Through accurate temperature monitoring and an intelligent control algorithm, the system can quickly respond to temperature change, automatically adjust the rotating speed of the fan, realize efficient heat dissipation and prolong the service life of equipment; the system adopts a variable-frequency speed regulation technology, the operation of the fan is adjusted according to actual requirements, unnecessary energy consumption is avoided, and the energy-saving effect is achieved.

The invention discloses a terrain-combined weather radar base data dynamic resolution three-dimensional structure reconstruction method, which realizes three-dimensional structure reconstruction through combination of a digital elevation model (DEM) and weather radar base data. The method comprises the steps of cutting DEM topographic data and dumping the DEM topographic data into grid data in a binary form, generating a bitmap as a mapping source, establishing an elevation angle index array based on weather radar base data, establishing an azimuth angle index array based on a conical scanning surface so as to quickly map an angle, determining a rectangular reconstruction area and establishing a three-dimensional grid, traversing the three-dimensional grid to obtain an elevation angle, an azimuth angle and a distance combination array of grid points so as to obtain grid point data, smoothing the grid point data, re-sampling terrain grid data, constructing a terrain grid surface, obtaining a mapping image of the terrain grid surface, and rendering a three-dimensional body; the method has the advantages that the method does not need to depend on online service, and dynamic high-precision three-dimensional structure reconstruction of radar echoes in a specified area can be realized while the interaction performance is ensured.

The invention discloses a power inspection unmanned aerial vehicle vision / inertia robust positioning method based on temperature compensation, and the method comprises the steps: firstly constructing an IMU temperature online compensation network, and introducing a Teaching Forcing mechanism to improve the learning capability of the network; then, an IMU error model is constructed, an LSTM-based unmanned aerial vehicle IMU zero offset temperature online compensation network is trained through IMU measurement information subjected to offline calibration compensation, the temperature, the temperature change rate and zero offset true values of a gyroscope and an accelerometer, and network parameters of an unmanned aerial vehicle temperature model are obtained; in the operation process of the unmanned aerial vehicle, trained parameters are called, online compensation is carried out on the zero offset of the gyroscope and the accelerometer corresponding to IMU measurement at each moment, and the problem that the zero offset error of the unmanned aerial vehicle becomes large due to high-frequency vibration and temperature change in the field inspection process is solved; and finally, designing a self-adaptive visual factor, performing joint estimation by using IMU measurement after zero offset compensation and a visual residual error, and resolving to obtain optimized positioning information.

The invention provides a deep reinforcement learning air combat decision-making method based on situation prediction, belongs to the technical field, and solves the technical problem that an unmanned aerial vehicle cannot realize autonomous decision-making and environment self-adaption in a complex air combat environment. According to the technical scheme, modeling is carried out through kinematics and dynamics characteristics of the unmanned aerial vehicle to adapt to the actual flight state; establishing a deep enhanced confrontation environment for unmanned aerial vehicle confrontation training; dynamically evaluating the state of the enemy unmanned aerial vehicle by using an LSTM prediction algorithm, and quickly obtaining the state of the enemy unmanned aerial vehicle at the next moment; and taking reward distribution as input of a decision maker, and inferring enemy unmanned aerial vehicle situation actions in combination with a prediction state and a reward result to realize tracking strike. According to the method, the advantage of machine intelligent calculation and human experience judgment are combined, the intention recognition accuracy of the enemy unmanned aerial vehicle is improved in a complex and uncertain environment, and the decision-making ability and tactical advantages of our unmanned aerial vehicle are enhanced.

The invention discloses a sewage treatment system based on crowd sensing, and relates to the technical field of pollution prediction.A pollution prediction module is based on a two-dimensional instantaneous pollution source diffusion model and combines sensor point location information provided by a sensor screening module and water depth influence data provided by a water depth measurement and calculation module; the dynamic simulation and prediction module is used for carrying out dynamic simulation and prediction on pollutant diffusion, calculating a water pollutant concentration prediction value of each selected sensor point location, and sending the pollutant concentration prediction value to the feedback determination module; correcting the position of the pollution source according to the deviation by using an inversion algorithm, specifically, continuously correcting the predicted pollution data value again by adjusting the position data of the pollution source and changing the values of x, y and b, and comparing the predicted pollution data value with an actual measurement value until an error requirement is met; therefore, the prediction precision of the pollution condition of the position, which is not covered by the sensor, of the monitoring area can be ensured by continuously calibrating the prediction value and the actual measurement value.

The invention provides a mechanical arm reward-free reinforcement learning method based on expert state learning, belongs to the technical field of automation, particularly focuses on operation control of a robot arm, and comprises two core modules: an expected state prediction network and a reward-free strategy network. The expected state prediction network is used for predicting state transition, and the non-reward strategy network optimizes action through an error between a prediction state of the expected state prediction network and a target state provided by an expert under the condition of no reward signal; according to the method, the mechanical arm can directly learn an effective grabbing strategy from state data observed by experts, complex reward function design is avoided, dependence on expert action data is not needed, and therefore understanding of dynamic characteristics of grabbing tasks is improved, and accuracy of action prediction is enhanced.

The invention relates to the technical field of visual robots, and discloses a visual navigation mobile robot under a GPS signal denial condition, the visual navigation mobile robot comprises a robot body, the top of the robot body is fixedly connected with a control box body; by integrating a visual navigation system and an intelligent path planning algorithm, the navigation problem of the mobile robot under a GPS signal denial condition is solved, so that the robot has higher autonomy and adaptability, and accurate positioning and navigation can be realized in a complex environment; meanwhile, the cleaning brush is used for cleaning the wheel body, sundries and the like which are attached to the surface of the wheel body and affect advancing of the robot body are reduced, the transmission fan is used for generating wind power, the ventilation effect in the robot body is improved, and dust on the surfaces of the heat dissipation holes can be cleaned through the dust removal brush which continuously moves; the situation that dust is attached to the surfaces of the heat dissipation holes to affect air circulation in the robot body and consequently temperature rise is caused is reduced, and the stability of a circuit in the robot body is improved.

The invention discloses an unmanned aerial vehicle flight path control method based on cloud computing, and relates to the technical field of data analysis, and the method comprises the steps: carrying out the same-type task historical data calling of a current target location and task data through a database, and carrying out the path pre-planning of a current unmanned aerial vehicle flight task; performing real-time evaluation on the flight environment data through an unmanned aerial vehicle real-time environment monitoring system, and performing adjustment judgment on a pre-planned flight path based on the evaluation data; based on a pre-planned flight trajectory judgment result, performing associated space safety distribution point analysis on trajectory points with adjustment requirements, and constructing a corresponding safety distribution point set based on analysis data; comprehensive safety performance evaluation is carried out on each space safety distribution point in the set, and a pre-planned flight path is adjusted according to an evaluation result; and feeding back the real-time flight data of the unmanned aerial vehicle by a monitoring end, synchronously displaying a real-time track adjustment record, and feeding back a track adjustment command to the unmanned aerial vehicle.

The invention discloses an auxiliary device for armless disabled people, and relates to the technical field of brain-computer interfaces. In order to solve the problems that in the prior art, an invasive type and a semi-invasive type of existing wearable auxiliary devices for providing life assistance for people with upper limb disability need surgical operation, electrodes are implanted into the cerebral cortex, but the surgical risk is large, complications such as infection and bleeding are possibly caused, and long-term maintenance is needed after implantation; in order to solve the technical problems that a non-invasive interbrain interface is relatively small in risk, convenient to use, simple to operate, low in cost and relatively low in control precision, the technical scheme provided by the invention is as follows: the auxiliary system for the armless disabled person comprises a brain signal acquisition module for acquiring an electroencephalogram signal of a user in a non-invasive manner; the visual control module is used for collecting target object positioning information; and the main control module is used for generating grabbing action group signals according to the signals acquired by the brain signal acquisition module and the visual control module. The auxiliary grabbing device is suitable for being applied to auxiliary grabbing work of the arm-free handicapped.

The invention discloses an intelligent elevator maintenance method, device, equipment and system based on artificial intelligence. The elevator DTU terminal collects information, uploads the information to the intelligent maintenance system and pushes the information to the elevator large model, the diagnosis model polls and positions an elevator and a project needing to be maintained according to data, the task model determiner generates a task and instructs the automatic programming model to generate a plug-in, and the maintenance personnel completes maintenance and uploads data according to the prompt of the mobile phone client. And cases are generated after evaluation and scoring of the effect evaluation model and stored in the maintenance case model, and if the cases are qualified, the elevator health degree is reset. According to the system, self-developed key technologies such as automatic programming and elevator large model building are utilized, intelligent maintenance and knowledge sharing are achieved, maintenance quality and standard unification are improved, many defects of a traditional elevator maintenance mode are effectively overcome, elevator maintenance efficiency, quality and safety are improved, reliable operation of an elevator is guaranteed, and intelligent development of the elevator maintenance industry is promoted.

The invention provides a control method of a multi-mode robot. The method comprises the following steps: acquiring home environment data and personnel data of an area where the multi-mode robot is located; according to the home environment data and the personnel data, whether a target home task exists or not is determined, and the target home task is at least one of home tasks preset by the multi-mode robot; if it is determined that the target home task exists, determining a target mode of the multi-mode robot based on the target home task; and controlling the multi-mode robot to be switched to the target mode, so that the multi-mode robot executes the target home task in the target mode. Whether the target home task exists or not is determined by acquiring the home environment data and the personnel data of the located area, and the corresponding target home task is executed in the corresponding target mode under the condition that the target home task exists, so that a user does not need to input the corresponding task in advance, and the user experience is improved. And the autonomous ability and practicability of the multi-mode robot in the home environment are improved.

The invention relates to the technical field of precision and ultra-precision machining, and provides a hydrostatic pressure guide rail device which comprises a guide rail and a sliding block which are in sliding connection. A sliding block body oil inlet channel and a sliding block body oil return channel are arranged in the sliding block; the sliding block comprises a sliding block body and a pair of bearing strips, an opening groove is formed in the bottom end of the sliding block body, the guide rail and the pair of bearing strips are located in the opening groove, one side of each bearing strip is fixedly connected with the sliding block body, and the other side of each bearing strip is slidably connected with the guide rail; the combination faces of the sliding block body, the bearing strip and the guide rail are matched, and a gap between the bearing strip and the guide rail forms an oil film bearing area. After the sliding block is designed in a split mode, the sliding block body plays a role in installation, the bearing strips play roles in static pressure supporting and oil film gap adjustment, the difficulty in manufacturing, measuring, assembling and adjusting the static pressure sliding block is lowered, the sliding block bodies with different opening sizes and the bearing strips with different thicknesses can be freely arranged, and therefore the static pressure sliding block can be conveniently assembled and disassembled. The precise adjustment of the oil film gaps is realized, and the consistency of the oil film gaps between the sliding blocks is ensured.

The invention belongs to the technical field of spaceflight launching, and particularly relates to a primary and secondary satellite in-orbit maneuvering control method and device and a storage medium. The control method comprises the following steps: step 1, controlling a primary satellite and a secondary satellite to enter an orbit; 2, acquiring task requirements in real time, and calculating to obtain an on-orbit maneuvering strategy of the child satellites based on an autonomous maneuvering control algorithm; 3, potential attack and defense threats are analyzed, and the possible influence on in-orbit maneuver control is evaluated; key defense measures of the child satellite and the mother satellite in the maneuvering process are determined, and a coping strategy is formulated; and 4, establishing a real-time monitoring system, continuously collecting state information, orbit data and potential threat information of the child satellites, and adjusting a maneuvering control strategy according to the state information, the orbit data and the potential threat information of the child satellites. According to the method, the operation flexibility and the task response speed in a complex environment are improved.

The invention discloses a voice-driven virtual scene generation and switching method and an implementation system, which are applied to meta universe VR (virtual reality) glasses equipment, and comprise the steps of recognizing an instruction of a user through voice recognition and natural language processing technologies, generating or switching a virtual scene in real time, and realizing personalized scene creation and object generation. The edge computing node is adopted to process a high-calculation-amount task, the delay of scene generation and switching is remarkably reduced, the data transmission efficiency is improved by dynamically selecting the optimal node, the privacy security of a user is guaranteed, and through frame rate smooth adjustment and a scene fade-out mechanism, the experience of the user for exiting the virtual scene is optimized, the dizziness is reduced, and the user experience is improved. And the interaction fluency and comfort are improved. The method has the characteristics of quick response, convenient operation and strong privacy protection, and is widely applied to the virtual reality application fields of games, education, medical treatment and the like.

The invention discloses an object tracking method, a mobile intelligent device, a medium and a product, and relates to the mobile intelligent device. The method comprises the following steps: when a user object walks in a target area, receiving an area sound signal collected by the acoustic sensor; extracting a target foot sound signal of the user object from the area sound signal; determining relative position information and walking speed of the user object according to the target footstep sound signal; and controlling the moving direction and the moving speed of the mobile device to be matched with the user object according to the relative position information and the walking speed so as to track the display device. The footstep sound signals of the user are accurately captured and tracked through the acoustic sensor, real-time monitoring of user actions and automatic following of the mobile device are achieved, and interactivity and user experience of the device anytime and anywhere are enhanced.

The invention relates to the technical field of sea surface target multi-mode fusion recognition system design, in particular to a multi-mode fusion sea surface target recognition system for a high-dynamic unmanned platform. The system is characterized by comprising a platform sensor subsystem, a multi-mode characteristic processing and identification subsystem, an information transmission control subsystem and a far-end display control subsystem, the system is combined with a corresponding sea surface target image feature extraction technology, an active and passive radar signal feature extraction technology and a sea surface target identification technology of a multimode heterogeneous feature fusion multi-core classifier, so that an efficient fusion identification system of four modal data of an optical image, an SAR image, an active radar signal and a passive radar signal is realized; according to the method, the high-dynamic unmanned system can autonomously judge the type of the sea surface slow-moving target, the multi-mode feature fusion utilization efficiency is enhanced, the target recognition precision and robustness are improved, and the autonomy and intelligence level of the high-dynamic unmanned system is improved.

The invention discloses a satellite autonomous task planning method and system based on a ground digital mirror image, and belongs to the technical field of spacecraft measurement and control. Through the states of a satellite-ground link synchronous satellite and a ground digital mirror image, a task request is received in the ground digital mirror image, a planning algorithm is operated, a candidate scheme is generated for high-fidelity simulation deduction and verification, a feasible scheme is evaluated and selected and converted into an instruction sequence to be uploaded to a satellite, the satellite executes an instruction and feeds back the state, and a closed loop is formed. According to the method, a complex planning and verification process is placed in a ground digital mirror image, the efficiency and reliability of task planning are remarkably improved by using the strong computing power of the ground, meanwhile, the autonomous operation capability of a satellite is improved, and the problems that traditional satellite task planning is slow in response and poor in reliability, and the autonomous planning capability of a pure satellite is weak can be solved.

The invention discloses a space-based / space-based graph multi-level off-road network extraction system and method. The system comprises an image acquisition module for acquiring a target image; the semantic extraction module performs attachment coefficient semantic classification and road network extraction on the target image to obtain an attachment coefficient classification graph and a semantic road network graph, and different attachment coefficients represent different earth surface types; the morphological processing module generates a topological structure diagram of the target image by using a morphological method; and the result output module outputs a semantic road network diagram, a topological structure diagram and an attachment coefficient classification diagram. The invention relates to the field of artificial intelligence, and utilizes the advantages of strong interactivity and strong data fitting ability of a generative deep network to realize efficient automatic extraction of an off-road network in an unknown environment and improve the extraction precision, and the hierarchical road network can reduce the problems of discontinuous global reference road network and traffic limitation caused by shielding and identification errors, thereby improving the accuracy of the off-road network extraction. Passing guiding information is provided for local planning, and the autonomous ability under the complex terrain is improved.