326 results about "Drone flies" patented technology

The invention provides an unmanned aerial vehicle path planning method and system and a storage medium, and the method comprises the steps: constructing a three-dimensional path planning model of an unmanned aerial vehicle in a target flight region; solving the three-dimensional path planning model by using an improved artificial bee colony algorithm, obtaining the optimal flight path of the unmanned aerial vehicle under each target function, and summarizing the optimal flight path into a Pareto optimal solution set; constructing a plurality of decision intelligent agents in one-to-one correspondence with the plurality of objective functions, performing multi-dimensional scoring under different objective functions on each flight path in the Pareto optimal solution set by using the plurality of decision intelligent agents, obtaining a comprehensive score of each flight path, and determining a global optimal unmanned aerial vehicle flight path based on the comprehensive score; according to the method, through refined multi-dimensional constraint modeling, an improved multi-target artificial bee colony algorithm and multi-agent collaborative decision based on a near-end strategy optimization algorithm, full-process optimization from path generation to intelligent decision is realized.

The invention discloses a multi-rotor unmanned aerial vehicle broken propeller fault rapid diagnosis and fault-tolerant stable control system and method, belongs to the technical field of unmanned aerial vehicle flight control, and aims to solve the problems that traditional broken propeller detection is high in cost and unreliable, power compensation robustness is insufficient and return flight logic is lacked. According to the system and the method, on the basis of a high-order nonlinear observation theory, rapid and accurate identification of the abnormal state of the unmanned aerial vehicle power system is realized by constructing a multi-modal signal prediction and residual evaluation system; the method effectively prevents the out-of-control, rolling and even crash of the unmanned aerial vehicle caused by power asymmetry, solves the problem that a traditional fixed control strategy is difficult to adapt to fault working conditions, and adapts to dynamic changes under complex working conditions such as hovering and cruising. Finally, closed-loop control from fault detection to safe return can be realized, the autonomous safe return capability of the unmanned aerial vehicle under the condition of the fault of the propulsion system is ensured, and the method is suitable for unmanned aerial vehicle application scenes with high reliability requirements, such as logistics transportation and inspection monitoring.

The invention discloses a warehouse goods accurate inventory method based on RFID and unmanned aerial vehicle cooperation, and the method comprises the steps: S1, pasting an RFID tag on a warehouse-in goods, binding the warehouse-in goods, and putting the warehouse-in goods on a shelf, and storing the goods inventory information in a warehouse management system; s2, establishing a three-dimensional model and a space coordinate system of the warehouse, wherein each storage location corresponds to a unique three-dimensional space coordinate; s3, the unmanned aerial vehicle executes an inventory task according to a preset route; s4, the unmanned aerial vehicle binds the RFID tag with the strongest signal when hovering in front of each storage location, so that the storage locations are in one-to-one correspondence with the goods; s5, comparing the RFID signal value acquired when the unmanned aerial vehicle flies to the next storage location with the RFID signal value acquired when the unmanned aerial vehicle flies to the previous storage location, and binding the tag with the strongest signal to the current storage location; and S6, after the checking task is finished and the unmanned aerial vehicle returns, the system automatically generates a checking report, compares the RFID real-time data with the WMS inventory record and marks a difference item. According to the invention, efficient and accurate unmanned inventory checking can be realized, and the inventory quantity and inventory position accuracy of inventory checking can be ensured.

The invention discloses an unmanned aerial vehicle countering system, and relates to the technical field of unmanned aerial vehicle countering, and the system comprises a plurality of guidance unmanned aerial vehicles which are used for carrying out the rigid interception of black flight unmanned aerial vehicles; the radar is used for discovering a black flight unmanned aerial vehicle target; the medium-wave infrared camera is used for performing image recognition on the black-flight unmanned aerial vehicle target; the control center is used for displaying a signal detected by the radar and a target image and generating a control instruction; the radar transmits the control instruction to the unmanned aerial vehicle, and controls and guides the unmanned aerial vehicle to fly to the black flight unmanned aerial vehicle and collide with the target; guidance of the unmanned aerial vehicle further comprises image terminal guidance, namely, an airborne image recognition and tracking system autonomously finds a target, tracks the target and guides the unmanned aerial vehicle to intercept collision; and guiding the unmanned aerial vehicle to autonomously adjust the flight attitude after the target is hit, and executing a task according to an instruction after stabilization. According to an actual deployment scheme, the radar instructs the guidance unmanned aerial vehicle close to the deployment incoming attack direction to take off and execute a countering task, and the interception probability can be effectively improved.

The invention discloses an unmanned aerial vehicle-based control method and a related device, and is applied to a control platform in an unmanned aerial vehicle control system, and the method comprises the steps: transmitting first request information to a target unmanned aerial vehicle when it is monitored that the target unmanned aerial vehicle enters a preset airspace; detecting whether first response information is received within a preset duration; if yes, verifying the identity information of the target unmanned aerial vehicle through a preset unmanned aerial vehicle database to obtain a first verification result; when the first verification result comprises successful verification, collecting multi-dimensional data; determining a target flight state according to the first response information and the multi-dimensional data; when the target flight state comprises a black flight state, determining a target early warning level according to the multi-dimensional data; determining a target processing scheme corresponding to the target early warning level; and processing the target unmanned aerial vehicle according to the target processing scheme, so that the target unmanned aerial vehicle is out of the black flight state. According to the embodiment of the invention, the recognition accuracy of the flight state of the unmanned aerial vehicle is improved.

The invention discloses an unmanned aerial vehicle flight path repetition area identification and comprehensive evaluation method and system, and belongs to the technical field of unmanned aerial vehicle intelligent control. The objective of the invention is to accurately find out a repeated flight area of an unmanned aerial vehicle. The method comprises the following steps: completely converting flight track segments of the unmanned aerial vehicle into track segment structure vectors; constructing a multi-scale similarity evaluation method, and performing scoring evaluation on the similarity of the structure vectors of the track segments from two aspects of structure similarity and point location matching similarity; the repetition frequency of the track segments is calculated, the number of total similar segments between each track segment and all other track segments is counted based on a set threshold value, and a repeated track segment set is extracted; introducing a kernel function to construct a trajectory heat function, then calculating an information entropy of a trajectory region based on the heat function, and establishing a heat map of the trajectory region; and the information entropy, the direction consistency and the historical trajectory density are fused to construct a comprehensive scoring model of the flight trajectory repetition region of the unmanned aerial vehicle, and multi-dimensional quantitative evaluation of the flight trajectory repetition region of the unmanned aerial vehicle is realized.

The invention relates to a method for intercepting a flying object through aerial high-speed net casting, which is used for solving the technical problem of low interception success rate caused by insufficient maneuverability of an interception means and lack of enough large and reliable interception area when approaching a target in the prior art, and comprises the following steps: controlling an unmanned aerial vehicle to fly to approach the target; an unlocking signal is sent to a locking mechanism arranged on the machine main body, so that the locking mechanism synchronously releases all the power systems; the released power system flies away by means of self-rotation inertia, and the catching net connected with the power system is pulled by the pulling rope, so that the catching net is unfolded to form an intercepting area in the flying-away process. The unmanned aerial vehicle keeps flying at a high speed in the pursuit stage, the unmanned aerial vehicle flies away through inertia of a plurality of power systems in the interception stage, the capture net is unfolded to form an interception area larger than the projection area of the vehicle body, and compared with a traditional interception method, the interception method has the higher interception speed and the higher interception success rate.

The invention relates to the technical field of edge computing, and discloses a service area hazardous chemical substance vehicle intelligent supervision method and system based on edge computing, and the method comprises the steps: obtaining the real-time position data and state information of a hazardous chemical substance vehicle in a service area; integrating the real-time position data and the vehicle state information on the edge computing node to construct a dynamic behavior portrait, and extracting motion track features in the dynamic behavior portrait; comparing the motion trail features with a planned route in the electronic waybill data, judging the consistency of the route and detecting aggregation abnormity so as to generate a potential risk signal; based on the potential risk signal, distributing a response priority and automatically triggering an unmanned aerial vehicle system, and planning a flight path by combining a geographic information system so as to control the unmanned aerial vehicle to fly to a target area and perform data acquisition; according to the method, the accuracy and real-time performance of risk identification can be improved, it is ensured that potential risks are quickly sensed and effectively responded, and a complete supervision link from risk early warning to on-site checking is constructed.

This utility model discloses a surveying drone with a rockfall protection structure, relating to the field of drone technology. It includes a main cabin for housing the drone's electronic components; a measurement host located at the top center of the main cabin for performing measurement functions and data acquisition; a protective frame located on the top outer side of the main cabin for protecting the measurement host; several extension arms located around the main cabin for welding to form the drone's frame; a propeller for providing flight propulsion; a rockfall protection assembly located on the outer side of one end of each extension arm for preventing damage to the propeller from falling rocks; a landing support located in the middle of each extension arm for supporting the drone's landing; and a control mechanism located inside the main cabin for controlling the drone's flight and signal transmission. This utility model effectively solves the problem of surveying drones being easily damaged by falling rocks when operating in areas prone to geological disasters.

The invention discloses an unmanned aerial vehicle precipitation enhancement system and method based on compressed gas sound wave driving, and relates to the technical field of artificial precipitation enhancement, and the method comprises the steps that an unmanned aerial vehicle aircraft provides flight support needed by system high-altitude operation, and supports fixed-height cruise and dual-mode positioning; the high-pressure gas supply module stores compressed gas and provides a continuous and controllable energy source for sound wave generation; the sound wave generation module converts the air pressure energy into sound energy and generates directional low-frequency sound waves, and the directional low-frequency sound waves act on a target cloud area to achieve precipitation enhancement catalysis; the control module is used for unmanned aerial vehicle flight state regulation and control, gas path on-off and pressure adjustment, sound wave frequency closed-loop control, receiving feedback data of all the modules and dynamically adjusting operation parameters through an algorithm. The damping suspension module absorbs counter-acting force generated when sound waves are generated, and interference on the flight attitude of the unmanned aerial vehicle is counteracted. Based on the design, light-weight, low-power-consumption, pollution-free and efficient artificial rainfall enhancement operation can be realized.

The application discloses a kind of unmanned plane flight plan pre-dispatching tool and method, wherein the tool includes: information input module, target constraint generation module, dispatching model establishment module, dispatching scheme generation module and dispatching scheme release module;The unmanned plane flight plan pre-dispatching method is realized using the above tool, including the following steps: step 1, receiving various information;Step 2, generating the target constraint of unmanned plane flight plan pre-dispatching;Step 3, establishing the target planning model of unmanned plane flight plan pre-dispatching;Step 4, solving the generation of unmanned plane flight plan pre-dispatching scheme;Step 5, release scheme, complete the unmanned plane flight plan pre-dispatching.The application provides implementation tool and technical basis for low-altitude flight service, urban air traffic management, unmanned plane command control.

This application relates to the field of unmanned aerial vehicle (UAV) control technology, and discloses a flight control method, device, program, and storage medium for an inspection UAV. The method includes: stacking standard operating condition time-series data of the UAV under the current environment based on a sliding time window to output a multi-dimensional disturbance perception matrix to determine the core feature set of the UAV; determining the surrounding wind intensity category under the current environment by combining a preset feature threshold set; if it is a strong wind, determining the actual disturbance torque vector based on the core feature set and a preset torque data table; determining a feedforward flight compensation vector based on a preset dynamic model and the actual disturbance torque vector; generating a feedback correction vector based on the multi-dimensional disturbance perception matrix, a preset basic neural network model, a preset expected disturbance torque vector, the core feature set, the actual disturbance torque vector, and a feedback control algorithm; and controlling the UAV flight based on the feedforward flight compensation vector and the feedback correction vector. This application can improve the UAV's resistance to strong wind interference.

The utility model belongs to the technical field of unmanned aerial vehicles, and discloses a loading unmanned aerial vehicle. The loading unmanned aerial vehicle comprises an unmanned aerial vehicle body, a loading basket and an adjustable clamp. And a loading platform is arranged on the top back part of the unmanned aerial vehicle body and is detachably fixed. The object carrying basket is placed on the object carrying platform with an opening facing upwards, and the object carrying basket is used for carrying objects. The adjustable clamp comprises two clamping plates, the two clamping plates are oppositely arranged on the carrying platform, and the two clamping plates can be close to or away from each other to clamp or loosen the carrying basket. The object-carrying unmanned aerial vehicle is good in flight stability; manufacturing and fixing are easy, article loading and unloading are convenient, and the device is more suitable for convenient carrying of miniature articles; and the adaptability to carried articles is high.

This invention discloses a drone trajectory planning method and apparatus for edge data retrieval, relating to the navigation field, to improve the reliability of data retrieval tasks while ensuring data retrieval efficiency. The invention obtains edge node information for all target edge nodes; acquires basic drone parameters and initial state information, thereby obtaining the drone's unit energy consumption; calculates the drone's flight energy consumption between each pair of nodes, constructing an edge node geographic information model; then iterates through the following steps until all edge nodes have been visited, obtaining the drone's flight trajectory: based on the edge node geographic information model and the drone's state information, a greedy strategy is used to plan the access trajectory corresponding to the maximum number of visited nodes; the drone visits nodes sequentially along this access trajectory and updates its state information. This invention can effectively improve the reliability of data retrieval, ensuring both data retrieval efficiency and energy efficiency of the system.

The invention discloses an energy-saving multi-rotor express delivery unmanned aerial vehicle flight control method, and relates to the technical field of unmanned aerial vehicle flight control, in the sensor deployment and data acquisition step, sensors are reasonably configured, original data are accurately acquired, and basic information is provided for subsequent control; through the sensor data preprocessing step, the data quality is improved, and the accuracy and stability of data are ensured; by means of the key action node recognition step, dynamic sensing of the loading and unloading process is achieved, and key nodes such as lifting, translation and placement are precisely recognized; in the step of state parameter analysis, quantitative parameters are extracted for different nodes, and a scientific basis is provided for power adjustment; and finally, in the rotor power output dynamic adjustment step, according to the analysis result of the state parameters of each node, a targeted power adjustment strategy is adopted, so that the energy consumption waste caused by instantaneous high power in the initial hoisting stage is effectively avoided, the extra power consumption for maintaining the stable attitude in the translation stage is reduced, and the power distribution in the placement stage is optimized.

The invention discloses a folding mechanical mechanism and a folding device and method of an intelligent morphing wing. The folding mechanical mechanism is composed of a folding wing fixing seat, a main wing fixing seat, an electric driving assembly and a wing lower eccentric shaft. The folding wing fixing seat is used for transmitting an aerodynamic force load of the outer-section folding wing to the main wing fixing seat; the main wing fixing seat is used for bearing an aerodynamic force load transmitted by the outer-section folding wing; the wing lower eccentric shaft is connected with the folding wing fixing seat and the main wing fixing seat; the electric driving assembly is used for driving the unfolding and folding states of the outer-section folding wing and comprises an electric driver, a limiting movable shaft, a thrust rod and a movement thrust shaft. According to the scheme, the folding angle and the unfolding function of the wings can be accurately adjusted and controlled in the flight stage of the unmanned aerial vehicle, optimal control folding system control parameters can be autonomously calculated and loaded according to mechanical energy and the model state, autonomous adjustment of the wing shapes in the flight process is met, and the flexibility and adaptability of the unmanned aerial vehicle are improved.

The utility model discloses an unmanned plane landing anti -thrust device belongs to unmanned plane technical field, the device is in the abdomen of large fixed wing unmanned plane, including anti -thrust board and two groups of drive adjusting mechanism, the anti -thrust board is paddle formula arc structure, and the bottom surface is equipped with longitudinal fairing and is made with carbon fiber composite material, and the angle on the board is equipped with pressure sensor, drive adjusting mechanism contains support, connection hanging cylinder, drive assembly, axle seat, connecting seat and connecting rod assembly, can drive anti -thrust board and realize 0 degree 90 degree angle adjustment, and sensor feedback signal reaches controller, and controller receives unmanned plane flight system landing information and controls motor, forms closed loop control. The device utilizes the airflow to generate the reverse thrust and shortens the brake distance, and the anti -thrust board is horizontal when not working and does not influence the flight, and is light in weight, and the adjustment is accurate, and is convenient to maintain, is applicable to the safe landing of large fixed wing unmanned plane.

The invention discloses a fixed-wing unmanned aerial vehicle flight control method based on active disturbance rejection control, and belongs to the technical field of fixed-wing unmanned aerial vehicle flight control. The problem that the attitude control performance is poor due to the fact that aerodynamic interference of the propeller is not considered in an existing method is solved. According to the method, aerodynamic interference factors of propellers are systematically introduced into modeling and control design, namely, reaction torque and gyroscopic moment are introduced into the modeling and control design, and a flight control system of the fixed-wing unmanned aerial vehicle is designed based on an active disturbance rejection control strategy; and dynamic and external disturbances which are not covered by the model are estimated and compensated in real time, so that the attitude control performance of the fixed-wing unmanned aerial vehicle is improved. Meanwhile, under various given input signals, simulation verification is performed on the performance of the active-disturbance-rejection controller designed by the invention, which shows that the performance of the active-disturbance-rejection controller designed by the invention can meet design indexes. The method can be applied to flight control of the fixed-wing unmanned aerial vehicle.

The invention relates to the technical field of unmanned aerial vehicle acoustic measurement, in particular to a method for acoustically measuring environmental noise of unmanned aerial vehicle mounting equipment, which comprises the following steps of: during the flight of an unmanned aerial vehicle, continuously acquiring original noise signals, and synchronously recording rotating speed, attitude, acceleration and track position data; generating a harmonic sequence according to the rotating speed of the rotor wing, establishing a rotor wing echo template, and adjusting template parameters in combination with a track position and a reflection path; carrying out difference on the original noise and the rotor echo template in a time-frequency domain to obtain an echo residual signal, and carrying out local interpolation on the gap to form a continuous first noise sequence; identifying a wind shear event segment and reconstructing the event segment according to front and back normal segment trends to obtain a second noise sequence; a sound pressure consistency entropy value is calculated in a multi-track intersection area, and a minimum entropy measuring point is selected as a calibration anchor point; and carrying out trend correction on the adjacent track sequences by taking the anchor points as references, constructing a measurement point network diagram, fusing multi-track data, and finally obtaining a noise field of the target area.

A system for imaging a scene includes a plurality of drones, each drone moving over the scene along a corresponding flight path and having a drone camera to capture a corresponding first image of the scene at a corresponding first pose and first time; a flight controller to control the flight path of each drone, in part by using a first pose estimate of each drone camera provided by a camera controller to create and maintain a desired pattern of drones having desired camera poses; the camera controller to receive the corresponding plurality of captured images from the drones, process the received images to generate a 3D representation of the scene as a system output, and provide the estimate of the first pose of each drone camera to the flight controller. The system is fully operational with only one operator.

This application provides a logistics distribution method, system, and equipment. The method belongs to the field of logistics distribution technology. The method includes: acquiring real-time location information of an unmanned vehicle (UAV), first real-time status information of a UAV, and second real-time status information of a decanting rack; controlling the UAV to fly to the decanting rack based on the first and second real-time status information; after detecting that the UAV has landed on the decanting rack, sending a throwing command to the UAV, causing the UAV to perform a cargo throwing task according to the throwing command; after detecting that the UAV has flown away from the decanting rack, sending an upper push command to the decanting rack, causing the decanting rack to perform an upper push task, the upper push task being used to push the cargo into the decanting rack's storage compartment; when it is determined that the number of throwing attempts corresponding to the decanting rack has reached a preset maximum throwing quantity, sending a scheduling command to the UAV based on the real-time location information, causing the UAV to drive to the decanting rack to receive the cargo in the decanting rack's storage compartment.

This invention proposes an optimized method for drone data acquisition based on matrix completion and trust assessment, applicable to drone forensics in IoT network defense. First, in matrix completion, the sampling point locations and data packet acquisition times are constructed into a matrix, and matrix completion technology is used to recover all information and select sampling points. Second, in the drone flight trajectory, the selected sampling points and the Elite Ant Trail Optimization (EATO) algorithm are combined to optimize the drone's flight trajectory. Third, in the trust evolution mechanism, the comprehensive trust level of sensor nodes is obtained through dual evaluation by neighboring nodes and the drone. The proposed method can solve the security risks and resource consumption problems of data acquisition from IoT smart devices, effectively identify malicious nodes, optimize the accuracy of trust assessment, improve network security, and reduce drone energy consumption.

This invention provides a method and system for correcting the polarization of fragmented sky light for UAV navigation, relating to the fields of UAV navigation and multi-sensor fusion technology. The method includes: during UAV flight, acquiring a raw polarization image containing sky regions in real time and performing distortion correction to obtain a distortion-free polarization image; using a lightweight sky segmentation model to identify the distortion-free polarization image and extract effective sky fragment regions; extracting the polarization information of the effective sky fragment regions based on the distortion-free polarization image covered by the effective sky fragment regions; calculating the absolute geographic heading angle of the UAV at the current moment using a fragmented polarization heading solution model; obtaining the predicted heading angle at the current moment and correcting it using an unscented Kalman filter method; calculating the deviation between the corrected heading angle and the desired heading angle to control the UAV to fly along a predetermined route. This invention effectively achieves stable and reliable control of the UAV's positioning trajectory.

This utility model discloses a dual-rotor drone, relating to the field of drones. It includes a casing, with an upper rotor rotatably mounted on the top of the casing and a lower rotor rotatably mounted on the bottom of the casing. The upper and lower rotors are arranged coaxially at the top and bottom of the casing, respectively, thus driving the drone to fly using a dual-rotor configuration. The upper and lower rotors are controlled independently, which facilitates the control of the drone and simplifies the dual-rotor structure, enabling the dual-rotor drone to be miniaturized and applied to more complex and varied environments.

The utility model discloses a kind of unmanned plane radar pod structure, it is related to unmanned plane radar field, including unmanned plane and the laser radar being arranged in the lower portion of unmanned plane, the butt joint sleeve is fixed in the unmanned plane shell bottom end, the butt joint sleeve outer periphery is equipped with multiple limit rods equidistantly distributed along circumference track, gimbal is fixed on the laser radar, multiple butt joint bosses equidistantly distributed along circumference track are fixed on the gimbal surface.The utility model forms multiple balanced distribution butt joint point positions below unmanned plane, improves the compactness and stability of gimbal and laser radar and butt joint sleeve under butt joint state.And multiple point positions can be simultaneously locked operation, avoid laser radar in with unmanned plane flight process produce shaking, deviation phenomenon.Reduce the time required for operating each point position, improve installation portability, and then improve the efficiency of pod installation operation.

The invention relates to the technical field of automatic detection, in particular to an aerial work safety rope automatic detection method and system based on an unmanned aerial vehicle and a storage medium, and the method comprises the steps: controlling the unmanned aerial vehicle to fly to an aerial work area, and recognizing and positioning a target cage; the relative distance is calculated based on the cage space position, a rudder control parameter is generated, and the unmanned aerial vehicle is controlled to execute autonomous fly-around monitoring; continuously tracking an operator by adopting a DeepSORT multi-target tracking algorithm in the fly-around process, and distributing a unique ID for each target; for each tracked person target, intercepting a human body region image and inputting the human body region image into a binary classification convolutional neural network model to judge the wearing state of the safety rope; and after the fly-around task is finished, violation alarm information is generated based on the final state judgment result of all the tracked persons. According to the method, the problem of shielding under a single view angle is solved, the accuracy and reliability of detection are ensured by utilizing a multi-target tracking and state caching mechanism, and the full-process automation of high-altitude operation safety supervision is realized.

The utility model relates to unmanned plane technical field discloses a big heavy load unmanned plane flight equipment with high stability, including main part assembly, including base, the base bottom is fixed with the hook, the base outside is provided with the flight mechanism, the base bottom is fixed with the support frame, auxiliary assembly is located base below, including the clamping piece, the clamping piece includes the clamping plate in support frame one side, the base bottom is fixed with the fixed plate. The utility model has the advantages that: through the design of gravity trigger clamping, the use scene of adapting goods ground loading and unloading and air transportation, when goods are placed on the ground, the goods gravity is supported by the ground, does not apply effective force to the hook, the auxiliary clamping device is in the untriggered state, and the loading and unloading operation is not affected, when the unmanned plane takes off, the goods are separated from the ground, and its gravity is gradually completely transmitted to the hook, at this moment, the clamping device is automatically triggered, and the goods are stably constrained, thereby improving the transportation safety.

The invention discloses an intelligent crowd gathering detection method under the view angle of an unmanned aerial vehicle, and the method comprises the following steps: image collection: carrying out the patrolling shooting of a target region through the unmanned aerial vehicle, and obtaining an aerial image; pedestrian detection: preprocessing the acquired image, and inputting the preprocessed image into a special YOLOv8-AFPN detection model for pedestrian detection; wherein the special YOLOv8-AFPN detection model is constructed by introducing an AFPN into the YOLOv8 and carrying out multi-stage training on the AFPN and the YOLOv8; the AFPN is used for replacing a PAN-FPN structure adopted by the YOLOv8 in a Neck part; and aggregation analysis: introducing a density-based aggregation judgment algorithm on the basis of completing pedestrian detection by the YOLOv8-AFPN detection model, and identifying an aggregation behavior by analyzing detected pedestrian spatial distribution. The invention further discloses an intelligent crowd gathering detection system under the view angle of the unmanned aerial vehicle. According to the invention, high maneuverability and wide-angle visual field of the unmanned aerial vehicle are utilized to carry out patrol flight on the urban open area, and a special deep learning model is used to realize real-time and accurate identification and early warning of the personnel gathering phenomenon.

This invention discloses a foldable ducted-type unmanned aerial vehicle (UAV) and its folding method, relating to the field of UAV technology. The ducted-type UAV includes a fuselage, multiple ducted components, a rotating connecting component, and a locking structure. The fuselage includes a front fuselage section and a rear fuselage section, with multiple ducted components respectively disposed on the front and rear fuselage sections. The rotating connecting component connects the front and rear fuselage sections, allowing them to rotate relative to each other. The locking structure is located at the connection point and is used to lock or unlock, enabling the UAV to unfold or fold. Based on the technical solution disclosed in this invention, the entire UAV can be folded forward and backward, simplifying the folding structure and making operation convenient. The folded storage volume is significantly reduced, making it easy to carry. Furthermore, the locking mechanism is reliable in the unfolded state, ensuring the stability of the ducted-type UAV's flight structure.

The application discloses a kind of unmanned aerial vehicle hidden ground flight path planning method and system, method includes: the grid processing of unmanned aerial vehicle flight area forms several voxels;According to wind speed characteristics, topographic features and threat source data, the mixed Riemann tensor of each voxel is calculated;Sampling area is sampled in search node according to sampling probability to voxel and obtains sampling candidate point;According to the Riemann geometric distance of mixed Riemann tensor calculation search node and sampling candidate point, the smallest n sampling candidate points of Riemann geometric distance are as next search node, repeat sampling until reaching target position and obtain search tree;According to path cost scalar value, flight theoretical path is screened from search tree, and interpolation smoothing is carried out to final flight execution path;The application plans the optimal trajectory for long time, long distance hidden ground exploration task of unmanned aerial vehicle, and safety and energy efficiency are considered.