316 results about "Urban environment" patented technology

The invention relates to the technical field of aircrafts, and discloses a noise-considered urban low-altitude unmanned aerial vehicle path optimization method, which comprises the steps of urban environment rasterization and environment parameter setting; constructing an unmanned aerial vehicle noise attenuation model; calculating a noise interference critical distance and building sensitivity weight assignment; solving a noise interference grid matrix; a low-altitude unmanned aerial vehicle path planning model; and improving A * algorithm design. According to the method, the urban environment is rasterized, environmental parameters are set, an outdoor noise attenuation model is established by integrating geometric divergence, atmospheric absorption, ground effect and other factors, the propagation law of unmanned aerial vehicle noise in a complex environment is accurately described, the overall noise exposure and the sensitive area noise exposure are remarkably reduced while the flight safety is guaranteed, and the unmanned aerial vehicle noise attenuation performance is improved. The calculation efficiency is improved through the critical distance, path redundancy is avoided, collaborative optimization of noise control and operation efficiency is achieved, and technical support is provided for standardized operation of urban ultra-low-altitude unmanned aerial vehicles.

The invention provides an unmanned aerial vehicle flight path dynamic planning method and system, and relates to the technical field of flight path planning, and the method comprises the steps: obtaining the starting and ending points of the flight of an unmanned aerial vehicle, and planning an initial unmanned aerial vehicle flight path based on the starting and ending points of the flight of the unmanned aerial vehicle and a preset constraint; constructing an unmanned aerial vehicle flight environment model based on a preset flight area map, the elevation information and the obstacle information; route optimization is carried out based on the initial unmanned aerial vehicle flight route and a flight environment model, and an unmanned aerial vehicle initial obstacle avoidance route is generated; the unmanned aerial vehicle initial obstacle avoidance route is optimized based on a preset iterative optimization model, and an optimized unmanned aerial vehicle obstacle avoidance route is obtained; and updating the optimized unmanned aerial vehicle obstacle avoidance route to the initial unmanned aerial vehicle flight route to generate a final unmanned aerial vehicle flight route. According to the invention, the flight time and cost are saved, the adaptability to the environment, especially the urban complex environment, is enhanced, and the safety is guaranteed.

The invention belongs to the technical field of laser radar-camera panoramic segmentation, and particularly relates to a multi-mode panoramic segmentation method for multi-view space-time alignment and implicit feature interaction, and the method is executed by a multi-mode panoramic segmentation network, and comprises the steps: S1, obtaining laser radar point cloud data and multi-view camera image data in the same scene; s2, performing double-branch feature coding on the laser radar point cloud data; performing multi-scale image feature extraction on the camera image data; s3, generating false point cloud features with geometric perception capability; s4, generating semantic pixel features; s5, performing implicit fusion on the pseudo point cloud features generated in the S3 and the semantic pixel features generated in the S4 to obtain cross-modal fusion features; and S6, based on the cross-modal fusion features obtained in the S5, generating a unified panoramic segmentation result containing semantic tags and instance IDs. The method can effectively improve the robustness and precision of multi-mode panoramic segmentation in a complex urban environment.

The invention relates to the technical field of unmanned aerial vehicles, and discloses an intelligent logistics unmanned aerial vehicle and system, and the system comprises a space-time synchronization module which is used for obtaining an original data flow of a multi-source sensor on an unmanned aerial vehicle body, and carrying out the space-time synchronization processing of the data flow of the multi-source sensor; the quality evaluation module is used for carrying out quality evaluation on the sensor data subjected to time-space synchronization; the fusion positioning module adopts a multi-sensor fusion positioning method to obtain the high-precision three-dimensional position, attitude and speed state of the unmanned aerial vehicle; the semantic map module is used for constructing a three-dimensional semantic map comprising a static obstacle, a dynamic target and a landing area; the path planning module is used for performing intelligent path planning under a multi-constraint condition; the control execution module performs path execution and real-time adjustment; according to the invention, the technical problems of insufficient unmanned aerial vehicle positioning precision, limited environment perception capability and low path planning intelligence level in a complex urban environment are solved.

The invention discloses a multi-unmanned aerial vehicle cooperative task allocation and path planning method based on a genetic algorithm, and relates to an unmanned aerial vehicle path planning method. And operating a Dijkstra algorithm to accurately solve the shortest feasible path between all airports and task points, and finally generating a global path cost matrix for quick query. A complete and safe flight path that each unmanned aerial vehicle starts from an airport, sequentially accesses task points and returns is graphically displayed, a convergence curve of an algorithm, population diversity changes and performance comparison data under different task scales, unmanned aerial vehicle numbers and obstacle densities can be output, and a parameter sensitivity analysis function is supplemented. And the effectiveness, the stability and the practical value of the proposed method in a static urban environment are comprehensively verified.

The invention discloses an unmanned aerial vehicle inspection optimal waypoint discovery method based on three-dimensional space shielding detection, and the method comprises the steps: 1) obtaining the latitude and longitude coordinates and height information of a to-be-inspected point, and loading a triangular patch model of a surrounding building or terrain; 2) generating a plurality of candidate observation waypoints with different heights and orientations above the to-be-inspected point; 3) calculating whether the sight line from the candidate waypoint to the ground inspection point is shielded by a triangular patch or not by using an R tree spatial index and a ray tracing algorithm; and 4) comprehensively considering the sight shielding condition, the observation distance and the observation angle, and selecting a waypoint which meets the non-shielding condition and has the optimal observation effect as an unmanned aerial vehicle inspection position. Compared with the prior art, the method has the advantages of being high in efficiency, low in cost and good in quality, the problem of viewpoint shielding in unmanned aerial vehicle routing inspection path planning under the urban complex environment is effectively solved, and the routing inspection efficiency and the data acquisition quality are improved.

The invention relates to the technical field of environment monitoring, in particular to an urban carbon emission intelligent prediction method based on multi-modal data and machine learning integration, which comprises the following steps: feature acquisition and preprocessing: acquiring multi-source heterogeneous data and processing the multi-source heterogeneous data into a standardized data set; constructing an LSTM (Long Short Term Memory) and XGBoost hybrid prediction model; predicting future data on the basis of existing data, and predicting input features of future time steps of the weight integration prediction model on the basis of historical data in a standardized data set; and predicting carbon emission in the future. Industrial structure indexes, environment variables and social and economic substitution indexes are integrated through time characteristic engineering, and emission driving factors in different urban environments can be comprehensively captured; a recursive prediction mechanism is established, development trajectories of different cities are considered, reliable emission prediction can be carried out, meanwhile, time consistency is kept, and prediction uncertainty is quantified; interference influences under different policies are quantified, and a quantitative basis is provided for carbon management decisions.

The invention relates to the field of city analysis, and discloses a method for analyzing the nonlinear influence of a city environment on city vitality, and the method comprises the steps: carrying out the preprocessing of multi-source geographic big data and multi-source remote sensing data; according to a Deeplab V3 + deep learning semantic segmentation algorithm, predicting the pixel ratio of each category in each streetscape image, and constructing streetscape features based on the pixel ratio; constructing urban vitality evaluation indexes, and aggregating the urban vitality evaluation indexes by using a TOPSIS algorithm to obtain an evaluation result of the urban vitality; constructing an urban environment index according to the preprocessed multi-source remote sensing data; analyzing the spatial distribution difference of the non-linear influence of the urban environment on the urban vitality by using a geographically weighted random forest algorithm; and analyzing the threshold effect of the non-linear influence of the urban environment on the urban vitality by using a Gaussian fitting line algorithm. According to the method, street view features are extracted through a semantic segmentation technology, and comprehensive, scientific and refined quantitative evaluation of urban vitality is realized.

The invention discloses a non-line-of-sight moving target three-dimensional reconstruction method based on an MIMO millimeter wave radar, and is applied to the technical field of radar target detection in a complex urban environment. Aiming at the problem of difficulty in realizing three-dimensional reconstruction of a non-line-of-sight moving target in the existing radar target detection technology, the method comprises the following steps: firstly, establishing a non-line-of-sight multipath propagation model, and exporting a multipath signal model of an MIMO millimeter wave radar; the invention further provides a multipath signal departure angle (DoD) / arrival angle (DoA) unambiguous estimation algorithm, and solves the problem that a main lobe and a grating lobe are difficult to distinguish in the DoD / DoA estimation process of an existing commercial MIMO radar. And finally, proposing a path-oriented non-line-of-sight target three-dimensional positioning algorithm, respectively positioning the non-line-of-sight target by using different paths, and fusing different path positioning results to form a three-dimensional point cloud. According to the method, three-dimensional reconstruction of a plurality of non-line-of-sight moving targets can be realized, and the correlation problem between paths does not need to be considered.

The invention provides an unmanned aerial vehicle communication intensity calculation method and system based on data driving, and belongs to the technical field of low-altitude traffic network communication, and the method comprises the steps: processing obtained communication parameter data through employing a pre-trained graph neural network model, and achieving the prediction of the signal intensity of each grid; wherein the graph neural network model is composed of a plurality of graph attention network modules, a full connection layer and an output layer. According to the method, characteristic parameters related to urban environment and signal attenuation serve as input, signal intensity values serve as output, a graph neural network model is trained, and a high-precision and high-efficiency low-altitude communication signal attenuation estimation model is established. The model can effectively estimate the low-altitude communication signal intensity in different urban scenes, and the estimation result can provide a scientific basis for communication quality partition and system optimization of an urban environment.

The invention discloses an unmanned aerial vehicle route automatic planning system based on AI identification, and relates to the technical field of unmanned aerial vehicle route planning and obstacle avoidance. The unmanned aerial vehicle route automatic planning system based on neural network identification processes camera and laser radar data in real time through a lightweight convolutional neural network of an environment sensing module; accurate identification and classification of dynamic obstacles are realized, the perception ability in a dense city environment is effectively improved, and the risk of obstacle avoidance failure caused by sensor data updating delay is reduced. The fusion and tracking module adopts a space-time alignment and multi-source data fusion technology to generate uniform occupation representation and motion trail, so that the system can adapt to sudden obstacle change, the dependence on a preloaded map is reduced, and the navigation reliability in an unknown or dynamic scene is enhanced; the path planning module integrates a reinforcement learning algorithm, takes a dynamic obstacle state as input, and optimizes path generation through a multi-target reward function.

The invention discloses a PPP / INS / vision / LIDAR tight coupling navigation method based on multi-system real-time precision service, and belongs to the technical field of navigation and positioning. In order to solve the problem of insufficient real-time positioning precision and reliability in a complex urban environment, the invention provides a hierarchical fusion architecture: firstly, by using original data of an inertial navigation system, a visual sensor and a laser radar, high-precision and high-frequency local pose estimation is generated through tight coupling factor graph optimization; the accumulative error of inertial navigation is effectively inhibited; then, taking the local attitude as observation information, and performing tight coupling factor graph optimization on the observation information, a precise orbit obtained by PPP enhanced service decoding and a GNSS original observation value after clock correction, namely a pseudo range and a carrier phase; multi-source information is deeply fused on the observation value level, the complementary advantages of the sensors are fully played, and finally continuous and reliable centimeter-level high-precision positioning in the urban complex environment is achieved.

The invention discloses a multi-unmanned aerial vehicle low-altitude service scheduling result generation method and device, equipment and a medium, and relates to the technical field of unmanned aerial vehicle scheduling, and the method comprises the steps: constructing a low-altitude service semantic grid, converting the service demand characteristics of each region of a city into a region semantic vector, and mapping an unmanned aerial vehicle task to the grid to generate a task semantic vector; a semantic enhancement mechanism is utilized to calculate the semantic association strength of a task and a region, a multi-dimensional fairness index system is constructed, and a dynamic fairness preference weight is generated through self-adaptive correction. And finally, task allocation and path planning are performed based on the dynamic weight and the semantic association strength, so that the dynamic balance service efficiency and fairness of multi-unmanned aerial vehicle scheduling are improved, regional service deviation is dynamically corrected, the service accessibility of vulnerable regions and crowds is ensured, and the method is adaptive to complex urban environments and abnormal scenes.

The invention belongs to the technical field of software engineering, particularly relates to an automatic driving system performance enhancement method based on an expert hybrid architecture, and aims to solve the core problems that an end-to-end automatic driving system is confronted with semantic fuzziness to cause unreliable decision, multi-task interference hinders optimization planning, too long reasoning delay increases driving risks and the like. According to the method, an ExpertAD framework is provided, task key features are amplified through a perception adapter (PA), and the relevance of scene context understanding is guaranteed; related driving tasks are dynamically activated through a sparse expert mixture (MoSE), and task interference is minimized; and in combination with a customized training loss function, collaborative optimization of planning effectiveness and reasoning efficiency is realized. Experiments show that compared with an existing method, the method has the advantages that the average collision rate is reduced by 20%, the reasoning delay is reduced by 25%, higher multi-skill planning capacity is achieved in rare scenes (such as accident handling and first-aid vehicle avoiding), and good generalization is achieved for unseen urban environments.

The invention discloses an urban atmospheric pollution real-time monitoring and tracing method based on reinforcement learning, and relates to the technical field of atmospheric environment monitoring, and the method comprises the following steps: S1, collecting a pollution source data set; s2, constructing a Gaussian plume fidelity simulation model; s3, constructing a CFD fidelity simulation model; s4, constructing a multi-fidelity simulation model based on a Gaussian process proxy model; s5, constructing a DPPO reinforcement learning model; s6, using an improved multi-fidelity Bayesian optimization algorithm to continuously train and iterate the DPPO reinforcement learning model; and S7, generating a standardized pollution source real-time traceability analysis report. According to the method, the limitations of much manual intervention, low efficiency and poor real-time performance in a traditional urban pollution monitoring and tracing method are overcome, and an efficient and accurate solution is provided for intelligent real-time monitoring of urban environmental pollution and accurate and rapid tracing of pollution sources.

The invention discloses an environmental benefit and resource load evaluation method for an urban sewage treatment plant, and belongs to the field of sustainable evaluation. The implementation method comprises the following steps: training a random forest model by taking pollutant effluent concentration, energy consumption intensity and medicament consumption intensity of a national town sewage treatment plant as output variables and taking other historical operation information as input variables; on the basis, quantile regression is used for calculating quantiles of actual values of three operation indexes of each factory under the original processing condition; constructing an environmental benefit evaluation index system represented by pollutant removal efficiency and a resource load evaluation system represented by consumption efficiency of resources such as energy and chemicals; through obtaining environmental benefit and resource load grading benchmark values of the town sewage treatment plant, core functions and necessary input of each plant are accurately quantified, and real environmental contribution of the town sewage treatment industry is clarified, so that evaluation of sustainability of the town sewage treatment plant is more objective and fair, and sustainable development of urban environment infrastructures is facilitated.

The invention provides an urban water body efficient extraction method for a high-resolution satellite image, and belongs to the technical field of image processing, and the method comprises the following steps: 1, preprocessing satellite image data; 2, water body extraction based on index characteristics; step 3, water body extraction based on spectral characteristics; 4, water body extraction based on numerical characteristics; and 5, carrying out morphological processing on the water body binary image based on spatial characteristics. According to the method, when water body extraction is carried out on a high-resolution image with only four wave bands, compared with the method which only depends on calculation of a spectral index and setting of a threshold value, spectral characteristics of a real water body are comprehensively considered, and threshold values such as a spectral slope and a wave band value are set, so that the water body identification precision can be effectively improved; and the spatial distribution characteristics of the water body are further combined and morphological operation is carried out, so that the error of water body extraction caused by pixels such as building shadows in the urban complex environment can be greatly weakened.

The invention provides an urban environment performance prediction method and system based on multi-modal fusion and attention enhancement, and the method comprises the steps: collecting image data and numerical data, and generating a plurality of urban environment performance distribution truth value maps; preprocessing the multi-modal data to obtain an image map and a numerical value feature vector, and pairing the image map and the numerical value feature vector with the true value map to form a multi-modal data set; a multi-target model of a conditional generative adversarial network based on attention enhancement is constructed, a generator of the multi-target model comprises a two-way encoder, spatial features can be extracted based on an image map, and physical features can be extracted based on a numerical feature vector; an image coding path adopts a U-Net down-sampling structure containing a convolution block attention module, and a numerical value coding path adopts a multi-layer perceptron; and the multi-head output layer outputs a plurality of predicted urban environment performance distribution diagrams. After the model is trained, target area data are input, and three types of prediction distribution diagrams are output. According to the invention, the urban environment performance prediction effect is improved.

The invention belongs to the technical field of radio wave propagation prediction and deep learning, discloses an urban environment radio map prediction method, system and device and a medium, and solves the problem that radio map prediction is difficult and low in efficiency in a complex urban environment. The method comprises the following steps: setting corresponding simulation information by using various environmental element vector data of an urban scene, generating two-dimensional radio maps in different urban environments by using ray tracing simulation, forming a data set for deep learning network training and learning, and disassembling the urban environment into image channels capable of being independently expanded, different actual city scene features are simulated by increasing or combining different image channels, and rapid migration of a small sample new city scene radio map prediction model is achieved; the system, the equipment and the medium are used for implementing the method. Based on multi-channel input feature fusion, a data set is made through ray tracing, and radio map prediction requirements of low cost, low error, high efficiency and strong generalization are met through deep learning training.

The invention belongs to the technical field of data processing, and particularly relates to an intelligent scheduling method and system for garbage transfer trucks, and the method comprises the steps: carrying out the time-space alignment and quantification processing of multi-source data, constructing a feature vector, and dynamically generating a transfer task set with a priority through a pollution prediction model; constructing a dynamic comprehensive transit time model fusing real-time traffic congestion, a predicted traffic trend and a vehicle operation mode; an improved genetic algorithm is adopted, the dynamic passing time is used as a core index to evaluate the path fitness, and path optimization is carried out; and smoothing the optimized path and issuing a control instruction. According to the invention, dynamic time is changed into a decision-making core of the introduced path planning, so that a real optimal path for intelligently avoiding traffic congestion can be planned, and the working efficiency of the garbage transfer vehicle and the adaptability to a dynamic urban environment are remarkably improved.

A system and method for providing an accurate position for a GNSS device in an urban environment. The method includes determining a correction model based on differencing data and visibility data received from a plurality of sensors, estimating a current location of the GNSS device, deriving satellite parameters of a set of best visible satellites based at least on the determined correction model and the estimated current location, determining an accurate position of the GNSS device based on derived satellite parameters of the set of best visible satellites and a current location measurement provided by a GNSS receiver in the GNSS device, and setting a location of the GNSS device based on the accurate position.

The invention relates to an unmanned aerial vehicle cluster autonomous cooperative control method. Firstly, static obstacles and dynamic obstacles are identified, and risk levels are marked; secondly, when the target is sheltered, each unsheltered unmanned aerial vehicle is tracked by an infrared camera, the sheltered unmanned aerial vehicle switches a prediction mode, a distributed interactive multi-model algorithm is adopted to predict a trajectory and fuse data; static obstacles are avoided based on an artificial potential field method and a height layer division strategy, and different response strategies are adopted for dynamic obstacles with different risks; the role of each unmanned aerial vehicle is dynamically allocated, the task priority is adjusted according to the positioning error and the obstacle distance, each unmanned aerial vehicle reports the state in real time, and local re-planning is carried out if the deviation planning path exceeds a threshold value; and finally, optimizing a role and path distribution strategy through reinforcement learning. According to the method, the task execution efficiency and the cooperative capability are improved, the problem of each unmanned aerial vehicle cluster in target positioning and dynamic avoidance in a dense city environment is solved, and the cooperative adaptive capability is improved.

The invention relates to the technical field of radar signal processing, in particular to an urban environment low, small and slow target radar clutter suppression method, which comprises the following steps of: 1, acquiring and decomposing a signal; step 2, adaptive clutter cancellation; step 3, space-time combined treatment; step 4, constant false alarm rate detection; step 5, fine classification and identification; step 6, target tracking and early warning; according to the method, a cascade processing framework integrating multi-scale signal decomposition, adaptive filtering, space-time combined processing and intelligent identification is constructed, so that the defect that the performance of a traditional method is sharply reduced in a city strong non-uniform and non-stationary clutter environment is effectively overcome; and in combination with a recursive least square filter with dynamically adjustable parameters, the combined suppression capability of static ground clutter and dynamic traffic interference is remarkably improved, so that the detection of a'low, small and slow 'target under the condition of an extremely low signal-to-clutter ratio becomes possible.

The invention discloses an unmanned aerial vehicle control method integrating satellite navigation and inertial navigation and related equipment, and relates to the technical field of integrated navigation. According to the method, the control system collects the satellite quality intensity of the unmanned aerial vehicle at the current navigation point and predicts the satellite quality intensity of the unmanned aerial vehicle at the next navigation point, the reliability degree of satellite navigation is evaluated in advance, and the signal conversion type from the current navigation point to the next navigation point and the corresponding navigation strategy are determined accordingly. According to the self-adaptive navigation method based on prediction, preparation can be made before the satellite signal quality changes, and the problems of navigation precision abrupt change and positioning drift easily occurring when the signal abrupt change occurs in a traditional fixed weight fusion scheme are solved. Meanwhile, the control system carries out fusion calculation on satellite navigation data and inertial navigation data and flight control parameter adjustment based on deviation, it is ensured that the unmanned aerial vehicle can stably fly according to a preset route, and the unmanned aerial vehicle is particularly suitable for being used in complex urban environments and mountainous terrains with unstable satellite signals.

The invention belongs to the technical field of artificial intelligence and computers, and particularly relates to a multi-modal data intelligent identification and early warning system for a low-altitude safety emergency scene. The objective of the invention is to solve the problems of difficult small low-altitude target detection and lagging emergency response in a complex urban environment. The system integrates radio frequency, optical, acoustic and meteorological multi-source sensing nodes, and target fusion tracking is realized through space-time reference synchronization and cross-modal correlation matching; threat cognition is carried out by using a deep neural network with an attention mechanism, three-dimensional risk assessment is carried out by combining Monte Carlo simulation and a dynamic weighting algorithm, and yellow, orange and red three-level early warning instructions are generated; an early warning result is pushed to a multi-department collaborative response platform through an encryption interface, and the whole process is traceable through block chain evidence storage. According to the system, the low-altitude security situation awareness precision and the emergency response efficiency are remarkably improved.

The invention discloses an unmanned aerial vehicle flight control method and system based on a Mangbar and a dual-channel attention mechanism under wind field disturbance, and particularly relates to the technical field of unmanned aerial vehicle autonomous navigation and intelligent control. The method comprises the following steps: constructing a wind field disturbance model based on computational fluid mechanics, and simulating an unsteady wind field environment among urban building groups; designing a deep reinforcement learning network fusing a Mama framework and a double-channel attention mechanism, wherein the deep reinforcement learning network is used for realizing dynamic modeling of long-sequence wind field features and attention weighting of key spatial-temporal features; a dynamic road sign point guiding mechanism and a multi-stage attenuation greedy strategy are put forward, the sparse reward problem is relieved, and the local path optimization capability is improved; and a multi-target composite reward function including energy constraint, safety distance and path efficiency is constructed, and global path planning of energy consumption perception is realized. The method can improve the flight stability, path smoothness and energy efficiency of the unmanned aerial vehicle in a strong wind disturbance environment, and is suitable for unmanned aerial vehicle autonomous navigation tasks in an urban complex environment.

The invention discloses an urban environment quality monitoring method based on deep learning. The urban environment quality monitoring method is used for predicting an air pollution index API in the future 6 hours. The method comprises the following steps: collecting concentration data of six pollutants, namely PM2.5, PM10, SOO, NOO, Oand CO, and constructing a deep learning model comprising a double-layer time sequence feature extraction network and a pollution index prediction network; in the double-layer time sequence feature extraction network, a time scale layer adopts an LSTM structure to capture short-term change features, and a periodic scale layer adopts an attention-enhanced GRU structure to capture periodic features; after the time scale feature and the periodic scale feature are spliced, calculating a weighted feature through a self-attention mechanism, and inputting the weighted feature into a full-connection layer to generate a predicted value; according to the method, the prediction precision of the atmospheric pollution index is remarkably improved, the model robustness is enhanced, and a scientific basis is provided for environment decision making.

The invention discloses a multi-target hierarchical depth optimization method for illumination control, and belongs to the technical field of illumination control, and the optimization method specifically comprises the following steps: I, collecting and preprocessing various types of information at edge nodes of an illumination area, and extracting semantic information describing a real-time scene from the preprocessed various types of information; according to the method, the influence of sensing noise, missing data and heterogeneous sampling on decision is remarkably reduced, the accuracy and stability of environment sensing are improved, the illumination control strategy has the immediate response capability and the prospective adjustment capability, the problem that a traditional fixed weight method is insufficient in adaptability in different time and different scenes is solved, and the method is suitable for popularization and application. According to the method, the targets of energy conservation, safety, comfort and the like can be dynamically balanced according to the actual environment, the complex decision problem is effectively decomposed, the convergence speed and robustness of the strategy are improved, meanwhile, sudden performance drop caused by scene extrapolation is avoided, and the generalization ability of the system in the complex urban environment is remarkably improved.

The invention discloses an end-side data quality evaluation method and device oriented to man-machine and object fusion crowd sensing. The method comprises the following steps: constructing an end-side data quality evaluation mechanism framework oriented to man-machine and object fusion crowd sensing; by introducing a time interval coding and dynamic gating modulation mechanism, performing forward prediction on the data at the current sampling moment, generating credible prediction data, and determining a prediction error according to the credible prediction data; weighting the first prediction data and the second prediction data through a gating fusion strategy to obtain robust prediction data; dynamically updating the reputation value of the terminal equipment according to the historical data of the equipment; calculating a credibility score of the current sampling data based on the prediction error and the equipment reputation value; according to the method, the communication burden can be effectively reduced, the fusion data quality can be improved, and the robustness and adaptability of a sensing system in a complex urban environment can be remarkably enhanced.

The invention relates to a logistics unmanned aerial vehicle multi-objective optimization method based on an MODDPG-NSGA2 double-layer architecture. The method comprises the following steps: (1) establishing a logistics unmanned aerial vehicle scheduling model of multiple objective functions (a minimum distance function, a maximum time limit-reaching rate function and a minimum energy consumption function) and multiple constraint conditions (load balance, flight height, distribution distance, distribution speed and order distribution time constraint); (2) developing an MODDPG module to perceive a dynamic environment in real time, and quickly responding to a local strategy to complete re-planning according to sudden changes of the environment and orders; and (3) developing an NSGA2 module to globally optimize a multi-objective function, searching an optimal solution set, a balance path, an aging standard-reaching rate and an energy consumption target condition under complex constraints, and enhancing the adaptability and operation efficiency of the logistics unmanned aerial vehicle in a complex urban environment. Through deep fusion of the MODDPG module and the NSGA2 module, the method has the sensitive response of a dynamic scene and the multi-target global optimization capability, the transportation efficiency under complex constraints is greatly improved, and organic unification of real-time decision and global optimization is realized.