46 results about "Curve smoothing" patented technology

The invention discloses an unmanned aerial vehicle transformer substation inspection path planning method and device, equipment and a medium. The method comprises the following steps: firstly, generating a grid map; dividing the substation inspection space into a plurality of sub-regions; establishing an electromagnetic exposure intensity model, and setting an electromagnetic exposure intensity safety threshold; randomly sampling a plurality of nodes in each divided sub-region, constructing a random geometric graph, and generating an initial inspection path by adopting an RRT algorithm; optimizing the generated initial inspection path by using a path pruning optimization algorithm and a gradient descent convex optimization algorithm, and smoothing the path into a continuous curve by using a B-spline curve fitting technology to obtain a final optimized inspection path; according to the invention, through an overall strategy of first region division and then path planning, random geometric graph tree building, path pruning optimization, gradient curve smoothing and key region guiding sampling mechanisms are fused, and the efficient, stable and high-environment-adaptability unmanned aerial vehicle three-dimensional path planning method for the substation complex scene is realized.

The invention belongs to the technical field of robot path planning, and provides a path planning method for an electric power inspection mobile robot, which comprises the following steps of: firstly, constructing an environment grid map, establishing a corner directional expansion safety boundary, and performing safety expansion on an outer right angle of an obstacle; secondly, establishing an intelligent neighborhood selection mechanism based on fuzzy control, and performing adaptive adjustment neighborhood search; then, a multi-target heuristic function fusing the local obstacle density, the safety distance and the traffic difficulty is established, path search is carried out, and an initial path is obtained; then, constructing a path optimization strategy, and carrying out redundant point deletion and B spline curve smoothing processing on the initial path until a target executable path is obtained; and finally, optimizing an executable track in the target executable path in a time-space domain through an improved time-domain elastic band algorithm to obtain an optimal path. According to the invention, accurate obstacle avoidance of complex geometric obstacles can be realized.

The invention discloses an unmanned aerial vehicle complex path planning method based on an improved RRT * fusion APF algorithm, and the method comprises the steps: firstly, obtaining an operation environment of an unmanned aerial vehicle through a binocular camera, converting the environment into a three-dimensional geometric map, building a global coordinate system for the map, and determining the coordinates of each obstacle; secondly, performing path planning by using an improved RRT * fusion APF algorithm to generate a flight path; thirdly, optimizing the track through a third-order B-spline curve smoothing strategy; and finally, inputting the optimized flight path into the unmanned aerial vehicle, and enabling the unmanned aerial vehicle to run according to the planned path. The improved RRT * fusion APF algorithm adopted by the invention optimizes the path nodes of the traditional RRT * algorithm, shortens the path planning time and length, can avoid obstacles in real time, and ensures the adaptive capacity of the unmanned aerial vehicle in a complex environment.

The invention discloses a coal mine porosity calculation method for improving sequential Gaussian simulation under multi-source data fusion. On the basis of logging data preprocessing, logging curves of natural gamma, density, three-lateral resistivity and the like are synthesized, the high-organic-matter stratum is accurately discriminated, a volume physical model is constructed to explain the porosity of the rock stratum, a linear regression model is constructed to explain the porosity of the high-organic-matter stratum, and the porosity of the high-organic-matter stratum is accurately discriminated. After the two results are spliced and combined, abnormal sudden change points on a curve are eliminated through a curve smoothing algorithm, then the porosity curve, rock core data and the water temperature experiment result are normalized and mapped into a geological grid model, variation function analysis and parameter selection work are carried out, improved sequential Gaussian simulation and post-processing are carried out on the basis, and the geological grid model is obtained. And the reliability of the porosity attribute model is improved.

The application discloses a discrete fracture network generation method based on an iterative function system, which comprises the following steps: generating a traditional discrete fracture network model according to set parameters; then, converting all line segments into multi-segment lines with different directions and shapes at random; converting the multi-segment lines into fractal curves representing fractures by using an iterative function system; then, smoothing the fractal curves by using a curve smoothing algorithm and exporting the processed model into a geometric file, such as a dxf format file; realizing intersection operation between the curves by using software or code; setting an error value to detect small lines and gaps, deleting the short lines, merging small gaps into a point, and merging points close to the boundary; and finally, carrying out mesh division on the model. Compared with the traditional discrete fracture network model, the application can generate fractal curves representing fractal fractures, can control the roughness degree of the fractures through relevant parameters, can more accurately describe the fractures, and can improve the efficiency and precision of numerical simulation.

The application relates to the field of machine vision and image recognition, and discloses a high-precision edge extraction method based on image automatic processing, which comprises the following steps: a standardized image system is constructed, and an initial standardized wood template image is acquired through the standardized image system; the initial standardized wood template image is subjected to multimodal fusion pretreatment; an Otsu algorithm is used to determine a high threshold value and a low threshold value, an initial edge image and an edge gradient image are generated after edge detection of a binary image; then, the initial edge image is input into a pre-trained lightweight adaptive U-Net model, and an edge probability image is output; the edge probability image is sequentially subjected to morphological opening operation denoising processing, B-spline curve smoothing fitting processing and coordinate system calibration processing, and wood template edge coordinates are obtained; the average error of the wood template edge coordinates and standard template edge coordinates is calculated. The application realizes accurate conversion of wood template edge from an image to actual physical coordinates.

The invention relates to the technical field of trace detection, in particular to a rapid nondestructive detection method for phellinus igniarius polysaccharide content based on a near infrared spectrum technology. The method comprises the following steps: acquiring an original spectrum set of phellinus igniarius samples from various sources under a near infrared spectrum, and dividing the samples from the same source into the same group of original spectrum curves; evaluating the stability and distinguishing capability of light absorption change in different wavelength intervals, and obtaining the light absorption credibility of each target wavelength of the original spectrum curve; analyzing the morphological difference of a single curve in each group of spectrum curves relative to the whole group of curves, and obtaining an initial judgment coefficient for curve smoothing processing; and combining the light absorption credibility with the initial judgment coefficient, performing corresponding smoothing processing on each original spectrum curve according to the determined window length and processing order, and analyzing the actual polysaccharide content of the phellinus igniarius sample of the corresponding type. According to the technical scheme, the accuracy of polysaccharide content detection of phellinus igniarius through near infrared spectroscopy is improved.

The invention relates to the technical field of machine vision and image recognition, and discloses a high-precision edge extraction method based on automatic image processing, which comprises the following steps: constructing a standardized image system, and obtaining an initial standardized wood template image through the standardized image system; carrying out multi-modal fusion preprocessing on the initial standardized wood template image; determining a high threshold value and a low threshold value by adopting an Otsu algorithm, and generating an initial edge image and an edge gradient map after carrying out edge detection on the binarized image; inputting the initial edge image into a pre-trained lightweight adaptive U-Net model, and outputting an edge probability graph; performing morphological opening denoising processing, B-spline curve smooth fitting processing and coordinate system calibration processing on the edge probability graph in sequence to obtain wood template edge coordinates; and calculating an average error between the edge coordinates of the wood template and the edge coordinates of the standard template. According to the method, accurate conversion of the wood template edge from the image to the actual physical coordinate is realized.

The invention discloses a complex multi-runner optimization design method for a hydraulic element, and belongs to the technical field of digital design and manufacturing of the hydraulic element. The method comprises the steps that parameters such as a runner starting point and an initial obstacle control point are input; generating an initial obstacle; obstacle avoidance and path searching are carried out by adopting an optimization algorithm, and a continuous flow channel is generated through spline curve smoothing processing by taking the shortest flow channel as a constraint; and taking the newly generated flow channel as a dynamic obstacle to update the map, circulating until all the flow channels are completely arranged, and then outputting a result. Aiming at the problems of low efficiency, weight redundancy, large pressure loss and the like of a traditional manual layout method in the design process of a hydraulic element with a complex multi-runner structure, the method realizes automatic layout of the multi-runner structure, and removes redundant materials of the element by reducing a runner right-angle bend and the total length of the runner structure and cooperating with advanced manufacturing technologies such as additive manufacturing, so that the design efficiency of the hydraulic element is improved. Light weight is realized; the pressure loss is reduced by optimizing the runner shape and shortening the length, the layout efficiency and the element performance are improved, and manpower is reduced.

The invention relates to the technical field of computer graphic processing, and discloses a method for automatically drawing a DCS (Distributed Control System) picture into a real-time database picture, which comprises the following steps of: firstly, identifying a DCS source file format, directly analyzing a public text format or intercepting a bottom layer rendering instruction for a private binary format, and extracting standardized discrete data; constructing an intermediate vector model, and performing coordinate normalization and curve smoothing processing on the static primitives by using an affine transformation matrix; meanwhile, syntactic analysis is conducted on the control script to construct an abstract syntax tree, and dynamic logic is converted; then recombining a composite object based on spatial semantics, and repairing pipeline topology connection by utilizing automatic adsorption and an orthogonal routing algorithm; and finally, calling a target system interface to complete object instantiation and persistent storage. According to the invention, the automatic high-fidelity migration of the DCS picture to the real-time database is realized, the labor cost is reduced, and the consistency and accuracy of the monitoring picture are ensured.

The application discloses a tree branch skeleton extraction method for unmanned aerial vehicle collected point cloud data, and comprises the following steps: S1, acquiring tree branch point cloud data collected by an unmanned aerial vehicle; S2, preprocessing the tree branch point cloud data, wherein the preprocessing comprises point cloud denoising and improving the density of the tree branch point cloud; S3, based on an octree algorithm, performing spatial division on the gathered point cloud, and extracting branch skeleton points from the point cloud data subjected to data preprocessing in the divided subspace; S4, based on the extracted skeleton points, using a spherical contraction skeleton topology connection mode to construct a rough skeleton of the tree branch and performing fine adjustment; and S5, performing curve smoothing on the rough skeleton subjected to fine adjustment, optimizing the three-dimensional morphology of the rough skeleton, so that a fine skeleton is obtained as a final tree branch skeleton. Corresponding model construction systems, electronic devices and computer readable storage media are also disclosed.

The invention discloses a multi-agent priority obstacle avoidance path planning method for a dynamic obstacle, and relates to the technical field of mobile agent path planning, the method comprises the following steps: a global planning stage: optimizing an A * algorithm by introducing a heuristic scaling factor, an obstacle and direction penalty term and a neighborhood adaptive extension mechanism, a path is smoothed by combining broken line reconstruction and a Bezier curve; in the local planning stage, the weight of a DWA evaluation function is dynamically adjusted through fuzzy control, and the real-time obstacle avoidance robustness is improved. Meanwhile, a priority obstacle avoidance strategy and a dynamic look-ahead mechanism are designed, multi-agent conflicts are coordinated, and collective stagnation is avoided. Simulation results show that the method shows better path length, search efficiency and obstacle avoidance performance in static, unknown static and dynamic obstacle environments, effectively improves the multi-agent coordination stability, and is suitable for actual scenes such as warehouse logistics and the like.

The application discloses a kind of based on visual image detection's processing piece weld mark undercut defect identification processing method and system, method includes: processing piece is collected image, the image of processing piece is preprocessed, obtains image to be detected;Edge detection algorithm is analyzed to the image to be detected, obtains the weld mark area of image to be detected;Curve smoothing is carried out to weld mark area, obtains sampling point;According to the total arc length of weld mark area, the curvature of each sampling point is calculated by total arc length, and the curvature of sampling point is screened abnormal point;Through abnormal point, form undercut area, and the symmetry deviation index is calculated by segmenting undercut area;According to symmetry deviation index, it is judged whether there is undercut.

The invention relates to the technical field of energy distribution, and solves the technical problems that in the prior art, a traditional system often regulates and controls a whole building, neglects regional functions, easily causes supercooling and energy waste, controls start and stop according to a fixed time table, cannot respond to dynamic factor regulation and control lag and is poor in economical efficiency. The method comprises the following steps: S1, obtaining a planar graph of each floor of a target building, and deploying a plurality of data acquisition points for carrying out multi-position multi-dimensional data dispersion acquisition on the target building, according to the method, through the self-attention mechanism model and the one-dimensional convolutional network model, finer modeling is realized, the prediction precision is remarkably improved, the relevance of a modeling area is improved through the improved graph attention network model, optimization and updating are automatically performed, the universality and the adaptability of the method are enhanced, curve smoothing prediction is performed on a result, and the prediction accuracy is improved. And the stability of prediction results is improved.

The invention discloses a ground-air electromagnetic exploration method and system based on optimized extended harmonic waves, and the method comprises the steps: obtaining a pseudo-random wave current of a transmitting frequency and correspondingly received magnetic field data, and calculating a smoothing coefficient of a magnetic field intensity curve; constructing a harmonic frequency table, and calculating a relative error of curve smoothing coefficients of the transmitting frequency before and after each harmonic frequency is added; if the relative error corresponding to a certain harmonic frequency does not exceed a preset value, the harmonic frequency and the magnetic field intensity data thereof are reserved; constructing a layered medium model according to the emission frequency and the reserved harmonic frequency, and calculating forward magnetic field intensity data in the model; calculating the relative error of the curve smoothing coefficients before and after the addition of the currently reserved harmonic frequencies according to the method, and then screening the harmonic frequencies again; and finally, analyzing the underground medium of the measuring point by using the magnetic field intensity data of the emission frequency and the finally reserved harmonic frequency. The method can improve the longitudinal resolution of underground medium property exploration through an electromagnetic method.

This invention discloses an AIS-based UAV search and rescue deployment method and apparatus, relating to the field of data processing technology. The method includes: decoding the AIS signal to obtain decoded information; performing ship information filtering and analysis on the decoded information using a particle filter algorithm to obtain target ship information; obtaining ballistic trajectory calculation information based on the target ship information through ballistic trajectory analysis and ballistic calculation; preprocessing real-time wind field data; constructing a layered wind disturbance model based on the preprocessed real-time wind field data; correcting and optimizing the ballistic trajectory information based on the ballistic calculation information and the layered wind disturbance model to obtain optimized ballistic trajectory information; and generating an execution trajectory command set based on B-spline curve smoothing using the optimized ballistic trajectory information to perform UAV search and rescue deployment in conjunction with real-time control feedback. This invention achieves ballistic trajectory correction control under wind field disturbances, thereby achieving precise UAV deployment of distressed targets under complex sea conditions.

This invention discloses a Marchenko multiple suppression method for tracking wave impedance interfaces, belonging to the field of seismic data processing technology. The method includes the following steps: S1, obtaining wave impedance inversion results across the entire depth domain based on surface observation seismic data and the background velocity field; S2, extracting the location information of strong wave impedance interfaces and identifying several key locations between these interfaces; S3, using a Bezier curve smoothing method to obtain the spatial location of the focal point that maximizes the penetration of the strong wave impedance interface; S4, determining the ascending and descending Green's functions for the spatial location of the focal point; S5, predicting interlayer multiples using seismic interferometry; and S6, obtaining the seismic shot gather for suppressing interlayer multiples through adaptive matched filtering. This invention does not require a precise velocity model, relying only on a macroscopic velocity model, and can obtain deep-domain strong wave impedance geological information, accurately predicting and suppressing interlayer multiples by combining wave impedance information.

The invention relates to the technical field of laser and optical sensing, in particular to a rapid absolute wavelength calibration method and system for a continuous frequency sweeping laser light source, and the method comprises the steps: carrying out the filtering of broadband frequency sweeping light through an adjustable narrow-band filter, generating transmission light 1, and generating transmission light 2 through an FP etalon; the generated transmission light 1 and transmission light 2 are converted into electric signals by a photoelectric detector 1 and a photoelectric detector 2 respectively, and trigger signals and electric signals are acquired by an oscilloscope; and the upper computer PC end performs waveform fitting and peak searching on the electric signal according to the trigger signal acquired by the oscilloscope, and performs curve smoothing and interpolation processing on a wavelength and time coordinate point set represented by a peak value position of a transmission peak to obtain a change relation of the wavelength of the original nonlinear frequency sweep light along with time. The calibration method provided by the invention is simple and efficient, is not influenced by wavelength tuning step size and frequency sweeping speed, and solves the problem of wavelength overlapping at the switching position of each adjacent DFB laser channel of the laser array.

The present application relates to a gas detection curve smoothing method, a cleaning control method, an electronic device, and a semiconductor process device. The gas detection curve smoothing method comprises: acquiring a curve of a clean output gas which is output by an end-point detection apparatus, wherein the curve of the clean output gas comprises all cleaning output values between a first cleaning output value and the current cleaning output value of the clean output gas; and using the first cleaning output value as a first cleaning estimated value, and on the basis of a preset forgetting parameter, performing smoothing processing on the curve of the clean output gas, so as to obtain cleaning estimated values corresponding to the cleaning output values. By using a preset forgetting parameter as a smoothing factor and a first cleaning output value as a first cleaning estimated value, smoothing of the curve of a clean output gas can be implemented with a smaller calculation amount and a faster calculation speed, which not only provides a more accurate determination basis for a subsequent cleaning progress, but also lays the foundation for improving the cleaning efficiency.

This application provides a trajectory point fitting method, apparatus, electronic device, and readable storage medium. Based on the straight-line distance between any adjacent trajectory points in the trajectory point set as the distance increment, multiple sets of cubic spline curves are generated based on the trajectory point set and the distance increment. The endpoints of the cubic spline curves satisfy a specific terminal reciprocal continuity condition, while the cubic spline curves of other trajectory points that are not endpoints are continuous in the first derivative and in the second reciprocal. Under the premise of ensuring the smoothness of the final curve, the amount of data processing is small, thereby improving the vehicle tracking response speed.

The invention relates to the technical field of industrial robot control based on artificial intelligence, and discloses an industrial robot control method based on artificial intelligence. The method comprises the following steps: acquiring longitude and latitude of an operation area, unifying projection original points, mapping the longitude and latitude into plane coordinates, generating indexes and ranges according to fixed grids, and constructing a complete grid point set; then, an infrared sensor is installed to collect a heat map, temperature cost mapping is established, incremental priority search is implemented in combination with accumulated cost and heuristic search, a discrete path is generated through backtracking and converted into a continuous instruction, finally, quadratic curve smoothing is conducted at the break point, and stable break point driving is achieved. According to the method, boundary and coordinate conversion errors are eliminated, discrete addressable nodes are constructed, the search range is limited, and the planning precision and real-time performance are improved; the unified data model simplifies module integration and maintenance, and the stability and expandability of the system are remarkably enhanced.

The invention relates to the technical field of power supply and demand balance optimization, in particular to a power supply and demand balance optimization method based on full time sequence simulation, which comprises the following steps of: pairing a start-stop signal and an output adjustment amplitude item by item through a deep Q network, calculating a state action value, and screening action fragments meeting conditions by using a probability strategy; meanwhile, charging and discharging intervals are divided by using positive and negative difference values of charging and discharging power, and then are matched with an offset direction to generate an action track, so that invalid starting and stopping and power misadjustment are reduced, the number of times of starting and stopping is reduced, a power curve is smooth, and the reward value of each time slice is compared with a threshold section by section, and the slices which do not meet the threshold are deleted. And the residual segments are compared with the upper limit of the step number, the Benders decomposition algorithm is adopted to divide the segments into a main problem and a sub-problem for alternate iteration, a cut plane is generated, adjacent segments are spliced, intervals are filled, a continuous action chain is formed, it is guaranteed that a scheduling track is free of breakpoints in the time dimension, and splitting of an executable interval is avoided.

Methods and computer systems for utilizing gapless surface models in computer-aided design (CAD) applications to produce printing instructions for additive manufacturing (AM). A geometrically watertight CAD spline model of an object to be printed is received. For of a plurality of AM layers of the object, an intersection routine is performed of a plane of the layer with the geometrically watertight CAD spline model to obtain a respective smooth contour curve. For each AM layer, a plurality of hatch curves is determined within the plane of the layer and interior to the respective smooth contour curve. The smooth contour curves and the pluralities of hatch curves are stored in a non-transitory computer-readable memory medium.

The invention provides a virtual navigator path planning method based on SAC-RRT *, which innovatively introduces formation geometric envelope parameters to map multi-agent entity constraints into virtual navigator geometric constraints, replaces traditional RRT uniform sampling with non-deterministic Gaussian sampling of an SAC algorithm, and realizes adaptive step length extension and formation-level collision detection in combination with a Critic network. Meanwhile, the path cost optimization quantity of RRT rewiring is creatively converted into rewards to be fed back to the SAC network to complete backward fusion, network training is enhanced in cooperation with a real and virtual dual-experience playback strategy, formation trafficability factors are fused in a state space, a multi-dimensional reward function optimization decision is designed, and finally, the formation trafficability is improved through three times of B spline curve smoothing processing. The multi-agent formation path planning considering safety, optimality and convergence efficiency is realized, and the problems that a traditional method ignores formation geometric constraints, sampling blindness is large, and reinforcement learning and sampling algorithm fusion is not deep are effectively solved.

The application discloses a segmented smooth interpolation method and device based on DLG contour lines and a computer readable storage medium, belongs to the field of geographic information technology, and can generate an interpolated initial curve conforming to actual geographic conditions. The method comprises the following steps: selecting adjacent count curves A and B, setting equal-length trend step points on the count curves A and B at a trend step length s, constructing a line-in-triangle network between the count curves A and B, optimizing Z-shaped line clusters, performing segmented processing, interpolating across line segments, and generating an initial curve C. The application improves operation efficiency and smoothness by segmenting the count curves according to the trend and performing smooth interpolation on the segmented areas. The application has a clever concept, fully excavates feature points in geographic information, conforms to actual geographic characteristics, generates smooth and beautiful interpolated initial curves, and has a high running efficiency when the method is loaded on a computer and runs, and has a wide application prospect.

The application discloses a kind of to utilize U-net neural network and carry out rotor blade tip vortex vortex core image identification method, belong to vortex core image processing technical field, including the following steps: S1: constructs training U-net neural network model;S2: U-net neural network model predicts blade tip vortex position;S3: obtain vortex core position and area;S4: vortex core position ellipse curve fitting;S5: equal division curve elliptic arc segment and take index;S6: calculate vortex core position and elliptic arc segment distance and belong to nearest elliptic arc segment;S7: the number of vortex core is about arc segment index curve;S8: curve smoothing processing;S9: find peak position;S10: peak position index mapping vortex cluster label, calculate peak index corresponding peak arc segment position;S11: calculate vortex core position and curve peak arc segment distance and belong to nearest peak arc segment, and each vortex is marked with belonging vortex cluster label;The application can accurately identify blade tip vortex, simultaneously without treating PIV image, simple and intuitive operation.

The invention discloses a wind power prediction curve smoothing method and system based on a time trend, and belongs to the technical field of wind power airport prediction. Original new energy day-ahead declaration curve data is adopted to determine fitting parameters of a sliding window suitable for the original new energy day-ahead declaration curve data, and then iterative operation is carried out based on a Savitzky-Golay filtering fitting method, so that the new energy day-ahead declaration curve data is obtained; and simulating the whole NDVI time sequence data to obtain a long-term change trend. According to the method, the low-frequency component in the original data at the abrupt increase or abrupt drop position is reserved, and the high-frequency component is smoothed, so that the phenomenon of abrupt increase or abrupt drop in a new energy day-ahead declaration curve is avoided, the basic trend and width of the original data can be ensured to be unchanged while noise is filtered, and the method is suitable for popularization and application. The method is suitable for a scene in which the profit effect of an original curve cannot be greatly changed, and meets the'inertia 'requirement of a transaction center on the power supply curve.

The invention discloses an AIS-based unmanned aerial vehicle search and rescue throwing method and device, and relates to the technical field of data processing, and the method comprises the steps: decoding an AIS signal, and obtaining decoding information; performing ship information screening analysis on the decoded information based on a particle filtering algorithm to obtain target ship information; carrying out ballistic trajectory analysis and ballistic calculation processing on the basis of the target ship information to obtain ballistic calculation information, preprocessing the real-time wind field data, and constructing a layered wind disturbance model on the basis of the preprocessed real-time wind field data; and the trajectory trajectory information is corrected and optimized based on the trajectory calculation information and the layered wind disturbance model to obtain optimized trajectory trajectory information, and an execution trajectory instruction set is generated by utilizing the optimized trajectory trajectory information based on B-spline curve smoothing so as to perform unmanned aerial vehicle search and rescue throwing in combination with real-time control feedback. According to the invention, ballistic trajectory correction control under wind field disturbance is realized, so that unmanned aerial vehicle accurate throwing of a distress target under complex sea conditions is realized.

The application discloses a method for solving the multi-objective optimization problem, comprising the following steps: S1), designing a target function, constructing a weighted single-target function to realize collaborative optimization; S2), an initialization stage: adopting refraction reverse learning and an elite selection strategy; S3), a rolling ball stage: fusing a Pareto guide and an Osprey search thought; S4), a breeding dung beetle stage: introducing an adaptive t-distribution disturbance mechanism; S5), a foraging dung beetle stage; S6), a stealing dung beetle stage: fusing a multi-objective collaborative sharing mechanism of the Pareto guide; S7), merging offspring and parent populations and updating an external solution set; and S8), after iteration termination, outputting an optimal track. The application has excellent performance in path search and obstacle avoidance ability under complex terrain, and introduces an adaptive t-distribution disturbance and a Jacobian curve smoothing mechanism, which significantly enhances global jumping and local fine search, and guarantees the smoothness of the planned track and the multi-objective convergence quality.

The invention discloses an AGV trolley control system and control method in an automation system, and the system comprises a trolley unit, a central control unit, a scheduling unit, an interaction unit, a function unit and an environment perception unit which are in communication connection through a network. The environment sensing unit integrates a visual sensor, an ultrasonic radar and an infrared detector to collect obstacle information, a dynamic decision module is arranged in the central control unit, the threat degree of an obstacle is calculated based on distance, speed, size and direction factors and divided into three levels, and differential obstacle avoidance instructions are generated; the scheduling unit supports cooperation of multiple trolleys, and an A * algorithm is adopted to plan an obstacle avoidance path and smooth processing is carried out through a B spline curve. The problems that an existing system is poor in dynamic environment adaptability, low in cooperation efficiency and weak in scene adaptation are effectively solved, safe and stable operation of the AGV and efficient and reliable work of an automatic system are achieved, and the operation efficiency, safety and the intelligent level are improved.