Path planning simulation method and system for operation of reach stacker in container yard

Abstract

The invention relates to the technical field of path analysis, and discloses a path planning simulation method and system for operation of a reach stacker in a container yard. The method comprises the following steps: performing multi-scale path topology analysis on a dynamic cost map, a density cost map and a safety cost map to obtain potential path manifold data; non-stationary state quantitative analysis is carried out on the potential path manifold data to obtain path dynamic characteristics, and the path dynamic characteristics comprise path differential geometric characteristics, space-time entropy characteristics and energy gradient characteristics; according to a preset path performance standard, performing multi-modal feature fusion and hierarchical weight distribution on the path dynamic features to obtain an optimal path score and dynamic performance parameters of the operation of the front lifting machine with space-time adaptability; and generating a self-correcting path planning scheme according to the optimal path score and the dynamic performance parameters of the operation of the reach stacker. According to the invention, the accuracy of the path planning simulation of the operation of the reach stacker in the container yard is improved.

Description

Technical Field

[0001] The present application relates to the field of path analysis, and in particular to a path planning simulation method and system for container yard reach stacker operations. Background Art

[0002] In the field of intelligent management of container yards, traditional path planning methods mainly rely on static path planning algorithms and simple obstacle avoidance strategies. Existing technologies usually use classic path planning methods such as the A* algorithm and the Dijkstra algorithm, combined with the kinematic model of the reach stacker to generate paths. As the core loading and unloading equipment of the road-rail intermodal container yard, the reach stacker has nonlinear operating characteristics in its operation path, which also constitutes complex nonlinear kinematic constraints, which makes traditional path planning methods face many challenges in practical applications. At the same time, some improvement schemes introduce fast path planning algorithms based on sampling, such as the RRT (fast random tree) algorithm, the probabilistic road map method, etc., and deal with the mutual interference problem between devices by adding a simple dynamic obstacle avoidance module. These methods perform well when dealing with small-scale, low-complexity path planning tasks.

[0003] However, the existing technologies have the following shortcomings: First, traditional methods often simplify the path planning problem into the shortest path search in a static environment, ignoring the dynamic coupling effects and time-varying constraints between containers and reach stackers in the container yard; second, existing obstacle avoidance strategies are mostly based on simple geometric relationship judgments, which cannot effectively handle the complex interaction scenarios when multiple devices work together; third, traditional methods lack the ability to systematically model and quantitatively analyze the spatiotemporal uncertainty of paths, which makes path conflicts and efficiency losses easy to occur in actual operations; finally, existing technologies generally do not consider the coupling effects of equipment dynamics and environmental constraints, which may make the generated path infeasible or unstable during execution. Summary of the invention

[0004] The present application provides a path planning simulation method and system for container yard reach stacker operations, which are used to improve the accuracy of optimal path planning simulation for container yard reach stacker operations.

[0005] In the first aspect, the present application provides a path planning simulation method for the operation of a reach loader in a container yard, the path planning simulation method for the operation of a reach loader in a container yard comprising: performing a spatiotemporal correlation analysis on the container yard and the reach loader to obtain digital parameters of the container yard; based on the digital parameters of the container yard, performing nonlinear multi-body dynamic three-dimensional modeling of a preset container yard space to obtain a heterogeneous data set including equipment coupling state data, dynamic constraint propagation data, and time-varying boundary condition data; performing adaptive resolution multi-layer grid division analysis on the heterogeneous data set to obtain a dynamic cost map that considers topological changes, a density cost map based on entropy values, and a safety cost map based on collision probability. ; Perform multi-scale path topology analysis on the dynamic cost map, the density cost map and the safety cost map to obtain potential path manifold data with spatiotemporal uncertainty; Perform non-stationary state quantitative analysis on the potential path manifold data to obtain path dynamics characteristics, which include path differential geometry characteristics, spatiotemporal entropy characteristics and energy gradient characteristics; According to preset path performance standards, perform multi-modal feature fusion and hierarchical weight allocation on the path dynamics characteristics to obtain the optimal path score and dynamics performance parameters of the front loader operation with spatiotemporal adaptability, and generate a self-correcting path planning scheme based on the optimal path score and the dynamics performance parameters of the front loader operation.

[0006] In a second aspect, the present application provides a path planning simulation system for a reach stacker operation in a container yard, the path planning simulation system for a reach stacker operation in a container yard comprising: The analysis module is used to perform spatiotemporal correlation analysis between the container yard and the reach stacker to obtain digital parameters of the container yard; A modeling module, for performing nonlinear multi-body dynamics three-dimensional modeling of a preset container yard space based on the digital parameters of the container yard, and obtaining a heterogeneous data set including equipment coupling state data, dynamic constraint propagation data and time-varying boundary condition data; A partitioning module is used to perform adaptive resolution multi-layer grid partitioning analysis on the heterogeneous data set to obtain a dynamic cost map considering topological changes, a density cost map based on entropy values, and a safety cost map based on collision probability; A topology module, used for performing multi-scale path topology analysis on the dynamic cost map, the density cost map and the safety cost map to obtain potential path manifold data with spatiotemporal uncertainty; A quantification module, used for performing non-stationary state quantitative analysis on the potential path manifold data to obtain path dynamics characteristics, wherein the path dynamics characteristics include path differential geometry characteristics, spatiotemporal entropy characteristics, and energy gradient characteristics; The allocation module is used to perform multimodal feature fusion and hierarchical weight allocation on the path dynamic characteristics according to a preset path performance standard, so as to obtain an optimal path score and dynamic performance parameters of a reach stacker operation with spatiotemporal adaptability, and to generate a self-correcting path planning scheme according to the optimal path score and the dynamic performance parameters of the reach stacker operation.

[0007] In the technical solution provided by the present application, the digital parameters of the container yard are obtained by performing spatiotemporal correlation analysis on the container yard and the reach stacker, thereby realizing the accurate digital expression of the yard environment and effectively reflecting the dynamic interaction between the reach stacker and the yard environment. Based on the digital parameters of the container yard, nonlinear multi-body dynamics three-dimensional modeling is performed to obtain a heterogeneous data set containing equipment coupling state data, dynamic constraint propagation data and time-varying boundary condition data, which accurately describes the complex coupling relationship and dynamic constraint conditions between multiple devices. By performing adaptive resolution multi-layer grid division analysis on heterogeneous data sets, a dynamic cost map considering topological changes, a density cost map based on entropy values ​​and a safety cost map based on collision probability are generated, realizing a multi-dimensional evaluation of the path planning environment. Multi-scale path topology analysis is performed on these cost maps to obtain potential path manifold data with spatiotemporal uncertainty, which effectively captures the dynamic change characteristics of the path. By performing non-stationary state quantitative analysis on the potential path manifold data, path dynamic characteristics including path differential geometry characteristics, spatiotemporal entropy characteristics and energy gradient characteristics are obtained, which fully characterizes the geometric and dynamic properties of the path. Finally, based on the preset path performance standard, the path dynamics characteristics are multimodally fused and hierarchically weighted, and the optimal path score and dynamic performance parameters of the reach stacker operation with spatiotemporal adaptability are obtained, and a self-correcting path planning scheme is generated to ensure the real-time adaptability and robustness of the planning scheme. Through multi-level path analysis and feature extraction, accurate planning of the nonlinear operation path of the reach stacker in a complex yard environment is achieved, which improves the accuracy and reliability of path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0009] Figure 1 A schematic diagram of an embodiment of a path planning simulation method for a reach stacker operation in a container yard in an embodiment of the present application; Figure 2It is a schematic diagram of an embodiment of a path planning simulation system for container yard reach stacker operation in an embodiment of the present application. DETAILED DESCRIPTION

[0010] The embodiment of the present application provides a path planning simulation method and system for the operation of a container yard front loader. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0011] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the path planning simulation method for container yard reach stacker operation in the embodiment of the present application includes: Step S101, performing a spatiotemporal correlation analysis on the container yard and the reach stacker to obtain digital parameters of the container yard; Step S102: Based on the digital parameters of the container yard, nonlinear multi-body dynamics three-dimensional modeling is performed on the preset container yard space to obtain a heterogeneous data set including equipment coupling state data, dynamic constraint propagation data and time-varying boundary condition data; Step S103, performing adaptive resolution multi-layer grid division analysis on the heterogeneous data set to obtain a dynamic cost map considering topological changes, a density cost map based on entropy values, and a safety cost map based on collision probability; Step S104: Perform multi-scale path topology analysis on the dynamic cost map, the density cost map, and the safety cost map to obtain potential path manifold data with spatiotemporal uncertainty; Step S105, performing non-stationary state quantitative analysis on the potential path manifold data to obtain path dynamics characteristics, which include path differential geometry characteristics, spatiotemporal entropy characteristics, and energy gradient characteristics; Step S106: According to the preset path performance standard, multimodal feature fusion and hierarchical weight allocation are performed on the path dynamic characteristics to obtain the optimal path score and dynamic performance parameters of the reach stacker operation with time and space adaptability, and a self-correcting path planning scheme is generated based on the optimal path score and dynamic performance parameters of the reach stacker operation.

[0012] It can be understood that the execution entity of the present application can be a path planning simulation system for the operation of a container yard reach loader, and the hardware facilities it relies on are mainly servers. The embodiment of the present application is explained by taking the server as the execution entity as an example.

[0013] Specifically, the spatiotemporal correlation analysis of the container yard and the reach stacker is carried out. The spatial grid analysis of the container location, channel distribution, loading and unloading area and other information in the static layout data of the yard is carried out, and the real-time position, speed, spreader height and rotation angle of the reach stacker and other dynamic data are combined for time series processing to form digital parameters reflecting the overall state of the yard. As a kind of equipment specially used for container loading and unloading operations, the reach stacker's unique structural characteristics (such as spreader system, control system, etc.) and kinematic characteristics are included in the analysis scope. Specifically, when the reach stacker moves in the yard, its position data is collected in real time and divided into time windows. The spatiotemporal features are extracted through the bidirectional long short-term memory network (LSTM), so as to obtain accurate container yard-reach stacker interaction features.

[0014] Based on the digital parameters of the container yard, a nonlinear multi-body dynamic three-dimensional modeling of the preset container yard space is performed. In this process, each reach stacker is regarded as a composite rigid body system, and the motion equation containing state variables such as position, velocity, acceleration, etc. is established, while considering the interaction forces and constraints between the equipment. In particular, the model also includes the dynamic parameters unique to the reach stacker, such as the swing effect of the spreader system, the load characteristics of the lifting mechanism, and the influence of motion inertia. By analyzing the coupling relationship between the equipment, a heterogeneous data set reflecting the dynamic characteristics of the entire system is obtained.

[0015] Subsequently, adaptive resolution multi-layer meshing analysis is performed on heterogeneous data sets, and meshing strategies with different densities are adopted in different areas. Finer meshes are used in areas where front loader operations are frequent (such as loading and unloading areas, empty and heavy container yards, etc.) to improve accuracy, and coarser meshes are used in open areas to improve computational efficiency. Based on the meshing results, dynamic cost maps, density cost maps, and safety cost maps are constructed to evaluate various aspects of path planning. After obtaining the three cost maps, multi-scale path topology analysis is performed. By extracting and analyzing path features at different scales, manifold data reflecting the spatiotemporal uncertainty of the path are obtained. These data contain the geometric characteristics, topological structure, and dynamic change characteristics of the path.

[0016] For the potential path manifold data obtained, the dynamic characteristics of the path are extracted through non-stationary state quantitative analysis. These characteristics include: differential geometry characteristics that describe the geometric properties of the path, entropy characteristics that characterize the spatiotemporal distribution of the path, and gradient characteristics that reflect energy changes. According to the preset path performance criteria, the path dynamic characteristics are fused and weighted. The feature fusion is performed through the deep probabilistic graph network, and a hierarchical weight allocation strategy is adopted to finally obtain the optimal path score and dynamic performance parameters of the reach stacker operation, and generate a self-correcting path planning solution.

[0017] For example, in a container yard, a reach stacker needs to move from starting point A to target point B to transport a 40-foot container. Through spatiotemporal correlation analysis, the digital parameters of the container yard, such as the initial position (0,0), target position (50,30) (unit: meter), and spreader height of 12 meters, of the reach stacker are obtained. After nonlinear multi-body dynamics 3D modeling, the coupling force and constraint conditions between the three devices are calculated considering the influence of the other two reach stackers in operation in the area. At the same time, considering the structural characteristics of the reach stacker, the swing effect and load state of the spreader system are included in the modeling scope. After that, the operation area is gridded, with a grid density of 0.2 meters within 2 meters around the equipment and a grid density of 0.5 meters in other areas, and a cost map reflecting various dimensions of path planning is generated. Through multi-scale analysis and feature extraction, an optimal path that takes into account dynamic obstacle avoidance, energy consumption and safety is finally generated. The total length of the path is 85 meters, and the estimated running time is 300 seconds, which can ensure that the reach stacker can complete the task safely and efficiently.

[0018] In the embodiment of the present application, the digital parameters of the container yard are obtained by performing spatiotemporal correlation analysis on the container yard and the reach stacker, thereby realizing the accurate digital expression of the yard environment and effectively reflecting the dynamic interaction between the reach stacker and the environment. Based on the digital parameters of the container yard, nonlinear multi-body dynamics three-dimensional modeling is performed to obtain a heterogeneous data set containing equipment coupling state data, dynamic constraint propagation data and time-varying boundary condition data, which accurately describes the complex coupling relationship and dynamic constraint conditions between multiple devices. By performing adaptive resolution multi-layer grid division analysis on heterogeneous data sets, a dynamic cost map considering topological changes, a density cost map based on entropy values ​​and a safety cost map based on collision probability are generated, realizing a multi-dimensional evaluation of the path planning environment. Multi-scale path topology analysis is performed on these cost maps to obtain potential path manifold data with spatiotemporal uncertainty, which effectively captures the dynamic change characteristics of the path. By performing non-stationary state quantitative analysis on the potential path manifold data, path dynamic characteristics including path differential geometry characteristics, spatiotemporal entropy characteristics and energy gradient characteristics are obtained, which comprehensively characterizes the geometric and dynamic properties of the path. Finally, based on the preset path performance standard, multimodal feature fusion and hierarchical weight allocation are performed on the path dynamics characteristics to obtain the optimal path score and dynamic performance parameters of the reach stacker operation with spatiotemporal adaptability, and a self-correcting path planning scheme is generated to ensure the real-time adaptability and robustness of the planning scheme. Through multi-level path analysis and feature extraction, accurate planning of the reach stacker path in a complex yard environment is achieved, improving the accuracy and reliability of path planning.

[0019] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) Perform spatial grid analysis on the static layout data of the container yard to obtain the basic spatial parameter table of the yard, and perform time series segmentation on the real-time position data of the reach stacker to obtain the dynamic trajectory sequence of the equipment; (2) Perform topological structure analysis on the channel area data in the basic spatial parameter table of the yard to obtain the channel connectivity map, and perform time window segmentation processing on the equipment dynamic trajectory sequence to obtain the equipment behavior feature sequence; (3) Calculate the node importance of the channel connectivity graph to obtain the critical path node set, and perform time-frequency domain conversion on the equipment behavior feature sequence to obtain the equipment typical operating condition spectrum; (4) The spatiotemporal features of the key path node set and the equipment typical operating condition spectrum are extracted through a bidirectional long short-term memory network to obtain the container yard-reach stacker interaction feature matrix. The principal component dimensionality reduction processing of the container yard-reach stacker interaction feature matrix is ​​then performed to obtain the key spatiotemporal feature vector. (5) The key spatiotemporal feature vectors are normalized to obtain a standardized feature data set. The standardized feature data set is then subjected to multimodal separation processing through tensor decomposition to obtain the digital parameters of the container yard.

[0020] Specifically, the static layout data of the container yard is analyzed by spatial grid analysis, and the container yard space is divided into multiple grid units, each of which contains information such as location coordinates and occupancy status. The spatial parameter value of each grid is calculated by spatial grid analysis: in Representation Grid The spatial parameter value of represents the grid occupancy, Indicates the distance to the nearest obstacle. Represents the grid weight coefficient. At the same time, the real-time position data of the front loader is segmented according to a fixed time interval Δt to generate a dynamic trajectory sequence of the equipment.

[0021] When performing topological structure analysis on the channel area data in the basic space parameter table of the storage yard, the following connectivity calculation formula is used: in represents the connectivity value of node v, Representation and Node The set of adjacent nodes, represents the reachability coefficient between nodes u and v, Represents the distance between nodes. After the dynamic trajectory sequence of the device is divided into time windows, the behavior features in each time window are extracted, including parameters such as speed, acceleration, and steering angle.

[0022] The critical path nodes are obtained by calculating the node importance: in Representation Node The importance of represents forward connectivity, represents backward connectivity, Indicates the historical access frequency of the node, , , is the weight coefficient. Fast Fourier transform is performed on the equipment behavior feature sequence to obtain frequency domain features and form the typical operating condition spectrum of the equipment. Feature extraction is performed through a bidirectional long short-term memory network, which contains two LSTM layers, forward and reverse. Each LSTM unit contains an input gate, a forget gate, and an output gate to fuse the spatiotemporal features of the key path nodes and the operating condition spectrum. Then, the principal component analysis method is used to reduce the dimension of the high-dimensional feature matrix, and the principal components with a cumulative contribution rate of 95% are retained. Finally, the standardized feature data set is decomposed into multiple modal components through tensor decomposition.

[0023] For example, a container yard has an area of ​​100×80 meters and is divided into 50×40 grid cells. The reach stacker numbered E001 is analyzed and its position data within 24 hours is collected with a time interval of 1 second. Through spatial grid analysis, the spatial parameter value P(25,20)=0.85 of the grid (25,20) is calculated, indicating that this location is suitable as a channel node. Connectivity analysis is performed, and its adjacent nodes , The accessibility coefficients of are 0.9 and 0.8 respectively, and the distances are 2 meters and 3 meters. The calculated connectivity value C(v1)=0.73. In the node importance calculation, set =0.4, =0.3, = 0.3, for nodes Calculate the importance I( )=0.82. Finally, a 300-dimensional digital parameter vector of the container yard is obtained through path analysis, which provides basic data support for subsequent path planning.

[0024] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) Perform nonlinear dynamic three-dimensional modeling on the equipment parameters in the digital parameters of the container yard to obtain the equipment motion state equation, and perform multi-body system coupling analysis on the equipment motion state equation to obtain the equipment coupling state data; (2) Perform constraint analysis and processing on the device coupling state data to obtain an initial constraint condition set, and perform dynamic propagation link analysis and processing on the initial constraint condition set to obtain dynamic constraint propagation data; (3) Perform boundary feature extraction on the dynamic constraint propagation data to obtain a fixed boundary constraint set, and perform time-varying perturbation analysis on the fixed boundary constraint set to obtain time-varying boundary condition data; (4) Perform relative motion analysis on the device position data in the device coupling state data to obtain the force data between the devices, and perform state space reconstruction on the force data between the devices to obtain a set of coupled dynamic equations; (5) The heterogeneous feature combination processing of device coupling state data, dynamic constraint propagation data and time-varying boundary condition data is performed through the multimodal data fusion algorithm to obtain a heterogeneous data set.

[0025] Specifically, nonlinear dynamic three-dimensional modeling is performed on the equipment parameters in the digital parameters of the container yard, and the reach stacker is regarded as a rigid body with mass and moment of inertia, and the equipment motion state equation is established: in Represents the device state vector, including position and attitude, M is the mass matrix, is the Jacobian matrix, is the force vector, For a coupled system of multiple devices, the constraint equation is used: in represents the constraint function, arrive Represents the state vector of n devices. Thus, the device coupling state data is obtained, which contains the position, velocity and acceleration information of each device. Next, the constraint condition analysis is performed on the device coupling state data to construct the constraint propagation graph: in To constrain the propagation intensity, is the coupling coefficient between devices i and j, is the constraint influencing factor. By solving the equation, dynamic constraint propagation data is obtained to describe the transmission law of constraint conditions between devices. Boundary features are extracted from dynamic constraint propagation data to form a fixed boundary constraint set. Then, the influence of time-varying disturbances is analyzed to obtain time-varying boundary condition data. Relative motion analysis is performed on the position information in the device coupling state data, the forces between devices are calculated, and a set of coupling dynamic equations is constructed. Finally, the multimodal data fusion algorithm is used to combine the features of various types of data to generate a heterogeneous data set.

[0026] For example, there are three reach stackers operating simultaneously in a container yard, numbered E001, E002, and E003, with a mass of 20 tons and a moment of inertia of 15,000 kg·m². Through nonlinear dynamic three-dimensional modeling, the mass matrix M=[20000, 0; 0, 15000] and the force vector F=[5000N, 2000N] in the motion state equation of the E001 device are obtained. The constraint relationship between E001 and E002 is analyzed, and the constraint propagation strength G(t)=0.85 is obtained, indicating that there is a strong coupling between the two devices. After multimodal data fusion, a heterogeneous data set containing position, velocity, constraints, and boundary conditions is finally obtained, with a data dimension of 500×8.

[0027] In a specific embodiment, the process of executing step S103 may specifically include the following steps: (1) Perform multi-layer grid density calculation on the spatiotemporal state data in the heterogeneous data set to obtain the basic grid partition matrix, and then perform topological structure change analysis on the basic grid partition matrix to obtain a dynamic cost map; (2) Perform entropy feature extraction on the device coupling state data in the heterogeneous data set to obtain the regional entropy distribution matrix, and perform density mapping on the regional entropy distribution matrix to obtain a density cost map; (3) Perform collision risk prediction on the time-varying boundary condition data in the heterogeneous data set to obtain a collision probability distribution matrix, and then perform safety level classification on the collision probability distribution matrix to obtain a safety cost map; (4) Perform time-series segmentation processing on the topology change data in the dynamic cost map to obtain the topology change feature sequence, and perform spatial correlation analysis on the topology change feature sequence to obtain the grid dynamic update parameters; (5) The dynamic cost map, density cost map, and safety cost map are calibrated by an adaptive grid refinement algorithm to obtain a multi-layer grid cost map group.

[0028] Specifically, first perform multi-layer grid density calculation using the density function: in is the grid point The density value of For the The weight of a spatiotemporal state point, ( , ) is the state point coordinate, is the smoothing factor. The topological structure of the basic grid partition matrix is ​​analyzed to examine the connection relationship between grids and construct a dynamic cost map.

[0029] Calculate regional entropy features: in For Region The entropy value of For Region Middle The probability distribution of the device state, is the number of state categories. The entropy value is mapped to the spatial grid through the density function to form a density cost map.

[0030] Using the collision risk prediction model: in is the collision risk value at position p at time t, φ(t) is the time weight function, is the risk contribution of the jth obstacle. The risk values ​​are classified into different levels to generate a safety cost map.

[0031] The topological data is segmented according to a fixed time window, and the topological change features within each segment are extracted. The spatial correlation analysis of the feature sequence is performed, and the degree of association between adjacent grids is calculated to obtain the parameters required for dynamic grid update. Based on the quadtree structure, the grid division granularity is determined according to the cost value of each area. Fine grids are used in high-cost areas, and sparse grids are used in low-cost areas to achieve multi-resolution cost map representation.

[0032] For example: In a 120×100m container yard, the space is initially divided into 60×50 basic grids. Taking the position (30,25) as an example, there are 3 state points around it, with weights of [1.2, 0.8, 1.0]. Substituting into the density function, we get λ(30,25)=0.75. For the equipment state analysis of area (35,40), the state probability distribution is [0.3, 0.4, 0.2, 0.1], and the entropy value μ(35,40)=1.28 is calculated. In the collision risk analysis, at t=10s, there are two obstacles at the position (45,35), and the risk value θ(10,[45,35])=0.9 is calculated, which is classified as a high risk level. Through adaptive grid refinement, the grid size is set to 0.5m in the high risk area and 2m in the low risk area, and finally a complete multi-layer grid cost map group is formed.

[0033] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Perform multi-scale decomposition on the dynamic cost map to obtain topological structure sets of different scales, and perform connected domain analysis on the topological structure sets of different scales to obtain the path connectivity matrix; (2) Perform hierarchical feature extraction on the density cost map to obtain density gradient field data, and perform manifold embedding on the density gradient field data to obtain the initial manifold structure; (3) Perform probability field construction on the safety cost map to obtain a time-varying probability distribution map, and perform uncertainty propagation on the time-varying probability distribution map to obtain state uncertainty data; (4) Perform feature fusion processing on the path connectivity matrix and the initial manifold structure to obtain a path candidate set, and perform spatiotemporal mapping processing on the path candidate set and state uncertainty data to obtain potential path manifold data.

[0034] Specifically, the dynamic cost map is decomposed at multiple scales and processed using a multi-level pyramid structure. Starting from the original resolution of the lowest level, cost maps of different scales are formed by downsampling step by step, and the resolution of each layer is 1 / 2 of the next layer. At each scale level, the connectivity of adjacent regions is identified by the connected domain labeling algorithm, and the adjacent regions with cost value differences less than the threshold are classified as the same connected domain using the 8-neighborhood connectivity judgment criterion. For each connected domain, its topological features such as area, perimeter, and center of gravity position are calculated, and the adjacency relationship between different connected domains is established, and finally the path connectivity matrix is ​​generated. Then, the density cost map is hierarchically extracted, and the density features are gradually extracted from local to global using a density-based hierarchical clustering method. The density gradient, including the gradient size and direction, is calculated at each level to form the density gradient field data. The high-dimensional density gradient field data is mapped to the low-dimensional manifold space by the local linear embedding algorithm, and the local geometric relationship between the data points is maintained to obtain the initial manifold structure. This manifold structure reflects the inherent law of density distribution in the yard.

[0035] When constructing the probability field of the safety cost map, the kernel density estimation method is used to convert the discrete safety cost value into a continuous probability distribution. The probability distribution is dynamically updated through a sliding time window to obtain a time-varying probability distribution map. On this basis, the Monte Carlo sampling method is used to simulate the propagation process of uncertainty, generate multiple groups of state samples, and obtain state uncertainty data through statistical analysis. The path connectivity matrix and the initial manifold structure are feature fused, and the feature weighted combination method is used to comprehensively consider the connectivity and density distribution characteristics to generate a preliminary path candidate set. The path candidate set and state uncertainty data are mapped in time and space, and the corresponding relationship between path points and state uncertainty is established to form the final potential path manifold data.

[0036] For example: in a 100×100 meter container yard, the original dynamic cost map has a resolution of 0.5 meters / pixel, and after three-level pyramid decomposition, scale layers of 1 meter / pixel and 2 meters / pixel are obtained. Taking the second layer as an example, five main connected domains are identified, with areas of 150, 200, 180, 160, and 190 square meters, respectively, and the adjacency relationship matrix between these connected domains is calculated. In density feature extraction, the density gradient field of the 200 square meter area is analyzed to extract three main density aggregation centers. In safety analysis, the state uncertainty distribution of each area is obtained through 1,000 Monte Carlo samplings. Finally, 15 potential paths are generated through feature fusion, including 8 main paths and 7 alternative paths.

[0037] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) Perform differential geometry calculation on the potential path manifold data to obtain a curvature change sequence, and perform feature extraction on the curvature change sequence to obtain the path differential geometry features; (2) Performing spatiotemporal state analysis on the potential path manifold data to obtain a state transfer matrix, and performing entropy calculation on the state transfer matrix to obtain spatiotemporal entropy features; (3) Constructing energy functions for potential path manifold data to obtain energy distribution maps, and performing gradient calculations on the energy distribution maps to obtain energy gradient features; (4) The path differential geometry features, spatiotemporal entropy features, and energy gradient features are processed by feature combination to obtain the path dynamics features.

[0038] Specifically, potential path manifold data refers to a set of possible paths generated during the path planning process, each of which contains information such as position, direction, and speed. When performing differential geometry calculations on these data, the path must first be parameterized, and then the curvature value must be calculated at each path point. The curvature calculation uses the formula: in is the curvature of the path at point t, is the path parameter equation, and are the first and second order derivatives respectively. The curvature here reflects the curvature of the path. The larger the curvature value, the sharper the turn. The curvature values ​​on the entire path are serialized to obtain a curvature change sequence. The sequence is then feature extracted, including calculating the statistical characteristics (mean, variance, peak), geometric characteristics (turning radius, arc length) and dynamic characteristics (curvature change rate) of the curvature, and finally forming the differential geometric characteristics of the path. Spatiotemporal state analysis and processing is to study the motion state of path points and their conversion laws. First, the continuous path motion needs to be discretized into a finite number of states, such as basic states such as linear motion, turning motion, acceleration and deceleration. The state transition probability is calculated using: in is the state transition probability, the probability of transitioning from state x to state y, is the statistical value of the number of transfers, and e is the total number of states. The state transfer matrix is ​​constructed by statistically analyzing the state transitions at adjacent moments on the path. The entropy value of the matrix is ​​calculated to obtain the spatiotemporal entropy characteristics that reflect the uncertainty of state transitions. The energy function construction process is to analyze the energy consumption characteristics of the path. It is necessary to consider various forms of energy of the front loader during movement, including kinetic energy (related to speed), potential energy (related to height), and constraint energy (related to steering). By calculating the energy value of each point on the path, an energy distribution map is formed. The spatial gradient of the map is calculated to obtain the energy gradient characteristics that reflect the trend of energy changes.

[0039] Feature combination processing is to fuse the above three types of features. This step needs to consider the dimensions and importance of different features, and form a complete path dynamics feature vector through feature normalization and weighted combination. This feature vector fully describes the geometric characteristics, state change characteristics and energy consumption characteristics of the path.

[0040] For example, in a 120×100m container yard, a reach stacker loaded with 15-ton containers needs to move from the starting point (10,15) to the end point (90,75). To analyze a candidate path, first sample a point every 0.5m on the path, and obtain a total of 200 path points. At the path point (45,40), the calculated curvature value is 0.156, indicating that the turn is relatively gentle. The curvature values ​​of the five sampling points before and after this point are feature extracted, and the local curvature mean is 0.145 and the variance is 0.012. In the state analysis, the motion state of the path point is divided into five categories, and the statistical transition probability from straight-line motion to left turn is ρ=0.25, and the state entropy value is 1.82. Energy analysis shows that the total energy value of this point is 48.5kJ, and the energy gradient value is 0.65kJ / m. Finally, these features are combined into a feature vector containing 300 components, including 100-dimensional geometric features, 100-dimensional state features, and 100-dimensional energy features.

[0041] In a specific embodiment, the process of executing step S106 may specifically include the following steps: (1) Perform multimodal hierarchical decomposition on the path dynamics features to obtain a feature subspace sequence, and perform cross-modal self-attention calculation on the feature subspace sequence to obtain an inter-modal correlation matrix; (2) Perform nonlinear feature decoupling processing on the inter-modal correlation matrix to obtain a set of key modal components, and perform hierarchical encoding processing on the key modal component set to obtain a multi-layer feature representation vector; (3) Confidence inference is performed on the multi-layer feature representation vector through a deep probabilistic graph network to obtain a modal fusion weight matrix, and the modal fusion weight matrix is ​​dynamically adjusted to obtain an adaptive weight allocation scheme; (4) The adaptive weight allocation scheme is subjected to spatiotemporal consistency constraint processing to obtain the optimal path score of the reach stacker operation, and the optimal path score of the reach stacker operation is subjected to dynamic parameter mapping processing to obtain the dynamic performance parameters; (5) The optimal path score and dynamic performance parameters of the reach stacker operation are predicted in time series by using a bidirectional recurrent neural network to obtain a path evolution sequence, which is then feedback-corrected to obtain an initial planning scheme. (6) Perform robustness analysis on the initial planning scheme to obtain the scheme stability index, and then use the reinforcement learning algorithm to optimize the strategy of the scheme stability index to obtain a set of alternative schemes; (7) Perform multi-objective trade-off processing on the alternative plan set to obtain candidate planning solutions, and perform constraint verification processing on the candidate planning solutions to obtain planning feasibility evaluation; (8) The uncertainty of planning feasibility assessment is quantified through the variational inference network to obtain the risk assessment matrix, and the risk assessment matrix is ​​subjected to threshold screening to obtain a self-correcting path planning solution.

[0042] Specifically, the path dynamics features are subjected to multimodal hierarchical decomposition. Multimodal hierarchical decomposition refers to hierarchical processing of path feature data containing geometric features, dynamic features and energy features according to different feature modes. This process decomposes the original features into multiple subspaces, each of which represents a specific feature mode. Then, the correlation between different feature modes is calculated through the cross-modal self-attention mechanism to generate an inter-modal correlation matrix. The self-attention mechanism reflects the degree of mutual influence between different features by calculating the similarity scores between different modal features. The obtained inter-modal correlation matrix is ​​subjected to nonlinear feature decoupling to separate the key components in each modality. The decoupling process uses nonlinear transformation to separate the mutually coupled features and obtain a set of independent key modal components. These components are hierarchically encoded to form a multi-level feature representation vector. Hierarchical coding adopts a multi-level coding structure to gradually extract more abstract feature representations from low-level local features to high-level global features.

[0043] Then, a deep probabilistic graph network is used to perform confidence reasoning on the multi-layer feature representation vector. The deep probabilistic graph network evaluates the reliability of different features by establishing probabilistic dependencies between feature nodes and generates a modal fusion weight matrix. The weight matrix is ​​dynamically thresholded and the weights of each modality are adaptively adjusted according to the real-time status to form an adaptive weight distribution scheme. Spatiotemporal consistency constraints are imposed on the weight distribution scheme to ensure the continuity of the path score in time and space, and the optimal path score for the front loader operation is obtained. The path score is mapped to a specific physical parameter space through a dynamic model to obtain dynamic performance parameters including speed, acceleration and other parameters. Then, a bidirectional recurrent neural network is used to perform time series prediction on these parameters to generate an evolution sequence of the path, and the prediction results are corrected through a feedback mechanism to form an initial planning scheme.

[0044] The initial solution is analyzed for robustness and its stability under different working conditions is evaluated. The decision strategy of the solution is optimized by reinforcement learning algorithm to generate multiple alternative solutions. Multi-objective trade-offs are made for these alternative solutions, considering multiple objectives such as efficiency and safety, and candidate planning solutions are screened out. Constraint verification is performed on the candidate solutions to evaluate their feasibility. Finally, the variational inference network is used to quantify the uncertainty of the planning solution and generate a risk assessment matrix. The solutions are screened by setting risk thresholds, and finally a self-correcting path planning solution is obtained.

[0045] For example, in a 120×100m container yard, a device carrying a 15-ton container is planned for path planning. The original 300-dimensional path dynamics feature is first decomposed into 5 subspaces, each containing 60-dimensional features. A 5×5 modal association matrix is ​​obtained by self-attention calculation, in which the correlation strength between geometric features and dynamic features is 0.85. After nonlinear decoupling and hierarchical encoding, a 150-dimensional multi-layer feature representation vector is obtained. After deep probabilistic graph network analysis, the fusion weights of each modality are obtained, in which the weight of dynamic features is 0.4, the weight of geometric features is 0.35, and the weight of energy features is 0.25. The path evolution prediction generates a state sequence of 10 time steps, each state contains parameters such as position, velocity, and acceleration. Through robustness analysis and multi-objective trade-offs, 10 candidate solutions are selected from 50 alternative solutions. The final self-correction path planning solution has characteristic parameters of a total length of 108 meters, an average speed of 2.5m / s, and a maximum steering angle of 30 degrees, which meets the requirements of safety and efficiency.

[0046] The above describes the path planning simulation method for the container yard reach stacker operation in the embodiment of the present application. The following describes the path planning simulation system for the container yard reach stacker operation in the embodiment of the present application. Figure 2 In the embodiment of the present application, an embodiment of the path planning simulation system for container yard reach stacker operation includes: An analysis module 201 is used to perform a spatiotemporal correlation analysis on the container yard and the reach stacker to obtain digital parameters of the container yard; A modeling module 202 is used to perform nonlinear multi-body dynamics three-dimensional modeling of a preset container yard space based on the digital parameters of the container yard, and obtain a heterogeneous data set including equipment coupling state data, dynamic constraint propagation data and time-varying boundary condition data; A partitioning module 203 is used to perform adaptive resolution multi-layer grid partitioning analysis on the heterogeneous data set to obtain a dynamic cost map considering topological changes, a density cost map based on entropy values, and a safety cost map based on collision probability; A topology module 204 is used to perform multi-scale path topology analysis on the dynamic cost map, the density cost map and the safety cost map to obtain potential path manifold data with spatiotemporal uncertainty; A quantization module 205 is used to perform non-stationary state quantitative analysis on the potential path manifold data to obtain path dynamics characteristics, wherein the path dynamics characteristics include path differential geometry characteristics, spatiotemporal entropy characteristics, and energy gradient characteristics; The allocation module 206 is used to perform multimodal feature fusion and hierarchical weight allocation on the path dynamic characteristics according to the preset path performance standard, to obtain the optimal path score and dynamic performance parameters of the reach stacker operation with time and space adaptability, and to generate a self-correcting path planning scheme according to the optimal path score and the dynamic performance parameters of the reach stacker operation.

[0047] Through the collaboration of the above components, the digital parameters of the container yard are obtained by analyzing the spatiotemporal correlation between the container yard and the reach stacker, realizing the accurate digital expression of the yard environment and effectively reflecting the dynamic interaction between the reach stacker and the environment. Based on the digital parameters of the container yard, nonlinear multi-body dynamics three-dimensional modeling is performed to obtain a heterogeneous data set containing equipment coupling state data, dynamic constraint propagation data and time-varying boundary condition data, accurately describing the complex coupling relationship and dynamic constraint conditions between multiple devices. By performing adaptive resolution multi-layer meshing analysis on the heterogeneous data set, a dynamic cost map considering topological changes, a density cost map based on entropy values ​​and a safety cost map based on collision probability are generated, realizing a multi-dimensional evaluation of the path planning environment. Multi-scale path topology analysis is performed on these cost maps to obtain potential path manifold data with spatiotemporal uncertainty, effectively capturing the dynamic change characteristics of the path. By performing non-stationary state quantitative analysis on the potential path manifold data, the path dynamic characteristics including path differential geometry characteristics, spatiotemporal entropy characteristics and energy gradient characteristics are obtained, which comprehensively characterizes the geometric and dynamic properties of the path. Finally, based on the preset path performance standard, multimodal feature fusion and hierarchical weight allocation are performed on the path dynamics characteristics to obtain the optimal path score and dynamic performance parameters of the reach stacker operation with spatiotemporal adaptability, and a self-correcting path planning scheme is generated to ensure the real-time adaptability and robustness of the planning scheme. Through multi-level path analysis and feature extraction, accurate planning of the reach stacker path in a complex yard environment is achieved, improving the accuracy and reliability of path planning.

[0048] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A path planning simulation method for container yard reach stacker operation, characterized in that: The path planning simulation method for the container yard reach stacker operation includes: Conduct time-space correlation analysis on container yard and reach stacker to obtain digital parameters of container yard; Based on the digital parameters of the container yard, a nonlinear multi-body dynamic three-dimensional modeling is performed on the preset container yard space to obtain a heterogeneous data set including equipment coupling state data, dynamic constraint propagation data and time-varying boundary condition data; Performing adaptive resolution multi-layer grid division analysis on the heterogeneous data set to obtain a dynamic cost map considering topological changes, a density cost map based on entropy values, and a safety cost map based on collision probability; Performing multi-scale path topology analysis on the dynamic cost map, the density cost map, and the safety cost map to obtain potential path manifold data with spatiotemporal uncertainty; Performing non-stationary state quantitative analysis on the potential path manifold data to obtain path dynamics characteristics, wherein the path dynamics characteristics include path differential geometry characteristics, spatiotemporal entropy characteristics, and energy gradient characteristics; According to the preset path performance standard, the path dynamic characteristics are subjected to multimodal feature fusion and hierarchical weight allocation to obtain the optimal path score and dynamic performance parameters of the reach loader operation with temporal and spatial adaptability, and a self-correcting path planning scheme is generated based on the optimal path score and the dynamic performance parameters of the reach loader operation.

2. The path planning simulation method for container yard reach stacker operation according to claim 1, characterized in that: The spatial and temporal correlation analysis of the container yard and the reach stacker is performed to obtain digital parameters of the container yard, including: Perform spatial grid analysis on the static layout data of the container yard to obtain the basic spatial parameter table of the yard, and perform time series segmentation on the real-time position data of the reach stacker to obtain the dynamic trajectory sequence of the equipment; Performing a topological structure analysis on the channel area data in the basic spatial parameter table of the storage yard to obtain a channel connectivity map, and performing time window segmentation processing on the equipment dynamic trajectory sequence to obtain an equipment behavior feature sequence; Calculating the node importance of the channel connectivity graph to obtain a critical path node set, and performing time-frequency domain conversion processing on the device behavior feature sequence to obtain a typical operating condition spectrum of the device; The key path node set and the typical operating condition spectrum of the equipment are extracted through a bidirectional long short-term memory network to obtain a yard-equipment interaction feature matrix, and the yard-equipment interaction feature matrix is ​​subjected to principal component dimensionality reduction processing to obtain a key time-space feature vector; The key spatiotemporal feature vectors are normalized to obtain a standardized feature data set, and the standardized feature data set is subjected to multimodal separation processing through tensor decomposition to obtain digital parameters of the container yard.

3. The path planning simulation method for container yard reach stacker operation according to claim 1, characterized in that: Based on the digital parameters of the container yard, nonlinear multi-body dynamics three-dimensional modeling is performed on the preset container yard space to obtain a heterogeneous data set including equipment coupling state data, dynamic constraint propagation data and time-varying boundary condition data, including: Performing nonlinear dynamic three-dimensional modeling processing on the equipment parameters in the digital parameters of the container yard to obtain the equipment motion state equation, and performing multi-body system coupling analysis processing on the equipment motion state equation to obtain the equipment coupling state data; Performing constraint condition analysis processing on the device coupling state data to obtain an initial constraint condition set, and performing dynamic propagation link analysis processing on the initial constraint condition set to obtain the dynamic constraint propagation data; Performing boundary feature extraction processing on the dynamic constraint propagation data to obtain a fixed boundary constraint set, and performing time-varying disturbance analysis processing on the fixed boundary constraint set to obtain the time-varying boundary condition data; Performing relative motion analysis processing on the device position data in the device coupling state data to obtain inter-device force data, and performing state space reconstruction processing on the inter-device force data to obtain a coupling dynamics equation group; The heterogeneous data set is obtained by performing heterogeneous feature combination processing on the device coupling state data, the dynamic constraint propagation data and the time-varying boundary condition data through a multimodal data fusion algorithm.

4. The path planning simulation method for container yard reach stacker operation according to claim 1, characterized in that: The adaptive resolution multi-layer grid division analysis of the heterogeneous data set is performed to obtain a dynamic cost map considering topological changes, a density cost map based on entropy values, and a safety cost map based on collision probability, including: Performing multi-layer grid density calculation processing on the spatiotemporal state data in the heterogeneous data set to obtain a basic grid partition matrix, and performing topological structure change analysis processing on the basic grid partition matrix to obtain the dynamic cost map; Performing entropy feature extraction processing on the device coupling state data in the heterogeneous data set to obtain a regional entropy distribution matrix, and performing density mapping processing on the regional entropy distribution matrix to obtain the density cost map; Performing collision risk prediction processing on the time-varying boundary condition data in the heterogeneous data set to obtain a collision probability distribution matrix, and performing safety level classification processing on the collision probability distribution matrix to obtain the safety cost map; Performing time-series segmentation processing on the topology change data in the dynamic cost map to obtain a topology change feature sequence, and performing spatial correlation analysis processing on the topology change feature sequence to obtain a grid dynamic update parameter; The dynamic cost map, the density cost map and the safety cost map are subjected to resolution calibration processing by using an adaptive grid refinement algorithm to obtain a multi-layer grid cost map group.

5. The path planning simulation method for container yard reach stacker operation according to claim 1, characterized in that: The multi-scale path topology analysis is performed on the dynamic cost map, the density cost map, and the safety cost map to obtain potential path manifold data with spatiotemporal uncertainty, including: Performing multi-scale decomposition processing on the dynamic cost map to obtain topological structure sets of different scales, and performing connected domain analysis processing on the topological structure sets of different scales to obtain a path connectivity matrix; Performing hierarchical feature extraction processing on the density cost map to obtain density gradient field data, and performing manifold embedding processing on the density gradient field data to obtain an initial manifold structure; Performing probability field construction processing on the safety cost map to obtain a time-varying probability distribution map, and performing uncertainty propagation processing on the time-varying probability distribution map to obtain state uncertainty data; The path connectivity matrix and the initial manifold structure are subjected to feature fusion processing to obtain a path candidate set, and the path candidate set and the state uncertainty data are subjected to spatiotemporal mapping processing to obtain the potential path manifold data.

6. The path planning simulation method for container yard reach stacker operation according to claim 1, characterized in that: The non-stationary state quantitative analysis of the potential path manifold data is performed to obtain path dynamics characteristics, and the path dynamics characteristics include path differential geometry characteristics, spatiotemporal entropy characteristics and energy gradient characteristics, including: Performing differential geometry calculation processing on the potential path manifold data to obtain a curvature change sequence, and performing feature extraction processing on the curvature change sequence to obtain the path differential geometry feature; Performing spatiotemporal state analysis processing on the potential path manifold data to obtain a state transfer matrix, and performing entropy value calculation processing on the state transfer matrix to obtain the spatiotemporal entropy feature; Performing energy function construction processing on the potential path manifold data to obtain an energy distribution spectrum, and performing gradient calculation processing on the energy distribution spectrum to obtain the energy gradient feature; The path differential geometry feature, the spatiotemporal entropy feature and the energy gradient feature are subjected to feature combination processing to obtain the path dynamics feature.

7. The path planning simulation method for container yard reach stacker operation according to claim 1, characterized in that: According to the preset path performance standard, the path dynamic characteristics are subjected to multimodal feature fusion and hierarchical weight allocation to obtain the optimal path score and dynamic performance parameters of the reach stacker operation with spatiotemporal adaptability, and a self-correcting path planning scheme is generated according to the optimal path score and the dynamic performance parameters of the reach stacker operation, including: Performing multimodal hierarchical decomposition processing on the path dynamics features to obtain a feature subspace sequence, and performing cross-modal self-attention calculation processing on the feature subspace sequence to obtain an inter-modal association matrix; Performing nonlinear feature decoupling processing on the inter-modal correlation matrix to obtain a key modal component set, and performing hierarchical encoding processing on the key modal component set to obtain a multi-layer feature representation vector; Performing confidence reasoning processing on the multi-layer feature representation vector through a deep probability graph network to obtain a modal fusion weight matrix, and performing dynamic threshold adjustment processing on the modal fusion weight matrix to obtain an adaptive weight allocation scheme; Performing spatiotemporal consistency constraint processing on the adaptive weight allocation scheme to obtain an optimal path score for the reach stacker operation, and performing dynamic parameter mapping processing on the optimal path score for the reach stacker operation to obtain the dynamic performance parameter; Performing time series prediction processing on the optimal path score of the reach stacker operation and the dynamic performance parameters through a bidirectional recurrent neural network to obtain a path evolution sequence, and performing feedback correction processing on the path evolution sequence to obtain an initial planning scheme; Performing robustness analysis on the initial planning scheme to obtain a scheme stability index, and performing strategy optimization on the scheme stability index through a reinforcement learning algorithm to obtain a set of alternative schemes; Performing multi-objective trade-off processing on the set of alternative solutions to obtain candidate planning solutions, and performing constraint verification processing on the candidate planning solutions to obtain planning feasibility evaluation; The uncertainty of the planning feasibility assessment is quantified through a variational inference network to obtain a risk assessment matrix, and the risk assessment matrix is ​​subjected to threshold screening to obtain the self-correcting path planning solution.

8. A path planning simulation system for container yard reach stacker operation, used to implement the path planning simulation method for container yard reach stacker operation as claimed in any one of claims 1 to 7, characterized in that: The path planning simulation system for container yard reachstacker operation includes: The analysis module is used to perform spatiotemporal correlation analysis between the container yard and the reach stacker to obtain digital parameters of the container yard; A modeling module, for performing nonlinear multi-body dynamics three-dimensional modeling of a preset container yard space based on the digital parameters of the container yard, and obtaining a heterogeneous data set including equipment coupling state data, dynamic constraint propagation data and time-varying boundary condition data; A partitioning module is used to perform adaptive resolution multi-layer grid partitioning analysis on the heterogeneous data set to obtain a dynamic cost map considering topological changes, a density cost map based on entropy values, and a safety cost map based on collision probability; A topology module, used for performing multi-scale path topology analysis on the dynamic cost map, the density cost map and the safety cost map to obtain potential path manifold data with spatiotemporal uncertainty; A quantification module, used for performing non-stationary state quantitative analysis on the potential path manifold data to obtain path dynamics characteristics, wherein the path dynamics characteristics include path differential geometry characteristics, spatiotemporal entropy characteristics, and energy gradient characteristics; The allocation module is used to perform multimodal feature fusion and hierarchical weight allocation on the path dynamic characteristics according to a preset path performance standard, so as to obtain an optimal path score and dynamic performance parameters of a reach stacker operation with spatiotemporal adaptability, and to generate a self-correcting path planning scheme according to the optimal path score and the dynamic performance parameters of the reach stacker operation.

Images