Multi-objective path planning method, device and equipment and storage medium

Abstract

The application discloses a multi-target path planning method and device, equipment and a storage medium, and relates to the technical field of traffic path planning. The method comprises the following steps: acquiring solar radiation data and original map data, performing multi-source data fusion based on the solar radiation data and the original map data, and obtaining radiation road network data; constructing a total cost function of path length by using a cumulative cost function of path length and a heuristic function of estimated cost based on the radiation road network data, generating a candidate path according to the total cost function; calculating the average radiation intensity of the candidate path based on the radiation road network data, and then obtaining the energy recovery amount of the candidate path; constructing a double-target cost function based on the total cost function and the energy recovery amount, adjusting the node priority and screening and updating a non-dominated solution set according to the double-target cost function, generating a target candidate path set according to the non-dominated solution set; and determining an optimal balance path in the target candidate path set by using a multi-dimensional index quantitative evaluation and a balance coefficient sorting.

Description

Technical Field

[0001] This application relates to the field of traffic route planning technology, and in particular to a multi-objective route planning method, apparatus, device and storage medium. Background Technology

[0002] With the rapid electrification transformation of the ride-hailing industry, solar-powered electric vehicles (SEVs) are gradually becoming an important direction for alleviating range anxiety associated with pure electric vehicles due to their potential to improve energy self-sufficiency through onboard photovoltaic modules. Route planning, as a crucial aspect of vehicle energy management, needs to incorporate solar radiation beyond traditional shortest path or lowest energy consumption objectives. This allows vehicles to maximize the use of solar energy during operation, thereby extending driving range and reducing dependence on the external power grid. Therefore, route planning methods for solar-powered electric vehicles urgently need to integrate solar radiation data to achieve synergistic optimization of route selection and energy recovery, meeting the technical requirements of multi-objective decision-making in complex traffic environments.

[0003] Currently, existing route planning methods mainly focus on optimizing single objectives such as route length, travel time, or energy consumption. While some studies have incorporated environmental factors, they typically only consider static energy consumption models or simple weather classifications, failing to deeply integrate high spatiotemporal resolution solar radiation data with road network structure. Regarding heuristic search strategies, existing techniques mostly use Euclidean distance as the estimated cost function, failing to fully reflect the impact of three-dimensional spatial distance on route cost under complex terrain conditions. Furthermore, existing methods often treat energy recovery as an additional constraint or weight term when constructing the objective function, lacking modeling of a direct quantitative relationship between the average radiation intensity of the route and the amount of energy recovered, leading to significant deviations in the energy utilization efficiency of the planning results.

[0004] Therefore, how to simultaneously consider the cost of path length and the benefits of solar radiation recovery during the path planning process has become a pressing technical problem.

[0005] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main objective of this application is to provide a multi-objective path planning method, apparatus, device, and storage medium, which aims to solve the technical problem of how to simultaneously consider the path length cost and the solar radiation recovery benefits during the path planning process.

[0007] To achieve the above objectives, this application proposes a multi-objective path planning method, the method comprising:

[0008] Acquire solar radiation data and raw map data, and perform multi-source data fusion based on the solar radiation data and raw map data to obtain radial road network data;

[0009] Based on the radial road network data, a total cost function for the path length is constructed using a cumulative cost function for the path length and a heuristic function for the estimated cost. Candidate paths are then generated based on the total cost function.

[0010] Based on the radiation network data, the average radiation intensity of the candidate path is calculated to obtain the energy recovery amount of the candidate path;

[0011] A dual-objective cost function is constructed based on the total cost function and the energy recovery amount. Node priorities are adjusted and non-dominated solution sets are updated according to the dual-objective cost function. A set of target candidate paths is generated based on the non-dominated solution sets.

[0012] The optimal balanced path is determined from the set of target candidate paths through multi-dimensional quantitative evaluation and balance coefficient ranking.

[0013] In one embodiment, the step of acquiring solar radiation data and raw map data, and performing multi-source data fusion based on the solar radiation data and the raw map data to obtain radial road network data includes:

[0014] Solar radiation data is obtained through sensor networks, meteorological satellites, or historical observation databases; raw map data is obtained through open street maps or systems designated by transportation departments.

[0015] The solar radiation data is preprocessed by removing outliers and filling in missing values, and the original map data is preprocessed by coordinate projection transformation and format standardization.

[0016] Based on linear nearest neighbor interpolation, spatial interpolation is performed on the preprocessed discrete solar radiation points to generate continuous radiation intensity surface data covering the target area, and a mapping relationship between geographic coordinates and radiation intensity is established.

[0017] The original map data is parsed into a "node-edge" graph structure, where nodes refer to road intersections and edges refer to road segments, and each edge is assigned a length attribute.

[0018] Through spatial overlay analysis, the continuous radiation intensity surface data is mapped to the nodes and edges of the road network to form radiation road network data containing length and radiation attributes; wherein, each node is associated with the real-time radiation intensity of its geographical location, and each edge is associated with the average radiation intensity along its line.

[0019] In one embodiment, the step of constructing a total cost function for the path length based on the radial road network data using a cumulative cost function of the path length and a heuristic function of the estimated cost, and generating candidate paths based on the total cost function, includes:

[0020] Based on the length attribute of the radial road network data, the cumulative cost of the starting node is set to zero, and the cumulative cost of the remaining nodes is initialized to a preset value, forming the initial state of the path length cost matrix.

[0021] Traverse all adjacent nodes of the current search node, and calculate the cumulative path length from the starting node through the current node to the adjacent nodes based on the edge length attribute in the radial road network data.

[0022] For each adjacent node, based on the coordinate information of the adjacent node in the radial road network data and the coordinates of the target node, the Chebyshev distance is calculated as a heuristic function for estimating the cost.

[0023] The cumulative cost is summed with the heuristic function value to form the total cost function in the path length dimension;

[0024] Based on the total cost function, nodes are prioritized to generate candidate paths that minimize path length cost.

[0025] In one embodiment, the step of calculating the path-average radiation intensity of the candidate path based on the radiation network data, and then obtaining the energy recovery amount of the candidate path, includes:

[0026] The node set of the candidate path is obtained based on the radial road network data, and the real-time radiation intensity of each node in the candidate path is extracted.

[0027] The path average radiation intensity is calculated by averaging the real-time radiation intensity of all nodes in the candidate path.

[0028] The total length of the candidate path is obtained based on the radial road network data, and the path travel time is calculated by combining the preset average driving speed.

[0029] The energy recovery of the candidate path is calculated based on the average radiation intensity of the path and the travel time of the path, combined with the parameters of the photovoltaic panel.

[0030] In one embodiment, the step of constructing a dual-objective cost function based on the total cost function and the energy recovery amount includes:

[0031] Define the dual-objective dimension of the dual-objective cost function; wherein, the dual-objective dimension is path length minimization and energy recovery maximization;

[0032] By introducing a negative sign, the energy recovery amount is converted into a radiation energy cost function;

[0033] The total cost function of the path length and the cost function of the radiation energy are combined to form a dual-objective cost function.

[0034] In one embodiment, the step of adjusting node priorities and filtering and updating the non-dominated solution set according to the bi-objective cost function, and generating a set of target candidate paths based on the non-dominated solution set includes:

[0035] Construct an empty non-dominated solution set with the starting point as the initial node, and set a path search priority queue;

[0036] Select the path with the lowest current cost from the path search priority queue, expand the adjacent nodes of the endpoint node in the path with the lowest current cost, and generate a new path.

[0037] Calculate the bi-objective cost of the new path and update the non-dominated solution set using a Pareto optimization mechanism;

[0038] When the path search reaches the endpoint node, the expansion stops and each path in the non-dominated solution set is extracted to form a target candidate path set; where each path is a Pareto optimal solution.

[0039] In one embodiment, the multidimensional indicators include one or more of the following: total path length, detour ratio, average path radiation intensity, and cumulative energy recovery; the calculation of the balance coefficient involves dynamic weighting and summing of the path length dimension and the radiation energy dimension.

[0040] Furthermore, to achieve the above objectives, this application also proposes a multi-objective path planning device, which includes:

[0041] The data preprocessing module is used to acquire solar radiation data and raw map data, and perform multi-source data fusion based on the solar radiation data and the raw map data to obtain radial road network data;

[0042] The first processing module is used to construct a total cost function for the path length based on the radial road network data by using a cumulative cost function for the path length and a heuristic function for the estimated cost, and to generate candidate paths based on the total cost function;

[0043] The second processing module is used to calculate the average radiation intensity of the candidate path based on the radiation road network data, and then obtain the energy recovery amount of the candidate path.

[0044] The candidate path generation module is used to construct a dual-objective cost function based on the total cost function and the energy recovery amount, adjust node priorities and filter and update the non-dominated solution set according to the dual-objective cost function, and generate a target candidate path set according to the non-dominated solution set.

[0045] The path evaluation module determines the optimal balanced path from the set of target candidate paths through multi-dimensional quantitative evaluation and balance coefficient ranking.

[0046] In addition, to achieve the above objectives, this application also proposes a multi-objective path planning device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the multi-objective path planning method as described above.

[0047] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the multi-objective path planning method described above.

[0048] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the multi-objective path planning method described above.

[0049] One or more technical solutions proposed in this application have at least the following technical effects:

[0050] This application acquires solar radiation data and raw map data, performs multi-source data fusion based on the solar radiation data and the raw map data to obtain radial road network data; based on the radial road network data, constructs a total cost function for the path length using a cumulative cost function of path length and a heuristic function of estimated cost, and generates candidate paths according to the total cost function; based on the radial road network data, calculates the average radiation intensity of the candidate paths to obtain the energy recovery amount of the candidate paths; constructs a dual-objective cost function based on the total cost function and the energy recovery amount, adjusts node priorities and updates the non-dominated solution set according to the dual-objective cost function, and generates a set of target candidate paths based on the non-dominated solution set; and determines the optimal balanced path in the set of target candidate paths through multi-dimensional index quantification evaluation and balance coefficient sorting. By constructing a dual-objective cost function, this application enables the system to simultaneously optimize path length and radiation benefits during path search, significantly improving the energy recovery capability of solar-powered electric vehicles while maintaining high driving efficiency, and providing a feasible path solution that achieves the best balance between time and energy benefits for actual operation. Attached Figure Description

[0051] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating an embodiment of the multi-objective path planning method of this application.

[0054] Figure 2 This is a flowchart illustrating Embodiment 2 of the multi-objective path planning method of this application.

[0055] Figure 3 This is a flowchart illustrating Embodiment 3 of the multi-objective path planning method of this application;

[0056] Figure 4 This is a flowchart illustrating Embodiment 4 of the multi-objective path planning method of this application.

[0057] Figure 5 This is a flowchart illustrating Embodiment 5 of the multi-objective path planning method of this application;

[0058] Figure 6 This is a flowchart illustrating Embodiment Six of the multi-objective path planning method of this application;

[0059] Figure 7 This is a schematic diagram of a path planning result using the multi-objective path planning method of this application;

[0060] Figure 8 This is a schematic diagram of the module structure of the multi-objective path planning device according to an embodiment of this application;

[0061] Figure 9 This is a schematic diagram of the device structure of the hardware operating environment involved in the multi-objective path planning method in the embodiments of this application.

[0062] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0063] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0064] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0065] Existing technologies present a technical challenge in balancing path length costs and solar radiation recovery benefits during path planning.

[0066] This application provides a solution that obtains radial road network data by acquiring solar radiation data and raw map data, and then performing multi-source data fusion based on the solar radiation data and the raw map data. Based on the radial road network data, a total cost function for the path length is constructed using a cumulative cost function of path length and a heuristic function of estimated cost. Candidate paths are generated based on the total cost function. The average radiation intensity of the candidate paths is calculated based on the radial road network data to obtain the energy recovery amount of the candidate paths. A dual-objective cost function is constructed based on the total cost function and the energy recovery amount. Node priorities are adjusted and non-dominated solution sets are updated based on the dual-objective cost function. A set of target candidate paths is generated based on the non-dominated solution sets. The optimal balanced path is determined from the set of target candidate paths through multi-dimensional quantitative evaluation and balance coefficient sorting.

[0067] Based on this, embodiments of this application provide a multi-objective path planning method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the multi-objective path planning method of this application.

[0068] In this embodiment, the multi-objective path planning method includes steps S10 to S50:

[0069] Step S10: Obtain solar radiation data and raw map data, and perform multi-source data fusion based on the solar radiation data and the raw map data to obtain radial road network data;

[0070] It should be noted that, in this application embodiment, solar radiation data refers to information obtained through satellite remote sensing, ground monitoring stations, or numerical meteorological models, reflecting the distribution of solar irradiance within a specific spatiotemporal range. It typically includes geographical location, timestamps, and radiation intensity values. Original map data refers to the basic geographic information describing the road network, including road grade, number of lanes, speed limits, topological connections, and the latitude and longitude coordinates of nodes. Multi-source data fusion refers to the process of integrating heterogeneous datasets from different sensors, formats, or physical meanings into a unified, consistent new dataset containing rich attributes through a series of algorithms and processing flows. Radiation road network data refers to enhanced road network data obtained by fusing solar radiation data with original map data, containing both road geometric attributes and radiation environment attributes; its essence is a graph structure with "length" and "radiation intensity" attributes. This application overcomes the limitations of a single data source through data fusion, enabling path search to be performed simultaneously in both road space and radiation energy dimensions. The system can tightly integrate the abstract radiation field with the concrete road network, thereby accurately evaluating and optimizing paths in a real urban traffic environment.

[0071] In one possible implementation, multi-source data fusion may further include sub-steps such as data alignment, coordinate system unification, and attribute association.

[0072] Step S20: Based on the radial road network data, construct the total cost function of the path length through the cumulative cost function of the path length and the heuristic function of the estimated cost, and generate candidate paths according to the total cost function;

[0073] It should be noted that, in this embodiment, the cumulative cost function of path length refers to the sum of the lengths of all road segments traversed from the path's starting point, used to measure the spatial distance cost of the path. Chebyshev distance refers to the maximum difference between the horizontal and vertical coordinates of two points in a two-dimensional grid coordinate system, used in this embodiment as a distance estimate from the current node to the target point. The heuristic function, in graph search algorithms, is a function used to estimate the minimum cost from the current node to the target node, guiding the search direction and affecting algorithm efficiency. The total cost function of path length is a mathematical expression composed of the cumulative cost and the heuristic function, evaluating the quality of the path from the starting point to the current node in the "distance" dimension. Candidate paths refer to potential feasible paths generated during the search process that require further evaluation. The purpose of this step is to efficiently generate a series of candidate path solutions that are competitive in the path length dimension. By constructing a total cost function that balances accurate cumulative values ​​and efficient heuristic estimation, the system can quickly narrow the search range in a vast road network space, focusing on promising paths, and significantly improve search efficiency while ensuring a certain level of path length competitiveness.

[0074] In one possible implementation, the cumulative cost function can be represented as the sum of the length attributes of all edges on the path P(s, n) from the starting point s to the current node n.

[0075] Step S30: Based on the radiation network data, calculate the path average radiation intensity of the candidate path to obtain the energy recovery amount of the candidate path;

[0076] It should be noted that, in this embodiment, the path-average radiant intensity refers to the arithmetic mean or weighted average of the radiant intensity values ​​of all nodes (or edges) traversed on a candidate path, used to characterize the overall solar energy resource level of the path. Energy recovery refers to the total amount of electrical energy that the onboard photovoltaic system of a solar-powered electric vehicle can theoretically collect and convert when traveling along a candidate path. The energy recovery of a candidate path is a quantified value calculated by combining parameters such as the path-average radiant intensity, path travel time, photovoltaic panel area, and photoelectric conversion efficiency. This step quantifies and evaluates each generated candidate path from the perspective of energy revenue. By performing this step, the system can transform the abstract radiant intensity into a concrete and comparable energy revenue, providing a second key quantification dimension for dual-objective optimization. This application can explicitly incorporate environmental energy supply into the path decision-making process, thereby improving the overall energy utilization efficiency of the vehicle.

[0077] Step S40: Construct a dual-objective cost function based on the total cost function and the energy recovery amount; adjust node priorities and filter and update the non-dominated solution set according to the dual-objective cost function; generate a target candidate path set according to the non-dominated solution set.

[0078] It should be noted that, in the embodiments of this application, the dual-objective cost function refers to a comprehensive evaluation function that simultaneously includes the two objective dimensions of minimizing path length and maximizing energy recovery. The non-dominated solution set refers to a set of solutions in a multi-objective optimization problem where any solution is not dominated by any other solution in the set across all objective dimensions; that is, it is better in one objective but not worse in another, and is called the Pareto front. By jointly optimizing the separately established path length cost and energy recovery benefits, and by introducing a Pareto optimization mechanism, the system can automatically find a series of path schemes that achieve the optimal balance between length and energy without pre-setting the weights of the two objectives. The system can effectively overcome the one-sidedness of single-objective optimization, avoid falling into extreme cases where either the path is too long or the energy gain is too low, and enhance the objectivity of the system's decision-making.

[0079] In one possible implementation, the rule for filtering and updating the non-dominated solution set could be: if a new path is better than the other in terms of both path length and energy recovery, then it is added to the non-dominated solution set, and solutions in the original set dominated by the new path are removed. To ensure the practicality of the path, a path length constraint can also be added during the update process, for example, requiring the length of the new path to not exceed a certain percentage (e.g., 110%) of the shortest path, to avoid unreasonable detours caused by excessive pursuit of energy recovery.

[0080] Step S50: Determine the optimal balanced path from the target candidate path set through multi-dimensional quantitative evaluation and balance coefficient ranking.

[0081] It should be noted that, in this embodiment, multi-dimensional quantitative evaluation refers to using multiple independent quantitative indicators with clear physical meaning to conduct a comprehensive, multi-faceted performance evaluation of each path in the target candidate path set. The balance coefficient is a comprehensive scalar indicator used to quantify the degree to which a path achieves a compromise and balance between driving efficiency (e.g., path length) and energy benefits (e.g., energy recovery). Its calculation can rely on the normalization and weighting of each indicator. The optimal balanced path refers to the path that best meets the current needs from the target candidate path set according to preset evaluation criteria (e.g., the highest balance coefficient). By performing this step, the system can provide users with a clear and comprehensive optimal suggestion, reducing the user's choice burden and improving the system's usability and decision-making efficiency.

[0082] In one possible implementation, the balance coefficient can be calculated by normalizing the two core indicators, path length and energy recovery, and then applying a linear weighted sum based on different weights according to the actual application scenario.

[0083] This application's embodiments construct radial road network data through multi-source data fusion, achieving unified modeling of road geometric features and environmental radiation factors. Secondly, based on dual-objective modeling of the total cost function of path length and energy recovery, combined with the Pareto optimization mechanism, it fundamentally overcomes the contradiction between driving efficiency and energy recovery inherent in traditional single-objective path planning. This ensures that the generated path achieves an effective balance between the two objectives of shortest distance and maximum energy, avoiding the unreasonable path selection problems caused by traditional methods that unilaterally pursue a single objective. Furthermore, through multi-dimensional index quantitative evaluation and balance coefficient ranking, the system can automatically identify the optimal balance path between efficiency and energy from numerous candidate paths, improving the scientific nature of decision-making and the practicality of the system.

[0084] Furthermore, referring to Figure 2 This application provides a flowchart based on the second embodiment of the multi-objective path planning method, based on the above. Figure 2 In the illustrated embodiment, the steps of acquiring solar radiation data and raw map data, and performing multi-source data fusion based on the solar radiation data and the raw map data to obtain radial road network data include A201-A205:

[0085] Step A201: Obtain solar radiation data through sensor networks, meteorological satellites, or historical observation databases, and obtain raw map data through open street maps or systems designated by the transportation department;

[0086] In one possible implementation, solar radiation intensity sampling points are established, and panoramic images of the corresponding sampling point locations are obtained using the Baidu API. The solar radiation intensity at the current location is then calculated based on the panoramic images.

[0087] Step A202: Perform preprocessing on the solar radiation data, including outlier removal and missing value imputation; and perform preprocessing on the original map data, including coordinate projection transformation and format standardization.

[0088] It should be noted that, in this embodiment, outlier removal refers to identifying and removing observational data that significantly deviates from the normal range based on statistical methods. Missing value imputation refers to filling in the missing parts of the data records using reasonable estimation algorithms. Coordinate projection transformation is the process of transforming geographic coordinates from one map projection system to another, aiming to ensure the accuracy of spatial measurements (such as length calculations). Format standardization preprocessing refers to converting map data from different sources and in different formats into a unified internal data format. Through refined preprocessing of solar radiation data and raw map data, the system can effectively eliminate noise and bias in the raw data, improve data quality and consistency, and ensure that they can be fused within the same spatial reference frame.

[0089] In one possible implementation, outlier removal from solar radiation data can be achieved using a fixed threshold method, while missing value imputation can be performed using a neighborhood averaging method.

[0090] Step A203: Based on linear nearest neighbor interpolation, spatial interpolation is performed on the preprocessed discrete solar radiation points to generate continuous radiation intensity surface data covering the target area, and a mapping relationship between geographic coordinates and radiation intensity is established.

[0091] It should be noted that, in this embodiment, linear nearest neighbor interpolation refers to acquiring several radiation sampling points around a certain grid point, calculating their average value or a simple linear weighted average, and obtaining the radiation intensity of that grid point; discrete solar radiation points refer to radiation observations that are not continuously distributed in space; continuous radiation intensity surface data refers to a surface model that covers the entire target area and has a corresponding radiation intensity value for each geographical location. By performing spatial interpolation, the system can overcome the problems of limited number and uneven distribution of monitoring points, thereby obtaining an estimated value of radiation intensity at any road location.

[0092] Step A204: Parse the original map data into a "node-edge" graph structure, where nodes refer to road intersections and edges refer to road segments, and assign a length attribute to each edge;

[0093] It should be noted that, in this embodiment, the node-edge graph structure is a mathematical model used to represent network topology relationships. In this embodiment, it specifically refers to a road network, where nodes represent road intersections or key decision points for path planning; edges represent road segments connecting two nodes; and the length attribute is a numerical value characterizing the actual spatial distance of road segments. This step transforms the original road geographic information into a graph theory model that can be recognized and processed by a computer to achieve automated path search.

[0094] Step A205: Through spatial overlay analysis, the continuous radiation intensity surface data is mapped to the nodes and edges of the road network to form radiation road network data containing length and radiation attributes; wherein, each node is associated with the real-time radiation intensity of the node's geographical location, and each edge is associated with the average radiation intensity along the edge.

[0095] It should be noted that, in this embodiment, spatial overlay analysis is used to combine two or more spatial datasets within the same geographical area to derive new spatial relationships and attribute information. By overlaying a continuous radiation intensity surface onto the road network structure, the system ensures that each element (node ​​and edge) in the road network possesses radiation environment characteristics. This achieves the organic integration of the environmental physical field and the transportation infrastructure network, enabling route planning to simultaneously consider spatial distance and energy benefits.

[0096] In one specific implementation, the length of each edge e is:

[0097] ,

[0098] in( , )and( , ) are the coordinates of the two nodes of the edge.

[0099] This application's embodiments acquire solar radiation and raw map data from multiple authoritative sources, including sensor networks, meteorological satellites, and historical databases, ensuring the comprehensiveness and timeliness of the input information. Secondly, rigorous preprocessing of the data, including outlier removal, missing value imputation, coordinate projection transformation, and format standardization, significantly improves data quality, consistency, and spatial accuracy. Furthermore, spatial interpolation based on linear nearest neighbor interpolation transforms discrete radiation observations into a continuous radiation intensity surface, effectively overcoming problems such as uneven distribution of monitoring points and data sparsity, achieving seamless spatial coverage of the radiation field. Further, by parsing the road network into a "node-edge" graph structure and adding a length attribute, a mathematical model conforming to the real road topology is constructed. Through spatial overlay analysis, the radiation attribute and road geometric attributes are successfully coupled, forming enhanced road network data with both "length" and "radiation" attributes.

[0100] In one specific implementation, spatial interpolation is performed based on linear nearest neighbor interpolation:

[0101]

[0102] in, Let R be the solar radiation intensity at node p to be interpolated, n be the number of neighboring discrete radiation monitoring points participating in the interpolation calculation, and R be the solar radiation intensity at node p to be interpolated. i The measured radiation intensity refers to the i-th discrete radiation monitoring point. This represents the distance from any interpolation point p (such as a road network node) in space to the i-th radiation monitoring point. The straight-line distance is m, which is the distance weight exponent (usually 2, but can be adjusted according to accuracy requirements). It is used to control the degree of influence of distance on the interpolation result. The larger the value of m, the greater the contribution weight of the closer monitoring point to the radiation intensity of point p.

[0103] Furthermore, referring to Figure 3 This application provides a flowchart based on the third embodiment of the multi-objective path planning method, based on the above. Figure 3 In the illustrated embodiment, the step of constructing a total cost function for the path length based on the radial road network data using a cumulative cost function for the path length and a heuristic function for the estimated cost, and generating candidate paths based on the total cost function, includes steps A301-A305:

[0104] Step A301: Based on the length attribute of the radial road network data, set the cumulative cost of the starting node to zero, and initialize the cumulative cost of the remaining nodes to a preset value to form the initial state of the path length cost matrix.

[0105] It should be noted that the length attribute refers to the numerical value stored in the radial road network data, representing the actual spatial distance of each road segment. The cumulative cost refers to the sum of the lengths of all road segments traversed from the starting node to the current node during the path search process, used to measure the actual distance cost of the path. The starting node refers to the node corresponding to the starting position specified in the path planning task. The default value is usually set to a sufficiently large positive number, such as infinity, to represent the initial cost of nodes that have not yet been explored or are unreachable. The path length cost matrix is ​​a data structure used to store the minimum known cumulative cost of each node in the graph; its initial state reflects the unknown state of the cost of each node before the search begins.

[0106] In one specific implementation, the cumulative cost is: , where P(s,n) represents the path from the starting point s to the current node n.

[0107] Step A302: Traverse all adjacent nodes of the current search node, and calculate the cumulative path length from the starting node through the current node to the adjacent node based on the edge length attribute in the radial road network data.

[0108] It should be noted that, in this embodiment, the current search node refers to the node being processed in each iteration of the path search algorithm. Adjacent nodes refer to other nodes in the graph structure that are directly connected to the current search node via edges. The edge length attribute is stored in the radial road network data, representing the numerical value of the actual spatial distance of road segments. This embodiment explores all next-hop nodes reachable from the current node and updates the cumulative path length of these nodes. By systematically traversing all adjacent nodes of the current node, the system can progressively explore and update the shortest path information from the starting point to each node in the network, discovering and recording better paths.

[0109] Step A303: For each adjacent node, calculate the Chebyshev distance as a heuristic function for estimating the cost based on the coordinate information of the adjacent node in the radial road network data and the coordinates of the target node.

[0110] It should be noted that, in the embodiments of this application, Chebyshev distance refers to the maximum absolute value of the difference between the horizontal and vertical coordinates of two points in a two-dimensional grid coordinate system. The heuristic function for cost estimation is a function used in graph search algorithms to estimate the minimum cost from the current node to the target node. It guides the search direction, avoids blind searching, and thus significantly improves the convergence speed of the algorithm.

[0111] In one specific implementation, the Chebyshev distance is used as a heuristic estimate:

[0112] ,

[0113] in,( , ) represents the planar coordinates of the current node n, ( , Let be the planar coordinates of the target node t. =max() is a maximum value function that calculates the larger of the absolute values ​​of the distances between the current node and the target node along the x-axis and y-axis as a heuristic distance estimate.

[0114] Step A304: The cumulative cost is superimposed with the heuristic function value to form the total cost function in the path length dimension;

[0115] It should be noted that the heuristic function value refers to the estimated cost from the current node N to the target node G. The total cost function in the path length dimension is a comprehensive evaluation function that combines the actual cost of the already traversed paths and the estimated cost of the remaining paths. Overlay refers to adding the cumulative cost to the heuristic function value to form the final cost estimate that guides node expansion.

[0116] In one specific implementation, the total cost function is: .

[0117] Step A305: Prioritize the nodes based on the total cost function to generate candidate paths that minimize path length cost.

[0118] It should be noted that priority ranking refers to determining the order in which nodes are processed in the search queue based on their total cost function value. By utilizing the total cost function as a guide, the system can effectively filter out high-quality path candidates from a large search space. By prioritizing the expansion of the most promising nodes, the system can find the optimal or near-optimal path with high efficiency.

[0119] In one possible implementation, the system can continue searching after generating the first path to generate a set of paths that satisfy length constraints (such as not exceeding λ times the shortest path).

[0120] In one possible implementation, path constraints are set:

[0121]

[0122] Where λ is the allowed detour ratio. The total length of the current candidate path P. This is the shortest path length from the starting point to the ending point.

[0123] This embodiment ensures a correct starting point and efficient progress in the search process by initializing the path length cost matrix and setting the cumulative cost of the starting point to zero. The system dynamically updates the cumulative path length while traversing adjacent nodes, allowing the path search to accurately reflect the actual distance cost. Using Chebyshev distance as a heuristic function effectively improves the algorithm's convergence speed and directional guidance, avoiding resource waste caused by blind searching. Constructing a total cost function combines the cumulative actual cost with estimated future expenses, providing a scientific basis for node expansion decisions. Finally, priority ranking based on the total cost function generates a competitive set of candidate paths in the path length dimension, laying the foundation for subsequent multi-objective optimization by introducing radiating targets. This scheme significantly optimizes search efficiency while ensuring path length competitiveness.

[0124] Furthermore, referring to Figure 4This application provides a flowchart based on the fourth embodiment of the multi-objective path planning method, based on the above. Figure 4 In the illustrated embodiment, the step of calculating the path-average radiation intensity of the candidate path based on the radiation network data, and then obtaining the energy recovery amount of the candidate path, includes A401-A404:

[0125] Step A401: Obtain the node set of the candidate path based on the radial road network data, and extract the real-time radiation intensity of each node in the candidate path;

[0126] Step A402: Calculate the path average radiation intensity by performing an arithmetic mean on the real-time radiation intensity of all nodes in the candidate path.

[0127] It should be noted that by summing the radiation intensity values ​​of all nodes and dividing by the total number of nodes, a single value representing the average radiation level of the entire path is obtained.

[0128] In one possible implementation, the path-averaged radiation intensity is:

[0129] ,in, The path P = (n1, n2...n) i The average radiation intensity of path P represents the arithmetic mean of the radiation intensity of all nodes along the path, where k refers to the total number of nodes in path P. The solar radiation intensity refers to the i-th node ni in path P.

[0130] Step A403: Based on the radial road network data, obtain the total length of the candidate path, and calculate the path travel time by combining it with the preset average driving speed;

[0131] It should be noted that the total length of the candidate path refers to the sum of the length attributes of all edges on the candidate path, i.e., the total spatial distance of the path. The preset average driving speed is a value representing the typical moving speed of a vehicle on this path, set based on road grade, historical traffic flow data, or real-time traffic information. The path travel time refers to the time required for a vehicle to travel through the path at a constant speed of the preset average driving speed. Optimizing the geometric length of the path into a time cost, that is, transforming the static spatial distance into a dynamic time dimension, is used for dynamically calculating energy recovery.

[0132] Step A404: Calculate the energy recovery amount of the candidate path based on the average radiation intensity of the path and the travel time of the path, combined with the photovoltaic panel parameters.

[0133] In one possible implementation, the energy recovery amount is:

[0134]

[0135] in, The average radiation intensity of path P = (n1, n2... ni) represents the arithmetic mean of the radiation intensity of all nodes on the path. PL is the path length, PVA is the area of ​​the photovoltaic panel, and TT is the path travel time.

[0136] It should be noted that photovoltaic panel parameters mainly include the panel's area and photoelectric conversion efficiency. Energy recovery refers to the absolute amount of electrical energy that a solar-powered electric vehicle's onboard photovoltaic system can theoretically collect and convert into electricity while traveling along a specific candidate path, typically measured in joules or kilowatt-hours. By combining the two key factors of radiation intensity and time with the vehicle's own physical properties, the actual energy gain achievable along each candidate path can be quantified.

[0137] This embodiment achieves accurate conversion from radial road network data to path energy recovery through systematic data extraction, statistical averaging, and physical modeling. It combines path length and driving speed to calculate travel time, enabling the energy recovery estimate to dynamically reflect the actual solar radiation situation of vehicles on the path, and providing energy dimension data for multi-objective path optimization.

[0138] Furthermore, referring to Figure 5 This application provides a flowchart based on the fifth embodiment of the multi-objective path planning method, based on the above. Figure 5 In the embodiment shown, the step of constructing a dual-objective cost function based on the total cost function and the energy recovery amount includes A501-A503:

[0139] Step A501: Define the dual-objective dimension of the dual-objective cost function; wherein the dual-objective dimension is path length minimization and energy recovery maximization;

[0140] It should be noted that the dual-objective cost function refers to a comprehensive evaluation function that simultaneously incorporates two optimization objectives, used to balance performance requirements across different dimensions during path search. The dual-objective dimensions refer to the two specific directions optimized by the function; in this embodiment, they specifically refer to the conflicting objectives of minimizing path length and maximizing energy recovery. Minimizing path length aims to improve driving efficiency by minimizing the total spatial distance of the path; while maximizing energy recovery aims to improve energy utilization efficiency by maximizing solar energy collection.

[0141] Step A502: The energy recovery amount is converted into a radiation energy cost function by introducing a negative sign;

[0142] It should be noted that the radiation energy cost function refers to the function form that transforms the energy recovery amount into a minimization problem through mathematical transformation (such as adding a negative sign). By introducing a negative sign, the system can equate "maximizing energy recovery" with "minimizing negative energy recovery," transforming the original maximization objective (energy recovery) into a minimization problem, so as to be mathematically consistent with the path length dimension.

[0143] Step A503: Combine the total cost function of the path length and the cost function of the radiation energy to form a dual-objective cost function.

[0144] It should be noted that the combination refers to merging two independent cost functions (path length total cost function and radiation energy cost function) into a multi-objective function, but without weighted summation, but rather preserving their independence for Pareto comparison.

[0145] In one possible implementation, the bi-objective cost function is:

[0146]

[0147] in, This refers to the cumulative distance to reach the node. For distance estimation to the target node, This refers to the cumulative radiation benefit reaching the node. This refers to the estimation of the radiation benefits of the remaining path.

[0148] This embodiment constructs a systematic dual-objective cost function that takes into account both efficiency and energy, thereby achieving synergistic optimization of driving efficiency and solar energy collection benefits for solar-powered electric vehicles in path planning. This allows the path search results to automatically seek the optimal balance between the two objectives without the need for manual weighting.

[0149] Furthermore, referring to Figure 6 This application provides a flowchart based on the sixth embodiment of the multi-objective path planning method, based on the above. Figure 6 In the illustrated embodiment, the steps of adjusting node priorities and updating the non-dominated solution set according to the dual-objective cost function, and generating a target candidate path set based on the non-dominated solution set, include A601-A604:

[0150] Step A601: Using the starting point as the initial node, construct an empty non-dominated solution set and set a path search priority queue;

[0151] It should be noted that the non-dominated solution set refers to the set of all Pareto optimal solutions in a multi-objective optimization problem. An empty non-dominated solution set refers to the initial state during the search initialization phase, which does not yet contain any Pareto optimal solutions.

[0152] Step A602: Select the path with the lowest current cost from the path search priority queue, expand the adjacent nodes of the endpoint node in the path with the lowest current cost, and generate a new path.

[0153] It should be noted that the path with the lowest current cost refers to the path with the lowest overall cost evaluated according to the bi-objective cost function in the priority queue. The endpoint node here specifically refers to the last node of the path currently being expanded. A new path refers to a new path formed by connecting an adjacent node to the current path.

[0154] Step A603: Calculate the bi-objective cost of the new path and update the non-dominated solution set using a Pareto optimization mechanism;

[0155] It should be noted that the Pareto optimization mechanism is used to manage and update the non-dominated solution set. This is achieved by comparing the dominance relationship between the new path and the existing solution set across the two objectives, thus maintaining the optimality of the solution set. Dominance is a core concept in multi-objective optimization; if solution A is superior to solution B in at least one objective and not inferior to solution B in the remaining objectives, then A is said to dominate B. This application ensures that each solution in a dynamically maintained, high-quality non-dominated solution set is optimal under both objectives.

[0156] Step A604: When the path search reaches the endpoint node, stop expanding and extract each path in the non-dominated solution set to form a target candidate path set; wherein each path is a Pareto optimal solution.

[0157] It should be noted that the endpoint node refers to the node corresponding to the specified destination location in the path planning task. A Pareto optimal solution is one in the feasible solution set where no other solution is inferior to it in all objectives and strictly superior to it in at least one objective. The target candidate path set refers to the final set of candidate solutions consisting of all paths in the non-dominated solution set. This step is used to determine the termination condition of the search and finally output the Pareto-optimized path set. At this point, the system has completed the core process of multi-objective path search, obtaining a path candidate set that is Pareto optimal in both efficiency and energy dimensions.

[0158] This application's embodiments establish a correct starting point and organizational framework for multi-objective optimization search by initializing the non-dominated solution set and path search priority queue. At each expansion step, the bi-objective cost of the new path is calculated, and the non-dominated solution set is dynamically updated using a Pareto optimization mechanism, ensuring that the output path achieves Pareto optimality in both efficiency and energy dimensions. This scheme forms a complete Pareto front maintenance process, capable of automatically generating a set of candidate paths that achieve the optimal balance between path length and radiation benefits without requiring manual weight setting. This effectively solves the trade-off problem between driving efficiency and solar energy collection benefits in traditional single-objective optimization methods.

[0159] Furthermore, the multidimensional indicators include one or more of the following: total path length, detour ratio, average path radiation intensity, and cumulative energy recovery; the calculation of the balance coefficient involves the dynamic weighting and summation of the path length dimension and the radiation energy dimension.

[0160] In one specific implementation, the balance coefficient is:

[0161]

[0162] in, The total length of the current candidate path P. The shortest path length from the starting point to the destination. The average radiation intensity of the current candidate path P, The maximum radiation intensity from the starting point to the ending point.

[0163] In one possible implementation, Figure 7 This is a schematic diagram of a route planning result, including three strategy examples from the starting point to the destination. Path 1, Path 2, and Path 3 are the shortest paths with efficiency as the priority, effectively balancing path length and radiation benefits. Drivers can choose the appropriate passenger transport strategy according to their actual needs.

[0164] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the multi-objective path planning method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0165] This application also provides a multi-objective path planning device; please refer to... Figure 8 The multi-objective path planning device includes:

[0166] Data preprocessing module 10 is used to acquire solar radiation data and raw map data, and perform multi-source data fusion based on the solar radiation data and the raw map data to obtain radial road network data;

[0167] The first processing module 20 is used to construct a total cost function for the path length based on the radial road network data by using a cumulative cost function for the path length and a heuristic function for the estimated cost, and to generate candidate paths based on the total cost function;

[0168] The second processing module 30 is used to calculate the average radiation intensity of the candidate path based on the radiation road network data, and then obtain the energy recovery amount of the candidate path.

[0169] The candidate path generation module 40 is used to construct a dual-objective cost function based on the total cost function and the energy recovery amount, adjust node priorities and filter and update the non-dominated solution set according to the dual-objective cost function, and generate a target candidate path set according to the non-dominated solution set.

[0170] The path evaluation module 50 determines the optimal balanced path from the set of target candidate paths through multi-dimensional quantitative evaluation and balance coefficient ranking.

[0171] The multi-objective path planning device provided in this application, employing the multi-objective path planning method described in the above embodiments, can solve the technical problem of simultaneously considering path length costs and solar radiation recovery benefits during path planning. Compared with the prior art, the beneficial effects of the multi-objective path planning device provided in this application are the same as those of the multi-objective path planning method described in the above embodiments, and other technical features in the multi-objective path planning device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0172] This application provides a multi-objective path planning device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the multi-objective path planning method in Embodiment 1 above.

[0173] The following is for reference. Figure 9 The diagram illustrates a structural schematic of a multi-objective path planning device suitable for implementing embodiments of this application. The multi-objective path planning device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 9The multi-objective path planning device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0174] like Figure 9 As shown, the multi-objective path planning device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the multi-objective path planning device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the multi-target path planning device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a multi-target path planning device with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0175] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0176] The multi-objective path planning device provided in this application, employing the multi-objective path planning method described in the above embodiments, can solve the technical problem of simultaneously considering path length costs and solar radiation recovery benefits during path planning. Compared with the prior art, the beneficial effects of the multi-objective path planning device provided in this application are the same as those of the multi-objective path planning method provided in the above embodiments, and other technical features of this multi-objective path planning device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0177] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0178] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0179] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the multi-objective path planning method in the above embodiments.

[0180] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0181] The aforementioned computer-readable storage medium may be included in the multi-objective path planning device; or it may exist independently and not assembled into the multi-objective path planning device.

[0182] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a multi-objective path planning device, the multi-objective path planning device performs the following actions: acquires solar radiation data and raw map data; performs multi-source data fusion based on the solar radiation data and the raw map data to obtain radial road network data; constructs a total cost function for the path length based on the radial road network data using a cumulative cost function for path length and a heuristic function for estimated cost; generates candidate paths based on the total cost function; calculates the average radiation intensity of the candidate paths based on the radial road network data, thereby obtaining the energy recovery amount of the candidate paths; constructs a dual-objective cost function based on the total cost function and the energy recovery amount; adjusts node priorities and updates the non-dominated solution set based on the dual-objective cost function; and generates a set of target candidate paths based on the non-dominated solution set.

[0183] The optimal balanced path is determined from the set of target candidate paths through multi-dimensional quantitative evaluation and balance coefficient ranking.

[0184] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0185] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0186] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0187] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described multi-objective path planning method. This solves the technical problem of simultaneously considering path length costs and solar radiation recovery benefits during path planning. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the multi-objective path planning method provided in the above embodiments, and will not be repeated here.

[0188] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the multi-objective path planning method described above.

[0189] The computer program product provided in this application can solve the technical problem of how to simultaneously consider the path length cost and the solar radiation recovery benefits during the path planning process. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the multi-objective path planning method provided in the above embodiments, and will not be repeated here.

[0190] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A multi-objective path planning method, characterized in that, The multi-objective path planning method includes: Acquire solar radiation data and raw map data, and perform multi-source data fusion based on the solar radiation data and raw map data to obtain radial road network data; Based on the radial road network data, a total cost function for the path length is constructed using a cumulative cost function for the path length and a heuristic function for the estimated cost. Candidate paths are then generated based on the total cost function. Based on the radiation network data, the average radiation intensity of the candidate path is calculated to obtain the energy recovery amount of the candidate path; A dual-objective cost function is constructed based on the total cost function and the energy recovery amount. Node priorities are adjusted and non-dominated solution sets are updated according to the dual-objective cost function. A set of target candidate paths is generated based on the non-dominated solution sets. The optimal balanced path is determined from the set of target candidate paths through multi-dimensional quantitative evaluation and balance coefficient ranking.

2. The multi-objective path planning method as described in claim 1, characterized in that, The steps of acquiring solar radiation data and raw map data, and performing multi-source data fusion based on the solar radiation data and raw map data to obtain radial road network data include: Solar radiation data is obtained through sensor networks, meteorological satellites, or historical observation databases; raw map data is obtained through open street maps or systems designated by transportation departments. The solar radiation data is preprocessed by removing outliers and filling in missing values, and the original map data is preprocessed by coordinate projection transformation and format standardization. Based on linear nearest neighbor interpolation, spatial interpolation is performed on the preprocessed discrete solar radiation points to generate continuous radiation intensity surface data covering the target area, and a mapping relationship between geographic coordinates and radiation intensity is established. The original map data is parsed into a "node-edge" graph structure, where nodes refer to road intersections and edges refer to road segments, and each edge is assigned a length attribute. Through spatial overlay analysis, the continuous radiation intensity surface data is mapped to the nodes and edges of the road network to form radiation road network data containing length and radiation attributes; wherein, each node is associated with the real-time radiation intensity of its geographical location, and each edge is associated with the average radiation intensity along its line.

3. The multi-objective path planning method as described in claim 2, characterized in that, The step of constructing a total cost function for the path length based on the radial road network data using a cumulative cost function for the path length and a heuristic function for the estimated cost, and generating candidate paths based on the total cost function, includes: Based on the length attribute of the radial road network data, the cumulative cost of the starting node is set to zero, and the cumulative cost of the remaining nodes is initialized to a preset value, forming the initial state of the path length cost matrix. Traverse all adjacent nodes of the current search node, and calculate the cumulative path length from the starting node through the current node to the adjacent nodes based on the edge length attribute in the radial road network data. For each adjacent node, based on the coordinate information of the adjacent node in the radial road network data and the coordinates of the target node, the Chebyshev distance is calculated as a heuristic function for estimating the cost. The cumulative cost is summed with the heuristic function value to form the total cost function in the path length dimension; Based on the total cost function, nodes are prioritized to generate candidate paths that minimize path length cost.

4. The multi-objective path planning method as described in claim 3, characterized in that, The step of calculating the path-average radiation intensity of the candidate path based on the radiation network data, and then obtaining the energy recovery amount of the candidate path, includes: The node set of the candidate path is obtained based on the radial road network data, and the real-time radiation intensity of each node in the candidate path is extracted. The path average radiation intensity is calculated by averaging the real-time radiation intensity of all nodes in the candidate path. The total length of the candidate path is obtained based on the radial road network data, and the path travel time is calculated by combining the preset average driving speed. The energy recovery of the candidate path is calculated based on the average radiation intensity of the path and the travel time of the path, combined with the parameters of the photovoltaic panel.

5. The multi-objective path planning method as described in claim 4, characterized in that, The step of constructing a dual-objective cost function based on the total cost function and the energy recovery amount includes: Define the dual-objective dimension of the dual-objective cost function; wherein, the dual-objective dimension is path length minimization and energy recovery maximization; By introducing a negative sign, the energy recovery amount is converted into a radiation energy cost function; The total cost function of the path length and the cost function of the radiation energy are combined to form a dual-objective cost function.

6. The multi-objective path planning method as described in claim 5, characterized in that, The steps of adjusting node priorities and updating the non-dominated solution set according to the dual-objective cost function, and generating a set of target candidate paths based on the non-dominated solution set, include: Construct an empty non-dominated solution set with the starting point as the initial node, and set a path search priority queue; Select the path with the lowest current cost from the path search priority queue, expand the adjacent nodes of the endpoint node in the path with the lowest current cost, and generate a new path. Calculate the bi-objective cost of the new path and update the non-dominated solution set using a Pareto optimization mechanism; When the path search reaches the endpoint node, the expansion stops and each path in the non-dominated solution set is extracted to form a target candidate path set; where each path is a Pareto optimal solution.

7. The multi-objective path planning method as described in claim 6, characterized in that, The multidimensional indicators include one or more of the following: total path length, detour ratio, average path radiation intensity, and cumulative energy recovery; the calculation of the balance coefficient involves the dynamic weighting and summation of the path length dimension and the radiation energy dimension.

8. A multi-objective path planning device, characterized in that, The multi-objective path planning device includes: The data preprocessing module is used to acquire solar radiation data and raw map data, and perform multi-source data fusion based on the solar radiation data and the raw map data to obtain radial road network data; The first processing module is used to construct a total cost function for the path length based on the radial road network data by using a cumulative cost function for the path length and a heuristic function for the estimated cost, and to generate candidate paths based on the total cost function; The second processing module is used to calculate the average radiation intensity of the candidate path based on the radiation road network data, and then obtain the energy recovery amount of the candidate path. The candidate path generation module is used to construct a dual-objective cost function based on the total cost function and the energy recovery amount, adjust node priorities and filter and update the non-dominated solution set according to the dual-objective cost function, and generate a target candidate path set according to the non-dominated solution set. The path evaluation module determines the optimal balanced path from the set of target candidate paths through multi-dimensional quantitative evaluation and balance coefficient ranking.

9. A multi-objective path planning device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the multi-objective path planning method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the multi-objective path planning method as described in any one of claims 1 to 7.

Images