Airline optimization method and system based on genetic algorithm and geographic information

Abstract

The invention discloses an air route optimization method and system based on a genetic algorithm and geographic information, and relates to the technical field of intelligent navigation and path planning, and the method comprises the steps: receiving geographic data related to air route planning, and constructing a multi-level spatial index; a waypoint optimization algorithm is adopted, and under the support of spatial indexes, a genetic algorithm based on population diversity adaptive adjustment is utilized to determine a waypoint sequence of the route; for any two adjacent waypoints in the waypoint sequence, adopting a path optimization algorithm, combining geographic information provided by the spatial index, and utilizing a genetic algorithm to generate a corresponding optimal path segment; and carrying out iterative optimization on the optimal path segment, carrying out iterative optimization on the waypoint sequence and the optimal path segment, and integrating an optimization result to the autonomous navigation system after convergence. The spatial information processing efficiency is remarkably improved, high-risk and limited areas are effectively eliminated, and the optimal layout of a global route structure is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent navigation and path planning, and specifically to a route optimization method and system based on genetic algorithms and geographic information. Background Art

[0002] With the rapid development of unmanned autonomous navigation technology, intelligent transportation, and intelligent logistics systems, path planning and route optimization play a crucial role in autonomous navigation platforms (such as unmanned aerial vehicles, autonomous driving vehicles, intelligent ships, etc.). Existing path planning methods usually rely on basic terrain, obstacle, and airspace management data provided by a Geographic Information System (GIS), combined with traditional shortest path algorithms (such as Dijkstra, A*, etc.) or heuristic search methods, to achieve a preliminary guarantee of the safety and economy of the route. However, with the complication of application scenarios, such as urban three-dimensional space, changing meteorological conditions, dynamic environmental factors, and diversified task constraints, traditional path planning methods have significant deficiencies in dealing with large-scale spaces, complex constraints, and multi-objective trade-offs.

[0003] On the one hand, existing algorithms mainly focus on single-level point-to-point path searching, making it difficult to simultaneously optimize the global route structure and refine local paths, resulting in the overall route planning result being difficult to adapt to changing task requirements and complex space constraints. On the other hand, in the face of a dynamic environment (such as wind field changes, sudden flight restrictions, etc.), traditional static planning schemes cannot achieve real-time response and adaptive adjustment to environmental changes, and are prone to problems such as local optimality, slow convergence speed, and poor scalability. In addition, the large amount of spatial geographic data and complex spatio-temporal attributes will significantly increase the computational burden and reduce the system response efficiency when directly applied to traditional algorithms.

[0004] In recent years, intelligent optimization algorithms (such as genetic algorithms, ant colony algorithms, etc.) have received attention in the field of path planning due to their global search capabilities and multi-objective optimization characteristics. However, how to efficiently combine spatial indexing technology to achieve rapid retrieval and environmental perception of large-scale, multi-level geographic information remains a difficult point in this field. The currently disclosed technologies still have deficiencies in the collaborative optimization of multi-level spatial indexing and adaptive genetic algorithms, dynamic constraint processing of path segments, and system-level real-time integration, and are difficult to meet the requirements of autonomous navigation systems for the efficiency, real-time performance, and adaptability of route planning. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is that existing path planning methods have problems of weak route optimization ability, poor environmental adaptability, and lack of an efficient global adaptive optimization mechanism in complex geographical environments and multi-constraint scenarios.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: A route optimization method based on genetic algorithms and geographic information, including receiving geographic data related to route planning and constructing a multi-level spatial index; Adopting a waypoint optimization algorithm, with the support of the spatial index, using a genetic algorithm based on adaptive adjustment of population diversity to determine the waypoint sequence of the route; For any two adjacent waypoints in the waypoint sequence, adopting a path optimization algorithm, combining the geographic information provided by the spatial index, and using a genetic algorithm to generate the corresponding optimal path segment; Performing iterative optimization on the optimal path segment, performing iterative optimization on the waypoint sequence and the optimal path segment, and integrating the optimization result into the autonomous navigation system after convergence.

[0008] As a preferred solution of the route optimization method based on genetic algorithms and geographic information of the present invention, wherein: the geographic information data includes static data and dynamic data; among them, the static data includes regional terrain data, airspace management data, and regional task rule data, and the dynamic data includes static environment data and dynamic environment data; The multi-level spatial index includes a coarse-grained spatial index layer and a fine-grained spatial index layer; Based on the static data, a coarse-grained spatial index layer is constructed. The coarse-grained index uses a two-dimensional square area as the basic unit, and the side length of the unit is set to L. The value of L is preset according to the area of the task region; a quadtree structure is used to construct the index, and the index node stores: unit coordinate range, regional average terrain height, airspace label set, task rule label, risk level field, and unique spatial coding identifier; Based on the dynamic data, a fine-grained spatial index layer is constructed. The fine-grained index is divided into two-dimensional square spatial units, and the side length is set to l. An R-tree structure is used to construct the index. The fields stored in the index node include static fields and dynamic fields. Among them, the static fields include the coordinate range of the spatial unit, obstacle spatial boundary information, node status label, and spatial coding information, and the dynamic fields include the environmental data field value and its corresponding timestamp information.

[0009] As a preferred solution of the route optimization method based on genetic algorithms and geographic information of the present invention, wherein: the waypoint optimization algorithm includes: based on the airspace label set, risk level field, and task rule label field stored in each index node of the coarse-grained spatial index structure, setting screening rules, screening each index node, extracting the central coordinate point as a candidate waypoint, and establishing a candidate waypoint set based on the candidate waypoint; The screening rules include removing the nodes in the airspace tags that contain no-fly zones or restricted airspace identifiers, and only retaining the spatial index nodes with a risk level lower than the preset threshold and marked as passable in the task rules; Taking several waypoint indices in the candidate waypoint set as chromosome genes, and forming a chromosome with the arrangement order of the waypoint indices as the search individual of the genetic algorithm; During the execution of the genetic algorithm, a spatial perception control mechanism is set up to verify the spatial attributes of the waypoints generated in the mutation stage, and restrict the chromosomes that do not meet the risk conditions or airspace requirements from entering the next generation; The spatial perception control mechanism includes: when performing the mutation operation, calling the coarse-grained spatial index structure to retrieve the risk level field and the airspace tag set of the spatial unit where the mutated waypoint is located, and judging whether the mutated waypoint is located in an area with a risk level higher than that of the original waypoint, or whether the airspace tag set contains no-fly zone identifiers or restricted airspace identifiers; if the conditions are not met, the mutated waypoint is removed and the mutation result is not included in the subsequent population; During the iteration of the genetic algorithm, a fitness function is constructed based on the path distance, regional risk value, and task fitness, and the waypoint sequence with the highest fitness score is determined as the optimal individual of the current generation and used as the input for subsequent path optimization.

[0010] As a preferred scheme of the route optimization method based on genetic algorithm and geographic information according to the present invention, wherein: the path optimization algorithm includes constructing a path segment optimization task according to any two adjacent waypoints in the waypoint sequence; the path segment consists of a starting point, an ending point, and several path points; Based on the fine-grained spatial index layer, call the field information in the spatial index node where the path point is located, and combine the task time step to establish a binding relationship between the path point and the temporal environment data; Use the A* search algorithm to perform path search in the fine-grained spatial index layer, construct a path cost function based on the cumulative environment cost and heuristic function of the path point, and generate an initial path segment; Based on the initial path segment, introduce a path perturbation mechanism to generate perturbation path segment individuals as the initial population of the genetic algorithm; During the evolution of the genetic algorithm, a fitness function is constructed with the path segment length, the risk level field of the path node, the dynamic environment field value at the time step, and the path curvature, and a space-time dual constraint mechanism is used to perform effectiveness screening on the path individuals generated in each generation to ensure that only the path individuals that meet the environmental and spatial requirements can enter the next generation population; When the path segment optimization meets the convergence condition or reaches the maximum number of iterations, output the corresponding optimal path segment, and splice the optimal results of all path segments to form a complete path set, which is used as the input for route quality evaluation and subsequent waypoint sequence iterative update.

[0011] As a preferred solution of the route optimization method based on genetic algorithm and geographic information according to the present invention, wherein: the path perturbation mechanism includes performing a spatial perturbation operation on the intermediate path points of the path segment within a limited perturbation radius range; calling the index nodes in the multi-level spatial index, and determining whether the perturbed path points are located in an obstacle area, a no-fly zone, a height-limited zone or a high-risk level area, and only retaining the perturbed path segment individuals that do not fall into the above areas for constructing the initial population of the genetic algorithm.

[0012] As a preferred solution of the route optimization method based on genetic algorithm and geographic information according to the present invention, wherein: the space-time dual constraint mechanism includes a space constraint mechanism and a time constraint mechanism; The space constraint mechanism includes determining whether the path points fall into an obstacle area, a no-fly zone, a height-limited zone or a high-risk level area based on the airspace management label, obstacle information and risk level field of the nodes in the fine-grained spatial index; The time constraint mechanism includes determining whether it falls into an area where the environmental risk exceeds the threshold based on the dynamic environment field value of the task time step corresponding to the path node. If the passing requirement is not met, the path individual does not enter the next generation.

[0013] As a preferred solution of the route optimization method based on genetic algorithm and geographic information according to the present invention, wherein: the iterative optimization of the optimal path segment includes splicing the optimal path segments to form a complete path set, and performing a fitness score on the overall route according to the total length of the complete path set, the risk level field of the path nodes, the dynamic environment field value at the task time step, and the path curvature; According to the fitness score result, adjust the path segment through the genetic algorithm, and combine the space-time dual constraint mechanism to screen the optimized path segment; Loop to execute path optimization and fitness scoring until the fitness score of the complete path set meets the convergence condition or reaches the maximum number of iterations, and output the optimization result.

[0014] As a preferred solution of the route optimization system based on genetic algorithm and geographic information according to the present invention, wherein: a multi-layer module that receives geographic data related to route planning and constructs a multi-level spatial index; A sequence module that uses a waypoint optimization algorithm and, with the support of the spatial index, determines the waypoint sequence of the route by using a genetic algorithm with adaptive adjustment based on population diversity; A path segment module that, for any two adjacent waypoints in the waypoint sequence, uses a path optimization algorithm, combines the geographic information provided by the spatial index, and uses a genetic algorithm to generate the corresponding optimal path segment; Optimization module, which iteratively optimizes the optimal path segment, iteratively optimizes the waypoint sequence and the optimal path segment, and integrates the optimization result into the autonomous navigation system after convergence.

[0015] A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the route optimization method based on genetic algorithm and geographic information.

[0016] A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the route optimization method based on genetic algorithm and geographic information are implemented.

[0017] Advantages of the present invention: The route optimization method based on genetic algorithm and geographic information provided by the present invention realizes efficient hierarchical management and rapid retrieval of static and dynamic data of the geographical environment by constructing a multi-level spatial index structure, significantly improving the spatial information processing efficiency. In the waypoint optimization stage, the adaptive genetic algorithm combined with the spatial index screening mechanism can effectively eliminate high-risk and restricted areas, realizing the optimal layout of the global route structure. During the path optimization process, by introducing the initial path generated based on the A* algorithm and combining with the path perturbation mechanism, the initial population has higher diversity and feasibility, improving the global search ability of the genetic algorithm. Further, in the genetic evolution process, a spatial-temporal dual constraint mechanism is adopted to ensure that the path points avoid obstacles in real time and dynamically adapt to environmental changes, effectively avoiding no-fly zones, obstacles and extreme weather risks. The overall route uses fitness scoring for global feedback and iterative optimization, which can achieve rapid convergence in complex tasks and dynamic environments, ensuring the safety, smoothness and low energy consumption of the route. Finally, the optimization result can be seamlessly integrated into the autonomous navigation system to meet the high-efficiency, real-time and high-adaptability requirements of intelligent route planning. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0019] Figure 1 It is the overall flowchart of the route optimization method based on genetic algorithm and geographic information provided by the first embodiment of the present invention. Detailed Embodiments

[0020] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0021] Embodiment 1, referring to Figure 1 , which is an embodiment of the present invention, provides a route optimization method based on genetic algorithms and geographic information, including: S1: Receive geographic data related to route planning and construct a multi-level spatial index.

[0022] The geographic information data includes: regional terrain data, airspace management data, static environment data, dynamic environment data, and regional task rule data.

[0023] The regional terrain data includes: digital elevation model (DEM), slope map, ground relief information, surface roughness parameters, and rasterized terrain raster data.

[0024] The airspace management data includes: no-fly zone boundary information, height limit area definition, height limit map, temporary airspace passage restriction notice, and airspace classification information (such as civil aviation airspace, controlled airspace).

[0025] The static environment data includes: building outline boundaries, three-dimensional city models (such as CityGML data), permanent obstacle locations, and traffic infrastructure information (such as towers, overpasses, bridges, transmission towers).

[0026] The dynamic environment data includes: wind speed and direction data, air pressure and temperature / humidity data, rainfall prediction, thunderstorm or extreme weather warning information, and time-series-based wind field simulation output.

[0027] The regional task rule data includes: passable corridor boundaries, regional priority classification, task constraint area definition (such as military management areas, ecologically sensitive areas), risk level distribution maps, and task airworthiness score annotation maps.

[0028] According to the data type and spatial resolution requirements, the received geographic information data is divided into two types of index levels: Coarse-grained index layer: Aiming to support high-level waypoint selection, the input data includes: regional terrain data, airspace management data, and regional task rule data.

[0029] Fine-grained index layer: Aiming to support low-level path optimization, the input data includes: static environment data and dynamic environment data.

[0030] Construct a coarse-grained index structure: Divide the task area into spatial units of a fixed size. The spatial units are two-dimensional squares with a side length set to L. The value of L is preset according to the spatial scale of the task area and the complexity of the geographical features. Specifically: when the area of the task area is less than 25 square kilometers, L is set to 50 meters; when the area of the task area is between 25 and 100 square kilometers, L is set to 100 meters; when the area of the task area is greater than 100 square kilometers, L is set to 200 meters.

[0031] All spatial units are uniformly numbered to ensure that the task area is covered without overlap and without gaps.

[0032] To control the number of levels and the index granularity of the quadtree structure, set the following splitting rules: If there are more than two airspace management labels within the area covered by the current node (such as the overlap of height-limited areas and no-fly zones), then enforce a quadtree split once; If the risk level of any unit among the spatial units subordinate to the current node is higher than the threshold R (such as R≥4), and the current hierarchical depth does not exceed the set maximum level D (such as D = 4), then allow access to the next level of the index; If the areas covered by the child nodes after splitting are all low-risk areas, then stop further subdivision and terminate this path.

[0033] The field information stored in each index node includes: coordinate range (upper left corner coordinates and side length); average terrain height of the area; set of airspace labels (such as whether height-limited, whether no-fly); task rule labels (such as priority level, passability); maximum and average values of the risk level; reference to child nodes (if any, pointing to the index values of the four child nodes); Morton coding (uniquely identifying this node). All index nodes are organized in the form of a dictionary or an array, supporting fast spatial search and local update, and are called as needed by the subsequent high-level waypoint selection module.

[0034] Construct a fine-grained index structure: For static environment data and dynamic environment data, combine the spatial resolution requirements of the task area and the real-time access requirements in the path optimization stage to construct a fine-grained spatial index that supports high-frequency queries and dynamic updates. The specific steps are as follows: Divide the task area into small-sized spatial units. The spatial units are two-dimensional squares with a side length set to l. The value of l is set according to the spatial accuracy required for path optimization, and the preferred value range is from 1 meter to 10 meters. All spatial units are numbered in absolute coordinates to ensure complete coverage without overlap and without gaps.

[0035] Establish an R-tree-based data index structure for the divided spatial units. Each index node of the R-tree corresponds to a spatial area and stores the static object information and dynamic environment attributes within that area; The static object information includes: the boundary coordinates of obstacles, the set of outline points of buildings, and the location attributes of permanent facilities; the dynamic environment attributes include environmental fields such as wind speed, wind direction, air pressure, precipitation, visibility, etc., and are attached with time tags for time-series updates.

[0036] Each index node supports range queries, neighborhood searches, and dynamic interpolation access, which are used for collision detection and fitness calculation in path evaluation.

[0037] The field information stored in each fine-grained index node includes: divided into static fields and dynamic fields according to whether they change with time.

[0038] The static fields include: coordinate range (the upper left corner coordinates and side length); the identification of the static object it belongs to and its spatial boundary set (such as obstacles, buildings, etc.); node status tags (such as idle, obstacle, restricted area); Morton coding.

[0039] The dynamic fields include: the environmental field values at the current time step (such as wind speed, wind direction, air pressure, temperature and humidity, precipitation, etc.); the change trend or change rate of the environmental field; timestamp information.

[0040] Regarding the time-sensitive characteristics of dynamic environment data, the update mechanism of the dynamic index structure includes: all dynamic fields are attached with timestamps, and historical records and prediction results are maintained according to the time series; during the path planning process, according to the current optimization generation or simulation time step, the environmental data required at the current time point is loaded or interpolated and queried as needed; a local refresh mechanism is supported, and only the areas related to the task path are incrementally updated to avoid full-map reconstruction.

[0041] The fine-grained index structure is encapsulated as a modular interface, which supports path optimization algorithms to call the index node attributes according to the path node coordinates during operations such as fitness function evaluation, path mutation, and crossover, and realizes real-time environmental perception and terrain interaction judgment of path points.

[0042] Furthermore, by dividing the geographical data into two index levels of coarse-grained and fine-grained according to the data type and task resolution requirements, the management efficiency of multi-source heterogeneous geographical information in the task area is significantly improved. The coarse-grained index uses a quadtree structure to manage airspace labels and risk levels, supports efficient plot aggregation and airspace conflict identification, and is convenient for the upper-level module to perform large-range waypoint preselection; the fine-grained index uses an R-tree structure to encapsulate static and dynamic environment attributes, realizes high-frequency access and local update at the path node level, and meets the accuracy requirements of real-time path evaluation and dynamic obstacle avoidance. It significantly reduces the time complexity of full-map query and data redundant storage, and improves the spatial response speed of the system.

[0043] The coarse-grained index structure introduces rule fields such as an airspace management label set, regional priority classification, and mission airworthiness scores. During the high-level waypoint screening phase, it can quickly filter out unsuitable areas and aggregate features by risk level to guide waypoints to shift towards low-risk areas. The fine-grained index provides dynamic environmental data support at the path segment level. The node fields contain multidimensional parameters such as wind speed, air pressure, and visibility, and are accompanied by a time series update mechanism, enabling real-time perception and prediction capabilities during the path optimization process. Waypoints can real-time perceive local environmental changes during crossover and mutation operations, effectively avoiding risk areas such as sudden obstacles and extreme weather interference, and improving the airworthiness and robustness of the overall path.

[0044] Furthermore, by configuring a unique Morton code and standard field format for each level of spatial index node, modular encapsulation and efficient scheduling of the index structure are achieved. The optimization algorithm can call the corresponding granularity index as needed at different stages without redundant preloading, improving the overall algorithm operation efficiency. At the same time, the dynamic index supports time tags and local refresh mechanisms, dynamically loading environmental fields in combination with the current simulation time step, avoiding the pressure of full-map reconstruction caused by environmental updates, and providing iterable, interpolable, and dynamically adaptable environmental data support for the path optimization algorithm. This design gives the route optimization process good flexibility and algorithm compatibility, adapting to the needs of various mission scenarios and navigation systems.

[0045] S2: Adopt a waypoint optimization algorithm. With the support of the spatial index, use a genetic algorithm based on adaptive adjustment of population diversity to determine the waypoint sequence of the route.

[0046] Based on the regional terrain data, airspace management data, and regional mission rule data stored in the coarse-grained spatial index structure, a candidate waypoint set that meets the mission constraints is constructed. Specifically, traverse all coarse-grained index nodes , whose fields include the coordinate center point , airspace label set , risk level and mission rule label set . The construction rule of the candidate waypoint set is defined as: ; where, represents the candidate waypoint set; represents the center point coordinates of the coarse-grained spatial index node ; represents the airspace management label set corresponding to the node , used to mark whether this area belongs to a no-fly zone or restricted airspace; represents the mission rule label set corresponding to the node , including attributes such as whether it is marked as "passable"; represents the node Risk level field; Indicates a preset risk level threshold. Set The screening conditions of include: This node does not belong to a no-fly zone or restricted airspace, that is ; The risk level of this node is lower than the threshold, that is ; And the task rule contains the "passable" annotation, that is .

[0047] Use the waypoint sequence encoding as the chromosome , Each gene Represents a waypoint index in the candidate set . The genetic algorithm generates a waypoint sequence covering the task area by searching for the optimal arrangement , And its fitness function is designed as: ; Among them, Represents the fitness score of the waypoint sequence ; Represents the th waypoint in the candidate waypoint set; Represents the th waypoint and the th waypoint The Euclidean distance between; Represents the risk level of the space unit where the waypoint is located; Represents the number of waypoints in the waypoint sequence; , , Respectively represent the weight coefficients of path length, risk level and task matching degree, and are used to adjust the influence degree of each factor in the fitness function.

[0048] Represents the th waypoint and the th waypoint The task priority adaptation degree between, defined as the average value of the two-point task airworthiness scores and , That is: ; Among them, Represents the airworthiness score corresponding to the task rule label field in the coarse-grained index node.

[0049] To improve the convergence speed and search diversity, an adaptive genetic mechanism based on population diversity is introduced. Let the current generation be , The population size is , The average Hamming distance between chromosomes is: ; Among them, Represents the Hamming distance between chromosomes. Based on The characterized population structure features dynamically adjust the crossover probability and the mutation probability , implementing a self-balancing parameter adjustment mechanism of "enhancing mutation when population diversity decreases and enhancing convergence when population divergence is too strong". The specific update formula is as follows: ; If the population tends to be premature, increase the mutation intensity and introduce a segment perturbation operation; if the population diverges too strongly, then increase the retention weight of high-quality individuals.

[0050] In addition, a spatial perception mechanism based on environmental label judgment is introduced during the crossover and mutation processes: when the newly generated waypoint does not meet the regional risk level or airspace compliance requirements, impose an additional penalty on its fitness or reject it from being included in the next-generation population. Specifically: ; That is, if the waypoint generated by mutation falls into a region with a higher risk level, abandon this mutation. Through this spatial perception operation, guide the route structure to continuously concentrate on low-risk and task-priority regions.

[0051] Finally, output the optimal waypoint sequence that meets the risk level, task rules, and airspace management labels : ; As the basic input for the subsequent path refinement stage.

[0052] In the existing technology, the selection of candidate waypoints usually relies on regular grid sampling or simple range filtering, lacking a comprehensive judgment of airspace policies, regional risks, and task rules, and easily leading to the path structure passing through no-fly zones, high-risk areas, or task-restricted areas. In this technical solution, the candidate waypoint set is generated by coarse-grained spatial index nodes, and is jointly screened based on three attributes: the airspace management label, risk level field, and task rule label stored in the nodes, forming a waypoint set with compliant structure, legal space, and high task airworthiness. This multi-label space joint screening mechanism significantly improves the quality of waypoints in the path structure generation stage, avoids the risks of illegal area crossing and task violation from the source, and breaks through the limitations of the single waypoint selection criterion and difficult embedding of environmental constraints in the existing algorithms.

[0053] In the existing genetic algorithms for route optimization, fixed crossover probabilities and mutation probabilities are mostly adopted, which cannot be dynamically adjusted according to the population evolution state, and are prone to problems such as premature convergence or search divergence, affecting the ability to obtain the global optimum. In this technical solution, an adaptive genetic parameter adjustment mechanism based on population diversity measure (mean Hamming distance) is introduced, realizing the dynamic change of crossover probability and mutation probability with generations, and enhancing the adaptive ability and evolution rhythm control ability of the algorithm. This mechanism automatically adjusts the search intensity according to the population distribution state, enhances the global optimization ability under complex terrain and high-constraint task conditions, and effectively overcomes the problem of insufficient robustness caused by parameter inadaptability in the traditional genetic algorithm in complex search spaces.

[0054] The crossover and mutation operations in traditional genetic algorithms lack perception of the geographical environment and may generate illegal waypoints that fall into high-risk areas or airspace conflict areas, resulting in frequent failures in the path evaluation stage. In this technology, a perception-based evolutionary operator mechanism based on spatial index label feedback is introduced to judge in real time at the waypoint level whether the mutation result meets the requirements of regional risk and airspace compliance. For mutant individuals that do not meet the airworthiness conditions, the system will impose penalties or directly discard them to ensure that only available, legal, and high-quality solutions are retained during the evolution process. This mechanism introduces spatial adaptability filtering and guiding capabilities in the genetic evolution process, effectively avoiding the generation of illegal paths and wasting evaluation resources, and breaking through the structural limitations of traditional algorithms that are insensitive to space and do not feedback on the environment.

[0055] S3: For any two adjacent waypoints in the waypoint sequence, use a path optimization algorithm, combine the geographical information provided by the spatial index, and use an adaptive genetic algorithm to generate the corresponding optimal path segment.

[0056] Furthermore, based on the waypoint sequence , for any adjacent waypoint pair , construct a path segment optimization task with the goal of generating the optimal connection path that meets spatial passage constraints and task environment adaptability , where , , and the rest are intermediate path nodes.

[0057] During the path optimization process, combine the terrain data, static obstacle information, airspace management labels, and dynamic environment fields (including wind speed, wind direction, air pressure, precipitation, etc.) in the fine-grained spatial index structure to realize the joint perception of the spatial and temporal environment where the path nodes are located. Each path node corresponds to a task time step , and according to the spatial position and time step of the path point , query the field information of the corresponding node in the spatial index structure. If there is no observed data at this time step, interpolation calculation is performed based on the predicted fields in the index nodes to achieve the temporal binding of path points and dynamic environment fields. To construct the initial population of the genetic algorithm, the A* search algorithm is used to perform heuristic path search in the fine-grained spatial grid to construct the basic path solution . Search cost function is defined as: ; where represents the comprehensive evaluation cost of the path point ; represents the cumulative cost from the starting point to the current path point ; represents the heuristic cost from the current path point to the target point , and usually the Euclidean distance is used as an approximate evaluation; represents the adjustment coefficient of the heuristic term.

[0058] Based on , a path perturbation mechanism is introduced to expand the population diversity, specifically including: performing spatial micro-perturbation on the intermediate nodes of the path (the perturbation radius r is set according to the spatial resolution), filtering out the nodes that do not meet the passability after perturbation, and constructing multiple path individuals with legal structures but different morphologies to form the initial population set , which is used for the initial evolution of the genetic algorithm.

[0059] The path fitness function formula is expressed as: ; where represents the path segment length; represents the static risk level of the spatial unit where the path node is located; represents the cost of the dynamic environment field corresponding to the path node at the time step (such as wind speed squared, wind direction deviation, energy consumption evaluation, etc.); represents the curvature formed by adjacent nodes, which is used to evaluate the path smoothness; , , , are adjustment coefficients.

[0060] Both the crossover and mutation operations in the genetic algorithm are regulated by the space-time double constraint mechanism: The space constraint mechanism includes: for the path segments in the crossover result, call the fine-grained spatial index nodes to judge whether they cross obstacles, height-limited areas or no-fly zones. If the spatial label constraints are violated, they are removed or repaired.

[0061] The time constraint mechanism includes: for the newly generated path nodes by mutation , determine whether the dynamic environment fields at the task time step meet the acceptable range. If there are extreme weather, wind speed exceeding the limit or risk mutation, it is regarded as an illegal mutation, and the path node maintains the original value: ; Among them, represents the -th original path point in the path, represents the updated path point after the path mutation operation; represents the mutation candidate point, that is, the candidate value of the new path node generated by the genetic algorithm in the current generation for replacing ; represents the risk level field value in the spatial index node where the path point is located, represents the risk level corresponding to the candidate path point ; the symbol represents the logical "AND" operation, that is, both conditions are satisfied at the same time; represents the set of candidate path points, including all legal path points that meet the spatial passability requirements; represents "otherwise"; the meaning expressed by the entire piecewise function is: if the risk level of the newly generated path point is less than the risk level of the original path point , and this point belongs to the set of legal candidate path points , then replaces the original path point ; otherwise, the path point remains unchanged.

[0062] The path optimization process terminates after meeting the maximum number of evolutionary generations or the fitness convergence threshold, and outputs the optimal individual of this section of the path .

[0063] Finally, splice each path segment to form a complete path set , as the refined result of the overall route, for subsequent global fitness evaluation and iterative feedback module to call.

[0064] The path segment optimization adopts the A* search algorithm combined with the genetic evolution mechanism, and drives the perturbation through the spatial index, which can quickly generate diverse and feasible initial solutions in a large-scale complex geographical space. Compared with the traditional heuristic or single global search method, this effectively improves the spatial coverage and the initial optimization efficiency, and breaks through the technical barriers of low initial solution quality and poor globality in complex environments.

[0065] Furthermore, by introducing spatio-temporal dual constraints, path nodes dynamically avoid obstacles, circumvent airspace restrictions, and perceive meteorological changes in real time during the evolution process, ensuring that the path plan has high safety and environmental adaptability in a dynamic environment. Traditional methods mostly use single static obstacle avoidance or risk indicators and are difficult to cope with changing environments and high-risk situations. This mechanism significantly improves the robustness of path planning and solves the problem of route safety in dynamic environments.

[0066] Even further, the segmented path structure is combined with a global feedback iteration mechanism to continuously optimize the path structure through fitness scoring, achieving multi-objective balance, path smoothing, and energy consumption optimization. Existing solutions are prone to falling into local optima or lacking global-local coordination and are difficult to meet complex navigation requirements. The above mechanism provides the autonomous navigation system with efficient, stable, and dynamically responsive route optimization capabilities, overcoming the key technical barrier of being difficult to balance global and local aspects in complex environments.

[0067] S4: Iteratively optimize the optimal path segments, iteratively optimize the waypoint sequence and the optimal path segments, and integrate the optimization results into the autonomous navigation system after convergence.

[0068] Concatenate all the optimal path segments corresponding to the current generation of waypoint sequences into a complete route. According to the attributes of each path segment , calculate the fitness function of the entire route , and its expression is: ; where represents the overall fitness score corresponding to the current waypoint sequence ; , , , represent the weight coefficients of path length, risk level, dynamic environment cost, and curvature smoothness respectively; represents the total number of waypoints in the waypoint sequence; represents the optimal path segment connected by the th and the th waypoints; represents the total length of the path segment ; represents the th path point in the path segment ; represents the risk level field value of the spatial index node corresponding to the path point ; represents the dynamic environment field cost of the path point at the task time step ; represents the path point The corresponding curvature.

[0069] During the overall optimization iteration process, the current fitness score is used to perform genetic algorithm operations on the waypoint sequence population in turn, including: according to the fitness score, using strategies such as tournament selection or roulette wheel, screening out the waypoint sequences with better fitness from the current population as the parents. Performing single-point or multi-point crossover operations on the parent waypoint sequences, randomly exchanging some waypoint indexes to generate new offspring waypoint sequences. Performing spatial perturbation or random replacement on some waypoints in the offspring waypoint sequences to generate new candidate waypoints, and using the spatial-temporal dual constraint mechanism for screening to ensure that all mutated waypoints do not fall into obstacle areas, no-fly zones, height-limited zones or high-risk level areas, and at the same time the dynamic environment field values at the corresponding task time steps meet the safety threshold requirements.

[0070] For each newly generated offspring waypoint sequence in each generation, the path segment optimization step needs to be re-executed to obtain a new optimal path segment and spliced to form a complete path set P, based on which the overall fitness score is updated . The above process is continuously iterated as follows: ; Among them, represents the iterative operation of the adaptive genetic algorithm with a spatial-temporal dual constraint mechanism.

[0071] The iterative process terminates when any of the following convergence conditions are met: The overall fitness score changes less than a preset threshold within several consecutive generations , that is ; or reaches the maximum number of iterations .

[0072] Finally, the optimal waypoint sequence at the convergence moment and its corresponding complete path set are output as the final result of the route optimization.

[0073] The dynamic evaluation and real-time adjustment of the path segment quality break through the limitation that traditional single-path generation cannot perform global feedback optimization according to the overall route performance, and significantly improve the overall safety and economy of the route.

[0074] By using the genetic algorithm to cyclically update the path segments driven by fitness and cooperating with the spatial-temporal dual constraint mechanism, it can automatically eliminate solutions that do not meet environmental or spatial constraints, overcome the technical bottlenecks of traditional algorithms such as slow convergence speed, easy to fall into local optimum, and poor environmental dynamic adaptability, and effectively improve the route feasibility and stability under complex geographical and meteorological conditions.

[0075] The multi-round feedback adjustment and fitness scoring closed-loop enable the optimization results to dynamically adapt to task changes and environmental disturbances, realizing the adaptive evolution of the waypoint sequence and path structure, and providing a new intelligent route planning mode with high efficiency, real-time performance, and high reliability for the autonomous navigation system.

[0076] Example 2 is an embodiment of the present invention, which provides a route optimization method based on genetic algorithms and geographical information. To verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0077] Taking the intelligent UAV urban distribution route as the application scenario, a 10km×10km area in the core area of Pudong New Area, Shanghai is selected as the test area. The geographical data includes a digital elevation model with a resolution of 1m, three-dimensional building contours, urban road networks, meteorological conditions (including wind speed, wind direction, temperature, humidity, rainfall forecast), airspace management data (no-fly zones, height limits), and distribution task rules (priorities, time windows, sensitive areas, etc.).

[0078] First, all spatial data in the area is classified into static categories (such as terrain, buildings, airspace rules) and dynamic categories (such as meteorology, real-time road occupancy) according to types, and a coarse-grained (L = 100m) quadtree spatial index and a fine-grained (l = 5m) R-tree index are respectively constructed. The coarse-grained index is used for waypoint candidate screening, and the fine-grained index is used for path segment optimization and environmental constraint checking.

[0079] Based on the starting point (Warehouse A, 121.50°E, 31.22°N) and the ending point (Park B, 121.60°E, 31.26°N) of the route, an initial waypoint sequence is generated. Using a genetic algorithm with adaptive adjustment based on population diversity, with the coarse-grained index as the screening basis, only waypoints with a risk level lower than 3, passable task rules, and avoiding no-fly zones are retained. Set the population size to 50, the number of iterations to 100, the crossover probability to 0.7, and the mutation probability to 0.2, and adjust the parameters in real time during evolution to ensure diversity. After fitness scoring (including total path length, risk value, task priority matching degree), the waypoint sequence is determined as the input for subsequent path segment optimization.

[0080] For each pair of adjacent waypoints, the fine-grained spatial index is called, and the A* algorithm is used to generate a feasible initial path segment in combination with spatial constraints and dynamic environmental data. Based on the perturbation mechanism, the intermediate nodes are perturbed within a radius of 5m, and the spatial index is called to judge the legality of the path. Only path segments that do not cross obstacles, no-fly zones, and extreme meteorology are retained as the initial population of the genetic algorithm. The genetic algorithm optimizes with a multi-index fitness function such as path length, risk level, wind speed, and curvature, and each generation is screened through spatial-time dual constraints. Finally, all path segments are spliced, and after the overall route fitness score converges, a complete route and navigation instructions are generated and integrated into the UAV navigation system.

[0081] Experimental data: Total number of coarse-grained index units: 1000. Total number of waypoint candidates: 148. Number of waypoints participating in optimization (initial generation): 15. Total number of path segments: 14. Average number of waypoints per single path segment: 42.50. Number of generations for fitness convergence: 56. Total length of the flight path before optimization: 15.24 km. Total length of the flight path after optimization: 13.89 km. Average path risk value before optimization: 2.87. Average path risk value after optimization: 1.45. Number of times of exceeding the standard in the dynamic environment before optimization: 5. Number of times of exceeding the standard in the dynamic environment after optimization: 0. Average flight path curvature before optimization: 0.042. Average flight path curvature after optimization: 0.025. Theoretical energy consumption before optimization: 4.32 kWh. Theoretical energy consumption after optimization: 3.68 kWh. Planning time (including data loading, indexing, and full-process optimization): 112.75 seconds.

[0082] By comparing the key indicators before and after optimization in this embodiment, it can be clearly seen that the inventive solution has significantly improved in terms of flight path quality, mission adaptability, and system efficiency. First, the multi-level spatial index is adopted to manage large-scale geographic data, which greatly improves the efficiency of waypoint screening and path segment query, and reduces the spatial data access delay to 38.50% of that before optimization. Compared with the traditional algorithm based on single-level path search, the total length of the flight path of this solution is shortened by 1.35 km (a decrease of 8.86%), and the path selection is more economical. The average value of the risk level decreases by 49.48%, and the flight path is safer; the number of times of exceeding the standard in the dynamic environment (such as wind speed limit, extreme weather points) decreases from 5 times to 0, effectively avoiding potential dangers.

[0083] The optimization of the curvature index reflects that the flight path is smoother, which is beneficial to the stable flight of the UAV. The energy consumption is reduced from 4.32 kWh to 3.68 kWh (saving 14.81%), verifying the actual role of the multi-objective fitness function in the global feedback optimization of path segments. The space-time dual constraint mechanism ensures that each individual in each generation meets the spatial feasibility and environmental adaptability, realizing the real-time scheduling ability in the dynamic environment. The adaptive adjustment of the genetic algorithm parameters effectively prevents the premature convergence of the population, and the optimization convergence speed is increased by 28.36% compared with the traditional fixed-parameter algorithm.

[0084] In addition, experiments show that the final flight path output by this method can be directly docked with the UAV control system, and the planning time is less than 2 minutes, fully meeting the actual engineering requirements. Through comprehensive analysis, this solution breaks through the bottleneck that traditional methods are difficult to handle multi-level spatial indexing, dynamic constraints, and global feedback optimization, realizes the comprehensive improvement of the flight path safety, economy, and intelligence level, and has significant innovation and practical application value compared with the existing technologies.

[0085] Embodiment 3, an embodiment of the present invention, provides a route optimization system based on genetic algorithms and geographic information. The multi-layer module receives geographic data related to route planning and constructs a multi-level spatial index.

[0086] The sequence module uses a waypoint optimization algorithm. With the support of the spatial index, it uses a genetic algorithm with adaptive adjustment based on population diversity to determine the waypoint sequence of the route.

[0087] The path segment module, for any two adjacent waypoints in the waypoint sequence, uses a path optimization algorithm. Combining the geographic information provided by the spatial index, it uses a genetic algorithm to generate the corresponding optimal path segment.

[0088] The optimization module iteratively optimizes the optimal path segment, iteratively optimizes the waypoint sequence and the optimal path segment, and integrates the optimization result into the autonomous navigation system after convergence.

[0089] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks and other various media that can store program codes.

[0090] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0091] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0092] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0093] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An airway optimization method based on genetic algorithms and geographical information, characterized in that, Including: Receiving geographical data related to route planning and constructing a multi-level spatial index; Adopting a waypoint optimization algorithm, with the support of the spatial index, using a genetic algorithm based on adaptive adjustment of population diversity to determine the waypoint sequence of the route; the waypoint optimization algorithm includes: setting screening rules based on the airspace label set, risk level field, and task rule label field stored in each index node of the coarse-grained spatial index structure, screening each index node, extracting the central coordinate points as candidate waypoints, and establishing a candidate waypoint set based on the candidate waypoints; For any two adjacent waypoints in the waypoint sequence, adopting a path optimization algorithm, combining the geographical information provided by the spatial index, and using a genetic algorithm to generate the corresponding optimal path segment; Performing iterative optimization on the optimal path segment, performing iterative optimization on the waypoint sequence and the optimal path segment, and integrating the optimization result into the autonomous navigation system after convergence.

2. The route optimization method based on genetic algorithm and geographic information according to claim 1, characterized in that: The geographical information data includes static data and dynamic data; among them, the static data includes regional terrain data, airspace management data, and regional task rule data, and the dynamic data includes static environment data and dynamic environment data; The multi-level spatial index includes a coarse-grained spatial index layer and a fine-grained spatial index layer; Constructing a coarse-grained spatial index layer based on the static data, with the coarse-grained index taking a two-dimensional square area as the basic unit, and the side length of the unit set as L, and the value of L is preset according to the area of the task area; using a quadtree structure to construct the index, and the index node stores: unit coordinate range, regional average terrain height, airspace label set, task rule label, risk level field, and unique spatial coding identifier; Constructing a fine-grained spatial index layer based on the dynamic data, with the fine-grained index divided by two-dimensional square spatial units, and the side length set as l, using an R-tree structure to construct the index, and the fields stored in the index node include static fields and dynamic fields, where the static fields include the coordinate range of the spatial unit, obstacle spatial boundary information, node status label, and spatial coding information, and the dynamic fields include the environmental data field value and its corresponding timestamp information.

3. The route optimization method based on genetic algorithm and geographic information according to claim 2, characterized in that: The screening rules include eliminating the nodes whose airspace labels contain no-fly zone or restricted airspace identifiers, and only retaining the spatial index nodes with a risk level lower than the preset threshold and marked as passable in the task rules; Taking the indices of several waypoints in the candidate waypoint set as chromosome genes, and forming a chromosome with the arrangement order of the waypoint indices as the search individual of the genetic algorithm; During the execution of the genetic algorithm, setting a spatial perception control mechanism to verify the spatial attributes of the waypoints generated in the mutation stage, and restricting the chromosomes that do not meet the risk conditions or airspace requirements from entering the next generation; The spatial perception control mechanism includes: when performing the mutation operation, calling the coarse-grained spatial index structure, retrieving the risk level field and airspace label set of the spatial unit where the mutated waypoint is located, and judging whether the mutated waypoint is located in an area with a risk level higher than the original waypoint, or whether the airspace label set contains a no-fly zone identifier or a restricted airspace identifier; If the conditions are not met, the mutated waypoint is removed and the mutation result is not included in the subsequent population. During the iteration of the genetic algorithm, a fitness function is constructed based on the path distance, regional risk value, and task fitness, and the waypoint sequence with the highest fitness score is determined as the optimal individual of the current generation, serving as the input for subsequent path optimization.

4. The route optimization method based on genetic algorithm and geographic information according to claim 3, characterized in that: The path optimization algorithm includes constructing a path segment optimization task according to any two adjacent waypoints in the waypoint sequence; the path segment consists of a starting point, an ending point, and several path points. Based on the fine-grained spatial index layer, the field information in the spatial index node where the path point is located is called, and combined with the task time step, a binding relationship between the path point and the temporal environmental data is established. The A* search algorithm is used to perform path search in the fine-grained spatial index layer. A path cost function is constructed based on the cumulative environmental cost of the path point and the heuristic function to generate an initial path segment. Based on the initial path segment, a path perturbation mechanism is introduced to generate individual perturbation path segments as the initial population of the genetic algorithm. During the evolution of the genetic algorithm, a fitness function is constructed based on the path segment length, the risk level field of the path node, the dynamic environmental field value at the time step, and the path curvature. A space-time double constraint mechanism is used to perform validity screening on each generation of generated path individuals to ensure that only path individuals that meet the environmental and spatial requirements can enter the next generation population. When the path segment optimization meets the convergence condition or reaches the maximum number of iterations, the corresponding optimal path segment is output, and the optimal results of all path segments are spliced to form a complete path set, serving as the input for route quality evaluation and subsequent iteration update of the waypoint sequence.

5. The route optimization method based on genetic algorithm and geographic information according to claim 4, characterized in that: The path perturbation mechanism includes performing a spatial perturbation operation on the intermediate path points of the path segment within a limited perturbation radius; calling the index nodes in the multi-level spatial index to determine whether the perturbed path points are located in obstacle areas, no-fly zones, height-limited zones, or high-risk level areas, and only retaining the perturbed path segment individuals that do not fall into the above areas for constructing the initial population of the genetic algorithm.

6. The route optimization method based on genetic algorithm and geographic information according to claim 5, characterized in that: The space-time double constraint mechanism includes a spatial constraint mechanism and a temporal constraint mechanism. The spatial constraint mechanism includes judging whether the path point falls into an obstacle area, no-fly zone, height-limited zone, or high-risk level area based on the airspace management label, obstacle information, and risk level field of the node in the fine-grained spatial index. The temporal constraint mechanism includes judging whether it falls into an area where the environmental risk exceeds the threshold based on the dynamic environmental field value corresponding to the task time step of the path node. If the passage requirement is not met, the path individual does not enter the next generation.

7. The route optimization method based on genetic algorithm and geographic information according to claim 6, characterized in that: The iterative optimization of the optimal path segment includes splicing the optimal path segment to form a complete path set, and performing a fitness score on the overall route based on the total length of the complete path set, the risk level field of the path node, the dynamic environmental field value at the task time step, and the path curvature. According to the fitness score result, the path segment is adjusted through the genetic algorithm, and the optimized path segment is screened in combination with the space-time double constraint mechanism. Perform loop execution path optimization and fitness scoring until the fitness score of the complete path set meets the convergence condition or reaches the maximum number of iterations, and then output the optimization result.

8. A route optimization system based on genetic algorithm and geographic information, which adopts the route optimization method based on genetic algorithm and geographic information according to any one of claims 1-7, and is characterized in that: A multi-layer module that receives geographic data related to route planning and constructs a multi-level spatial index; A sequence module that uses a waypoint optimization algorithm and, with the support of the spatial index, determines the waypoint sequence of the route by using a genetic algorithm with adaptive adjustment based on population diversity; A path segment module that, for any two adjacent waypoints in the waypoint sequence, uses a path optimization algorithm, combines the geographic information provided by the spatial index, and generates the corresponding optimal path segment by using a genetic algorithm; An optimization module that iteratively optimizes the optimal path segment, iteratively optimizes the waypoint sequence and the optimal path segment, and integrates the optimization result into the autonomous navigation system after convergence.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the route optimization method based on genetic algorithm and geographic information according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the route optimization method based on genetic algorithm and geographic information according to any one of claims 1 to 7.

Images