GIS-Based Path Planning Method for Complex Terrain in the Wild

Abstract

The present invention provides a method for planning a field terrain path based on GIS. The method includes: obtaining geographical information data of the current area, converting the current area into different layers through ArcGIS based on the geographical information data, dividing the different layers into grids with equal length and width through surface type element classification to obtain a distribution map of the passing speed grids of the current area; determining the current position and the target position in the distribution map of the passing speed grids, and establishing a path planning model with the shortest time from the current position to the target position as the objective function; solving the optimal solution of the path planning model by using a genetic algorithm based on the distribution map of the passing speed grids, and obtaining the optimal path according to the optimal solution of the path planning model. It is used to solve the problem of the shortest path for vehicle driving under complex field terrain conditions.

Description

Technical Field

[0001] This document relates to the technical field of path planning, and particularly relates to a path planning method for complex terrain in the wild based on GIS. Background Art

[0002] Traditional obstacle avoidance path planning research usually binarizes the terrain and features within a region, distinguishing between passable and impassable areas for research, thereby obtaining the shortest distance path on the map. However, under the conditions of complex terrain in the wild, there is a lack of sufficient road information. In passable areas, due to different terrain conditions, the vehicle driving speeds are also different, and the shortest path obtained is often not the path with the shortest time. In actual work, the requirement for time is getting higher and higher, especially in tasks such as disaster rescue and emergency support. The shortest path considering the speed difference under actual terrain conditions is more meaningful.

[0003] In recent decades, with the development of space technology and IT technology, terrain recognition and judgment methods have become increasingly mature. Marked by Geographic Information System (GIS, sometimes also called Geo-Information System) technology, with the support of computer hardware and software systems, it realizes the acquisition, storage, management, calculation, analysis, display, and description of geographical distribution data in the space of the entire or part of the earth's surface (including the atmosphere). Especially the "new generation Web GIS" application mode makes full use of the advantages of cloud and local deployment. Users can easily obtain information on the map, create maps, models, and tools on smartphones and tablets, and make auxiliary decisions based on the latest data. It has been widely applied in fields including public health, national defense, sustainable development, natural resources, landscape architecture, archaeology, community planning, transportation, and logistics. Therefore, it is necessary for us to research a path planning method under complex terrain based on GIS technology to obtain the optimal path under complex terrain. Summary of the Invention

[0004] One or more embodiments of this specification provide a path planning method for wild terrain based on GIS, including:

[0005] S1. Obtain the geographical information data of the current area, convert the current area into different layers through ArcGIS based on the geographical information data, and divide different layers into grids with equal length and width through surface type element classification to obtain the traffic speed grid distribution map of the current area;

[0006] S2. Determine the current position and the target position in the traffic speed grid distribution map, and establish a path planning model with the shortest time from the current position to the target position as the objective function;

[0007] S3. Solve the optimal solution of the path planning model using the genetic algorithm based on the traffic speed raster distribution map, and obtain the optimal path according to the optimal solution of the path planning model.

[0008] By adopting the embodiment of the present invention, the ArcGIS software is used to perform spatial analysis on geographic information data, and combined with the driving speeds of vehicles under different terrains, different terrain speed distribution maps are constructed. Taking the adjacent raster numbers and the similar raster elevations as the basis for judging path continuity, a genetic algorithm based on raster information is designed to solve the path with the shortest driving time of vehicles under complex field terrain conditions. This method has high efficiency and can obtain a relatively satisfactory path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0010] Figure 1 It is a flowchart of a method for path planning in the wild terrain based on GIS according to an embodiment of the present invention;

[0011] Figure 2 It is a flowchart of using the genetic algorithm to solve the shortest path according to an embodiment of the present invention;

[0012] Figure 3 It is a traffic speed raster distribution map according to an embodiment of the present invention;

[0013] Figure 4 It is an efficiency curve diagram of the genetic algorithm according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will clearly and completely describe the technical solutions in one or more embodiments of this specification in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this document.

[0015] Method Embodiment

[0016] According to an embodiment of the present invention, a method for path planning in the wild terrain based on GIS is provided. Figure 1is a flowchart of the method for planning a field terrain path based on GIS according to an embodiment of the present invention. As Figure 1 described, the method for planning a field terrain path based on GIS according to an embodiment of the present invention specifically includes:

[0017] Step S101, obtaining geographical information data of the current area, converting the current area into different layers based on the geographical information data through ArcGIS, and dividing the different layers into grids with equal length and width through surface type element classification to obtain a distribution map of the passing speed grids of the current area; Step S101 specifically includes:

[0018] Under the conditions of complex field terrain, detailed geographical information data of the current area can be obtained by means of satellite remote sensing, unmanned aerial vehicles and other devices or by collecting network data. Use ArcGIS map to perform spatial analysis and information integration on data such as elevation and slope, determine the terrain and landforms, extract and convert them into different layers, reclassify through surface type elements, mosaic the attribute information into new grids, and finally divide the map into grids with equal length and width, and use the surface type with the worst passing ability in the grid as the surface type of the grid to finally obtain the distribution map of the passing speed of the current area.

[0019] Among them, in the field of geographical information, the division of surface types usually divides land terrain into five types: plain, plateau, mountain, hill, and basin according to the differences in height and morphological characteristics. GT / T13977—92 "Specifications for Aerial Photogrammetry Fieldwork of 1:5 000 and 1:10 000 Topographic Maps" is divided into four types: flat land, hilly land, mountain land, and high mountain land according to the ground tilt angle and height difference. In order to distinguish the passing speeds of vehicles on different grounds in the embodiments of the present invention, combined with the above classifications, the surface types are divided as shown in Table 1 below:

[0020] Table 1 Division of surface types

[0021]

[0022] Step S102, determining the current position and the target position in the distribution map of the passing speed grids, and establishing a path planning model with the shortest time from the current position to the target position as the objective function; Step S102 specifically includes:

[0023] In the grid map, number the map grids sequentially as 0, 1, 2, L, k, L, N in the order from left to right and from bottom to top, and the driving speed of the vehicle in the grid is v k , assuming that the vehicle is in good condition throughout the journey, establish a model with the shortest time required to complete the whole journey as the objective as follows:

[0024]

[0025] Among them, T(l) represents the travel time of the l-th path, (O, D) represents the set of all grid paths from the starting point to the target position, and V k , k ∈ (1, 2, …, N) represents the driving speed of the vehicle at different grids; X represents the number of grids in each row of the map, d represents the length of each grid, represents driving along the diagonal direction of the grid, [ ] is the rounding function, and \ is the modulo operation.

[0026] Step S103, use the genetic algorithm to solve the optimal solution of the path planning model based on the traffic speed grid distribution map, and obtain the optimal path according to the optimal solution of the path planning model. Step S103 specifically includes:

[0027] The genetic algorithm is a bionic method for globally searching for the optimal solution randomly. It applies the principle of biological evolution in nature to the optimization process of problem solutions, and uses the concept of population evolution to find the optimal individual. The algorithm regards the set of feasible solutions of the problem as a "population", and each individual in the set is composed of multiple "chromosomes". By simulating the process of gene recombination and evolution, the "chromosomes" in the initial population are screened, replicated, crossed, and mutated to obtain a new population with better adaptability. After multiple iterations of evolution, the obtained optimal solution tends to be stable, that is, it is considered that the optimal solution in the population at this time is the optimal solution of the problem. The genetic algorithm has a bionic evolution process and a random mutation characteristic, and can usually solve optimization problems efficiently. In this embodiment of the invention, the genetic algorithm is used to solve the path planning problem of complex terrain in the wild. The specific algorithm flow is as Figure 2 shown;

[0028] 1. Population initialization

[0029] In path planning, real number coding is usually adopted, and each path is defined as an individual. Initializing the population requires randomly generating multiple feasible paths. Generating a feasible path is completed in two steps: First, take one grid in each row of the grid map to form a discontinuous path, and the grids in the first row and the last row are taken as the grids where the current position and the target position are located; Second, insert one or more grids in each row to make the discontinuous path into a continuous path. Use max{|[(k + 1) / X] - (k / X)|, |(k + 1)\X - (k\X)|} = 1 to verify that grids k and k + 1 are adjacent. If they are not adjacent, continue to verify after inserting new grids until a complete path with connected grid roads is finally obtained after multiple iterations. The coordinates (x cha , x cha ) of the inserted grid are generated by the following formula:

[0030]

[0031]

[0032] When the complete path cannot be obtained after multiple iterations, this path is discarded.

[0033] 2. Fitness Design

[0034] Fitness is the key to measuring the performance of individuals in the population in genetic algorithms and is the basis for population selection. In this paper's model for solving the minimum value problem, the reciprocal of the objective function, i.e., F = 1 / T(k), is taken as the fitness function. Compared with the traditional simple calculation of fitness, in this paper, the path continuity is judged first before calculating the individual fitness. The elevations of the central positions of adjacent grids k and k + 1 in the path are compared. If the elevations do not differ much, the road is considered continuous, and there are no steep terrain changes such as deep pits and collapses. If the adjacent elevations differ greatly, this path is discarded.

[0035] 3. Selection Operation

[0036] The selection operation selects individuals with high fitness from the parent population with a certain probability to form a new population, usually using the roulette wheel method. The probability that individual i is selected is where F i is the fitness value of individual i; M is the number of individuals in the population. The roulette wheel method enables some non-optimal individuals to be selected, ensuring the population diversity to a certain extent and preventing the algorithm from falling into local optima.

[0037] 4. Crossover Operation

[0038] The crossover operation refers to randomly selecting two individuals from the parent population and generating new excellent individuals through chromosome exchange. The single-point crossover method is adopted in this paper, that is, all the same points in the two paths are found, and one of them is randomly selected, and the subsequent paths are exchanged to obtain two new paths.

[0039] 5. Mutation Operation

[0040] The main purpose of the mutation operation is to maintain the population diversity, mainly operating on an individual in the population. The method in this paper is to randomly select two grids except the starting point and the ending point in a path, discard the selected grids between the two grids, and use the method of inserting grids to regenerate a new continuous path. If a continuous path cannot be generated after multiple iterations, two grids are reselected and the above operations are performed until a new path is generated. If a continuous path cannot be generated after multiple iterations, this individual is discarded.

[0041] Figure 3 is the grid distribution map of the passing speed for the embodiment of the present invention, with Figure 3Taking the shown terrain as an example, in the grid map, X is 7500m, Y is 7500m, and the area is divided into 225 grids in total. The length and width of each grid are both 500m. Taking a crawler vehicle with better cross-country performance as the research object, assuming that the maximum driving speed of the vehicle is 60km / h when not considering terrain factors, the passing speeds of the vehicle in different terrains in this area are shown in Table 2:

[0042] Table 2 Vehicle Driving Speed Table in Different Terrains

[0043]

[0044] Using MATLAB 2014b, set the population size to 200, the maximum number of iterations to 50, the crossover probability to 0.8, the mutation probability to 0.2, the maximum number of iterations for grid interpolation calculation to 1000 times, and the elevation difference between the centers of adjacent grids not greater than 2 meters. Calculate the shortest time path for the vehicle to travel from the current position (0,0) grid to the target position (15,15) grid. The running results are shown in Figure 4 , and it can be known from the calculation that after 5 - 10 iterations, the population tends to be stable, and a relatively satisfactory shortest passing time path can be obtained. The obtained shortest path is shown in Table 3:

[0045] Table 3 Shortest Path of Driving Time Based on Genetic Algorithm

[0046]

[0047] By differentiating the passing speeds, the influence of obstacles on passing is quantitatively differentiated, which is more operable and has more practical significance. The shortest time path to reach the target position under the actual terrain can be obtained efficiently. Next, the discrimination accuracy of the terrain and landform can be improved, and the elevation information within the grid can be comprehensively used to judge the continuity of the road. Especially by refining the map grid and increasing the number of row and column grids, a more accurate driving route can be obtained.

[0048] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A GIS-based method for planning field terrain paths, characterized in that, Including: S1. Obtain the geographical information data of the current area, convert the current area into different layers through ArcGIS based on the geographical information data, and divide the different layers into grids with equal length and width through surface type element classification to obtain the traffic speed grid distribution map of the current area; S2. Determine the current position and the target position in the traffic speed grid distribution map, and establish a path planning model with the shortest time from the current position to the target position as the objective function; S3. Solve the optimal solution of the path planning model by using the genetic algorithm based on the traffic speed grid distribution map, and obtain the optimal path according to the optimal solution of the path planning model; In step S2, establishing a path planning model with the shortest time from the current position to the target position as the objective function specifically includes: Number each grid in the traffic speed grid distribution map in sequence from left to right and from bottom to top, with the numbers being 0, 1, 2, …, k, …, N, and the driving speed of the vehicle in each grid being v k , assuming that the vehicle is in good condition throughout the journey, establish the following model with the goal of minimizing the time required to complete the whole journey: Among them, T(l) represents the travel time of the l-th path, (O, D) represents the set of all grid paths from the starting point to the target position, and V k , k ∈ (1, 2, …, N) represents the driving speed of the vehicle at different grids; X represents the number of grid rows in the map, d represents the length of each grid, represents traveling in the diagonal direction of the grid, [] is the rounding function, and \ is the modulo operation; The step of solving the optimal solution of the path planning model by using the genetic algorithm based on the traffic speed grid distribution map and obtaining the optimal path according to the optimal solution of the path planning model specifically includes: Construct a continuous grid path in the traffic speed grid distribution map based on the current position and the target position to obtain an initial population; Obtain a fitness function based on the objective function, and calculate the fitness of the initial population based on the fitness function; Judge whether the preset number of iterations is reached. If the preset number of iterations is not reached, perform selection, crossover and mutation of the population and then calculate the fitness; If the preset number of iterations is reached, output the optimal path obtained based on the fitness function.

2. According to the method described in claim 1, step S1 specifically includes: Use ArcGIS map to perform spatial analysis and information integration on the geographical information data, conduct terrain and landform determination, and extract and convert the current area into different layers; Through surface type element classification, mosaic the attribute information into new grids, and finally divide the current area into grids with equal length and width, and use the surface type with the worst traffic capacity in the grid as the surface type of the grid, and finally obtain the traffic speed grid distribution map of the current area.

3. According to the method described in claim 1, the step of constructing a continuous grid path in the traffic speed grid distribution map based on the current position and the target position to obtain an initial population specifically includes: Take one grid from each row in the traffic speed grid distribution map to form a discontinuous path, and take the grids in the first row and the last row as the grids where the current position and the target position are located; Insert one or more grids into each row to make the discontinuous path a continuous path; use formula 2 to verify that grid k and k + 1 are adjacent, max{|[(k + 1) / X]-(k / X)|,|(k + 1)\X-(k\X)|} = 1 Formula 2; If they are not adjacent, continue to verify after inserting a new grid, and iterate the verification until a complete path of adjacent grid-connected roads is finally obtained. The coordinates of the inserted grid are denoted as (x cha , x cha ), x cha and y cha generated by Equation 3: If a complete path cannot be obtained even when the number of iterations is greater than the predetermined number of iterations, this path is discarded.

4. The method according to claim 1, wherein The step of obtaining a fitness function based on the objective function specifically includes: Take the reciprocal of the objective function, that is, F = 1 / T(k) as the fitness function.

5. The method according to claim 1, wherein Before calculating the fitness of the initial population based on the fitness function, the method further includes: First, the path continuity is judged by comparing the elevation of the central positions of adjacent grids k and k + 1 in the path. If the elevation difference is less than or equal to a specific threshold, the road is considered continuous without steep terrain changes such as deep pits or collapses. If the adjacent elevation difference is greater than the specific threshold, this path is discarded.

6. The method according to claim 1, wherein If the preset number of iterations is not reached, the specific steps of selection, crossover, and mutation of the population and then calculation of fitness include: Selection operation: Use the roulette wheel method to select continuous grid paths with fitness function values higher than a specific value to form a new population. Crossover operation: Adopt the single-point inspection method to find all the same points in two continuous grid paths, randomly select one of them, and exchange the subsequent grid paths to obtain two new paths. Mutation operation: Select two grids except the start and end points in a continuous grid path, discard the selected grids in the middle of the two grids, and use the method of inserting grids to regenerate a new continuous grid path.

7. The method according to claim 6, characterized in that, The method of using the inserted grid to regenerate a new continuous grid path further includes: If a continuous grid path cannot be generated after the first specific number of iterations, two grids are reselected until a new path is generated. If a continuous path cannot be generated after the second specific number of iterations, this continuous grid path is discarded.

8. The method according to claim 6, characterized in that, Obtaining the geographical information data of the current area specifically includes: Obtaining the geographical information data of the current area through satellite remote sensing, unmanned aerial vehicle equipment, and network materials.

Images