CN115185303B - Unmanned aerial vehicle patrol path planning method for national parks and natural protected areas - Google Patents
Unmanned aerial vehicle patrol path planning method for national parks and natural protected areas Download PDFInfo
- Publication number
- CN115185303B CN115185303B CN202211112515.1A CN202211112515A CN115185303B CN 115185303 B CN115185303 B CN 115185303B CN 202211112515 A CN202211112515 A CN 202211112515A CN 115185303 B CN115185303 B CN 115185303B
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- path
- solution
- solution space
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses an unmanned aerial vehicle patrol path planning method for national parks and natural protected areas, which comprises the following steps: step 1: inputting three-dimensional terrain data, generating a bounded three-dimensional area, and requiring the unmanned aerial vehicle to traverse all path points to complete a visual coverage task; step 2: taking the flight path of the unmanned aerial vehicle as an optimization target, adding constraint conditions of traversal path points of the unmanned aerial vehicle, electric quantity limitation of the unmanned aerial vehicle and self-service charging circuit planning of the unmanned aerial vehicle, and establishing an unmanned aerial vehicle path planning model; and step 3: and (3) under the unmanned aerial vehicle path planning model established in the step (2), solving by using a branch-and-bound algorithm and combining a linear relaxation algorithm and a greedy algorithm to obtain the traversal path of the unmanned aerial vehicle. The unmanned aerial vehicle monitoring system solves the problem that the unmanned aerial vehicle patrol monitoring can not be continuously carried out in a natural protection field, and realizes the unmanned aerial vehicle monitoring automation.
Description
Technical Field
The invention belongs to the technical field of unmanned aerial vehicle flight control, and particularly relates to an unmanned aerial vehicle patrol route planning method for national parks and natural protected areas.
Background
The field patrol monitoring is the most important ecological monitoring and daily supervision means in national parks and natural conservation places, and a patrol guard collects data in the aspects of wild species population, habitat, phenology and the like through patrol monitoring, can timely discover ecological environment problems, inhibit illegal activities and the like, realizes effective protection on the national parks and the natural conservation places, and provides decision basis for natural resource supervision. However, national parks and natural protection lands have large areas, wide ranges and complex terrains, people and vehicles in most regions are difficult to reach, and the traditional manual patrol mode has low efficiency and wastes time and labor. Therefore, in recent years, unmanned aerial vehicles are increasingly used for patrol monitoring work of various natural conservation places.
The unmanned aerial vehicle technology is an unmanned aerial vehicle remote sensing technology which is realized by fusing an aircraft technology, a communication technology, a GPS (global positioning system), a differential positioning technology and an image technology, and automatic acquisition and transmission of monitoring data are realized by carrying sensing equipment such as a high-definition camera and an intelligent sensor and combining a wireless communication network. The existing unmanned aerial vehicle used for patrol monitoring of national parks and natural conservation places has the challenges of short endurance, high requirement on flight control personnel, difficult storage and transportation of airplanes, high application integration difficulty and the like, and is difficult to meet the application requirements of normalized monitoring.
The automatic airport of unmanned aerial vehicle is the ground automation facility of assisting unmanned aerial vehicle full flow operation, for unmanned aerial vehicle provides all-weather protection, through automatic opening and shutting, go up and down, get and unload structural design, let unmanned aerial vehicle take off, descend, deposit and battery management all can accomplish automatically, need not artificial intervention. The unmanned aerial vehicle is stored in the automatic airport, and when flight demands exist, the unmanned aerial vehicle takes off from the airport autonomously, and automatically lands in the automatic airport after a task is finished, so that the unmanned aerial vehicle is charged in the automatic airport, preparation is made for the next task, and full-automatic operation is realized.
For realizing the normalized development of unmanned aerial vehicle in national park and the ecological monitoring work of nature protected area, satisfy the field and patrol and protect the monitoring management demand, this patent carries out path planning, electric quantity state control, commander's dispatch to unmanned aerial vehicle based on the automatic airport of unmanned aerial vehicle, and very big degree promotes unmanned aerial vehicle and patrols and protects monitoring efficiency.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an unmanned aerial vehicle patrol path planning method for national parks and natural conservation places.
The invention is realized by the following technical scheme:
an unmanned aerial vehicle patrolling path planning method for national parks and natural protected areas is characterized by comprising the following steps of:
step 1: inputting three-dimensional terrain data, generating a bounded three-dimensional area over which waypoints are placed in the air
The unmanned aerial vehicle is required to complete the visual coverage task after traversing all path points;
step 2: taking the flight path of the unmanned aerial vehicle as an optimization target, adding constraint conditions of traversal path points of the unmanned aerial vehicle, electric quantity limitation of the unmanned aerial vehicle and self-service charging circuit planning of the unmanned aerial vehicle, and establishing an unmanned aerial vehicle path planning model;
and step 3: and (3) under the unmanned aerial vehicle path planning model established in the step (2), solving by using a branch-and-bound algorithm and combining a linear relaxation algorithm and a greedy algorithm to obtain the traversal path of the unmanned aerial vehicle.
In the above technical solution, step 2 includes the following steps:
step 2.1: defining flight path decision variables for dronesx ij ；
x ij =1, representing unmanned aerial vehicle from a waypointiFly to the waypointj；
x ij =0, meaning that the drone is not following a waypointiFly to the waypointj；
Defining an objective function:
whereind ij Representing points of a pathiAnd a waypointjThe linear distance therebetween;
the flight path decision variables need to ensure that a complete and feasible one-time traversal path can be formed, and the specific constraints are as follows:
step 2.2: aiming at the self-service charging function of the unmanned aerial vehicle, the self-service charging circuit plan of the unmanned aerial vehicle with an automatic airport is adjusted;
measuring the energy consumption of the unmanned aerial vehicle by using the flight path, and recording the maximum endurance of the unmanned aerial vehicle asRDefining the energy loss variableE ij Automated airport assembly
；
The residual cruising distance of the unmanned aerial vehicle does not exceed the maximum cruising distanceRIs given by the following equation:
when the unmanned aerial vehicle leaves the automatic airport, the electric quantity is full, and the formula is as follows:
updating the target function:
in the above technical solution, step 3 includes the following steps:
step 3.1: let MIP be the unmanned aerial vehicle path planning problem that needs to be solved,best sol the current optimal solution is used for continuously updating the searched optimal solution in the solving process, and any feasible solution in the MIP is taken as an initial value; recording Lb as a lower boundary of a current solution space, and recording an objective function value corresponding to a current optimal solution searched in the solving process;
step 3.2: branch branch
Setting S as MIP solution space, and making flight path decision variablex ij Enumerating, and dividing the solution space S into two mutually disjoint sub-solution spaces S 0 And S 1 Wherein S is 0 All feasible solutions inx ij The value is 0; s 1 All feasible solutions inx ij The value is 1; the partitioned sub-solution space is called a branch node;
step 3.3: delimitation
Searching feasible solutions in the sub-solution space by using a greedy algorithm, and if the objective function value of the feasible solution is less thanbest sol The objective function value of (2) is updatedbest sol (ii) a Calculating the lower bound of the feasible solution objective function value by adopting a linear relaxation method, and converting the value range of the flight path decision variable with the unfixed value from {0,1} into [0,1 ]]Expanding the value range of flight path decision variables without fixed values in the sub-solution space, and calculating the relaxed sub-solution space by using a CPLEX solver;
step 3.4: pruning
Screening out proper branch nodes according to the solving condition, wherein no more feasible solution exists in the deleted branch nodesbest sol Preferably, or the lower bound is larger than the known solution space lower bound, the process of deleting the branch node is pruning;
step 3.5: updating the current solution space lower bound Lb sum according to the remaining branch nodes after pruningbest sol And then, the operations of branching, delimiting and pruning are carried out iteratively until the tree search of the solution space is completed.
In the above technical solution, in step 3.3, when searching for a feasible solution in a sub-solution space using a greedy algorithm, a plurality of local optimal solutions are first calculated using a plurality of different types of greedy algorithms, then a union is taken, and a flight path decision variable is defined in the union.
In the above technical solution, 3 greedy algorithms are used, which are respectively: a greedy algorithm based on the starting of the position of the unmanned aerial vehicle, a greedy algorithm based on the backtracking of the end point to the position of the unmanned aerial vehicle, and a greedy algorithm based on the global shortest path point distance;
greedy algorithm based on unmanned aerial vehicle position starting: recording the current position of the unmanned aerial vehicle, searching the nearest non-traversed path point away from the unmanned aerial vehicle, if so, the unmanned aerial vehicle flies to the path point, updating the current position of the unmanned aerial vehicle, and continuing searching; if not, outputting the flight path of the unmanned aerial vehicle, and ending;
greedy algorithm based on backtracking of end point to unmanned aerial vehicle position: recording the backtracking position of the unmanned aerial vehicle, searching the nearest non-traversed path point away from the unmanned aerial vehicle, if so, flying the unmanned aerial vehicle to the path point, updating the backtracking position of the unmanned aerial vehicle, and continuing searching; if not, outputting the flight path of the unmanned aerial vehicle, and ending;
greedy algorithm based on global shortest path point distance: searching edges among path points contained in the current solution space, selecting the edge with the minimum Euclidean distance as an element in the unmanned aerial vehicle traversal path, updating the current solution space, and stopping searching when the solution space is an empty set.
In the above technical solution, in step 3.5, in the iterative process, branching is performed by a depth-first or breadth-first search method;
the depth-first search method comprises the following steps: comparing all the delimited branch nodes, selecting the branch node with the minimum lower bound for branching, and if all the branch nodes corresponding to all the flight paths in the current state of the unmanned aerial vehicle are pruned or are not selected as the branched branch nodes in the planned unmanned aerial vehicle path, finishing the search;
breadth-first search method: and branching all newly generated branch nodes, and sequentially branching from small to large according to the size of the lower bound of the branch nodes.
In the above technical solution, in step 3.5, when there is no branch node that can continue branching, orbest sol When the objective function value of (a) is Lb, the search of the solution space is finished, and the solution space is outputbest sol As a result of the solution of MIP.
The invention has the advantages and beneficial effects that:
the invention can quickly design a visual traversal path of the unmanned aerial vehicle for one area, and allows planning the visual traversal path of the unmanned aerial vehicle capable of automatically charging under the condition of the ground automatic airport. The problem of can't continuously develop unmanned aerial vehicle and patrol the monitoring in nature protected ground is solved, unmanned aerial vehicle monitoring automation has been realized, reduces the technique and the personnel threshold that use unmanned aerial vehicle simultaneously, when satisfying daily patrol the demand, provides decision analysis support for the protected area.
The unmanned aerial vehicle path planning model established by the invention integrates the autonomous charging function of the unmanned aerial vehicle, and the branch-and-bound algorithm is utilized to solve the unmanned aerial vehicle path planning model. In order to improve the solving efficiency, the method also combines methods such as linear relaxation and greedy algorithm to improve the solving speed and quality, and obtains the traversal path of the unmanned aerial vehicle; during solving, a plurality of local optimal solutions are calculated by using 3 different types of greedy algorithms (a greedy algorithm based on unmanned aerial vehicle position starting, a greedy algorithm based on end point backtracking to unmanned aerial vehicle position, and a greedy algorithm based on global shortest path point distance), then a union set is taken, and flight path decision variables are defined in the union set to reduce the search space of feasible solutions.
Drawings
FIG. 1 is a basic flow diagram of the present invention.
FIG. 2 is a schematic diagram of a branch-and-bound algorithm.
For a person skilled in the art, other relevant figures can be obtained from the above figures without inventive effort.
Detailed Description
In order to make the technical solution of the present invention better understood, the technical solution of the present invention is further described below with reference to specific examples.
An unmanned aerial vehicle patrol path planning method for national parks and natural conservation places, referring to the attached figure 1, comprises the following steps:
step 1: inputting three-dimensional terrain data to generate a bounded three-dimensional region
Setting a path point in the air above the area according to the performance and patrol requirement of the airborne camera of the unmanned aerial vehicle>
And requiring the unmanned aerial vehicle to complete the visual coverage task after traversing all path points.
Step 2: and establishing a constraint formula, taking the flight path of the unmanned aerial vehicle as an optimization target, adding constraint conditions such as unmanned aerial vehicle traversal path points, unmanned aerial vehicle electric quantity limitation, unmanned aerial vehicle self-service charging circuit planning and the like, and establishing an unmanned aerial vehicle path planning model without considering uncontrollable factors such as wind power, visibility and unmanned aerial vehicle faults. The method comprises the following specific steps:
step 2.1: defining flight path decision variables for an unmanned aerial vehiclex ij ；
x ij =1, representing unmanned aerial vehicle from a waypointiFly to the waypointj；
x ij =0, meaning that the drone is not following a waypointiFly to the waypointj；
Defining an objective function:
whereind ij Representing points of a pathiAnd a waypointjThe linear distance between the unmanned aerial vehicle and the unmanned aerial vehicle is optimized by the taskThe flight path of (2) is minimized as much as possible on the premise of completing the mission objective. Meanwhile, flight path decision variables need to ensure that a complete and feasible one-time traversal path can be formed, and the specific constraints are as follows:
step 2.2: to unmanned aerial vehicle's the function of charging by oneself, the unmanned aerial vehicle self-service charging line planning at automatic airport is taken in the adjustment. Measuring the energy consumption of the unmanned aerial vehicle by using the flight path, and recording the maximum endurance of the unmanned aerial vehicle asRDefining the energy loss variableE ij Automated airport assembly
。
First, the drone consumes energy as it moves between waypoints and the remaining range of the drone during the mission should not exceed the maximum rangeRIs given by the following equation:
secondly, when unmanned aerial vehicle left the automatic airport, the electric quantity was full-loaded, and the formula is expressed as follows:
in addition, considering the flight distance between the unmanned aerial vehicle at the automatic airport and the path point, the number of times that the unmanned aerial vehicle comes and goes to the automatic airport and the distance that the unmanned aerial vehicle leaves the traversal path and flies to the automatic airport to charge are reduced as much as possible, and the objective function is updated:
in conclusion, an unmanned aerial vehicle path planning model is established, and comprises an objective function (7) and constraint formulas (2), (3), (4), (5) and (6).
And step 3: solving the unmanned aerial vehicle path planning model established in the step 2 by using a branch and bound algorithm, wherein the basic principle of the branch and bound algorithm is shown in the attached figure 2, the branch and bound algorithm has the main idea that a solution space is divided by enumerating feasible solutions of partial variables, the process is called as branch (branch), the number of the solution spaces after the branch is the same as the enumerated number, each branch represents a sub-solution set after the branch is divided, and the sub-solution sets are subsets of the solution space and are not intersected with each other. After each new branch is obtained, the lower bound of the objective function is calculated on the solution set corresponding to the branch, and this process is called "bounding" (bound), and the generation of the new branch must be accompanied by the bounding of its solution space. After delimiting all branches, comparing the delimitations of all branches with the objective function values of the known feasible solutions, if the delimitations of the branches are larger than the objective function values of the known feasible solutions, it is indicated that no more optimal feasible solution exists in the solution set, the optimal solution of the objective function cannot exist in the solution set, the solution set is not further branched, and the process is called pruning; the above is the basic idea of the branch delimiting method. In order to improve the solving efficiency, the method also combines methods such as linear relaxation and greedy algorithm to improve the solving speed and quality, and obtains the traversal path of the unmanned aerial vehicle. The specific process of solving comprises the following steps:
step 3.1: the MIP is taken as the unmanned plane path planning problem to be solved,best sol the current optimal solution is used for continuously updating the searched optimal solution in the solving process, and any feasible solution in the MIP is taken as an initial value; and recording Lb as the lower boundary of the current solution space, wherein the Lb is used for recording an objective function value corresponding to the current optimal solution searched in the solving process, and the initial value of Lb is- ∞.
Step 3.2: branch branch
And S is a solution space of the MIP, and comprises each feasible solution meeting MIP constraint conditions. Consider thatx ij For one fixed unmanned aerial vehicle flight path decision variable, the solution space S can be divided into two mutually disjoint sub-solution spaces S 0 And S 1 Wherein S is 0 All feasible solutions inx ij The value is 0; s 1 All feasible solutions inx ij The value is 1; the sub-solution space partitioned by enumerating the flight path decision variable values is called a branch node.
Step 3.3: delimitation
In the divided two sub-solution spaces S 0 And S 1 The existence of feasible solutions and the lower bound of the objective function values in the two sub-solution spaces are analyzed.
1, searching whether a feasible solution exists in a sub-solution space according to a constraint condition in the MIP problem;
2, carrying out 'delimitation' operation on the sub-solution space with feasible solution to obtain a sub-solution space S 0 For example, a greedy algorithm is used in the sub-solution space S 0 Searching feasible solution, if the objective function value of feasible solution is less thanbest sol The objective function value of (2) is updatedbest sol (ii) a A linear relaxation method is introduced to calculate the lower bound of the feasible solution objective function value, and the unmanned aerial vehicle with the unfixed value is flownPath decision variablesx kl The value range of (1) is changed from {0,1} to [0,1 ]]Expanding the sub-solution space S 0 The value range of flight path decision variables with no fixed value in the middle and the relaxed sub-solution space
The calculation is carried out by using a CPLEX solver, and the value range of the variable is enlarged, so the obtained value is judged to be greater than or equal to the value>
Must not be greater than the sub-solution space S 0 So the relaxed solution result is taken as the lower bound of the branch node and is marked as the lower bound of the objective function value of the feasible solutionLb 0 . The sub-solution space S 1 The same way of delimiting, updatingbest sol Calculate its corresponding lower boundLb 1 。
Further, the method for searching the feasible solution of the solution space by using the greedy algorithm is divided into three algorithms, which are respectively as follows: the system comprises a greedy algorithm based on unmanned aerial vehicle position starting, a greedy algorithm based on end point backtracking to the unmanned aerial vehicle position, and a greedy algorithm based on global shortest path point distance.
Algorithm 2, greedy algorithm based on endpoint backtracking to unmanned aerial vehicle position: the position of the terminal point in the feasible solution of the flight path of the unmanned aerial vehicle is fixed, so that the feasible solution can be searched from the backtracking perspective, namely that the unmanned aerial vehicle returns to the initial position from the terminal point. The algorithm records the backtracking position of the unmanned aerial vehicle, searches the nearest non-traversed path point away from the unmanned aerial vehicle, if yes, the unmanned aerial vehicle flies to the path point, updates the backtracking position of the unmanned aerial vehicle and continues searching; if not, outputting the flight path of the unmanned aerial vehicle, and ending.
Algorithm 3, greedy algorithm based on global shortest path point distance: the algorithm is different from the former two methods, does not track the current position of the unmanned aerial vehicle, but searches the edges between path points contained in the current solution space, selects the edge with the minimum Euclidean distance as an element in the traversal path of the unmanned aerial vehicle, updates the current solution space, continues to search the edge with the minimum distance, and stops searching when the solution space is an empty set.
When the lower bound of the branch node is calculated, the 3 greedy algorithms are used for calculating a plurality of local optimal solutions, a union set is taken, and flight path decision variables are defined in the union set, so that the search space of feasible solutions is greatly reduced; and then linearly relaxing, and rapidly obtaining an optimal solution through a CPLEX solver, thereby improving the precision of the lower bound.
Step 3.4: pruning
Screening out proper branch nodes according to the information obtained by the solution, wherein the screening process should satisfy the optimal solution of the MIP of the original problem and keep the optimal solution in the screened sub-solution space, and the deleted branch nodes do not have a solution which is more feasible than the known solutionbest sol Preferably, or the lower bound is larger than the known solution space lower bound, this process of deleting branch nodes is called "pruning" and is essentially a process of narrowing the search space. Specifically, when the branch node
When the following conditions are met, pruning is required:
1，
no feasible solution exists;
2，
is greater than or equal to>
Not less thanbest sol The objective function value of (1);
3, among all the branch nodes which are not pruned,
is one of the largest lower bound nodes.
Step 3.5: iterative process of branching → delimiting → pruning for tree search
Updating the current solution space lower bound Lb sum according to the remaining branch nodes after pruningbest sol And then, iteratively branching, delimiting and pruning, namely repeating the steps of 3.2 to 3.4 to complete the tree search of the solution space. When there is no node that can continue branching, orbest sol When the objective function value of Lb is obtained, the search of the solution space is finished, the branch-and-bound algorithm is finished, and the branch-and-bound algorithm is outputbest sol As a result of the solution of MIP.
Furthermore, in the iterative process, branching is performed by a depth-first or breadth-first search method, that is, the following two methods are available for selecting a branch node.
1, a depth-first search method: and comparing all the delimited branch nodes, selecting the branch node with the minimum lower bound for branching, and finishing the search if the branch nodes corresponding to all the flight paths in the current state of the unmanned aerial vehicle are pruned or are not selected as the branched nodes in planning the unmanned aerial vehicle path.
2, breadth-first search method: and branching all newly generated branch nodes, and sequentially branching from small to large according to the size of a lower bound of the branch nodes.
The invention has been described in an illustrative manner, and it is to be understood that any simple variations, modifications or other equivalent changes which can be made by one skilled in the art without departing from the spirit of the invention fall within the scope of the invention.
Claims (6)
1. An unmanned aerial vehicle patrolling path planning method for national parks and natural protected areas is characterized by comprising the following steps of:
step 1: inputting three-dimensional terrain data to generate a bounded three-dimensional terrainA region above which a path point V = { V } is set in the air 1 ，v 2 ，...，v n The unmanned aerial vehicle is required to complete the visual coverage task after traversing all the path points;
step 2: taking the flight path of the unmanned aerial vehicle as an optimization target, adding constraint conditions of traversal path points of the unmanned aerial vehicle, electric quantity limitation of the unmanned aerial vehicle and self-service charging circuit planning of the unmanned aerial vehicle, and establishing an unmanned aerial vehicle path planning model; the step 2 comprises the following steps:
step 2.1: defining a flight path decision variable x for a drone ij ；
x ij =1, indicating that the drone flies from waypoint i to waypoint j;
x ij =0, meaning that the drone does not fly from waypoint i to waypoint j;
defining an objective function:
wherein d is ij Represents the straight-line distance between the path point i and the path point j;
the flight path decision variables are to ensure that a complete and feasible one-time traversal path can be formed, and the specific constraints are as follows:
step 2.2: aiming at the self-service charging function of the unmanned aerial vehicle, the self-service charging circuit plan of the unmanned aerial vehicle with an automatic airport is adjusted;
measuring the energy consumption of the unmanned aerial vehicle by using the flight path, recording the maximum endurance of the unmanned aerial vehicle as R, and defining an energy loss variable E ij Automatic airport group B = { B = { (B) } 1 ，b 2 ，...，b m }；
The remaining cruising distance of the unmanned aerial vehicle does not exceed the non-negative number of the maximum cruising R, and the formula is as follows:
x ki is a decision variable for the unmanned aerial vehicle to fly from waypoint k to waypoint i, E ki The energy loss required for the unmanned aerial vehicle to fly from the path point k to the path point i;
when the unmanned aerial vehicle leaves the automatic airport, the electric quantity is full, and the formula is as follows:
updating the target function:
and step 3: and (3) under the unmanned aerial vehicle path planning model established in the step (2), solving by using a branch-and-bound algorithm and combining a linear relaxation algorithm and a greedy algorithm to obtain the traversal path of the unmanned aerial vehicle.
2. The unmanned aerial vehicle patrol route planning method for national parks and natural conservation sites according to claim 1, characterized in that: the step 3 comprises the following steps:
step 3.1: marking MIP as the unmanned plane path planning problem to be solved, best sol The current optimal solution is used for continuously updating the searched optimal solution in the solving process, and any feasible solution in the MIP is taken as an initial value; recording Lb as the lower boundary of the current solution space for recording the current solution space searched in the solving processThe objective function value corresponding to the former optimal solution;
step 3.2: branch branch
Let S be the solution space of MIP, and make a decision on the flight path variable x ij Enumerating, and dividing the solution space S into two mutually disjoint sub-solution spaces S 0 And S 1 Wherein S is 0 X of all feasible solutions in ij The value is 0; s 1 X of all feasible solutions in ij The value is 1; the partitioned sub-solution space is called a branch node;
step 3.3: delimitation
Searching feasible solutions in the sub-solution space by using a greedy algorithm, and if the objective function value of the feasible solution is less than best sol The objective function value of (1), then update best sol (ii) a Calculating the lower bound of the feasible solution objective function value by adopting a linear relaxation method, and converting the value range of the flight path decision variable with the unfixed value from {0,1} into [0,1 ]]Expanding the value range of flight path decision variables without fixed values in the sub-solution space, and calculating the relaxed sub-solution space by using a CPLEX solver;
step 3.4: pruning
Screening out proper branch nodes according to the solving condition, wherein no more known feasible solution best exists in the deleted branch nodes sol More preferably, or the lower bound is greater than the known solution space lower bound;
step 3.5: updating the current solution space lower bound Lb and best according to the remaining branch nodes after pruning sol And then, the operations of branching, delimiting and pruning are carried out iteratively until the tree search of the solution space is completed.
3. The unmanned aerial vehicle patrol route planning method for national parks and natural conservation sites according to claim 2, characterized in that: in step 3.3, when searching for a feasible solution in the sub-solution space by using a greedy algorithm, a plurality of local optimal solutions are calculated by using various greedy algorithms of different types, then a union set is taken, and a flight path decision variable is defined in the union set.
4. The unmanned aerial vehicle patrol route planning method for national parks and natural conservation sites according to claim 3, characterized in that: using 3 greedy algorithms, respectively: a greedy algorithm based on the starting of the position of the unmanned aerial vehicle, a greedy algorithm based on the backtracking of the end point to the position of the unmanned aerial vehicle, and a greedy algorithm based on the global shortest path point distance;
greedy algorithm based on unmanned aerial vehicle position starting: recording the current position of the unmanned aerial vehicle, searching the nearest non-traversed path point away from the unmanned aerial vehicle, if so, the unmanned aerial vehicle flies to the path point, updating the current position of the unmanned aerial vehicle, and continuing searching; if not, outputting the flight path of the unmanned aerial vehicle, and ending;
greedy algorithm based on backtracking of end point to unmanned aerial vehicle position: recording the backtracking position of the unmanned aerial vehicle, searching the nearest non-traversed path point away from the unmanned aerial vehicle, if so, flying the unmanned aerial vehicle to the path point, updating the backtracking position of the unmanned aerial vehicle, and continuing searching; if not, outputting the flight path of the unmanned aerial vehicle, and ending;
greedy algorithm based on global shortest path point distance: searching edges among path points contained in the current solution space, selecting the edge with the minimum Euclidean distance as an element in the traversal path of the unmanned aerial vehicle, updating the current solution space, and stopping searching when the solution space is an empty set.
5. The unmanned aerial vehicle patrol route planning method for national parks and natural conservation sites according to claim 2, characterized in that: in step 3.5, in the iterative process, branching is carried out by a depth-first or breadth-first search method;
the depth-first search method comprises the following steps: comparing all the delimited branch nodes, selecting the branch node with the minimum lower bound for branching, and if all the branch nodes corresponding to all the flight paths in the current state of the unmanned aerial vehicle are pruned or are not selected as the branched branch nodes in the planned unmanned aerial vehicle path, finishing the search;
breadth-first search method: and branching all newly generated branch nodes, and sequentially branching from small to large according to the size of the lower bound of the branch nodes.
6. The unmanned aerial vehicle patrol route planning method for national parks and natural conservation sites according to claim 2, characterized in that: in step 3.5, when there is no branch node that can continue branching, or best sol When the objective function value of (1) is Lb, the search of the solution space is completed, and best is output sol As a result of the MIP solution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211112515.1A CN115185303B (en) | 2022-09-14 | 2022-09-14 | Unmanned aerial vehicle patrol path planning method for national parks and natural protected areas |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211112515.1A CN115185303B (en) | 2022-09-14 | 2022-09-14 | Unmanned aerial vehicle patrol path planning method for national parks and natural protected areas |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115185303A CN115185303A (en) | 2022-10-14 |
| CN115185303B true CN115185303B (en) | 2023-03-24 |
Family
ID=83524467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211112515.1A Active CN115185303B (en) | 2022-09-14 | 2022-09-14 | Unmanned aerial vehicle patrol path planning method for national parks and natural protected areas |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115185303B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115574826B (en) * | 2022-12-08 | 2023-04-07 | 南开大学 | National park unmanned aerial vehicle patrol path optimization method based on reinforcement learning |
| CN116149375B (en) * | 2023-04-21 | 2023-07-07 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle search planning method and device for online decision, electronic equipment and medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108001684A (en) * | 2017-11-30 | 2018-05-08 | 上海拓攻机器人有限公司 | Unmanned plane, cloud server, wireless charging system and method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106813666B (en) * | 2017-02-13 | 2019-10-18 | 中国人民解放军国防科学技术大学 | The double-deck path construction method and system of vehicle loading unmanned plane |
| CN110949683A (en) * | 2019-12-11 | 2020-04-03 | 云南电网有限责任公司保山供电局 | Method for carrying out uninterrupted inspection on power transformation equipment by using unmanned aerial vehicle |
| CN113487264B (en) * | 2021-07-20 | 2022-09-02 | 中南大学 | Logistics distribution method and system based on heterogeneous multi-unmanned aerial vehicles |
| CN114139392A (en) * | 2021-12-03 | 2022-03-04 | 上海发网供应链管理有限公司 | Vehicle path problem method and system based on self-adaptive large-scale field search algorithm |
| CN114611616B (en) * | 2022-03-16 | 2023-02-07 | 吕少岚 | Unmanned aerial vehicle intelligent fault detection method and system based on integrated isolated forest |
| CN115014362B (en) * | 2022-08-09 | 2022-11-15 | 之江实验室 | Cattle-ploughing type full-coverage path planning method and device based on synthesis unit |
-
2022
- 2022-09-14 CN CN202211112515.1A patent/CN115185303B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108001684A (en) * | 2017-11-30 | 2018-05-08 | 上海拓攻机器人有限公司 | Unmanned plane, cloud server, wireless charging system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115185303A (en) | 2022-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115185303B (en) | Unmanned aerial vehicle patrol path planning method for national parks and natural protected areas | |
| CN110428111B (en) | UAV/UGV (unmanned aerial vehicle/user generated Union vector) cooperative long-time multitask operation trajectory planning method | |
| CN113342046B (en) | Power transmission line unmanned aerial vehicle routing inspection path optimization method based on ant colony algorithm | |
| CN111256702B (en) | Unmanned aerial vehicle autonomous inspection method for inspection of power tower | |
| CN103941744B (en) | Method for determining flight path | |
| CN110244750A (en) | A kind of unmanned plane makes an inspection tour paths planning method and device | |
| CN110413003A (en) | Inspection method, device, equipment and the computer readable storage medium of transmission line of electricity | |
| CN104596516A (en) | Unmanned aerial vehicle coverage flight path planning based on dynamic newly-added adjacent area | |
| CN106774421A (en) | A kind of unmanned plane Trajectory Planning System | |
| CN110597286B (en) | Method for realizing unmanned aerial vehicle autonomous inspection of power transmission line by using smart hangar | |
| CN105045274A (en) | Intelligent tower connected graph construction method for planning inspection route of unmanned aerial vehicle (UAV) | |
| CN109506654A (en) | Low latitude Route planner and device, aircraft | |
| CN113406968B (en) | Unmanned aerial vehicle autonomous take-off and landing cruising method based on digital twin | |
| CN109992923A (en) | A kind of transmission line of electricity paths planning method stage by stage based on variable resolution cost surface | |
| CN110187718B (en) | Urban Logistics System and method based on Scrapy frame and quadrotor | |
| CN112506216B (en) | Flight path planning method and device for unmanned aerial vehicle | |
| CN117032311A (en) | Automatic planning method, device, equipment and medium for inspection task of unmanned aerial vehicle of power transmission line | |
| CN115574826B (en) | National park unmanned aerial vehicle patrol path optimization method based on reinforcement learning | |
| Wang et al. | Coverage path planning design of mapping UAVs based on particle swarm optimization algorithm | |
| CN112382134A (en) | Method and device for generating flight path, storage medium and electronic equipment | |
| Huang et al. | Energy-efficient UAV flight planning for a general poi-visiting problem with a practical energy model | |
| Deng et al. | Heterogeneous vehicles routing for water canal damage assessment | |
| CN116820137B (en) | Unmanned aerial vehicle power distribution network routing inspection route generation method | |
| CN116938984B (en) | Pipeline inspection method based on unmanned aerial vehicle and automatic hangar | |
| CN115686070B (en) | Autonomous line patrol path planning method for unmanned aerial vehicle of power distribution/transmission line |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |