CN111811529B - Multi-region vehicle-machine cooperative reconnaissance path planning method and system - Google Patents
Multi-region vehicle-machine cooperative reconnaissance path planning method and system Download PDFInfo
- Publication number
- CN111811529B CN111811529B CN202010544496.4A CN202010544496A CN111811529B CN 111811529 B CN111811529 B CN 111811529B CN 202010544496 A CN202010544496 A CN 202010544496A CN 111811529 B CN111811529 B CN 111811529B
- Authority
- CN
- China
- Prior art keywords
- reconnaissance
- unmanned aerial
- aerial vehicle
- path
- vehicle
- 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
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The embodiment of the invention provides a multi-region vehicle-machine cooperative reconnaissance path planning method and a multi-region vehicle-machine cooperative reconnaissance path planning system, wherein the method comprises the following steps: determining candidate scanning paths of the unmanned aerial vehicle according to the geometric features of the reconnaissance area; determining a driving path of an automobile and a flying point and a recovery point of the unmanned aerial vehicle in each area based on a saving algorithm on the basis of the candidate scanning path of the unmanned aerial vehicle; and improving the determined driving path of the automobile and the flying point and the recovery point of the unmanned aerial vehicle in each area by adopting a local search algorithm, and determining a vehicle-machine cooperative reconnaissance path. According to the technical scheme, the automobile serves as a mobile platform of the unmanned aerial vehicle, and the unmanned aerial vehicle is carried to complete scanning reconnaissance tasks of a plurality of areas.
Description
Technical Field
The invention relates to a multi-region vehicle-machine cooperative reconnaissance path planning method and a multi-region vehicle-machine cooperative reconnaissance path planning system.
Background
In modern war, unmanned aircraft has the advantages of low cost, strong viability, no personnel loss risk, good maneuverability and the like, is widely used for executing boring, severe and dangerous combat missions, and has become an important tool for battlefield reconnaissance of countries in the world.
Unmanned aerial vehicle battlefield reconnaissance is an activity of acquiring battlefield information by using an unmanned aerial vehicle, wherein path planning is a key supporting technology for the unmanned aerial vehicle to execute reconnaissance tasks. In the current unmanned aerial vehicle regional coverage research, how to cover an area is mostly researched by an unmanned aerial vehicle, and the coverage scanning of the whole area is completed with the lowest cost possible by planning the flight path of the unmanned aerial vehicle. Many times, need scan reconnaissance to a plurality of battlefield regions, when a plurality of regions scatter in the different positions in battlefield on a large scale, unmanned aerial vehicle duration hangs down and becomes its key constraint factor who accomplishes the task.
In order to enlarge the range of the small unmanned aerial vehicle for executing the reconnaissance mission so as to complete the multi-region coverage reconnaissance mission, an automobile is introduced to serve as a mobile platform of the unmanned aerial vehicle, the unmanned aerial vehicle is carried to maneuver on a large scale on a battlefield, and a vehicle-machine cooperative battlefield reconnaissance system is constructed. The automobile is used as an unmanned aerial vehicle control and guarantee platform, carries the unmanned aerial vehicle to maneuver from one investigation region to another investigation region, and charges or changes the battery for the unmanned aerial vehicle in the maneuvering process. When the automobile carrying the unmanned aerial vehicle reaches a position near a certain target reconnaissance area, the unmanned aerial vehicle takes off from the automobile, flies to the sky of the reconnaissance area, finishes covering reconnaissance of the area and returns to the automobile. The combination of the automobile and the unmanned aerial vehicle can effectively enlarge the task range of the small unmanned aerial vehicle and improve the efficiency of battlefield multi-region reconnaissance. Automotive and drone collaboration systems have significant advantages in performing tasks in a variety of military and civilian areas.
The current research on vehicle-machine collaborative path planning mainly focuses on the access sequence and flight path of the unmanned aerial vehicle to the point target, and related research on multi-area coverage reconnaissance path planning does not exist. The path planning of the vehicle-machine cooperation multi-region reconnaissance faces more new research challenges. The problem is that there are two levels of paths where the flight path of the unmanned aerial vehicle and the travel path of the vehicle in the ground road network are connected to each other at different nodes. Due to differences between the vehicle and the unmanned aerial vehicle in terms of speed, endurance time and driving mode, the mutual influence of the two paths needs to be considered in the planning process. The interaction of the double-layer path makes the solution space of the problem more complex and the solution difficulty greater than that of the traditional path problem.
Disclosure of Invention
The embodiment of the invention provides a multi-region vehicle-machine cooperative reconnaissance path planning method and a multi-region vehicle-machine cooperative reconnaissance path planning system, wherein an automobile is used as a mobile platform of an unmanned aerial vehicle and carries the unmanned aerial vehicle to complete scanning reconnaissance tasks of a plurality of regions.
In order to achieve the above object, an embodiment of the present invention provides a multi-zone car machine cooperative reconnaissance path planning method, where the method includes:
determining candidate scanning paths of the unmanned aerial vehicle according to the geometric features of the reconnaissance area;
determining a driving path of an automobile and a flying point and a recovery point of the unmanned aerial vehicle in each area based on a saving algorithm on the basis of the candidate scanning path of the unmanned aerial vehicle;
and improving the determined driving path of the automobile and the flying point and the recovery point of the unmanned aerial vehicle in each area by adopting a local search algorithm, and determining a vehicle-machine cooperative reconnaissance path.
In another aspect, an embodiment of the present invention provides a multi-region car-machine cooperative reconnaissance path planning system, where the system includes:
a scan path determination unit: the unmanned aerial vehicle scanning system is used for determining candidate scanning paths of the unmanned aerial vehicle according to the geometric features of the reconnaissance area;
initial car machine path unit: the system is used for determining the driving path of the automobile and the flying and recovery points of the unmanned aerial vehicle in each area based on an economizing algorithm on the basis of the candidate scanning path of the unmanned aerial vehicle;
the vehicle-machine cooperative reconnaissance path determining unit: the method is used for improving the determined driving path of the automobile and the flying point and the recovery point of the unmanned aerial vehicle in each area by adopting a local search algorithm, and determining the vehicle-machine cooperative reconnaissance path.
The technical scheme has the following beneficial effects: this technical scheme is directed against the application of small-size unmanned aerial vehicle in the regional reconnaissance of battlefield, has proposed a car machine and has accomplished multizone in coordination and cover the new mode of reconnaissance task, and the car acts as unmanned aerial vehicle's moving platform, carries the scanning reconnaissance task that unmanned aerial vehicle accomplished a plurality of regions.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is an exemplary diagram of a path for a car-mounted device to cooperatively scout three areas according to an embodiment of the present invention;
fig. 2 is a flowchart of a multi-zone vehicle-machine cooperative scout path planning method according to an embodiment of the present invention;
FIG. 3 is a schematic view of the scanning path in the spiral scan mode and the mowing scan mode in an embodiment of the present invention;
FIGS. 4a-4b are schematic diagrams of a concave polygon decomposition and a post-decomposition path generation process in an embodiment of the invention;
fig. 5 is a schematic structural diagram of a multi-zone vehicle-machine cooperative reconnaissance path planning system according to an embodiment of the present disclosure;
FIG. 6 is a survey area and road network distribution map in the test case of the present invention;
fig. 7 is a schematic diagram of the car-machine cooperative detection path in the test case of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the process of cooperatively finishing the coverage scout tasks of a plurality of areas by the vehicle-mounted machine, the information such as the positions and the shapes of the road network and the scout areas are known. The automobile is used as a mobile carrying platform of the small unmanned aerial vehicle, can charge and replace a battery for the unmanned aerial vehicle in the driving process, and is also an instruction control center of the unmanned aerial vehicle. The duration of the car is enough to carry unmanned aerial vehicle and accomplishes whole reconnaissance task, but unmanned aerial vehicle's duration is limited, can accomplish the coverage reconnaissance of an area, when reconnaissance different regions, need charge or change the battery. In the cooperative multi-area coverage reconnaissance process of the vehicle machine, a small unmanned aerial vehicle is carried by one vehicle from a base, when the vehicle runs to a position near a region needing reconnaissance, the unmanned aerial vehicle is released, and the unmanned aerial vehicle flies above the reconnaissance region to perform full coverage scanning and collect information; after the unmanned aerial vehicle finishes coverage scanning of the target area, returning to the automobile, driving the automobile carrying the unmanned aerial vehicle to the next reconnaissance area, and finishing charging or battery replacement work of the unmanned aerial vehicle in the driving process; the vehicle carrying the unmanned aerial vehicle maneuvers on the battlefield, and returns to the base after reconnaissance of all target areas is completed. The car can only be in some specific points (being called interim stop) near the reconnaissance area and fly and retrieve unmanned aerial vehicle, and after flying unmanned aerial vehicle, the car can wait and retrieve unmanned aerial vehicle in situ, also can go to other interim stop and retrieve unmanned aerial vehicle.
Fig. 1 shows an example of the car machine cooperatively detecting three areas. In the cooperative reconnaissance process of the vehicle-mounted machine, the vehicle can only run on a ground road network, and the path planning for visiting all reconnaissance areas belongs to the typical problem of travelers; unmanned aerial vehicle flies to the reconnaissance region overhead from the car, carries out the scanning of covering in succession to the reconnaissance region, belongs to typical unmanned aerial vehicle flight path planning problem. Meanwhile, the path of the automobile needs to be closely matched with the path of the unmanned aerial vehicle, and the reconnaissance of all regions is rapidly completed under the condition that the endurance constraint condition of the unmanned aerial vehicle is met. How to optimize the paths of the vehicle and the unmanned aerial vehicle to complete the coverage of all areas in the shortest time on the premise of not exceeding the maximum cruising ability of the unmanned aerial vehicle is more complex than the simple solution of a traveler problem and an unmanned aerial vehicle track planning problem, and the interaction influence of the two paths needs to be considered.
For ease of model description, table 1 gives all the symbols and their meanings applied in the modeling process.
Table 1: symbols and their meanings
The mathematical programming model is as follows:
Min
s.t.
the objective function (1) minimizes the total time for completing the reconnaissance of all areas, wherein the first part is the total travel time for the vehicle carrying the unmanned aerial vehicle to transfer between all coverage areas and the base station, and the second part is the total flight time for the vehicle-mounted unmanned aerial vehicle to perform coverage scanning in all reconnaissance areas. In order to reduce the time of the first part, one of the criteria for selecting stops around different scout areas is to select stops with a small Floyd distance between each other. In order to reduce the time of the second part, on one hand, stop points with small Floyd distance between each other are selected in the same area; on the other hand, a suitable temporary stop point is selected to make the total flight distance of the drone shorter.
And the constraint condition (2) ensures that the vehicle-mounted unmanned aerial vehicle is required to start from the base station and return to the same base station after all coverage tasks are completed. The constraint (3) ensures that the out-degree of each temporary stop point is equal to the in-degree, thereby ensuring the connectivity of the vehicle travel route. The constraints (4) ensure that the vehicle enters each surveillance zone once and leaves the zone once, i.e. each surveillance zone can only be visited once. The constraint (5) ensures that the drone can only take off at the temporary stop accessed by the vehicle, while the constraint (6) ensures that the drone can only land at the temporary stop accessed by the vehicle. The constraints (7) ensure that the drone can only take off and land once per reconnaissance area. The constraints (8) ensure the connectivity of the flight path of the drone in each reconnaissance area and, together with the constraints (7), ensure that only one full coverage scan is performed in each reconnaissance area. The constraints (9) ensure that the flight time of the drone when scanning each reconnaissance area does not exceed its maximum duration. The constraints (10) and (11) define the value range of the variable 0-1.
A three-stage heuristic algorithm is provided for rapidly solving the problem of vehicle-machine cooperative multi-region coverage scout path planning. The first stage is to analyze the geometric characteristics of a reconnaissance area and calculate the coverage scanning path of the unmanned aerial vehicle; the second stage is to plan the driving path of the automobile and the flying and recovering points of the unmanned aerial vehicle in each area by using the idea of saving algorithm for reference on the basis of the candidate scanning path of the unmanned aerial vehicle; and in the third stage, improving the feasible solution constructed in the second stage by adopting a local search algorithm to obtain the optimal solution or the approximate optimal solution of the problem.
As the basic input of the three-stage heuristic algorithm, the Floyd distance between any two points needs to be calculated firstly. Order toIndicating the Floyd distance from point i to point j, as calculated by the Floyd algorithm. The Floyd algorithm (also called interpolation method) is an algorithm that uses the idea of dynamic programming to find the shortest path between points in a given weighted graph, similar to the Dijkstra's algorithm. The main process of the Floyd algorithm is as follows.
As shown in fig. 1, the present invention is a flowchart of a multi-zone car-machine cooperative reconnaissance path planning method, where the method includes:
s101: determining candidate scanning paths of the unmanned aerial vehicle according to the geometric features of the reconnaissance area;
preferably, the determining the candidate scanning path of the drone according to the geometric features of the reconnaissance area includes:
according to the geometric shape of the reconnaissance area, if the roundness of the geometric shape of the reconnaissance area is larger than a set threshold value, determining that the scanning mode of the reconnaissance of the unmanned aerial vehicle is a spiral scanning mode;
if the roundness of the geometric shape of the reconnaissance area is not larger than a set threshold value, determining that the scanning mode of the reconnaissance of the unmanned aerial vehicle is a mowing type scanning mode;
and determining candidate scanning paths of the unmanned aerial vehicle and an initial flying point and a final recovery point of the unmanned aerial vehicle according to the determined scanning mode.
Preferably, if the scanning mode of the unmanned aerial vehicle reconnaissance is a mowing type scanning mode, the concavity and the convexity of the geometric shape of the reconnaissance area are judged, and if the geometric shape of the reconnaissance area is a concave polygon, the reconnaissance area is decomposed into a plurality of convex polygons;
and determining candidate scanning paths of the unmanned aerial vehicle and initial flying points and final recovery points of the unmanned aerial vehicle in a mowing type scanning mode according to the decomposed convex polygons.
When the unmanned aerial vehicle carries out coverage scanning reconnaissance on an area, firstly, the shape of the reconnaissance area needs to be analyzed, and a proper scanning mode, such as mowing type scanning or spiral type scanning, is selected for the unmanned aerial vehicle; if grass cutting type scanning is selected, the concavity and the convexity of the detection area need to be further checked, and when the area is a concave polygon, the area needs to be decomposed into a plurality of convex polygon subregions; and finally, calculating the scanning flight path of the coverage area according to the relevant performance parameters of the unmanned aerial vehicle.
When using unmanned aerial vehicle to an area cover the scanning, there are mainly two kinds of scanning mode, mowing formula scanning mode and spiral scanning mode promptly. The flight path of the drone in both scanning modes is given in figure 3. In fig. 3, a polygon surrounded by a rectangular frame represents a reconnaissance mission area, dots represent a start point and an end point of a scanning path, a dashed-line trajectory represents a flight path of the drone, and an arrow represents a flight direction of the drone. The two scanning modes are specifically defined as follows.
Helical scan mode: the drone starts from the center of the reconnaissance area and then scans gradually outward with a constant helical pitch until the entire area is covered. The spiral may also be scanned inwards, starting from the outermost.
Mowing scan mode: the drone scans at equal intervals starting from the edge of the reconnaissance area in a parallel track reciprocating fashion until the complete area is covered.
Most of the current research adopts mowing type scanning modes [20, 21], and a few of the current research adopts spiral type scanning modes, and the selection optimization of a plurality of scanning modes is not researched. In practice, the total length of the scanning path may vary greatly when different scanning modes are used for the same region. For example, in fig. 2, the flight path generated by the helical scan pattern is significantly longer than the flight path generated using the grass cutting scan pattern. However, as the surveillance area approaches a circle, the spiral scan may work better than the mowing scan. Thus, different scan patterns may be selected depending on how close the coverage area is to the circle.
The roundness of the polygon is defined as follows:
where S is the area of the scout region and L is its perimeter. If the region is closer to a circle, its roundness C is closer to 1.
In order to analyze and compare the scanning efficiency of the two typical scanning modes for the polygon areas with different circularities, table 2 shows the scanning time of several typical polygons respectively adopting the two scanning modes. All polygons in table 2 have equal areas, taking 84 square units as a value, the scanning width of the drone is set to 2 units, and the speed is 1 unit. As can be seen from table 2, when the roundness of the polygon is small, the scan time of the mowing scan mode is significantly smaller than that of the spiral scan mode. As the circularity of the polygon becomes larger, the difference between them becomes smaller. When the polygon is a regular pentagon (C ═ 0.86), the scan times for the two scan modes are substantially the same. As the roundness of the polygon continues to increase, the time of the helical scan mode becomes shorter than the time of the mowing scan mode. Thus, the following approximate law can be summarized by experimental observations: when the roundness of the reconnaissance area is less than 0.86, the mowing type scanning mode is better; when the roundness is greater than 0.86, the helical scan mode is preferred.
Table 2: scanning time using two scanning modes for a typical polygon
2.1.2 concave Polygon determination and decomposition
When the spiral scanning mode is adopted, the influence of the concave-convex of the polygon on the scanning time is small. However, when the grass cutting type scanning mode is adopted, the influence of the unevenness of the polygon is large. The scanning path generated by using the mowing type scanning mode needs to be planned on the premise that the reconnaissance area is a convex polygon. When the scout region is a concave polygon, the concave polygon must be decomposed into a series of convex polygon subregions.
(1) Judgment of polygonal unevenness
The cross product of the vectors can be used to determine the concavity and convexity of a scout region. The determination principle is as follows: the vertexes with the same turning direction are convex points, and each vertex of the convex polygon is a convex point; the vertices with different turns are pits, and if there is more than one pit in the polygon, it is always a concave polygon. Suppose that polygon P has n vertices (v)1,v2,...,vn) The roughness of P is determined by whether P has pits. V. theiIs a random vertex of P, vi-1And vi+1Is v isiTwo adjacent vertices of (a).
Vertex viIs determined by the cross product of the vector Q.
When all vertices of P are convex points, the polygon is a convex polygon, otherwise P is a concave polygon.
(2) Decomposition of concave polygons
The scan path generated using the mowing scan pattern is commonly referred to as a Boustrophedon path. Decomposing a concave polygon into a series of convex polygon subregions, and then planning a Boustrophenon path for each convex polygon is called Boustrophenon decomposition (BCD) [22 ]. Li et al propose an accurate BCD method based on trapezoidal decomposition with an algorithm complexity of O (n). The BCD method is extended to an external cell decomposition method using convex hulls of concave polygons, effectively reducing the number of decomposed convex polygons. A BCD method based on trapezoidal decomposition is designed. Because the effect of decomposing concave polygon along different angles is different, in order to reduce the number of the convex polygons of decomposition and the number of turns of unmanned aerial vehicle, decompose concave polygon along the direction parallel with concave polygon major axis.
For each edge of the convex polygon, the distance of other vertices not belonging to the edge is calculated. The maximum of these distances is labeled as the span of the edge. And comparing the spans of all the edges, wherein the edge corresponding to the minimum span is called the long axis of the convex polygon. In order to find the long axis of the concave polygon, a convex hull of the concave polygon is first generated using a convex hull generation algorithm. A convex hull is the simplest convex polygon containing all the vertices of a concave polygon. The algorithm is summarized as follows.
(1) Find the poles in all vertices and remove all points that fall inside the polygon formed by the poles, dividing the remaining points into 4 regions.
(2) For regions 1 and 2, the points therein are sorted in ascending order, and for regions 3 and 4, they are sorted in descending order.
(3) For each region, a convex path is found from one pole to the other.
Then, the long axis of the convex hull is regarded as the long axis of the concave polygon. After decomposing the concave polygon trapezoid into a series of convex polygons in a direction parallel to the long axis, a Boustrophedon path is generated for each convex polygon by using a mowing-type scanning pattern.
Fig. 4 shows an exploded example of a concave polygon. The graph surrounded by the solid line in fig. 4(a) is a concave polygon to be decomposed, which becomes a convex polygon after adding the broken line, wherein the blue side represents the long axis of the convex polygon, and is also the long axis of the concave polygon. Fig. 4(b) shows a trapezoidal decomposition of a concave polygon along a direction parallel to its long axis, and fig. 4(c) shows a process of merging a series of convex polygons after the trapezoidal decomposition. Two adjacent convex polygons can be merged when one side of them coincides with each other and the long axes of them are parallel to each other. The process can effectively reduce the number of convex polygons and avoid unnecessary transfer of the unmanned aerial vehicle between different convex polygons. Fig. 4(d) shows the Boustrophedon path generated using the mowing scan mode.
Based on the unmanned aerial vehicle scanning mode selection and the polygonal region segmentation method, a flight path planning algorithm for the unmanned aerial vehicle to carry out coverage scanning on the reconnaissance region is designed, and the overall flow is shown as algorithm 2. The perimeter and area of the reconnaissance area are first calculated (line 1) and then the circularity of the reconnaissance area is calculated (line 2) given the geometric information of the reconnaissance area, the positional information of the potential temporary stopping points, and the flight speed of the drone. If the roundness of the region is greater than 0.86, then a spiral scan pattern is used and the scan path (line 4) and the start and end points of the path (line 5) are obtained. The length of the scan path is calculated in line 6. If the roundness is less than 0.86, a mowing scan mode is employed. In this case, the area is first inspected for unevenness (line 9). If the region is a concave polygon (line 10), it is decomposed into a series of convex polygons using the BCD method (line 11) of the above design, and then a Boustrophenon path is planned for the scout region. Starting in a direction parallel to the long axis, there are two scan paths (line 13) corresponding to two pairs of start and end points (line 14), respectively. The lengths of the two paths are calculated (lines 15-16).
S102: determining a driving path of an automobile and a flying point and a recovery point of the unmanned aerial vehicle in each area based on a saving algorithm on the basis of the candidate scanning path of the unmanned aerial vehicle;
preferably, on the basis of the candidate scanning path of the unmanned aerial vehicle, based on an economic algorithm, determining a driving path of the vehicle and a flying point and a recovery point of the unmanned aerial vehicle in each area includes:
by optimizing the sequence of visiting the reconnaissance areas by the automobile and selecting the temporary stop point near each reconnaissance area, on one hand, the flight time of the unmanned aerial vehicle is shorter by matching with the scanning path of the unmanned aerial vehicle, and on the other hand, the running distance of the automobile is optimized so that the running time of the automobile in the whole task process is shorter, thereby determining the running path of the automobile and the flying and recovering points of the unmanned aerial vehicle in each area.
The vehicle path planning is to optimize the sequence of the automobile visiting the reconnaissance areas and select a temporary stop point near each reconnaissance area, so that the flight time of the unmanned aerial vehicle is shorter by matching with the scanning path of the unmanned aerial vehicle, and the running time of the automobile in the whole task process is shorter by optimizing the running distance of the automobile. Combining the two aspects, based on the idea of saving algorithm, the path planning algorithm of the vehicle is designed, as shown in algorithm 3. First, the Floyd distance matrix dis (row 1) is calculated from the position information of all the points, and then a scanning path (row 2) is selected for each area, resulting in the start and end points (row 3) of the scanning path. Two temporary stopping points are randomly selected near each reconnaissance area, and then the distance from the unmanned aerial vehicle to take off from one temporary stopping point to the start of the scanning path and the distance from the end of the scanning path to the other temporary stopping point are calculated, wherein Dis is the sum of the two distances (lines 4-10). In each scout zone, two temporary stopping points corresponding to the minimum distance Dis are found as the selected stopping points (line 12) of the zone to form a set of stopping points, oral (line 14), and then a saving matrix is calculated (lines 15-19) and arranged in descending order (line 20). Starting from the maximum, the corresponding two reconnaissance areas are connected until all reconnaissance areas are included, so that a feasible solution for the route planning of the cars and drones is obtained (line 21).
S103: and improving the determined driving path of the automobile and the flying point and the recovery point of the unmanned aerial vehicle in each area by adopting a local search algorithm, and determining a vehicle-machine cooperative reconnaissance path.
Preferably, the local search algorithm includes: determining a vehicle-machine cooperative reconnaissance path for improving the running distance of the vehicle by randomly exchanging the access sequences of the two reconnaissance areas; randomly exchanging temporary stopping points of the unmanned aerial vehicle for flying and recovering in the vicinity of a certain reconnaissance area, and determining a vehicle-machine cooperative reconnaissance path for reducing the flight distance of the unmanned aerial vehicle and/or the driving distance of the vehicle;
adopt local search algorithm to improve the driving route of the car of confirming and unmanned aerial vehicle in the point of flying away and the recovery point in every region, confirm the car machine reconnaissance route in coordination, include:
and randomly determining the vehicle-machine cooperative reconnaissance path by adopting two modes in the local search algorithm until the continuous setting times are not improved, and taking the determined optimal vehicle-machine cooperative reconnaissance path as a final vehicle-machine cooperative reconnaissance path.
A better scheme of vehicle-machine collaborative multi-region reconnaissance can be obtained through the unmanned aerial vehicle and vehicle path planning algorithm in the two previous stages, but the optimal solution of the problem may not be obtained in many times, and the improved space is provided. Therefore, the local search algorithms for the vehicle path and the drone path are further designed to improve the quality of the solution. The local search is mainly carried out by adopting two types of random operators, the first type is to randomly exchange the access sequence of two reconnaissance areas and search a feasible solution for improving the driving distance of the automobile; the second type is to randomly exchange temporary stopping points of the automobile for flying and recovering the unmanned aerial vehicle near a certain reconnaissance area and search feasible solutions for reducing the flight distance of the unmanned aerial vehicle and/or the automobile driving distance. And randomly calling the two operators to search different feasible solutions until Nmax times of continuous improvement do not exist, and stopping searching to obtain a final scheme.
As shown in fig. 5, which is a schematic structural diagram of a multi-zone vehicle-machine cooperative reconnaissance path planning system according to an embodiment of the present invention, the system includes:
the scanning path determining unit 21: the unmanned aerial vehicle scanning system is used for determining candidate scanning paths of the unmanned aerial vehicle according to the geometric features of the reconnaissance area;
initial car-machine path unit 22: the system is used for determining the driving path of the automobile and the flying and recovery points of the unmanned aerial vehicle in each area based on an economizing algorithm on the basis of the candidate scanning path of the unmanned aerial vehicle;
the in-vehicle cooperative reconnaissance path determination unit 23: the method is used for improving the determined driving path of the automobile and the flying point and the recovery point of the unmanned aerial vehicle in each area by adopting a local search algorithm, and determining the vehicle-machine cooperative reconnaissance path.
Preferably, the scan path determining unit 21 is specifically configured to:
according to the geometric shape of the reconnaissance area, if the roundness of the geometric shape of the reconnaissance area is larger than a set threshold value, determining that the scanning mode of the reconnaissance of the unmanned aerial vehicle is a spiral scanning mode;
if the roundness of the geometric shape of the reconnaissance area is not larger than a set threshold value, determining that the scanning mode of the reconnaissance of the unmanned aerial vehicle is a mowing type scanning mode;
and determining candidate scanning paths of the unmanned aerial vehicle and an initial flying point and a final recovery point of the unmanned aerial vehicle according to the determined scanning mode.
Preferably, the scan path determining unit 21 is further configured to:
if the scanning mode of the unmanned aerial vehicle reconnaissance is a mowing type scanning mode, judging the concavity and convexity of the geometric shape of the reconnaissance area, and if the geometric shape of the reconnaissance area is a concave polygon, decomposing the reconnaissance area into a plurality of convex polygons;
and determining candidate scanning paths of the unmanned aerial vehicle and initial flying points and final recovery points of the unmanned aerial vehicle in a mowing type scanning mode according to the decomposed convex polygons.
Preferably, the initial car machine path unit 22 is specifically configured to:
by optimizing the sequence of visiting the reconnaissance areas by the automobile and selecting the temporary stop point near each reconnaissance area, on one hand, the flight time of the unmanned aerial vehicle is shorter by matching with the scanning path of the unmanned aerial vehicle, and on the other hand, the running distance of the automobile is optimized so that the running time of the automobile in the whole task process is shorter, thereby determining the running path of the automobile and the flying and recovering points of the unmanned aerial vehicle in each area.
Preferably, the local search algorithm includes: determining a vehicle-machine cooperative reconnaissance path for improving the running distance of the vehicle by randomly exchanging the access sequences of the two reconnaissance areas; randomly exchanging temporary stopping points of the unmanned aerial vehicle for flying and recovering in the vicinity of a certain reconnaissance area, and determining a vehicle-machine cooperative reconnaissance path for reducing the flight distance of the unmanned aerial vehicle and/or the driving distance of the vehicle;
the in-vehicle cooperative reconnaissance path determining unit 23 is specifically configured to: and randomly determining the vehicle-machine cooperative reconnaissance path by adopting two modes in the local search algorithm until the continuous setting times are not improved, and taking the determined optimal vehicle-machine cooperative reconnaissance path as a final vehicle-machine cooperative reconnaissance path.
Examples of the applications
An application example of the model and the algorithm is given through a typical calculation example, and the advantage of the vehicle-mounted machine cooperation for multi-region reconnaissance is explained. All the calculation experiments are carried out on Huacheng notebook computers, and the notebook computers use Core i71.8GHz four-Core processors, 16GB memories and Windows 10 operating systems and use Matlab R2018a for algorithm coding.
A 7 x 7 road network is generated on the plane, which divides the plane into 49 square meshes. The side length of each mesh is set to 10 units, 20 meshes are randomly selected from 49 meshes, and an irregular polygon is generated in each selected mesh, as shown in fig. 6. The 20 polygon regions are numbered in order from left to right, bottom to top. A random temporary stop is generated on each side of all polygons, indicated by the blue asterisk and the red squares indicate the base stations. Finally, the road network is connected to the coverage area by line segments. The unmanned aerial vehicle carried by the automobile starts from the base station to carry out coverage reconnaissance on 20 areas, and returns to the base station after the task is completed. And finding the optimal routes of the automobile and the unmanned aerial vehicle to complete scanning and reconnaissance of all areas.
The average speed of the vehicle is set to 0.5 units and the flying speed of the drone is set to 1 unit. The scanning width of the unmanned aerial vehicle is set to be 1 unit, and the maximum duration is set to be 140 unit times. Nmax is set to 200 in the local search algorithm. The circularity of the 20 scout regions was calculated using equation (12) as shown in table 3.
TABLE 3 roundness of 20 scout regions
As can be seen from table 3, the circularity of regions 1, 3, 6, 11 is significantly greater than 0.86, so the helical scan mode is used, and the remaining regions are grass-cutting scan mode. Regions 2, 12, 14, 16, 17, 18 are concave polygons, they are decomposed using the previously designed BCD method based on trapezoidal decomposition, and then a Boustrophedon path is planned for them using the mowing scan mode.
If the unmanned aerial vehicle is adopted to reconnoiter the areas, considering the limitation that the maximum endurance time of the unmanned aerial vehicle and the unmanned aerial vehicle must safely return to the base station and the like, the unmanned aerial vehicle cannot fly to the areas 14, 17, 19 and 20, so that the areas cannot be reconnoitered, the rest areas are all in the reconnaissance range of the unmanned aerial vehicle, but only the areas 1, 2, 3, 5, 8, 9, 11 and 12 can be reconnaissance completed in the primary flight process of the unmanned aerial vehicle, and the rest areas all need the unmanned aerial vehicle to continuously return to the base station for charging and then go to the areas again for reconnaissance to complete the total task. Therefore, for the problem of large-range multi-region reconnaissance, the simple small unmanned aerial vehicle is difficult to complete the reconnaissance task.
If the vehicle-machine cooperative reconnaissance mode is adopted, a feasible solution obtained by calculation through a three-stage heuristic algorithm is shown in fig. 7, wherein the sequence of the vehicle visiting 20 areas is 2-1-3-6-4-7-10-14-20-17-19-13-16-18-15-12-9-5-8-11 unmanned aerial vehicle scanning paths are shown in the figure, and the total time for completing all area scanning reconnaissance is 2379.71. The three-stage heuristic algorithm takes 18 minutes and 32 seconds to solve the path planning scheme for the 20 scout areas. Therefore, the vehicle-machine cooperation mode can efficiently complete reconnaissance tasks which cannot be completed by simply adopting the unmanned aerial vehicle, meanwhile, the problem of complex path planning caused by vehicle-machine cooperation can be effectively solved through the three-stage heuristic algorithm, and the practical action application requirements are met.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. To those skilled in the art; various modifications to these embodiments will be readily apparent, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (6)
1. A multi-region vehicle-machine cooperative reconnaissance path planning method is characterized by comprising the following steps:
determining candidate scanning paths of the unmanned aerial vehicle according to the geometric features of the reconnaissance area;
determining a driving path of an automobile and a flying point and a recovery point of the unmanned aerial vehicle in each area based on a saving algorithm on the basis of the candidate scanning path of the unmanned aerial vehicle;
improving the determined driving path of the automobile and the flying point and the recovery point of the unmanned aerial vehicle in each area by adopting a local search algorithm, and determining a vehicle-machine cooperative reconnaissance path;
wherein, according to the geometric features of the reconnaissance area, determining the candidate scanning path of the unmanned aerial vehicle comprises:
according to the geometric shape of the reconnaissance area, if the roundness of the geometric shape of the reconnaissance area is larger than a set threshold value, determining that the scanning mode of the reconnaissance of the unmanned aerial vehicle is a spiral scanning mode;
if the roundness of the geometric shape of the reconnaissance area is not larger than a set threshold value, determining that the scanning mode of the reconnaissance of the unmanned aerial vehicle is a mowing type scanning mode;
determining candidate scanning paths of the unmanned aerial vehicle and an initial flying point and a final recovery point of the unmanned aerial vehicle according to the determined scanning mode;
wherein the local search algorithm comprises: determining a vehicle-machine cooperative reconnaissance path for improving the running distance of the vehicle by randomly exchanging the access sequences of the two reconnaissance areas; randomly exchanging temporary stopping points of the unmanned aerial vehicle for flying and recovering in the vicinity of a certain reconnaissance area, and determining a vehicle-machine cooperative reconnaissance path for reducing the flight distance of the unmanned aerial vehicle and/or the driving distance of the vehicle;
adopt local search algorithm to improve the driving route of the car of confirming and unmanned aerial vehicle in the point of flying away and the recovery point in every region, confirm the car machine reconnaissance route in coordination, include:
and randomly determining the vehicle-machine cooperative reconnaissance path by adopting two modes in the local search algorithm until the continuous setting times are not improved, and taking the determined optimal vehicle-machine cooperative reconnaissance path as a final vehicle-machine cooperative reconnaissance path.
2. The multi-region vehicle-machine cooperative scout path planning method according to claim 1, wherein if the scanning mode of the unmanned aerial vehicle scout is a mowing type scanning mode, the concavity and convexity of the geometric shape of the scout region are determined, and if the geometric shape of the scout region is a concave polygon, the scout region is decomposed into a plurality of convex polygons;
and determining candidate scanning paths of the unmanned aerial vehicle and initial flying points and final recovery points of the unmanned aerial vehicle in a mowing type scanning mode according to the decomposed convex polygons.
3. The multi-region vehicle-machine cooperative reconnaissance path planning method according to claim 2, wherein the determining of the driving path of the vehicle and the flying point and the recovery point of the unmanned aerial vehicle in each region based on the saving algorithm based on the candidate scanning path of the unmanned aerial vehicle comprises:
by optimizing the sequence of visiting the reconnaissance areas by the automobile and selecting the temporary stop point near each reconnaissance area, on one hand, the flight time of the unmanned aerial vehicle is shorter by matching with the scanning path of the unmanned aerial vehicle, and on the other hand, the running distance of the automobile is optimized so that the running time of the automobile in the whole task process is shorter, thereby determining the running path of the automobile and the flying and recovering points of the unmanned aerial vehicle in each area.
4. The utility model provides a multi-zone car machine reconnaissance path planning system which characterized in that, the system includes:
a scan path determination unit: the unmanned aerial vehicle scanning system is used for determining candidate scanning paths of the unmanned aerial vehicle according to the geometric features of the reconnaissance area;
initial car machine path unit: the system is used for determining the driving path of the automobile and the flying and recovery points of the unmanned aerial vehicle in each area based on an economizing algorithm on the basis of the candidate scanning path of the unmanned aerial vehicle;
the vehicle-machine cooperative reconnaissance path determining unit: the system comprises a local search algorithm, a vehicle-mounted cooperative reconnaissance path determination module, a vehicle-mounted cooperative reconnaissance module and a vehicle-mounted cooperative reconnaissance path determination module, wherein the local search algorithm is used for improving the determined driving path of the vehicle and the flying point and recovery point of the unmanned aerial vehicle in each area, and the vehicle-mounted cooperative reconnaissance path is determined;
wherein the scan path determining unit is specifically configured to:
according to the geometric shape of the reconnaissance area, if the roundness of the geometric shape of the reconnaissance area is larger than a set threshold value, determining that the scanning mode of the reconnaissance of the unmanned aerial vehicle is a spiral scanning mode;
if the roundness of the geometric shape of the reconnaissance area is not larger than a set threshold value, determining that the scanning mode of the reconnaissance of the unmanned aerial vehicle is a mowing type scanning mode;
determining candidate scanning paths of the unmanned aerial vehicle and an initial flying point and a final recovery point of the unmanned aerial vehicle according to the determined scanning mode;
the local search algorithm includes: determining a vehicle-machine cooperative reconnaissance path for improving the running distance of the vehicle by randomly exchanging the access sequences of the two reconnaissance areas; randomly exchanging temporary stopping points of the unmanned aerial vehicle for flying and recovering in the vicinity of a certain reconnaissance area, and determining a vehicle-machine cooperative reconnaissance path for reducing the flight distance of the unmanned aerial vehicle and/or the driving distance of the vehicle;
the vehicle-machine cooperative reconnaissance path determination unit is specifically configured to: and randomly determining the vehicle-machine cooperative reconnaissance path by adopting two modes in the local search algorithm until the continuous setting times are not improved, and taking the determined optimal vehicle-machine cooperative reconnaissance path as a final vehicle-machine cooperative reconnaissance path.
5. The multi-region vehicle-machine cooperative reconnaissance path planning system of claim 4, wherein the scan path determining unit is further configured to:
if the scanning mode of the unmanned aerial vehicle reconnaissance is a mowing type scanning mode, judging the concavity and convexity of the geometric shape of the reconnaissance area, and if the geometric shape of the reconnaissance area is a concave polygon, decomposing the reconnaissance area into a plurality of convex polygons;
and determining candidate scanning paths of the unmanned aerial vehicle and initial flying points and final recovery points of the unmanned aerial vehicle in a mowing type scanning mode according to the decomposed convex polygons.
6. The multi-zone car-in-vehicle cooperative reconnaissance path planning system of claim 5, wherein the initial car-in-vehicle path unit is specifically configured to:
by optimizing the sequence of visiting the reconnaissance areas by the automobile and selecting the temporary stop point near each reconnaissance area, on one hand, the flight time of the unmanned aerial vehicle is shorter by matching with the scanning path of the unmanned aerial vehicle, and on the other hand, the running distance of the automobile is optimized so that the running time of the automobile in the whole task process is shorter, thereby determining the running path of the automobile and the flying and recovering points of the unmanned aerial vehicle in each area.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010544496.4A CN111811529B (en) | 2020-06-15 | 2020-06-15 | Multi-region vehicle-machine cooperative reconnaissance path planning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010544496.4A CN111811529B (en) | 2020-06-15 | 2020-06-15 | Multi-region vehicle-machine cooperative reconnaissance path planning method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111811529A CN111811529A (en) | 2020-10-23 |
CN111811529B true CN111811529B (en) | 2022-02-01 |
Family
ID=72846214
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010544496.4A Active CN111811529B (en) | 2020-06-15 | 2020-06-15 | Multi-region vehicle-machine cooperative reconnaissance path planning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111811529B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112327925B (en) * | 2020-11-24 | 2023-02-28 | 天津市公路工程总公司 | Road maintenance patrol cooperative auxiliary system |
CN112945255B (en) * | 2021-01-29 | 2022-06-21 | 中国人民解放军国防科技大学 | Method and system for planning multi-area coverage path by cooperation of multiple unmanned aerial vehicles carried by automobile |
CN116868142A (en) * | 2021-04-26 | 2023-10-10 | 深圳市大疆创新科技有限公司 | Path planning method, path planning device and medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9104201B1 (en) * | 2012-02-13 | 2015-08-11 | C&P Technologies, Inc. | Method and apparatus for dynamic swarming of airborne drones for a reconfigurable array |
CN108592928A (en) * | 2018-03-08 | 2018-09-28 | 中国人民解放军国防科技大学 | Construction method and device for double-layer path of vehicle-mounted unmanned aerial vehicle |
CN111024080A (en) * | 2019-12-01 | 2020-04-17 | 中国人民解放军军事科学院评估论证研究中心 | Unmanned aerial vehicle group-to-multi-mobile time-sensitive target reconnaissance path planning method |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9494937B2 (en) * | 2014-06-20 | 2016-11-15 | Verizon Telematics Inc. | Method and system for drone deliveries to vehicles in route |
CN104699102B (en) * | 2015-02-06 | 2017-07-18 | 东北大学 | A kind of unmanned plane and intelligent vehicle collaborative navigation and investigation monitoring system and method |
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 |
CN108256553B (en) * | 2017-12-20 | 2020-03-27 | 中国人民解放军国防科技大学 | Construction method and device for double-layer path of vehicle-mounted unmanned aerial vehicle |
CN111121783B (en) * | 2018-12-28 | 2023-09-19 | 中国人民解放军国防科技大学 | Double-layer path planning method and device for vehicle-mounted unmanned aerial vehicle power inspection |
CN110414722B (en) * | 2019-07-08 | 2023-04-07 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle cooperative reconnaissance path planning method based on energy consumption fairness |
CN110852554B (en) * | 2019-09-20 | 2022-03-22 | 合肥工业大学 | Unmanned aerial vehicle task allocation intelligent decision-making method and device under cooperation of vehicle machine |
CN110888456B (en) * | 2019-12-05 | 2023-06-30 | 中国北方车辆研究所 | Unmanned aerial vehicle and unmanned aerial vehicle autonomous collaborative reconnaissance control method |
-
2020
- 2020-06-15 CN CN202010544496.4A patent/CN111811529B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9104201B1 (en) * | 2012-02-13 | 2015-08-11 | C&P Technologies, Inc. | Method and apparatus for dynamic swarming of airborne drones for a reconfigurable array |
CN108592928A (en) * | 2018-03-08 | 2018-09-28 | 中国人民解放军国防科技大学 | Construction method and device for double-layer path of vehicle-mounted unmanned aerial vehicle |
CN111024080A (en) * | 2019-12-01 | 2020-04-17 | 中国人民解放军军事科学院评估论证研究中心 | Unmanned aerial vehicle group-to-multi-mobile time-sensitive target reconnaissance path planning method |
Also Published As
Publication number | Publication date |
---|---|
CN111811529A (en) | 2020-10-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111811529B (en) | Multi-region vehicle-machine cooperative reconnaissance path planning method and system | |
Wu et al. | Cooperative path planning for heterogeneous unmanned vehicles in a search-and-track mission aiming at an underwater target | |
CN112945255B (en) | Method and system for planning multi-area coverage path by cooperation of multiple unmanned aerial vehicles carried by automobile | |
CN108196575B (en) | Unmanned aerial vehicle task allocation and route planning method | |
CN111289005B (en) | Path finding method based on A star optimization algorithm | |
CN106813666B (en) | The double-deck path construction method and system of vehicle loading unmanned plane | |
CN112130587A (en) | Multi-unmanned aerial vehicle cooperative tracking method for maneuvering target | |
CN110097212B (en) | Unmanned ship high-energy-efficiency cooperative area detection method | |
CN102980581A (en) | Irregular-island-based method for planning covered flight route of unmanned aerial vehicle | |
CN114089762B (en) | Water-air amphibious unmanned aircraft path planning method based on reinforcement learning | |
Li et al. | A satisficing conflict resolution approach for multiple UAVs | |
CN112733251B (en) | Collaborative flight path planning method for multiple unmanned aerial vehicles | |
CN112000128B (en) | Unmanned plane cluster task cooperation method and system for rescue and relief work | |
CN113763695A (en) | Dispatching method and system for automatic driving vehicle | |
CN110986951B (en) | Path planning method based on penalty weight, navigation grid and grid map | |
CN113722553A (en) | Hamiltonian path searching method and system based on contour line thinking | |
CN109974708B (en) | Unmanned ship track planning method, terminal equipment and storage medium | |
CN117007067A (en) | River course inspection unmanned aerial vehicle path planning method based on A star algorithm | |
Ahmed et al. | Energy-efficient uavs coverage path planning approach | |
Agarwal et al. | Area coverage with multiple capacity-constrained robots | |
CN116430875A (en) | Unmanned ship and unmanned ship collaborative patrol path planning algorithm for marine pasture unmanned plane | |
CN114578827B (en) | Distributed multi-agent cooperative full-coverage path planning method | |
CN112214037B (en) | Unmanned aerial vehicle remote sensing networking flight path planning method based on field station | |
CN116382322A (en) | Device and method for searching collaborative area based on swarm unmanned plane | |
Zehua | MTSP UAV detection problem based on ant algorithm |
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 |