CN114967757A - Vehicle and multi-unmanned aerial vehicle collaborative path planning method, device, terminal and medium - Google Patents
Vehicle and multi-unmanned aerial vehicle collaborative path planning method, device, terminal and medium Download PDFInfo
- Publication number
- CN114967757A CN114967757A CN202210816082.1A CN202210816082A CN114967757A CN 114967757 A CN114967757 A CN 114967757A CN 202210816082 A CN202210816082 A CN 202210816082A CN 114967757 A CN114967757 A CN 114967757A
- Authority
- CN
- China
- Prior art keywords
- path
- vehicle
- unmanned aerial
- point
- aerial 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 238000005457 optimization Methods 0.000 claims abstract description 27
- 238000013507 mapping Methods 0.000 claims abstract description 26
- 238000005070 sampling Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 8
- 230000002040 relaxant effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000029087 digestion Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 230000000452 restraining effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 14
- 238000005265 energy consumption Methods 0.000 description 4
- 238000011065 in-situ storage Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to a vehicle and multi-unmanned aerial vehicle collaborative path planning method, a device, a terminal and a medium. The method comprises the steps that an unmanned aerial vehicle coverage path is determined according to an area to be searched in a target area set; determining a vehicle planning path according to the mapping points, constructing an unmanned aerial vehicle route set according to the flying points, the coverage path and the landing points, and performing iterative optimization on the unmanned aerial vehicle route set and the vehicle planning path by adopting an iterative relaxation algorithm to obtain the optimal path plan for cooperative coverage reconnaissance of the vehicle and the multiple unmanned aerial vehicles. The method designs the unmanned aerial vehicle airway based on the positions of take-off points and landing points of a real road network, and the unmanned aerial vehicle can take off and land at any node of the real road network, so that the take-off points and the landing points are flexibly selected, and the reconnaissance time is saved; and then, carrying out iterative optimization on the unmanned aerial vehicle route set and the vehicle planned path through an iterative relaxation algorithm, and generating a satisfactory reconnaissance path planning scheme in a short time.
Description
Technical Field
The invention relates to the technical field of information acquisition, in particular to a vehicle and multi-unmanned aerial vehicle collaborative path planning method, device, terminal and medium.
Background
Unmanned aerial vehicle regional reconnaissance is a typical mode of quick perception target area information, and is widely applied to the fields of geographic mapping, disaster investigation, target search, battlefield reconnaissance and the like at present. In practical application, only by quickly sensing and completely acquiring the information of the target area, reliable information support can be provided for commanders. But be limited by the relatively poor cruising ability of unmanned aerial vehicle, still need to rely on ground vehicle to provide support in the face of the reconnaissance demand of multizone, improve the cooperativity of air and ground resource, realize the high-efficient reconnaissance to the target area.
In recent years, most researches are carried out aiming at that an unmanned aerial vehicle independently completes regional coverage reconnaissance tasks, but the situations that a plurality of regions are distributed far and exceed the flight range of the unmanned aerial vehicle are not considered; the vehicle supports unmanned aerial vehicle's multizone cover reconnaissance model simpler, and lacks the research that supports many unmanned aerial vehicles simultaneously.
Disclosure of Invention
Therefore, in order to solve the technical problems, it is necessary to provide a vehicle and multi-drone collaborative path planning method, device, terminal and medium in which a drone can take off and land at any node of a real road network.
A vehicle and multi-drone collaborative path planning method, the method comprising:
acquiring a target area set, and determining a coverage path of the unmanned aerial vehicle according to the relative position of a sub-target area in the target area set;
determining the real road node closest to the sub-target area as the mapping point of the sub-target area; generating a vehicle moving path according to each mapping point; performing initial planning on the vehicle moving path to obtain an initial vehicle path; eliminating the crossed path of the initial vehicle path to obtain a vehicle path;
constructing an unmanned aerial vehicle airway set according to the road nodes in the vehicle path and the unmanned aerial vehicle coverage path;
respectively constructing alternative flying points and alternative landing points for each sub-unmanned aerial vehicle route in the unmanned aerial vehicle route set based on the vehicle route and the unmanned aerial vehicle route set; according to selection indexes in an iterative relaxation algorithm, respectively performing iterative optimization on the alternative flying points and the landing flying point set to obtain new flying points and new landing points of the sub unmanned aerial vehicle airway; and updating the new flying point and the new landing point in the vehicle path to obtain the collaborative optimal planning path of the vehicle and the multiple unmanned aerial vehicles.
In one embodiment, the determining the coverage path of the drone according to the relative positions of the sub-target areas in the set of target areas includes:
planning an unmanned aerial vehicle coverage path according to the number and the positions of the unmanned aerial vehicle air sampling points in the sub-target area, wherein connecting lines of the sampling points form an unmanned aerial vehicle coverage path; constructing a plurality of unmanned aerial vehicle coverage paths according to different coverage modes, and selecting an optimal coverage mode and an optimal coverage path; the sampling point is the central point of unmanned aerial vehicle sampling region, the sampling region is the projection region of unmanned aerial vehicle single sampling subaerial.
In one embodiment, the overlay mode includes: a spiral overlay mode and a reciprocating overlay mode; the coverage path includes a spiral coverage path and a reciprocating coverage path.
In one embodiment, the determining the real road node closest to the sub-target area as the mapping point of the sub-target area includes:
and calculating a centroid coordinate of the sub-target area, and determining the real road node closest to the centroid coordinate as a mapping point of the sub-target area.
In one embodiment, the initial planning of the vehicle moving path is performed to obtain an initial vehicle path; performing cross path elimination on the initial vehicle path to obtain a vehicle path, comprising:
performing initial planning on the vehicle moving path by adopting a greedy algorithm to obtain an initial vehicle path;
and detecting and eliminating the crossed path of the initial vehicle path by using a digestion cross method to obtain the vehicle path.
In one embodiment, the method further comprises the steps of constructing alternative departure points and alternative landing points for each sub-unmanned aerial vehicle route in the unmanned aerial vehicle route set based on the vehicle path and the unmanned aerial vehicle route set; according to selection indexes in an iterative relaxation algorithm, respectively performing iterative optimization on the alternative flying point and the landing flying point set to obtain a new flying point and a new landing point of the sub unmanned aerial vehicle airway, and the method comprises the following steps:
initializing the unmanned aerial vehicle route set, and restraining the same take-off point and landing point in the sub-unmanned aerial vehicle route;
arranging all unmanned aerial vehicles in the unmanned aerial vehicle route set from large to small according to the residual energy, selecting a sub unmanned aerial vehicle route, and constructing alternative departure points and landing departure points of the sub unmanned aerial vehicle route;
selecting one alternative point from the alternative flying starting points as a preset flying starting point, gradually relaxing the distance upper line of the preset flying starting point, calculating according to a selection index in an iterative relaxation algorithm, selecting the preset flying starting point meeting the conditions as a new flying starting point, and replacing the original flying starting point;
selecting one alternative point from the alternative falling points as a preset falling point, gradually relaxing the distance upper line of the preset falling point, calculating according to a selection index in an iterative relaxation algorithm, selecting the preset falling point meeting the conditions as a new falling point, and replacing the original falling point;
and updating the vehicle path according to the new flying start point and the new landing point to obtain the collaborative optimal planning path of the vehicle and the multiple unmanned aerial vehicles.
In one embodiment, the selection index calculation expression is:
C α ＝θC 1,α +(1-θ)C 2,α
where θ is a weight coefficient, C 1,α The shortest distance between the new takeoff point and the last point of the optimal vehicle planning path is represented, the smaller the value is, the closer the new takeoff point is to the last point of the optimal vehicle planning path is represented, and when C is 1,α When the vehicle is 0, the vehicle can pass through one road node less; c 2,α Indicating the increment of the planned path length of the vehicle when the new takeoff point is replaced by the original takeoff point.
A vehicle and multi-drone collaborative path planning apparatus, the apparatus comprising:
the unmanned aerial vehicle coverage path generation module is used for acquiring a target area set and determining a coverage path of the unmanned aerial vehicle according to the relative position of a sub-target area in the target area set;
the vehicle planning path generation module is used for determining a real road node closest to the sub-target area as a mapping point of the sub-target area; generating a vehicle moving path according to each mapping point; performing initial planning on the vehicle moving path to obtain an initial vehicle path; eliminating the crossed path of the initial vehicle path to obtain a vehicle path;
the iterative relaxation optimization module is used for constructing an unmanned aerial vehicle airway set according to the road nodes in the vehicle path and the unmanned aerial vehicle coverage path; respectively constructing alternative flying starting points and alternative landing points for each sub unmanned aerial vehicle route in the unmanned aerial vehicle route set based on the vehicle route and the unmanned aerial vehicle route set; according to selection indexes in an iterative relaxation algorithm, respectively performing iterative optimization on the alternative flying points and the landing flying point set to obtain new flying points and new landing points of the sub unmanned aerial vehicle airway; and updating the new flying point and the new landing point in the vehicle path to obtain the collaborative optimal planning path of the vehicle and the multiple unmanned aerial vehicles.
A terminal device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any of claims 1 to 7.
A terminal readable storage medium, having stored thereon a computer program, characterized in that the computer program, when being executed by a processor, realizes the steps of the method of any one of claims 1 to 7.
According to the vehicle and multi-unmanned aerial vehicle collaborative path planning method, the device, the terminal and the medium, considering that the target area is possibly far away from the passable road, the road network node closest to the sub-target area is taken as the mapping point, the unmanned aerial vehicle airway based on the take-off point and landing point positions of the real road network is designed, the unmanned aerial vehicle can take off and land at any node of the real road network, the take-off point and landing point are flexibly selected, and the reconnaissance time is saved; and then, iterative optimization and updating are carried out on the takeoff point and the landing point of the sub-target area through selection indexes in the iterative relaxation algorithm, a satisfactory reconnaissance path planning scheme can be generated in a short time, and the path planning of the cooperation of the vehicle and the multiple unmanned aerial vehicles is completed.
Drawings
FIG. 1 is a flow diagram illustrating a collaborative path planning for a vehicle and multiple drones;
FIG. 2 is an exemplary diagram of a collaborative path planning for a vehicle and multiple drones;
FIG. 3 is a diagram of drone coverage path constraints in one embodiment;
FIG. 4 is an exemplary diagram of a spiral coverage path based on a take-and-place point in one embodiment;
FIG. 5 is an exemplary diagram of a reciprocating overlay path based on landing points in one embodiment;
FIG. 6 is a diagram illustrating a road network and scene settings of a search area according to an embodiment;
FIG. 7 is a path planning diagram for a vehicle and a drone before iterative optimization in the scenario of FIG. 6;
FIG. 8 is a path planning diagram for the vehicle and the drone after iterative optimization in the scenario of FIG. 6;
fig. 9 is a diagram of energy utilization of the unmanned aerial vehicle before and after iterative optimization in the scenario of fig. 6;
FIG. 10 is a comparison graph of the mutual waiting times of the unmanned aerial vehicle and the vehicle before and after iterative optimization in the scenario of FIG. 6;
FIG. 11 is a diagram illustrating an internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The vehicle and multi-unmanned aerial vehicle collaborative path planning method provided by the invention can be applied to the application environment shown in fig. 2, the vehicle carries the unmanned aerial vehicle to drive along the known ground road from the base station, and the taking-off and landing environment can be provided for the unmanned aerial vehicle at the nodes of the road network. After taking off, the unmanned aerial vehicle autonomously goes to a target area to execute a covering task, and the flight path of the unmanned aerial vehicle is not restrained by a road network any more. The unmanned aerial vehicle drives to the edge of the target area from the flying point, and carries out coverage scanning on the unmanned aerial vehicle along the sampling path, and the vehicle can wait in situ during the period, and can also continue to drive along the road, and fly off or take back other unmanned aerial vehicles in due time. And the unmanned aerial vehicle is converged with the vehicle to charge or replace the battery after finishing the coverage scanning task. And circulating the steps until all the target areas are completely covered, and returning the vehicle to the starting point by carrying all the unmanned aerial vehicles.
In the collaborative path planning of the vehicle and multiple drones, in order to better solve the problem, the following assumptions can be made:
1. the time for the vehicle and the unmanned aerial vehicle to return to the base station after completing all the area coverage tasks is the total time for minimizing the area coverage;
2. the starting point and the end point of the planned path of the vehicle must be base stations;
3. the out-degree and in-degree of the vehicle planned path at each point are consistent;
4. ensuring that each target area is covered by one drone only once;
5. the path of the vehicle carrying the unmanned aerial vehicle to run is included in the vehicle planning path;
6. ensuring that the unmanned aerial vehicle has at most one path between any two road nodes;
7. the unmanned aerial vehicle has at most one path between any two road nodes;
8. ensuring the consistency of the out-degree and the in-degree of the unmanned aerial vehicle;
9. the electric quantity consumed by the unmanned aerial vehicle for executing the coverage reconnaissance task each time can not exceed the upper limit;
10. the time when the vehicle leaves the base station is 0;
11. the time when the vehicle arrives at the next node is not earlier than the time when the previous node leaves plus the time of the shortest path between the two nodes;
12. the moment when the vehicle leaves the node is not earlier than the moment when the vehicle arrives at the node, nor earlier than the moment when the unmanned aerial vehicle lands at the node;
13. the unmanned aerial vehicle can be launched only after the vehicle stops at the node;
14. the unmanned aerial vehicle can land after finishing the regional coverage task.
Based on the assumptions, the mixed integer programming model can be established to carry out concrete solution.
In one embodiment, as shown in fig. 1, a flow chart for planning a collaborative path of a vehicle and multiple drones includes the following steps:
It should be noted that the sub-target area refers to an area where coverage sampling is performed by the drone. Particularly, when the unmanned aerial vehicle carries out regional coverage reconnaissance mission, the area position of waiting to sample is big more dispersed and distributed far away, surpasss unmanned aerial vehicle flight range relatively easily. The method comprises the steps of combining a target area set constructed by an area to be sampled with a real road network, constructing unmanned aerial vehicle coverage sampling based on real roads and supported by ground vehicles, and realizing efficient reconnaissance of the target area.
It is worth explaining that, the vehicle runs to a certain road node along the road, and the working state of the unmanned aerial vehicle after taking off from the vehicle is divided into three stages: 1) travel to the target area edge; 2) executing the covering task along the established path; 3) leave the target area and return to the vehicle. Since only the energy consumption of stage 2 belongs to the effective working energy consumption, in order to improve the working efficiency of the unmanned aerial vehicle, the energy consumption of the unmanned aerial vehicle in the advancing process in stages 1 and 3 should be reduced. Therefore, the real road node closest to the sub-target area is determined as the mapping point of the sub-target area, so that the flight path of the unmanned aerial vehicle can be shortened, and the energy consumption is reduced; the mapping point of the vehicle driving to the sub-target area is regarded as accessing the target area, so that the Problem of the vehicle path is converted into a typical TSP (tracking Salesman Problem) Problem, and a heuristic algorithm can be effectively used for solving the Problem.
It is worth explaining that each target area is completed by one unmanned aerial vehicle at a time, all sampling points and landing points in the flying points, the covering paths form a sub-unmanned aerial vehicle route, all routes form an unmanned aerial vehicle route set, and the flying points, the sampling points and the landing points form a sub-unmanned aerial vehicle route set by using gamma U And (4) showing. Through the steps, the paths of the vehicle and the unmanned aerial vehicle are preliminarily determined, the scheme at the moment belongs to a feasible solution, but only one unmanned aerial vehicle is released each time, the vehicle and other unmanned aerial vehicles wait in situ, and obviously, the cooperativity between the vehicle and the unmanned aerial vehicle is not utilized, so that the iterative relaxation algorithm is adopted to carry out iterative optimization on the paths of the vehicle and the unmanned aerial vehicle.
According to the vehicle and multi-unmanned aerial vehicle collaborative path planning method, device, terminal and medium, considering that the target area is possibly far away from the passable road, the road network node closest to the area to be searched is taken as the mapping point, an unmanned aerial vehicle route based on the positions of take-off points and landing points of a real road network is designed, the take-off points and the landing points are flexibly selected, and the reconnaissance time is saved; and then, carrying out iterative optimization on the unmanned aerial vehicle route set and the vehicle planning path through an iterative relaxation algorithm, and generating a satisfactory reconnaissance path planning scheme in a short time to complete the path planning of the cooperation of the vehicle and the multiple unmanned aerial vehicles.
In one embodiment, as shown in fig. 3, determining the coverage path of the drone according to the relative positions of the sub-target areas in the target area set for the drone coverage path constraint map includes:
planning an unmanned aerial vehicle coverage path according to the number and the positions of the aerial sampling points of the unmanned aerial vehicle in the sub-target area, wherein connecting lines of the sampling points form the unmanned aerial vehicle coverage path; constructing a plurality of unmanned aerial vehicle coverage paths according to different coverage modes, and selecting an optimal coverage mode and an optimal coverage path; the sampling point is the central point in unmanned aerial vehicle sampling area, and the sampling area is the unmanned aerial vehicle single sampling subaerial projection region.
Specifically, the projection area of the single sampling on the ground is rectangular, and all the sampling projection areas can completely cover the target area when the coverage task is finished. Meanwhile, in order to ensure the accuracy of later image splicing or 3D modeling, a certain overlap should exist between adjacent sampling areas. As shown, L x Representing the transverse extent, ov, of the sampling region perpendicular to the direction of flight of the drone x Representing the amount of lateral overlap between adjacent sampling regions; similarly, L y And ov y Respectively, the longitudinal width and longitudinal overlap of the sampling region in the direction of flight.
In one embodiment, the overlay mode includes: a spiral overlay mode and a reciprocating overlay mode; the coverage path includes a spiral coverage path and a reciprocating coverage path.
Specifically, as shown in fig. 4, it is an exemplary diagram of a spiral coverage path based on a landing point; the unmanned aerial vehicle selects the top point of the area to be searched, which is closest to the flying point, as a reference point, two covering paths are respectively constructed by taking the reference point to two adjacent points as references, the optimal covering path which enables the unmanned aerial vehicle to have a smaller corner is selected as the area to be searched, and the area to be searched is covered inwards circle by circle along the edge of the area to be searched.
FIG. 5 is a diagram illustrating an example of a reciprocating overlay path based on landing points; and constructing different reciprocating covering paths by taking the longest edge of the area to be searched as a reference edge and respectively taking two vertexes of the reference edge as reference points, and selecting the shortest covering path from the constructed reciprocating covering paths as the optimal covering path of the area to be searched.
In one embodiment, determining the real road node closest to the sub-target area as the mapping point of the sub-target area includes:
and calculating a centroid coordinate of the sub-target area, and determining the real road node closest to the centroid coordinate as a mapping point of the sub-target area.
In particular, for any region δ to be searched t Calculating the coordinate of the centroid as c t The road node closest to the centroid is
This point is marked as an arbitrary region δ to be searched t Is mapped to a point v LR ＝v i* Where N represents the number of road nodes, c t Representing the area δ to be searched t Centroid coordinates of v i Coordinates representing road node i, d (c) t ,v i ) Denotes c t And v i The euclidean distance between them.
In one embodiment, a vehicle moving path is initially planned to obtain an initial vehicle path; performing cross path elimination on the initial vehicle path to obtain a vehicle path, comprising:
performing initial planning on the vehicle moving path by adopting a greedy algorithm to obtain an initial vehicle path;
and detecting and eliminating the crossed path of the initial vehicle path by using a resolution crossing method to obtain the vehicle path.
Specifically, the mapping point of the vehicle driving to the area to be searched is regarded as accessing the searched area, so that the generation Problem of the vehicle route planning is converted into a typical TSP Problem (tracking Salesman publishing). As an NP-complete problem, it is not practical to use exact algorithms in cases where there are a large number of areas to be searched, whereas simple heuristic algorithms such as greedy algorithms usually yield unsatisfactory solutions. Particularly, when intersection exists in the solved path, the quality of path planning can be rapidly improved through a heuristic method for eliminating the intersection. Therefore, when the access sequence is generated, a feasible initial vehicle path is constructed by a greedy algorithm, and then a digestion intersection method is adopted to detect and eliminate the intersection path in the initial vehicle path to obtain a vehicle planning path. The planned path of the vehicle only records road nodes related to takeoff points and landing points of the unmanned aerial vehicle, and the nodes run along the shortest path.
In one embodiment, based on a vehicle path and an unmanned aerial vehicle route set, respectively constructing alternative departure points and alternative landing points for each sub-unmanned aerial vehicle route in the unmanned aerial vehicle route set; according to the selection index in the iterative relaxation algorithm, respectively carrying out iterative optimization on the alternative flying point and landing flying point set to obtain a new flying point and a new landing point of the sub-unmanned aerial vehicle airway, and the method comprises the following steps:
initializing an unmanned aerial vehicle route set, and restraining the same take-off point and landing point in the routes of the sub-unmanned aerial vehicles;
arranging all unmanned aerial vehicles in the unmanned aerial vehicle route set from large to small according to the residual energy, selecting a sub unmanned aerial vehicle route, and constructing alternative flying starting points and landing flying starting points of the sub unmanned aerial vehicle route;
selecting one alternative point from the alternative flying starting points as a preset flying starting point, gradually relaxing the distance upper line of the preset flying starting point, calculating according to a selection index in an iterative relaxation algorithm, selecting the preset flying starting point meeting the conditions as a new flying starting point, and replacing the original flying starting point;
selecting one alternative point from the alternative falling points as a preset falling point, gradually relaxing the distance upper line of the preset falling point, calculating according to a selection index in an iterative relaxation algorithm, selecting the preset falling point meeting the conditions as a new falling point, and replacing the original falling point;
and updating the vehicle path according to the new flying start point and the new landing point to obtain the collaborative optimal planning path of the vehicle and the multiple unmanned aerial vehicles.
Specifically, in the initial stage, the takeoff point and the landing point of each route are constrained to be the same, that is, the distance epsilon between the takeoff point and the landing point of the unmanned aerial vehicle route is 0. And gradually relaxing the distance constraint in the subsequent iteration process, and guiding the unmanned aerial vehicle route and the vehicle path to carry out iterative optimization.
Setting iteration times I and the maximum value epsilon of the distance epsilon between take-off points and landing points of each unmanned aerial vehicle at the end of the iteration times I max Control the relaxation speed and the relaxation range ← ε + ε max And I. Integrating unmanned aerial vehicle airway U All the routes are arranged from large to small according to the residual energy of the unmanned aerial vehicle, and the routes of the unmanned aerial vehicle are integrated into a route gamma U Selecting an unmanned aerial vehicle airway ta with a row name of alphask (α) Unmanned aerial vehicle airway task (α) Point of origin flying
And the original drop point
Respectively located in the planned path of the vehicle α Bit and r α A bit.
Constructing unmanned aerial vehicle airway task (α) The alternative flying point set is calculated according to the selection indexes, all the alternative flying points in the alternative flying point set are calculated, and the selected one with the minimum comprehensive index is set as the unmanned aerial vehicle air route task (α) New flying spot of
If new flying spot
Not from the original flying spot
And the original flying spot
If the original flying point is not the flying point or the landing point of other routes, the original flying point in the vehicle path is set
By replacing with a new take-off point
If new flying spot
Not from the original flying spot
But originally flying spot
If the points are the take-off points or landing points of other routes, the new take-off points are taken off under the condition of meeting the number constraint of the unmanned aerial vehicles
Inserted into the original flying spot
And before or after the unmanned aerial vehicle takes off the unmanned aerial vehicle, the increment of the path length of the vehicle is smaller, and the takeoff point of the unmanned aerial vehicle and the planned path of the vehicle are updated.
And updating the landing points in the same manner to finally obtain the collaborative optimal planning path of the vehicle and the multiple unmanned aerial vehicles.
In one embodiment, the selection index calculation expression is:
C α ＝θC 1,α +(1-θ)C 2,α
where θ is a weight coefficient, C 1,α The shortest distance between the new takeoff point and the last point of the optimal vehicle planning path is represented, the smaller the value is, the closer the new takeoff point is to the last point of the optimal vehicle planning path is represented, and when C is 1,α When the vehicle is 0, the vehicle can pass through one road node less; c 2,α Indicating the increment of the planned path length of the vehicle when the new takeoff point is replaced by the original takeoff point.
In one embodiment, in order to verify the effectiveness of the vehicle and multi-unmanned aerial vehicle collaborative path planning method provided by the invention, as shown in fig. 6, a road network and a scene of an area to be searched are set for verification, and the verification is carried out at 60km 2 Randomly generating 16 target areas in the test area, wherein the area of each target area is 0.30-0.60 km 2 And the shape of the convex polygon is random. The 3 drones complete the coverage tasks for all areas with the support of one truck. The vehicles need to travel along the road network, with each intersection as a road node. The grey square represents the base station position, and the vehicle and the unmanned aerial vehicle start from the base station and return to the base station together with the vehicle after completing all covering tasks.
As shown in fig. 7, for the path planning of the vehicle and the unmanned aerial vehicle before iterative optimization in the scene of fig. 6, the total task time is 2.973h according to the initial path planning scheme constructed according to the mapping points of the target area to be searched.
Solving is carried out by applying the iterative relaxation algorithm, as shown in fig. 8, the paths of the vehicle and the unmanned aerial vehicle after iterative optimization in the scene of fig. 6 are planned, and the unmanned aerial vehicle selects an optimal coverage mode and an optimal coverage path for a single area to be searched; the vehicle path connects all target areas in series along the road network, and the condition of path intersection does not exist; under the restriction of the number of unmanned aerial vehicles, the vehicle path is cooperatively matched with the unmanned aerial vehicle path, the total time for completing the multi-region coverage reconnaissance task is 1.593h, and the arithmetic operation time is 15.903 s. It can be known that the proposed iterative relaxation optimization mechanism improves the path planning effect by 46.4%.
Because unmanned aerial vehicle airspeed is higher than the vehicle, consequently improve the energy utilization of unmanned aerial vehicle air route and help promoting task completion efficiency. As shown in fig. 9, after iterative optimization, the energy utilization rate of most unmanned aerial vehicle routes is improved, and is increased by 110.41% at most. Fig. 10 shows the time that the drone and the vehicle are waiting on each other, with the time that the vehicle waits for the drone being noted as positive. And respectively calculating the total time of the vehicle waiting for the unmanned aerial vehicle to be 1.862h and 0.893h before and after the iterative optimization. It follows that the task completion time period can be significantly shortened by reducing the waiting time of the vehicle. In conclusion, the mode that the vehicle supports multiple unmanned aerial vehicles can efficiently complete the area coverage task in a large range, and the heuristic algorithm of iterative relaxation can effectively solve the problem of vehicle-machine collaborative path planning.
In one embodiment, a vehicle and multi-drone collaborative path planning apparatus is provided, wherein the apparatus comprises:
the unmanned aerial vehicle coverage path generation module is used for acquiring a target area set and determining a coverage path of the unmanned aerial vehicle according to the relative position of a sub-target area in the target area set;
the vehicle planning path generation module is used for determining a real road node closest to the sub-target area as a mapping point of the sub-target area; generating a vehicle moving path according to each mapping point; initially planning a vehicle moving path to obtain an initial vehicle path; eliminating the crossed path of the initial vehicle path to obtain a vehicle path;
the iterative relaxation optimization module is used for constructing an unmanned aerial vehicle airway set according to the road nodes in the vehicle path and the unmanned aerial vehicle coverage path; respectively constructing alternative flying points and alternative landing points for each sub unmanned aerial vehicle route in the unmanned aerial vehicle route set based on the vehicle route and the unmanned aerial vehicle route set; respectively carrying out iterative optimization on the alternative flying points and the alternative landing flying point set according to selection indexes in the iterative relaxation algorithm to obtain new flying points and new landing points of the sub unmanned aerial vehicle airway; and updating the new flying start point and the new landing point in the vehicle path to obtain the optimal collaborative planning path of the vehicle and the multiple unmanned aerial vehicles.
For specific limitations of the vehicle and multi-drone collaborative path planning apparatus, reference may be made to the above limitations of the vehicle and multi-drone collaborative path planning method, which are not described herein again. All modules in the vehicle and multi-unmanned aerial vehicle collaborative path planning device can be completely or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a vehicle and multi-drone collaborative path planning method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the inventive arrangements and is not intended to limit the computing devices to which the inventive arrangements may be applied, as a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a terminal device is provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method in the above embodiments when executing the computer program.
In an embodiment, a readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, is adapted to carry out the steps of the method of the above embodiment.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that various changes and modifications can be made by those skilled in the art without departing from the spirit of the invention, and these changes and modifications are all within the scope of the invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A vehicle and multi-unmanned aerial vehicle collaborative path planning method is characterized by comprising the following steps:
acquiring a target area set, and determining a coverage path of the unmanned aerial vehicle according to the relative position of a sub-target area in the target area set;
determining the real road node closest to the sub-target area as the mapping point of the sub-target area; generating a vehicle moving path according to each mapping point; performing initial planning on the vehicle moving path to obtain an initial vehicle path; eliminating the crossed path of the initial vehicle path to obtain a vehicle path;
constructing an unmanned aerial vehicle airway set according to the road nodes in the vehicle path and the unmanned aerial vehicle coverage path; respectively constructing alternative flying starting points and alternative landing points for each sub unmanned aerial vehicle route in the unmanned aerial vehicle route set based on the vehicle route and the unmanned aerial vehicle route set; according to selection indexes in an iterative relaxation algorithm, performing iterative optimization on the alternative flying points and the alternative landing flying point set respectively to obtain new flying points and new landing points of the sub unmanned aerial vehicle airway; and updating the new flying point and the new landing point in the vehicle path to obtain the collaborative optimal planning path of the vehicle and the multiple unmanned aerial vehicles.
2. The method of claim 1, wherein determining a coverage path of the drone based on relative positions of sub-target areas in the set of target areas comprises:
planning an unmanned aerial vehicle coverage path according to the number and the positions of the unmanned aerial vehicle air sampling points in the sub-target area, wherein connecting lines of the sampling points form an unmanned aerial vehicle coverage path; constructing a plurality of unmanned aerial vehicle coverage paths according to different coverage modes, and selecting an optimal coverage mode and an optimal coverage path; the sampling point is the central point of unmanned aerial vehicle sampling region, the sampling region is the projection region of unmanned aerial vehicle single sampling subaerial.
3. The method of claim 2, wherein the overlay mode comprises: a spiral overlay mode and a reciprocating overlay mode; the coverage path includes a spiral coverage path and a reciprocating coverage path.
4. The method of claim 1, wherein determining the real road node closest to the sub-target area as the mapping point of the sub-target area comprises:
and calculating a centroid coordinate of the sub-target area, and determining the real road node closest to the centroid coordinate as a mapping point of the sub-target area.
5. The method of claim 1, wherein the initial planning of the vehicle movement path results in an initial vehicle path; performing cross path elimination on the initial vehicle path to obtain a vehicle path, comprising:
performing initial planning on the vehicle moving path by adopting a greedy algorithm to obtain an initial vehicle path;
and detecting and eliminating the crossed path of the initial vehicle path by using a digestion cross method to obtain the vehicle path.
6. The method of claim 4 or 5, wherein the alternative departure points and alternative landing points are constructed for each sub-drone airways of the set of drone airways based on the vehicle path and the set of drone airways; according to selection indexes in an iterative relaxation algorithm, respectively performing iterative optimization on the alternative flying point and the landing flying point set to obtain a new flying point and a new landing point of the sub unmanned aerial vehicle airway, and the method comprises the following steps:
initializing the unmanned aerial vehicle route set, and restraining the same take-off point and landing point in the sub-unmanned aerial vehicle route;
arranging all unmanned aerial vehicles in the unmanned aerial vehicle route set from large to small according to the residual energy, selecting a sub unmanned aerial vehicle route, and constructing alternative departure points and landing departure points of the sub unmanned aerial vehicle route;
selecting one alternative point from the alternative flying starting points as a preset flying starting point, gradually relaxing the distance upper line of the preset flying starting point, calculating according to a selection index in an iterative relaxation algorithm, selecting the preset flying starting point meeting the conditions as a new flying starting point, and replacing the original flying starting point;
selecting one alternative point from the alternative falling points as a preset falling point, gradually relaxing the distance upper line of the preset falling point, calculating according to a selection index in an iterative relaxation algorithm, selecting the preset falling point meeting the conditions as a new falling point, and replacing the original falling point;
and updating the vehicle path according to the new flying start point and the new landing point to obtain the collaborative optimal planning path of the vehicle and the multiple unmanned aerial vehicles.
7. The method according to claim 6, wherein the selection index calculation expression is:
C α ＝θC 1,α +(1-θ)C 2,α
where θ is a weight coefficient, C 1,α Representing new departure point and optimal vehicle plan pathThe shortest distance between one point on the path is smaller, the smaller the value is, the closer the new takeoff point is to one point on the optimal vehicle planning path is, when C 1,α When the vehicle is 0, the vehicle can pass through one road node less; c 2,α Indicating the increment of the planned path length of the vehicle when the new takeoff point is replaced by the original takeoff point.
8. A vehicle and many unmanned aerial vehicle collaborative path planning device, its characterized in that, the device includes:
the unmanned aerial vehicle coverage path generation module is used for acquiring a target area set and determining a coverage path of the unmanned aerial vehicle according to the relative position of a sub-target area in the target area set;
the vehicle planning path generation module is used for determining a real road node closest to the sub-target area as a mapping point of the sub-target area; generating a vehicle moving path according to each mapping point; performing initial planning on the vehicle moving path to obtain an initial vehicle path; eliminating the crossed path of the initial vehicle path to obtain a vehicle path;
the iterative relaxation optimization module is used for constructing an unmanned aerial vehicle airway set according to the road nodes in the vehicle path and the unmanned aerial vehicle coverage path; respectively constructing alternative flying starting points and alternative landing points for each sub unmanned aerial vehicle route in the unmanned aerial vehicle route set based on the vehicle route and the unmanned aerial vehicle route set; according to selection indexes in an iterative relaxation algorithm, performing iterative optimization on the alternative flying points and the alternative landing flying point set respectively to obtain new flying points and new landing points of the sub unmanned aerial vehicle airway; and updating the new flying point and the new landing point in the vehicle path to obtain the collaborative optimal planning path of the vehicle and the multiple unmanned aerial vehicles.
9. A terminal device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any of claims 1 to 7.
10. A terminal readable storage medium, having stored thereon a computer program, characterized in that the computer program, when being executed by a processor, realizes the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210816082.1A CN114967757A (en) | 2022-07-12 | 2022-07-12 | Vehicle and multi-unmanned aerial vehicle collaborative path planning method, device, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210816082.1A CN114967757A (en) | 2022-07-12 | 2022-07-12 | Vehicle and multi-unmanned aerial vehicle collaborative path planning method, device, terminal and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114967757A true CN114967757A (en) | 2022-08-30 |
Family
ID=82969141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210816082.1A Pending CN114967757A (en) | 2022-07-12 | 2022-07-12 | Vehicle and multi-unmanned aerial vehicle collaborative path planning method, device, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114967757A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115328210A (en) * | 2022-10-11 | 2022-11-11 | 深圳大学 | Path planning method and device, terminal equipment and storage medium |
-
2022
- 2022-07-12 CN CN202210816082.1A patent/CN114967757A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115328210A (en) * | 2022-10-11 | 2022-11-11 | 深圳大学 | Path planning method and device, terminal equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109520504B (en) | Grid discretization-based unmanned aerial vehicle patrol route optimization method | |
| CN107169608B (en) | Distribution method and device for multiple unmanned aerial vehicles to execute multiple tasks | |
| US8103532B2 (en) | Method and system for fast local search and insertion heuristics for vehicle routing | |
| Edison et al. | Integrated task assignment and path optimization for cooperating uninhabited aerial vehicles using genetic algorithms | |
| CN110852470B (en) | Optimization method for traffic patrol task allocation under cooperation of unmanned aerial vehicle and vehicle | |
| CN109087023B (en) | Multi-satellite observation layered scheduling method and system based on divide-and-conquer strategy | |
| CN111006693B (en) | Intelligent aircraft track planning system and method thereof | |
| CN103576698A (en) | Mission re-planning for coordinated multivehicle task allocation | |
| WO2022222386A1 (en) | Method and apparatus for planning vehicle lane-changing trajectory, device, storage medium, and vehicle | |
| CN107065929A (en) | A kind of unmanned plane is around flying method and system | |
| WO2020239092A1 (en) | Unmanned aerial vehicle and flight area planning method and device therefor and storage medium | |
| CN107478233B (en) | A kind of geological prospecting path planning method and system | |
| CN111950873A (en) | Satellite real-time guiding task planning method and system based on deep reinforcement learning | |
| CN114967757A (en) | Vehicle and multi-unmanned aerial vehicle collaborative path planning method, device, terminal and medium | |
| CN113671986B (en) | Task allocation method and system for unmanned aerial vehicle and vehicle under cooperation of air and ground | |
| EP4015999B1 (en) | Road updating method and apparatus for electronic map, computer device, and storage medium | |
| CN111047086A (en) | Vehicle path planning and unmanned aerial vehicle task allocation joint optimization method and device | |
| CN109472460B (en) | Real-time operation coverage area reconstruction method and system based on effective intersection points | |
| CN110647162B (en) | Route planning method for tour guide unmanned aerial vehicle, terminal equipment and storage medium | |
| CN111310919B (en) | Driving control strategy training method based on scene segmentation and local path planning | |
| CN116579564A (en) | Regional reconnaissance task planning method, device, computer equipment and medium | |
| CN116862091A (en) | Tobacco industry distribution line optimization method, system, equipment and medium | |
| CN116578120A (en) | Unmanned aerial vehicle scheduling method and device, unmanned aerial vehicle system and computer equipment | |
| CN114037131B (en) | Air-ground cooperative task route planning method, device, terminal and storage medium | |
| CN115031736A (en) | Multi-unmanned aerial vehicle area coverage track planning method and system |
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 |