CN109885095B - Unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization - Google Patents
Unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization Download PDFInfo
- Publication number
- CN109885095B CN109885095B CN201910254997.6A CN201910254997A CN109885095B CN 109885095 B CN109885095 B CN 109885095B CN 201910254997 A CN201910254997 A CN 201910254997A CN 109885095 B CN109885095 B CN 109885095B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- formation
- aerial vehicle
- bee colony
- stage
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000005457 optimization Methods 0.000 title claims abstract description 26
- 230000005757 colony formation Effects 0.000 title claims abstract description 12
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 103
- 238000005755 formation reaction Methods 0.000 claims description 102
- 230000004888 barrier function Effects 0.000 claims description 6
- 238000009472 formulation Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 14
- 238000004088 simulation Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Medicines Containing Material From Animals Or Micro-Organisms (AREA)
- Feedback Control In General (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a two-stage random optimization-based unmanned aerial vehicle bee colony formation reconstruction method, which enables unmanned aerial vehicle bee colonies to avoid obstacles through formation reconstruction in a complex space based on two-stage random optimization, and enables total cost to be minimum. In the first stage, only the determined fixed obstacle is considered, after the distribution of the moving obstacle is obtained through historical information or samples in the second stage, the cost of the bee colony for avoiding the uncertain moving obstacle is calculated, and finally the cost in the second stage is added into the first stage, so that the sum of the costs is minimum. The invention has the advantages that: solving the problem of group obstacle avoidance of the unmanned aerial vehicle bee colony in a dynamically-changing complex environment by a two-stage random optimization method; the method fully considers the complexity and the variability of the environment and has stronger use value; the method has higher execution efficiency, and the calculation time can not be increased along with the expansion of the bee colony scale.
Description
Technical Field
The invention belongs to the field of group intelligence, and particularly provides an unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization, which is used for avoiding barriers of unmanned aerial vehicle bee colonies in a complex environment.
Background
The single unmanned aerial vehicle in the unmanned aerial vehicle bee colony does not have higher individual intelligence, and simultaneously, they not only can communicate each other, but also have environment perception ability and team ability. Furthermore, the entire swarm has no leader, allowing each drone to enter or leave. The unmanned aerial vehicle bee colony is generally required to be arranged in a three-dimensional space according to a certain structure when performing tasks, so that the whole bee colony can keep a stable array shape in the flight process, but various emergency situations, such as change of a combat target, dynamic change of external environments such as obstacles and the like, and mutual collision among internal members, are inevitably encountered. In the face of the above situation, it is necessary to dynamically adjust the formation of the swarm to achieve overall swarm formation maintenance and continue to perform tasks. Therefore, the research on the rapid synchronous formation reconstruction algorithm of the unmanned aerial vehicle bee colony has important significance.
Current research on unmanned aerial vehicle formation reconstruction is performed in a certain environment, and the influence caused by an uncertain complex environment is not considered. However, during the course of the unmanned aerial vehicle swarm to perform tasks, the unmanned aerial vehicle swarm often encounters moving uncertain obstacles such as bird swarms, clouds or other unknown aircraft in addition to fixed obstacles such as hills, forests, high-rise buildings and the like. Therefore, only the reconstruction of the unmanned aerial vehicle bee colony formation under ideal conditions is considered, and the method has no practical significance.
Disclosure of Invention
Aiming at the problem that most of the existing unmanned aerial vehicle bee colony formation reconstruction technologies do not consider uncertain moving barriers in a complex environment, the invention provides an unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization.
The technical scheme of the invention is as follows:
an unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization comprises the following steps:
s1: constructing a cost function of the reconstruction of the formation of the swarm of the unmanned aerial vehicle, wherein the cost function can quantify the cost of the reconstruction of the formation;
s2: the method comprises the steps of designing a first stage of two-stage random optimization, calculating optimal formation parameters of fixed obstacles in an unmanned aerial vehicle bee colony avoidance environment and minimizing formation reconstruction cost;
s3: designing a second stage of two-stage random optimization, acquiring an event set of moving obstacle distribution from a sample, calculating the extra cost of the unmanned aerial vehicle bee colony for avoiding the moving obstacle possibly appearing and minimizing the cost;
s4: the additional cost of avoiding uncertain moving obstacles in the second stage is added to the first stage, so that the cost of avoiding collision with the obstacles by the reconstruction of formation of the unmanned aerial vehicle bee colony in a complex space is minimum.
Further, a two-stage random optimization-based unmanned aerial vehicle swarm formation reconstruction method is provided, wherein the step S1 specifically comprises the following steps:
s101: a set f e N of formations of a predefined swarm, the set comprising all formations, whereinRepresents the ith formation, formation +.>The position of each unmanned aerial vehicle is expressed as +.>The boundary nodes of the formation areni is the number of boundary nodes, and in order to reduce the complexity in calculating the formation, the formation of the unmanned aerial vehicle bee colony is represented by using the boundary nodes of the unmanned aerial vehicle bee colony.
S102: formation parameters of unmanned aerial vehicle bee colony pass through x i ＝[t，s，q]Representation of whereinFor the position after the bee colony moves, +.>Is a scaling factor, q is a quaternion used to represent the rotation of the bee colony, and then the unmanned plane nodes and boundary nodes inside the bee colony can be represented as:
s103: usingThe central position of the bee colony at the moment t is represented, the unmanned plane bee colony calculates a target formation once every time tau, and the current moment is t 0 Let t f ＝t 0 +τ, t f The target position of the time bee colony is d (t f ). Our goal is to fly the swarm to the target point d (t f ) The cost of formation reconstruction to avoid obstacles is minimal. The reconstruction cost of a formation can be expressed as:
C(x j ，x i )＝w t ||t j -t i || 2 +w s ||s j -s i || 2 +w q ||q j -q i || 2 ，
wherein x is i ＝[t i ，s i ，q i ]，x j ＝[t j ，s j ，q j ]，w t ，w s ，w q Representing the weight of each formation parameter in calculating the formation reconstruction cost, C (x i ，x j ) Representing the cost of transforming from formation i to formation j.
Further, a two-stage random optimization-based unmanned aerial vehicle swarm formation reconstruction method is provided, wherein the step S2 specifically comprises the following steps:
s201: after defining the formation reconstruction cost, an objective function of the first stage can be obtained:
wherein x is init ＝[d(t f )，s init ，q init ]For initial formation parameters, x f1 ＝[t f1 ，s f1 ，q f1 ]The target formation parameters obtained in the first stage are obtained;
s202: the unmanned aerial vehicle can not collide with the obstacle when the unmanned aerial vehicle bee colony is reconstructed; collision can not happen between each unmanned aerial vehicle, so the following constraint can be obtained:
wherein the first constraint is: the unmanned aerial vehicle at each vertex position of the unmanned aerial vehicle bee colony is in the barrier-free area, so that each unmanned aerial vehicle of the whole bee colony cannot collide with a barrier; the second constraint is: adjacent unmanned aerial vehicleThe distance between two adjacent unmanned aerial vehicles is constrained to be greater than l 0 The unmanned aerial vehicle inside the bee colony is guaranteed not to collide.
Further, a two-stage random optimization-based unmanned aerial vehicle swarm formation reconstruction method is provided, wherein the step S3 specifically comprises the following steps:
s301: in the second phase, affected by an uncertain movement obstacle, the obstacle-free area in front of the drone swarm will no longer be a constant value, we useRepresenting the forward unobstructed area, let Ω be the set of events for the unobstructed area and p (ω) be the probability of ω occurrence, +.>For the barrier-free region at this time, +.>The cost of the second stage is to avoid the uncertain movement obstacle, and the cost function of the second stage is:
this formulation represents an additional cost to the drone swarm when encountering a moving obstacle, which is a desirable form due to the uncertainty of the moving obstacle;
s302: given ω, the second stage our goal is to minimize the additional formation reconstruction cost, from which we can derive
S303: when the unmanned aerial vehicle bee colony avoids an uncertain moving obstacle in the second stage, the following constraints exist:
C(x f2 (ω)，x init )-C(x f1 ，x init )≥0，
ω∈Ω，
wherein first one has guaranteed unmanned aerial vehicle bee colony and has not collided with the barrier, and second one has guaranteed that unmanned aerial vehicle bee colony inside does not take place the mutual collision.
Further, a two-stage random optimization-based unmanned aerial vehicle swarm formation reconstruction method is provided, and the step S4 specifically comprises the following steps: combining the cost of the first stage for avoiding the determined fixed obstacle with the cost of the second stage for avoiding the uncertain moving obstacle can obtain the objective function of the unmanned aerial vehicle swarm for avoiding the obstacle in the complex space through formation reconstruction:
the constraint conditions are as follows:
C(x f2 (ω)，x init )-C(x f1 ，x init )≥0，
ω∈Ω，
the invention has the technical advantages that:
1. the unmanned aerial vehicle bee colony is enabled to avoid the obstacle through the reconstruction of the formation, so that the swarm is enhanced under the condition that each unmanned aerial vehicle is not damaged;
2. the two-stage random optimization method is adopted, and meanwhile, the determined and uncertain obstacles are considered, so that the method has strong practicability;
3. the method consumes less cost and shorter time when the formation is reconstructed, and does not increase the cost and time along with the expansion of the scale of the bee colony.
Drawings
FIG. 1 is a block diagram of the mechanism of the present invention.
Fig. 2 is an omnet++ simulation environment diagram.
Figure 3 our method and single stage method contrast (blue is our method).
FIG. 4 is a graph of the cost of the swarm formation reconstruction.
FIG. 5 is a time chart of the bee colony formation reconstruction.
Detailed Description
The invention is further described below with reference to the drawings and the detailed description.
The invention relates to a method for reconstructing an unmanned aerial vehicle bee colony formation based on two-stage random optimization, which is designed according to the random optimization theory and the technical characteristics of the unmanned aerial vehicle formation reconstruction, and mainly solves the following two problems:
(1) According to the technical characteristics of the formation reconstruction of the unmanned aerial vehicle bee colony, a cost function is designed, and the cost of the unmanned aerial vehicle bee colony from one formation to another formation can be well reflected by the function.
(2) According to the cost function, a two-stage random optimization method is adopted, wherein only deterministic fixed obstacles are considered in the first stage; the second stage takes into account the uncertain moving obstacle and minimizes the sum of the costs of the two stages.
The main idea of the invention is that: the problem of formation reconstruction of the unmanned aerial vehicle in a complex environment is solved by using a two-stage random optimization method, so that the cost of formation reconstruction of the unmanned aerial vehicle for avoiding obstacles is minimum.
Specifically, the method for reconstructing the swarm formation of the unmanned aerial vehicle based on two-stage random optimization comprises the following steps:
s1: constructing a cost function of the formation reconstruction of the unmanned aerial vehicle bee colony, wherein the cost function can quantify the cost of the formation reconstruction;
s101: a set f e N of formations of a predefined swarm, the set comprising all formations, whereinRepresents the ith formation, formation +.>The position of each unmanned aerial vehicle is expressed as +.>The boundary nodes of the formation areni is the number of boundary nodes, and in order to reduce the complexity in calculating the formation, the formation of the unmanned aerial vehicle bee colony is represented by using the boundary nodes of the unmanned aerial vehicle bee colony;
s102: formation parameters of unmanned aerial vehicle bee colony pass through x i ＝[t，s，q]Representation of whereinFor the position after the bee colony moves, +.>Is a scaling factor, q is a quaternion used to represent the rotation of the bee colony, and then the unmanned plane nodes and boundary nodes inside the bee colony can be represented as:
s103: usingThe central position of the bee colony at the moment t is represented, the unmanned plane bee colony calculates a target formation once every time tau, and the current moment is t 0 Let t f ＝t 0 +τ, t f The target position of the time bee colony is d (t f ). Our goal is to fly the swarm to the target point d (t f ) The cost of formation reconstruction to avoid obstacles is minimal. The reconstruction cost of a formation can be expressed as:
C(x j ，x i )＝w t ||t j -t i || 2 +w s ||s j -s i || 2 +w q ||q j -q i || 2 ，
wherein x is i ＝[t i ，s i ，q i ]，x j ＝[t j ，s j ，q j ]，w t ，w s ，w q Representing the weight of each formation parameter in calculating the formation reconstruction cost, C (x i ，x j ) Representing the cost of transforming from formation i to formation j.
S2: the method comprises the steps of designing a first stage of two-stage random optimization, calculating optimal formation parameters of fixed obstacles in an unmanned aerial vehicle bee colony avoidance environment and minimizing formation reconstruction cost;
s201: after defining the formation reconstruction cost, an objective function of the first stage can be obtained:
wherein x is init ＝[d(t f )，s init ，q init ]For initial formation parameters, x f1 ＝[t f1 ，s f1 ，q f1 ]The target formation parameters obtained in the first stage are obtained;
s202: the unmanned aerial vehicle can not collide with the obstacle when the unmanned aerial vehicle bee colony is reconstructed; collision can not happen between each unmanned aerial vehicle, so the following constraint can be obtained:
wherein the first constraint is: the unmanned aerial vehicle at each vertex position of the unmanned aerial vehicle bee colony is in the barrier-free area, so that each unmanned aerial vehicle of the whole bee colony cannot collide with a barrier; the second constraint is: distance constraint between adjacent unmanned aerial vehicles is achieved by letting the distance between two adjacent unmanned aerial vehicles be greater than l 0 The unmanned aerial vehicle inside the bee colony is guaranteed not to collide.
S3: designing a second stage of two-stage random optimization, acquiring an event set of moving obstacle distribution from a sample, calculating the extra cost of the unmanned aerial vehicle bee colony for avoiding the moving obstacle possibly appearing and minimizing the cost;
s301: in the second phase, affected by an uncertain movement obstacle, the obstacle-free area in front of the drone swarm will no longer be oneConstant value, we useRepresenting the forward unobstructed area, let Ω be the set of events for the unobstructed area and p (ω) be the probability of ω occurrence, +.>For the barrier-free region at this time, +.>The cost of the second stage is to avoid the uncertain movement obstacle, and the cost function of the second stage is:
this formulation represents an additional cost to the drone swarm when encountering a moving obstacle, which is a desirable form due to the uncertainty of the moving obstacle;
s302: given ω, the second stage our goal is to minimize the additional formation reconstruction cost, from which we can derive
S303: when the unmanned aerial vehicle bee colony avoids an uncertain moving obstacle in the second stage, the following constraints exist:
C(x f2 (ω)，x init )-C(x f1 ，x init )≥0，
ω∈Ω，
s4: adding the additional cost of avoiding the uncertain moving obstacle in the second stage to the first stage, so that the cost of avoiding collision with the obstacle by the unmanned aerial vehicle bee colony in the complex space through formation reconstruction is the minimum, and obtaining the objective function of avoiding the obstacle in the complex space by the unmanned aerial vehicle bee colony through formation reconstruction:
the constraint conditions are as follows:
C(x f2 (ω)，x init )-C(x f1 ，x init )≥0，
ω∈Ω，
the specific implementation method comprises the following steps:
we have chosen OMNeT++ platform for simulation test, FIG. 2 is simulation of the process of swarm formation reconstruction, OMNeT++ is an open-source discrete event simulator, it has modularization, C++ simulation library and framework based on components, facilitate users to expand function definition own simulation environment, currently occupy important place in the field of network simulation.
In the OMNet++ platform, the communication radius of each unmanned aerial vehicle is designed to be between 30m and 50m, and the moving speed is between 1m/s and 3m/s, so that the unmanned aerial vehicle bee colony can keep the team to pass through the obstacle area to reach the target point. The scenario of fig. 3 (a) is that there is no record in the history information about moving obstructions, so the term second satge in the method herein will be 0, and the resulting solution is then similar to the method using a single stage. FIG. 3 (b) shows that there is a moving obstacle in the history (FIG. 3 (b)) when the first formation changes to the second formation, our method reduces the formation size in advance, and adjusts the formation heading, while the single-stage method adjusts the formation only when encountering an obstacle, which results in that our method can be faster and more efficient when changing from the second formation to the third formation in order to avoid an obstacle, the same situation is also reflected in FIG. 3 (c), when there are two moving obstacles in the history, our method reduces the size in advance, adjusting the heading when changing from the first formation to the second formation, so that the bee colony can quickly and efficiently pass through the moving obstacle area, but the single-stage method cannot do not.
Figure 4 shows the cost of formation reconstruction by two methods as the number of moving obstacles increases. It can be seen that the cost of the proposed method to reconstruct the formation does not change significantly with increasing number of moving obstacles, but the cost of the monovalent segment method increases significantly. Figure 5 shows the effect of the size of the drone swarm on the passage of the space of the obstacle, and our method is largely unaffected by the size of the swarm, thanks to our use of the vertices of the swarm to represent the swarm formation.
It can be seen from the above that: the method provided by the invention not only can finish the obstacle avoidance of the unmanned aerial vehicle bee colony through formation reconstruction, but also has lower time and cost than the traditional method.
The preferred embodiments of the present invention have been described in detail above, but the present invention is not limited to the specific details of the above embodiments, and various equivalent exchanges (such as number, shape, position, etc.) may be performed on the technical solutions of the present invention within the scope of the technical concept of the present invention, and these equivalent exchanges are all included in the protection of the present invention.
Claims (2)
1. The unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization is characterized by comprising the following steps of:
s1: constructing a cost function of the formation reconstruction of the unmanned aerial vehicle bee colony, wherein the cost function quantifies the cost of the formation reconstruction;
s2: the method comprises the steps of designing a first stage of two-stage random optimization, calculating optimal formation parameters of fixed obstacles in an unmanned aerial vehicle bee colony avoidance environment and minimizing formation reconstruction cost;
s3: designing a second stage of two-stage random optimization, acquiring an event set of moving obstacle distribution from a sample, calculating the extra cost of the unmanned aerial vehicle swarm for avoiding the moving obstacle possibly appearing and minimizing the cost;
s4: adding the extra cost of avoiding the uncertain moving obstacle in the second stage to the first stage, so that the cost of avoiding collision with the obstacle by the formation reconstruction of the unmanned aerial vehicle bee colony in the complex space is minimum;
the step S1 specifically comprises the following steps:
s101: predefining a set of formations for a swarmThis set contains all formations, wherein +.>Indicate->Formation of individual, formation->The position of each unmanned aerial vehicle is expressed as +.>The boundary nodes of the formation are，/>For reducing complexity in calculating formation, the formation of the unmanned aerial vehicle bee colony is represented by using boundary nodes of the unmanned aerial vehicle bee colony as the number of boundary nodes;
s102: formation parameter passing of unmanned aerial vehicle bee colonyRepresentation of->For the position after the bee colony moves, +.>Is a scaling factor, q is a quaternion used to represent the rotation of the bee colony, and then the unmanned plane nodes and boundary nodes inside the bee colony are represented as:
；
s103: usingRepresentation->At the moment the center of the bee colony, the unmanned plane bee colony is +.>Calculating a primary target formation, wherein the current moment is +.>Let->Then->The target position of the time bee colony is +.>The goal is to let the bee colony fly to the target point +.>The reconstruction cost of the formation is the smallest for avoiding the obstacle, so the reconstruction cost of the formation is expressed as:
,
wherein the method comprises the steps ofWeight value representing each team member parameter when calculating team member reconstruction cost, +.>Representing>Conversion to formation->Cost of (2);
the step S2 specifically comprises the following steps:
s201: after the formation reconstruction cost is defined, an objective function of the first stage is obtained:
；
wherein the method comprises the steps ofFor the initial formation parameters, +.>The target formation parameters obtained in the first stage are obtained;
s202: the unmanned aerial vehicle can not collide with the obstacle when the unmanned aerial vehicle bee colony is reconstructed; no collision occurs between each unmanned aerial vehicle, so the following constraint is obtained:
；
wherein the first constraint is: the unmanned aerial vehicle at each vertex position of the unmanned aerial vehicle bee colony is in the barrier-free area, so that each unmanned aerial vehicle of the whole bee colony cannot collide with a barrier; the second constraint is: distance constraint between adjacent unmanned aerial vehicles is realized by enabling the distance between two adjacent unmanned aerial vehicles to be larger than that of each otherThe unmanned aerial vehicles inside the bee colony are prevented from collision;
the step S3 specifically comprises the following steps:
s301: in the second stage, the obstacle-free area in front of the drone swarm will no longer be a constant value, subject to the influence of an uncertain movement obstacle, usingRepresents the forward barrier-free area, assuming +.>Event collection in unobstructed areasIs->Probability of occurrence, ++>For the barrier-free region at this time, +.>The cost of the second stage is to avoid the uncertain movement obstacle, and the cost function of the second stage is:
；
this formulation represents an additional cost to the drone swarm when encountering a moving obstacle, which is a desirable form due to the uncertainty of the moving obstacle;
s302: at a known positionOn the premise of (1), the goal of the second stage is to minimize the additional formation reconstruction cost, thereby deriving：
；
S303: when the unmanned aerial vehicle bee colony avoids an uncertain moving obstacle in the second stage, the following constraints exist:
。
2. the method for reconstructing the bee colony formation of the unmanned aerial vehicle based on the two-stage random optimization according to claim 1, wherein the step S4 is specifically: combining the cost of avoiding the fixed obstacle in the first stage with the cost of avoiding the uncertain moving obstacle in the second stage to obtain an objective function of avoiding the obstacle in the complex space by the reconstruction of the unmanned aerial vehicle bee colony through the formation:
；
the constraint conditions are as follows:
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910254997.6A CN109885095B (en) | 2019-03-29 | 2019-03-29 | Unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910254997.6A CN109885095B (en) | 2019-03-29 | 2019-03-29 | Unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109885095A CN109885095A (en) | 2019-06-14 |
| CN109885095B true CN109885095B (en) | 2023-12-05 |
Family
ID=66935494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910254997.6A Active CN109885095B (en) | 2019-03-29 | 2019-03-29 | Unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109885095B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112947540A (en) * | 2021-01-13 | 2021-06-11 | 施长锋 | Data analysis type flight regulation system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101286071A (en) * | 2008-04-24 | 2008-10-15 | 北京航空航天大学 | Multiple no-manned plane three-dimensional formation reconfiguration method based on particle swarm optimization and genetic algorithm |
| CN104407619A (en) * | 2014-11-05 | 2015-03-11 | 沈阳航空航天大学 | Method enabling multiple unmanned aerial vehicles to reach multiple targets simultaneously under uncertain environments |
| CN107491086A (en) * | 2017-08-03 | 2017-12-19 | 哈尔滨工业大学深圳研究生院 | Unmanned plane formation obstacle avoidance and system under time-varying network topology |
| CN109254592A (en) * | 2018-09-17 | 2019-01-22 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle formation change control method and system |
| CN109521794A (en) * | 2018-12-07 | 2019-03-26 | 南京航空航天大学 | A kind of multiple no-manned plane routeing and dynamic obstacle avoidance method |
-
2019
- 2019-03-29 CN CN201910254997.6A patent/CN109885095B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101286071A (en) * | 2008-04-24 | 2008-10-15 | 北京航空航天大学 | Multiple no-manned plane three-dimensional formation reconfiguration method based on particle swarm optimization and genetic algorithm |
| CN104407619A (en) * | 2014-11-05 | 2015-03-11 | 沈阳航空航天大学 | Method enabling multiple unmanned aerial vehicles to reach multiple targets simultaneously under uncertain environments |
| CN107491086A (en) * | 2017-08-03 | 2017-12-19 | 哈尔滨工业大学深圳研究生院 | Unmanned plane formation obstacle avoidance and system under time-varying network topology |
| CN109254592A (en) * | 2018-09-17 | 2019-01-22 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle formation change control method and system |
| CN109521794A (en) * | 2018-12-07 | 2019-03-26 | 南京航空航天大学 | A kind of multiple no-manned plane routeing and dynamic obstacle avoidance method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109885095A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Distributed trajectory optimization for multiple solar-powered UAVs target tracking in urban environment by Adaptive Grasshopper Optimization Algorithm | |
| CN110737968B (en) | Crowd trajectory prediction method and system based on deep convolutional long and short memory network | |
| CN113495578B (en) | Digital twin training-based cluster track planning reinforcement learning method | |
| Li et al. | Trajectory planning for UAV based on improved ACO algorithm | |
| CN108564227B (en) | Rail transit passenger flow volume prediction method based on space-time characteristics | |
| CN107886201B (en) | Multi-objective optimization method and device for multi-unmanned aerial vehicle task allocation | |
| KR102279956B1 (en) | 3D optimal surveillance trajectory planning Method and Apparatus for multi-UAVs using particle swarm optimization with surveillance area priority | |
| AlMahamid et al. | Autonomous unmanned aerial vehicle navigation using reinforcement learning: A systematic review | |
| CN113705880A (en) | Traffic speed prediction method and device based on space-time attention diagram convolutional network | |
| Zhang et al. | Cooperative multi-agent actor–critic control of traffic network flow based on edge computing | |
| Liu et al. | Sliding mode control of multi-agent system with application to UAV air combat | |
| CN109799703B (en) | Particle swarm active disturbance rejection control method and device and storage medium | |
| CN109885095B (en) | Unmanned aerial vehicle bee colony formation reconstruction method based on two-stage random optimization | |
| Shi et al. | A multi-unmanned aerial vehicle dynamic task assignment method based on bionic algorithms | |
| Liu et al. | A multistate network approach for resilience analysis of UAV swarm considering information exchange capacity | |
| CN112363532A (en) | Multi-unmanned aerial vehicle simultaneous take-off aggregation method based on QUATRE algorithm | |
| Hu et al. | Pigeon-inspired fuzzy multi-objective task allocation of unmanned aerial vehicles for multi-target tracking | |
| CN114815891A (en) | PER-IDQN-based multi-unmanned aerial vehicle enclosure capture tactical method | |
| CN115278698A (en) | Unmanned aerial vehicle base station dynamic deployment method and device based on dynamic user distribution prediction | |
| CN113063419A (en) | Unmanned aerial vehicle path planning method and system | |
| CN112579285A (en) | Edge network-oriented distributed neural network collaborative optimization method | |
| Filipic et al. | People counting using visible and infrared images | |
| CN114967748A (en) | Unmanned aerial vehicle path planning method based on space deformation | |
| CN116400718A (en) | Unmanned aerial vehicle short-distance air combat maneuver autonomous decision-making method, system, equipment and terminal | |
| Nguyen et al. | Complex event analysis for traffic risk prediction based on 3D-CNN with multi-sources urban sensing data |
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 |