CN107992936A - The hedging method of hedging method and flying object based on population - Google Patents
The hedging method of hedging method and flying object based on population Download PDFInfo
- Publication number
- CN107992936A CN107992936A CN201711426543.XA CN201711426543A CN107992936A CN 107992936 A CN107992936 A CN 107992936A CN 201711426543 A CN201711426543 A CN 201711426543A CN 107992936 A CN107992936 A CN 107992936A
- Authority
- CN
- China
- Prior art keywords
- particle
- particles
- value
- iteration
- speed
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000002245 particle Substances 0.000 claims abstract description 159
- XOFYZVNMUHMLCC-ZPOLXVRWSA-N prednisone Chemical compound O=C1C=C[C@]2(C)[C@H]3C(=O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 XOFYZVNMUHMLCC-ZPOLXVRWSA-N 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 3
- YZCKVEUIGOORGS-IGMARMGPSA-N Protium Chemical compound [1H] YZCKVEUIGOORGS-IGMARMGPSA-N 0.000 claims description 2
- 238000002922 simulated annealing Methods 0.000 abstract description 14
- 238000005457 optimization Methods 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000000137 annealing Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to hedging method and the hedging method of flying object based on population, by the way that classical particle group algorithm and simulated annealing particle cluster algorithm are integrated, the Inertia Weight of each iteration cycle in classical particle group's algorithm is gradually reduced, so as to reduce convergence time.Present invention incorporates the advantages of classical particle group algorithm and simulated annealing particle cluster algorithm, security when unmanned plane performs task under complicated spatial domain environment can be improved, risk of collision caused by ground fixed obstacle and aerial other aircraft can not effectively be avoided in flight course by reducing unmanned plane, make it possible unmanned plane and there is human-computer communion spatial domain, can be unmanned plane safely, smoothly perform various tasks effective guarantee be provided.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle autonomous risk avoidance, in particular to a risk avoiding method based on particle swarm and a risk avoiding method of a flying object.
Background
The classical particle swarm algorithm and the simulated annealing particle swarm algorithm are algorithms which are commonly used in the obstacle danger avoiding process of the unmanned aerial vehicle in the flight process.
The classical particle swarm optimization can overcome the defect that basic particles are easy to fall into local optimum, but can increase convergence time; the simulated annealing particle swarm optimization has the defect that the convergence time is not too long, but the basic particles are easy to fall into local optimum.
In summary, in order to improve the safety of the unmanned aerial vehicle when performing tasks in a complex airspace environment and reduce the risk of collision caused by the fact that the unmanned aerial vehicle cannot effectively avoid ground fixed obstacles and other aerial vehicles in the air during the flight process, a new algorithm needs to be provided, so that the unmanned aerial vehicle can safely and smoothly perform various tasks.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a particle swarm-based risk avoiding method, which comprises the following steps of:
step S1: randomly initializing the number n of particles, and initializing the positions and the speeds of the particles to obtain the position and speed information of the particles;
step S2: obtaining an individual extreme value and a group extreme value of the particles in the current iteration period according to the position and speed information of the particles;
and step S3: if the particles meet the iteration condition, performing the steps S4-S5; if the particles do not meet the iteration condition, ending the iteration process, and obtaining the final optimal solution according to all individual extrema and group extrema in all current iteration cycles;
and step S4: updating the position and the speed of the particle to obtain the position and the speed information of the particle in the next iteration period;
step S5: comparing the position and speed information of the particles in the two iteration cycles in the step S2 and the step S4, if any one of the conditions of delta E ≦ 0 or exp (-delta E/T) > rand (0, 1) is satisfied, executing the step S2 to the step S3 again with the position and speed information of the particles in the step S4 as the standard, and if any one of the conditions is not satisfied, executing the step S2 to the step S3 again with the position and speed information of the particles in the step S2 as the standard;
in step S1, the position information and the velocity information of the particle are respectively:
X i ＝[x i1 x 12 … x iD ]
v i ＝[v i1 v 12 … v iD ]
d represents a D-dimensional vector shared by the particles, i represents the ith particle, and the value of the ith particle is between 1 and n;
Δ E is the difference between the energy corresponding to the particle state in step S4 and the energy corresponding to the particle state in step S2, k is the boltzmann constant, and T is the iteration temperature in the iteration cycle corresponding to step S4.
In step S2, the individual extremum and the group extremum of the particle are respectively
P i ＝[P i1 P 12 … P iD ]
P g ＝P g1 P g2 … P gD ]
D represents a D-dimensional vector shared by the particles, i represents the ith particle, and the value of the ith particle is between 1 and n; and the individual extreme value and the group extreme value are calculated through the fitness value of the particles.
In step S4, the position and velocity update formula of the particles is:
wherein,a value representing the updated velocity of the particle in the m-th vector,a value representing the m-th vector of the velocity before particle update;a value representing the updated position of the particle in the m-dimension vector;a value indicating that the position before the particle update is in the m-th vector;representing the value of the individual extreme value before particle updating in the m-dimension vector;representing the value of the population extreme value before particle updating in the m-dimension vector;
t represents the time difference of one iteration cycle, c 1 And c 2 Respectively representing that the acceleration coefficient is a non-negative constant; r is a radical of hydrogen 1 And r 2 Is a random constant ranging between (0, 1);
ω represents the inertial weight and this value is decremented in each iteration cycle.
In step S4, the speed of the particle is locked within a predetermined maximum speed when the speed of the particle is updated.
Wherein, in step S4, the velocity of the particle is locked within a predetermined maximum velocity by locking the velocity of the particle in the horizontal direction at a maximum value when updating the velocity of the particle.
Wherein, the calculation formula of ω is:
wherein, ω is s As an initial inertia weight, ω e Is the inertia weight when the iteration number is maximum, t is the current iteration number, t max Is the maximum number of iterations.
Wherein, the calculation formula of ω is:
wherein, ω is s Is an initial inertia weight, omega e Is the inertia weight when the iteration number is maximum, t is the current iteration number, t max Is the maximum number of iterations, c 3 Is an adjusting parameter of the inertia weight, and the value is between (0, 1).
The invention further provides a risk avoiding method for the flyer, which comprises the following steps: inputting parameter information of the flying object in the flying state into a computer; the computer then adopts the risk avoiding method based on the particle swarm to calculate to obtain operation information; then, the flying object flies according to the operation information.
The parameter information of the flying object comprises the speed of the aircraft and the environment where the aircraft is located.
The particle swarm-based risk avoiding method and the flight object risk avoiding method provided by the invention combine the advantages of the classical particle swarm algorithm and the simulated annealing particle swarm algorithm, can improve the safety of the unmanned aerial vehicle in executing tasks in a complex airspace environment, reduce the collision risk caused by the fact that the unmanned aerial vehicle cannot effectively avoid ground fixed obstacles and other aircrafts in the air in the flight process, enable the unmanned aerial vehicle and the manned aircraft to share an airspace to be possible, and can provide effective guarantee for the unmanned aerial vehicle to safely and smoothly execute various tasks.
Drawings
FIG. 1: the invention discloses a particle swarm-based risk avoiding method.
Detailed Description
In order to further understand the technical scheme and the advantages of the present invention, the technical scheme and the advantages thereof are described in detail below with reference to the accompanying drawings.
In the classical particle swarm optimization, n particles are initialized randomly in a feasible solution space to form an initial population, a velocity is initialized randomly for each particle, each particle corresponds to a solution of an optimization problem, an adaptive value is determined by an objective function, and the velocity is used for determining the motion of the particles in the solution space. In each iteration of the algorithm, the particles track the currently found optimal solution of the particles and the currently found optimal solution of the population, and search generation by generation until the optimal solution is finally obtained.
The particle swarm algorithm comprises a large number of particles, and a population consisting of n particles in a D-dimensional space
A D-dimensional vector can represent the ith particle
X i ＝[x i1 x 12 … x iD ]
The position of the ith particle in the D-dimensional space is represented, a fitness function is determined according to the practical problem, and the fitness value is calculated according to the fitness function, wherein the speed of the ith particle is
v i ＝[v i1 v 12 … v iD ]
Individual extremum of
P i ＝[P i1 P 12 …P iD ]
Global extremum
P g ＝[P g1 P g2 … P gD ]
Simulated annealing particle swarm algorithm was invented by S.Kirkpatrick, C.D.Gelatt and M.P.Vecchi in 1983. The essence of the simulated annealing algorithm is to simulate the annealing process in a thermodynamic system, and to visualize each effective particle as a molecule in air, each molecule having its own individual energy, i.e., kinetic energy, to indicate how appropriate the particle is for the problem to be solved. The simulated annealing particle swarm optimization adds random factors on the basis of a greedy algorithm, namely a solution worse than the current solution is received with a certain probability, and the probability is dynamically and gradually reduced along with time. The simulated annealing particle swarm algorithm is also an algorithm for solving the optimization problem. The simulated annealing adopts Metropolis standard so that the simulated annealing has the characteristic of snap-through.
The invention integrates the idea that the preset probability in the simulated annealing particle swarm optimization gradually reduces along with time into the classical particle swarm optimization, thereby forming the risk avoiding method based on the particle swarm, and the advantage of integrating the simulated annealing particle swarm optimization into the particle swarm optimization is that once a local environment is entered in the algorithm optimization, the population particles can have the maximum probability to accept the poor-quality solution, thereby jumping out of the environment and achieving the purpose of optimization, and the later temperature is gradually reduced, thereby realizing the global optimal solution.
As shown in fig. 1, which is a flowchart for implementing the particle swarm-based risk avoiding method of the present invention, as shown in the figure, the particle swarm-based risk avoiding method provided by the present invention includes the following steps:
step S1: randomly initializing the number n of particles, and initializing the positions and speeds of the particles to obtain the position and speed information of the particles:
X i ＝[x i1 x 12 …x iD ]
v i ＝[v i1 v 12 … v 1D ]；
d represents a D-dimensional vector shared by the particles, and i represents the ith particle, and the value of the ith particle is between 1 and n.
Step S2: determining the fitness value of the particles according to the position and speed information of the particles to obtain the individual extreme value and the group extreme value of the particles in the current iteration period:
P i ＝[P i1 P 12 … P iD ]
P g ＝[P g1 P g2 … P gD ]。
and step S3: if the particles meet the iteration condition, performing steps S4-S5; if the particles do not meet the iteration condition, the iteration process is ended, and the final optimal solution is obtained according to all individual extremum and group extremum in all current iteration cycles.
And step S4: updating the position and the speed of the particle to obtain the position and the speed information of the particle in the next iteration period:
wherein,representing the value of the updated velocity of the particle in the m-th vector,a value representing the m-dimensional vector of the velocity before particle update;a value representing the updated position of the particle in the m-dimension vector;a value representing a position before particle update in the m-dimensional vector;representing the value of the individual extreme value before particle updating in the m-dimension vector;representing the value of the m-dimension vector of the extreme value of the population before particle updating;
t represents the time difference of one iteration cycle, c 1 And c 2 Respectively representing that the acceleration coefficient is a non-negative constant; r is 1 And r 2 Is a random constant ranging between (0, 1);
ω represents an inertial weight, and this value is decremented in each iteration cycle;
specifically, ω may be linearly weighted down:
wherein, ω is s Is an initial inertia weight, omega e Is the inertia weight when the iteration number is maximum, t is the current iteration number, t max Is the maximum number of iterations.
Alternatively, ω may also be non-linearly weighted down:
wherein, ω is s Is an initial inertia weight, omega e Is the inertia weight when the iteration number is maximum, t is the current iteration number, t max Is the maximum number of iterations, c 3 Is an adjusting parameter of the inertia weight, and the value is between (0, 1).
In the present invention, when updating the velocity of the particle, it is necessary to lock the velocity of the particle within a predetermined maximum velocity. Specifically, the speed of the particles in the horizontal direction is locked at a maximum value, so that the speed of the particles is locked within a preset maximum speed, that is, only the speed in the horizontal direction of the same height needs to be adjusted according to the risk avoidance principle of the aircraft, so that the aircraft has a maximum horizontal speed.
Step S5: comparing the position and speed information of the particles in the two iteration cycles in the step S2 and the step S4, if any one of the conditions that delta E is less than or equal to 0 or exp (-delta E/T) > rand (0, 1) is satisfied, executing the step S2 to the step S3 again by taking the position and speed information of the particles in the step S4 as the standard, and if any one of the conditions is not satisfied, executing the step S2 to the step S3 again by taking the position and speed information of the particles in the step S2 as the standard until the iteration is finished, and finding the optimal solution.
Wherein Δ E is a difference between the energy value corresponding to the particle after update and the energy value corresponding to the particle before update, and k isBoltzmann constant, T is the iterative temperature of the iterative period corresponding to the updated particle, and the calculation formula of the initialization temperature of the first iterative period is as follows: t is t 0 ＝f(p g )/ln5。
That is, the present invention accepts the degradation solution with a certain probability based on the Metropolis criterion (accepting new states with probability), thereby giving the algorithm a global optimization capability to escape local extrema and avoid premature convergence. For an annealing system, a new state j is generated from the current state i, and if E (i) > E (j), the new state j is accepted (Δ E = E (j) -E (i)), otherwise the new state j is accepted with a probability exp (- Δ E/kT), where k is the Boltzmann constant and T is the temperature. The core of the whole algorithm is to calculate the energy change of the system, namely Delta E, if the energy change is less than 0, the new movement will reduce the energy of the system, and then accept (the lower is more stable), if the energy change is more than 0, a random number alpha between 0 and 1 is generated and compared with exp (-Delta E/kT), if alpha > exp (-Delta E/kT), the new movement is rejected, otherwise, the new movement is accepted, and the degradation solution is accepted with a certain probability.
The invention further provides a risk avoiding method for the flyer, which comprises the following steps: inputting parameter information of the flyer in the flying state into a computer; the computer then adopts the risk avoiding method based on the particle swarm to calculate to obtain operation information; then, the flying object flies according to the operation information. The input parameter information includes the speed of the flying object and the surrounding environment of the flying object, specifically, the maximum speed of the flying object limits the maximum speed of the particles, the surrounding environment of the flying object can be the actual environment around the flying object known by radar or a pre-fabricated electronic map, all fixed and moving obstacles are regarded as damaged particles, and the particles can be automatically avoided when a risk avoidance algorithm is performed.
The particle swarm based risk avoiding method and the flight object risk avoiding method provided by the invention combine the advantages of a classical particle swarm algorithm and a simulated annealing particle swarm algorithm, can improve the safety of the unmanned aerial vehicle in executing tasks in a complex airspace environment, reduce the collision danger caused by the fact that the unmanned aerial vehicle cannot effectively avoid fixed ground obstacles and other aerial vehicles in the air in the flight process, enable the unmanned aerial vehicle and the manned aircraft to share an airspace to be possible, and can provide effective guarantee for the unmanned aerial vehicle to safely and smoothly execute various tasks.
Although the present invention has been described with reference to the preferred embodiments, it should be understood that the scope of the present invention is not limited thereto, and those skilled in the art will appreciate that various changes and modifications can be made without departing from the spirit and scope of the present invention.
Claims (9)
1. A particle swarm-based risk avoiding method is characterized by comprising the following steps:
step S1: randomly initializing the number n of particles, and initializing the positions and the speeds of the particles to obtain the position and speed information of the particles;
step S2: obtaining an individual extreme value and a group extreme value of the particles in the current iteration period according to the position and speed information of the particles;
and step S3: if the particles meet the iteration condition, performing steps S4-S5; if the particles do not meet the iteration condition, ending the iteration process, and obtaining the final optimal solution according to all individual extrema and group extrema in all current iteration cycles;
and step S4: updating the position and the speed of the particle to obtain the position and the speed information of the particle in the next iteration period;
step S5: comparing the position and speed information of the particles in the two iteration cycles in the step S2 and the step S4, if any one of delta E ≦ 0 or exp (-delta E/T) > rand (0, 1) is satisfied, performing the steps S2-S3 again based on the position and speed information of the particles in the step S4, and if any one of the above conditions is not satisfied, performing the steps S2-S3 again based on the position and speed information of the particles in the step S2;
in step S1, the position information and the speed information of the particles are respectively:
X i ＝[x i1 x 12 … x iD ]
v i ＝[v i1 v 12 … v iD ]
d represents a particle total D-dimension vector, i represents an ith particle, and the value of the ith particle is between 1 and n;
Δ E is the difference between the energy corresponding to the particle state in step S4 and the energy corresponding to the particle state in step S2, k is the boltzmann constant, and T is the iteration temperature in the iteration cycle corresponding to step S4.
2. The particle swarm-based risk avoiding method according to claim 1, wherein: in the step S2, the individual extremum and the group extremum of the particle are respectively
P i ＝[P i1 P 12 … P iD ]
P g ＝[P g1 P g2 … P gD ]
D represents a D-dimensional vector shared by the particles, i represents the ith particle, and the value of the ith particle is between 1 and n; and the individual extreme value and the group extreme value are calculated through the fitness value of the particles.
3. The particle swarm-based risk avoiding method according to claim 1, wherein: in step S4, the position and velocity update formula of the particle is:
wherein,representing the value of the updated velocity of the particle in the m-th vector,a value representing the m-dimensional vector of the velocity before particle update;a value representing the updated position of the particle in the m-dimension vector;a value representing a position before particle update in the m-dimensional vector;representing the value of the individual extreme value before particle updating in the m-dimension vector;representing the value of the m-dimension vector of the extreme value of the population before particle updating;
t represents the time difference of one iteration cycle, c 1 And c 2 Respectively representing that the acceleration coefficient is a non-negative constant; r is a radical of hydrogen 1 And r 2 Is a random constant ranging between (0, 1);
ω represents the inertial weight and this value is decremented in each iteration cycle.
4. The particle swarm-based risk avoiding method according to claim 3, wherein: in step S4, the speed of the particle is locked within a predetermined maximum speed when the speed of the particle is updated.
5. The particle swarm-based risk avoidance method of claim 4, wherein: in step S4, the velocity of the particle is locked within a predetermined maximum velocity by locking the velocity of the particle in the horizontal direction at a maximum value when updating the velocity of the particle.
6. A particle swarm-based risk avoidance method according to claim 3, wherein: the formula for ω is:
wherein, ω is s Is an initial inertia weight, omega e Is the inertia weight when the iteration number is maximum, t is the current iteration number, t max Is the maximum number of iterations.
7. The particle swarm-based risk avoiding method according to claim 3, wherein: the formula for ω is:
wherein, ω is s Is an initial inertia weight, omega e Is the inertia weight when the iteration number is maximum, t is the current iteration number, t max Is the maximum number of iterations, c 3 Is an adjusting parameter of the inertia weight, and the value is between (0, 1).
8. A risk avoiding method for a flying object is characterized by comprising the following steps: inputting parameter information of the flying object in the flying state into a computer; the computer then adopts the risk avoiding method based on the particle swarm as claimed in any one of claims 1 to 6 to calculate to obtain operation information; then, the flying object flies according to the operation information.
9. A method as claimed in claim 8, wherein: the parameter information of the flyer comprises the speed of the aircraft and the environment where the aircraft is located.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711426543.XA CN107992936A (en) | 2017-12-26 | 2017-12-26 | The hedging method of hedging method and flying object based on population |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711426543.XA CN107992936A (en) | 2017-12-26 | 2017-12-26 | The hedging method of hedging method and flying object based on population |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107992936A true CN107992936A (en) | 2018-05-04 |
Family
ID=62042884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711426543.XA Withdrawn CN107992936A (en) | 2017-12-26 | 2017-12-26 | The hedging method of hedging method and flying object based on population |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107992936A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005651A (en) * | 2015-07-09 | 2015-10-28 | 北京航空航天大学 | Gradient separate zone optimization design method for spacecraft pulse rendezvous trajectory |
| CN106228234A (en) * | 2016-07-20 | 2016-12-14 | 浙江工业大学 | Multi-target particle swarm optimization method based on gradient descent method |
| CN107272403A (en) * | 2017-06-14 | 2017-10-20 | 浙江师范大学 | A kind of PID controller parameter setting algorithm based on improvement particle cluster algorithm |
| US20170364816A1 (en) * | 2017-08-29 | 2017-12-21 | aWhere, Inc. | Prediction of Discernible Fungus Establishment on a Crop |
-
2017
- 2017-12-26 CN CN201711426543.XA patent/CN107992936A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005651A (en) * | 2015-07-09 | 2015-10-28 | 北京航空航天大学 | Gradient separate zone optimization design method for spacecraft pulse rendezvous trajectory |
| CN106228234A (en) * | 2016-07-20 | 2016-12-14 | 浙江工业大学 | Multi-target particle swarm optimization method based on gradient descent method |
| CN107272403A (en) * | 2017-06-14 | 2017-10-20 | 浙江师范大学 | A kind of PID controller parameter setting algorithm based on improvement particle cluster algorithm |
| US20170364816A1 (en) * | 2017-08-29 | 2017-12-21 | aWhere, Inc. | Prediction of Discernible Fungus Establishment on a Crop |
Non-Patent Citations (5)
| Title |
|---|
| 孙致远 等: "基于改进粒子群算法的自动机性能评估", 《火力与指挥控制》 * |
| 戴月明 等: "核矩阵协同进化的震荡搜索粒子群优化算法", 《重庆邮电大学学报（自然科学版）》 * |
| 甄然 等: "基于改进粒子群算法的飞行器冲突解脱方法研究", 《河北科技大学学报》 * |
| 翟淑宁: "基于Metropolis准则粒子群算法的电力系统无功优化", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
| 马国庆 等: "学习因子和时间因子随权重调整的粒子群算法", 《计算机应用研究》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110456823B (en) | Double-layer path planning method aiming at unmanned aerial vehicle calculation and storage capacity limitation | |
| CN112880688B (en) | Unmanned aerial vehicle three-dimensional track planning method based on chaotic self-adaptive sparrow search algorithm | |
| CN111950873A (en) | Satellite real-time guiding task planning method and system based on deep reinforcement learning | |
| CN111077909B (en) | Novel unmanned aerial vehicle self-group self-consistent optimization control method based on visual information | |
| CN114594788B (en) | Four-rotor unmanned aerial vehicle track planning method and system in unknown environment | |
| CN111880574B (en) | Unmanned aerial vehicle collision avoidance method and system | |
| CN114840020A (en) | Unmanned aerial vehicle flight path planning method based on improved whale algorithm | |
| CN112414405A (en) | Unmanned aerial vehicle cluster flight path planning method considering emergency task of DSM | |
| CN115060263A (en) | Flight path planning method considering low-altitude wind and energy consumption of unmanned aerial vehicle | |
| CN114089776B (en) | Unmanned aerial vehicle obstacle avoidance method based on deep reinforcement learning | |
| CN111256681A (en) | Unmanned aerial vehicle group path planning method | |
| CN113671825A (en) | Maneuvering intelligent decision missile avoidance method based on reinforcement learning | |
| CN109870906A (en) | A kind of high-speed rotor aircraft paths planning method based on BBO optimization Artificial Potential Field | |
| CN115903888A (en) | Rotor unmanned aerial vehicle autonomous path planning method based on longicorn swarm algorithm | |
| CN115454115A (en) | Rotor unmanned aerial vehicle path planning method based on hybrid wolf-particle swarm algorithm | |
| CN115525063A (en) | Trajectory planning method for unmanned helicopter | |
| CN114967732A (en) | Method and device for formation and aggregation of unmanned aerial vehicles, computer equipment and storage medium | |
| CN117806346A (en) | Unmanned plane path planning method based on self-adaptive dung beetle optimizer | |
| Wu et al. | Multi-phase trajectory optimization for an aerial-aquatic vehicle considering the influence of navigation error | |
| CN116400718A (en) | Unmanned aerial vehicle short-distance air combat maneuver autonomous decision-making method, system, equipment and terminal | |
| CN114721423B (en) | Distribution method for multi-unmanned aerial vehicle to cooperatively reach preset target in consideration of collision avoidance constraint | |
| CN107992936A (en) | The hedging method of hedging method and flying object based on population | |
| CN116755463A (en) | Path planning method, equipment and storage medium for inspection of power transmission line by unmanned aerial vehicle | |
| CN116203990A (en) | Unmanned plane path planning method and system based on gradient descent method | |
| CN114815875B (en) | Unmanned aerial vehicle cluster formation controller parameter adjustment method based on intelligent optimization of integrated fully-shooting pigeon clusters |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180504 |