CN109947129A - Rotor wing unmanned aerial vehicle paths planning method based on Dijkstra and improvement particle swarm algorithm - Google Patents
Rotor wing unmanned aerial vehicle paths planning method based on Dijkstra and improvement particle swarm algorithm Download PDFInfo
- Publication number
- CN109947129A CN109947129A CN201910246693.5A CN201910246693A CN109947129A CN 109947129 A CN109947129 A CN 109947129A CN 201910246693 A CN201910246693 A CN 201910246693A CN 109947129 A CN109947129 A CN 109947129A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- rotor wing
- particle
- wing unmanned
- 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
Abstract
The invention discloses a kind of based on Dijkstra and improves the rotor wing unmanned aerial vehicle paths planning method of particle swarm algorithm, comprising steps of 1) pass through contrast echo wave sensor and laser sensor, suitable distance measuring sensor is selected for measuring distance and the direction of unmanned plane peripheral obstacle, constructs the global map of flight environment of vehicle；2) according to global map, the feasible path of a plurality of rotor wing unmanned aerial vehicle flight is planned using Dijkstra method；3) traditional particle swarm algorithm is improved, global optimum path is searched for using improved particle swarm optimization algorithm, and generate optimal path figure；The present invention detects environment by laser sensor and constructs global map, Dijkstra and improved particle swarm optimization algorithm are combined, hunt out the global optimum path for being conducive to rotor wing unmanned aerial vehicle flight, effectively realize the path planning function of unmanned plane, so that the accurate avoidance of rotor wing unmanned aerial vehicle, safe flight.
Description
Technical field
The present invention relates to the technical fields of consumer level unmanned plane safe flight, refer in particular to one kind based on Dijkstra and change
Into the rotor wing unmanned aerial vehicle paths planning method of particle swarm algorithm.
Background technique
With the raising of science and technology and economic level, rotor wing unmanned aerial vehicle is widely used to every field.Except early stage army
Thing prospecting is outer, and unmanned plane has been widely used in video display and has taken photo by plane, geological prospecting, agricultural irrigation, line maintenance, and environmental monitoring is gloomy
The fields such as woods fire prevention.More stringent requirements are proposed for these safety and reliabilities of application to unmanned plane.How unmanned plane passes through
Autonomous flight realizes that avoidance is current research hotspot.In order to realize barrier avoiding function, two parts, the first step can be classified as
It is flight environment of vehicle detection, second step is Obstacle avoidance.
The distance measuring sensor that Vehicles Collected from Market is used to detect barrier mainly has four classes, is ultrasonic sensor respectively, infrared
Sensor, laser sensor and visual sensor.Herein using ultrasonic sensor MB1043 and laser sensor TFMini into
Row comparison, finds out the distance measuring sensor for being most suitable for detection of obstacles.
After flight environment of vehicle detection is realized, just start to carry out path planning.There are many methods, such as grid for legacy paths planning
Method, graph search method, Artificial Potential Field Method etc..Dijkstra method is utilized herein, searches out a feasible path.But due to initial point
Limitation, it is not necessarily global optimum path.Therefore, it also needs to realize global optimum's route searching using optimization algorithm.It is existing
There are many some intelligent algorithms, such as genetic algorithm, ant group optimization, ant colony algorithm, neural network, particle swarm optimization algorithm etc..
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, propose a kind of based on Dijkstra and improvement population
The rotor wing unmanned aerial vehicle paths planning method of algorithm detects environment by TFMini laser sensor and constructs global map, will
Dijkstra and improved particle swarm optimization algorithm combine, and hunt out the global optimum road conducive to rotor wing unmanned aerial vehicle flight
Diameter effectively realizes the path planning function of unmanned plane, so that the accurate avoidance of rotor wing unmanned aerial vehicle, safe flight.Simulation result
Show that proposed rotor wing unmanned aerial vehicle Robot dodge strategy can obtain ideal global optimum path, effectively realization rotor wing unmanned aerial vehicle
Path planning function so that the accurate avoidance of rotor wing unmanned aerial vehicle, safe flight.
To achieve the above object, technical solution provided by the present invention are as follows: based on Dijkstra and improve particle swarm algorithm
Rotor wing unmanned aerial vehicle paths planning method, comprising the following steps:
1) by contrast echo wave sensor and laser sensor, suitable distance measuring sensor is selected for measuring unmanned plane
The distance of peripheral obstacle and direction construct the global map of flight environment of vehicle；
2) according to global map, the feasible path of a plurality of rotor wing unmanned aerial vehicle flight is planned using Dijkstra method；
3) traditional particle swarm algorithm is improved, global optimum road is searched for using improved particle swarm optimization algorithm
Diameter, and optimal path figure is generated, it is specific as follows:
In view of in conventional particle group's algorithm, the w of Inertia Weight is set as constant, for the optimization of accelerated particle group's algorithm
Speed preferably converges on globally optimal solution, in modified particle swarm optiziation, Inertia Weight w has been set separately and has linearly been declined
Subtraction function and nonlinear attenuation function:
The Inertia Weight of classical particle colony optimization algorithm:
W=C
In formula, C is constant；
The Inertia Weight of particle swarm optimization algorithm after improvement:
W=k* θi
In formula, k is proportionality coefficient, and θ is particle iteration radix, and i is particle the number of iterations；
Global optimum path is searched in resulting path tree using improved particle swarm optimization algorithm are as follows:
vid(t+1)=w*vid(t)+c1r1(pid(t)-xid(t))+c2r2(pgd(t)-xid(t))
xid(t+1)=vid(t+1)+xid(t)
In formula, vid(t) be particle i velocity vector in the t times iteration d dimensional vector, xidIt (t) is particle i at the t times
The d dimensional vector of position vector, p when iterationid(t) be particle i optimal location vector in the t times iteration d dimensional vector, pgd(t)
It is the optimal location of entire population, c1And c2It is the aceleration pulse for adjusting particle Learning Step, r1And r2It is between 0 to 1
Equally distributed random number, to increase the randomness of search, w is Inertia Weight, for the search range of adjustment algorithm.
In step 1), ultrasonic sensor MB1043 and laser sensor TFMini are compared, selectes and uses laser
Sensor TFMini measures direction and the distance of barrier, carries out barrier perception to the global context where rotor wing unmanned aerial vehicle,
Establish the global map of rotor wing unmanned aerial vehicle flight environment of vehicle.
In step 2), in conjunction with the constructed flight environment of vehicle global map of laser sensor perception, by Dijkstra method
Applied to the search of feasible path, the feasible path of a plurality of rotor wing unmanned aerial vehicle flight is planned, comprising the following steps:
2.1) operating radius for considering rotor wing unmanned aerial vehicle, while the kinetic model for establishing quadrotor drone, barrier
Hinder object to be also modeled as circle, the safe distance between unmanned plane and barrier is set；
2.2) the flight starting point and final of rotor wing unmanned aerial vehicle are established in global map；
2.3) the distance between all the points and starting point are calculated, signal source shortest path problem is solved using Dijkstra method,
Finally obtain feasible path tree.
Compared with prior art, the present invention have the following advantages that with the utility model has the advantages that
1, by the various types of distance measuring sensors of comparative analysis, laser sensor TFMini, range accuracy are finally selected
Height, moderate, cost performance is high.
2, this method blends Dijkstra method and particle swarm algorithm, after generating feasible path tree, with grain
Swarm optimization filters out its optimal path.Algorithm the convergence speed is fast, practical.
3, this method improves particle swarm algorithm, and by experimental analysis, successfully demonstrates improvement particle swarm algorithm
More preferably global solution can be obtained.
4, this method has broad prospects in the application of consumer level unmanned plane path planning, and algorithm parameter is few, structure letter
Single, route searching speed is fast, adaptable.
Detailed description of the invention
Fig. 1 is logical flow diagram of the present invention.
Fig. 2 is laser sensor range performance figure.
Fig. 3 is the global map of flight environment of vehicle.
Boundary condition schematic diagram when Fig. 4 is Dijkstra approach application.
Fig. 5 is to improve particle swarm algorithm flow chart.
Fig. 6 is that particle swarm optimization algorithm improves front and back optimal path generation figure.
Fig. 7 is algorithm fitness function curve graph.
Specific embodiment
The present invention is further explained in the light of specific embodiments.
As shown in Figures 1 to 7, provided by the present embodiment based on Dijkstra and improve particle swarm algorithm rotor nobody
Machine paths planning method has used the equipment such as quadrotor drone, ultrasonic sensor and laser sensor comprising following step
It is rapid:
1) by contrast echo wave sensor and laser sensor, suitable distance measuring sensor is selected for measuring unmanned plane
The distance of peripheral obstacle and direction construct the global map of flight environment of vehicle, wherein the ultrasonic sensor and laser sensing
Device is respectively MB1043 and TFMini, is specifically compared as shown in table 1 to the carry out performance parameter of the sensor:
1 two kinds of sensor performance parameters of table
Secondly, being tested respectively to two kinds of practical range performances of sensor.The experimental results showed that ultrasonic sensor
Effective measurement distance of MB1043 and laser sensor TFMini is respectively 3.6m and 6.5m or more.Meanwhile ultrasonic sensor
It is unstable in ranging process, it is easily lost signal.And it is based on the laser sensor of flight time telemetry (TOF) principle
TFMini will not lead to the problem of similar.For these reasons, direction and the distance of TFMini sensor measurement barrier are selected.
Experiment porch is a quadrotor drone, and there are three TFMini sensors for front side dress, and utilize third party software
Mission Planner earth station can observe its state of flight.As Fig. 2 is obtained from the ground Mission Planner
The laser sensor actual performance figure stood, it shows that laser sensor is detecting barrier.The data and reality of sensor measurement
Border data are identical, it means that laser sensor TFMini can accurately measure distance and the direction of barrier.According to laser
The resulting obstacle distance of sensor measurement and direction, model the global map of flight environment of vehicle.
2) Dijkstra method is applied to feasible by the flight environment of vehicle global map for combining laser sensor perception constructed
The feasible path of a plurality of rotor wing unmanned aerial vehicle flight is planned in the search in path, comprising the following steps:
2.1) operating radius for considering rotor wing unmanned aerial vehicle, while the kinetic model for establishing quadrotor drone, barrier
Hinder object to be also modeled as circle, the safe distance between unmanned plane and barrier is set；
2.2) the flight starting point S and final D of rotor wing unmanned aerial vehicle are established in global map；
2.3) the distance between all the points and starting point are calculated, signal source shortest path problem is solved using Dijkstra method,
Finally obtain feasible path tree.The Dijkstra method is applied to the search of active path, and specific method is explained as follows: first
First, other than starting point S and terminal D, there are also the point of some random distributions in environment, the line of these points is connected through entire environment.
Therefore, it is necessary to calculate the distance between all the points and starting point S.When tie point j and starting point S passes through bowlder, this explanation cannot
It is directly connected to starting point S, distance is infinitely great.If the line between fruit dot j and starting point S does not contact circle, then need to update newest
Distance dj。
After the distance between each point and starting point S has been calculated, shortest distance dkIt is known that therefore point k become one it is new
Starting point.Calculating the distance between each point and point k is identical mode.If distance dk+ dist [k, l] < dl, then distance dlIt needs
It is updated to newest distance, otherwise distance dlIt remains unchanged.Then, starting point is defined as the second short distance point, by above-mentioned side
Formula computes repeatedly, until having updated all the points to the distance of starting point.
Wherein j, k are the point of random distribution in modeling environment, dj, dkIt is point j, the distance between k and starting point, dlFor string away from,
Dist [k, l] is the linear distance between point k and point l.
In application Dijkstra method searching route, it is very crucial for determining whether unmanned plane encounters barrier.When
On unmanned aerial vehicle when barrier, path is also useless, even if it is shortest route.Therefore, defining impact conditions is obstacle
The core of detection.As shown in figure 4, there are two kinds of situations of unmanned plane and barrier collision.If the endpoint of any one line segment exists
In circle, path is obviously infeasible.In this case it is necessary to measure center to each line segment endpoint distance.If from circle
Center to endpoint distance be less than circle radius, then path is inappropriate.Such case can be indicated with following equations:
Wherein (xk,yk) be straight line extreme coordinates, (Xn,Yn) it is round centre coordinate rnIt is round radius.If line segment
Endpoint it is outer in circle, but line segment has already passed through circle, this is corresponding with another situation, and two aspects need to discuss at this time.One side
Face needs to calculate string away from dlAnd dm, it is evident that away from both less than corresponding radius, but for circle m, only line segment prolongs the two strings
Long line passes through circle.It on the other hand, is that circle is passed through by the extended line of circle or line segment to distinguish line segment, it is necessary to calculate and hang down
Foot.If intersection point be between the endpoint of line segment, it mean path be it is useless, otherwise it is exactly a feasible path.
In the latter case, if line segment meets following three condition, which is inappropriate.
(x in formulai,yi), (xj,yj) be respectively both ends endpoint coordinate value, XlAnd YlFor the centre coordinate value of circle l, A=
yj-yi, B=- (xj-xi), C=yi*(xj-xi)-xi*(yj-yi)。
3) by analyzing various optimal methods, final select is searched in resulting path tree using particle swarm optimization algorithm
Seek global optimum path:
vid(t+1)=w*vid(t)+c1r1(pid(t)-xid(t))+c2r2(pgd(t)-xid(t))
xid(t+1)=vid(t+1)+xid(t)
In formula, vid(t) be particle i velocity vector in the t times iteration d dimensional vector, xidIt (t) is particle i at the t times
The d dimensional vector of position vector, p when iterationid(t) be particle i optimal location vector in the t times iteration d dimensional vector, pgd(t)
It is the optimal location of entire population, c1And c2It is the aceleration pulse for adjusting particle Learning Step, r1And r2It is between 0 to 1
Equally distributed random number, to increase the randomness of search, w is Inertia Weight, for the search range of adjustment algorithm.
In view of in conventional particle group's algorithm, the w of Inertia Weight is set as constant.For the optimization of accelerated particle group's algorithm
Speed preferably converges on globally optimal solution, in modified particle swarm optiziation, Inertia Weight w has been set separately and has linearly been declined
Subtraction function and nonlinear attenuation function:
The Inertia Weight of classical particle colony optimization algorithm:
W=C
In formula, C is constant.
The Inertia Weight of particle swarm optimization algorithm after improvement:
W=k* θi
In formula, k is proportionality coefficient, and θ is particle iteration radix, and i is particle the number of iterations.
Particle swarm optimization algorithm is a kind of evolution algorithm.By simulating birds foraging behavior, optimal solution t is obtained.Optimization is asked
Topic can be found in search space.In the initialization procedure of modified particle swarm optiziation, each particle have one it is initial
State determines its speed and position.In search process, each particle will be according to the history optimum position p of particle itselfidWith
Entire public history optimum position pgdUpdate its speed.For particle, there are velocity interval limitation and position range limitation, with true
Particle is protected always to search in solution space.However, Inertia Weight w is the weaker constant of Algorithm Convergence under canonical form.?
Convergent early stage it is expected that Inertia Weight w is bigger, often to accelerate convergence rate.In the convergent later period, especially work as particle
When near optimal solution pair, the available better optimal solution of smaller w.In short, Inertia Weight w needs to be configured to one
A attenuation function, to find better global path.
Using particle group optimizing formula, the Inertia Weight for improving front and back is substituted into respectively, wherein w1It is set as constant, w2It is set as line
Property attenuation function, w3It is set as nonlinear attenuation function.By emulation experiment, classical particle swarm algorithm (w is found1) with it is improved
Particle swarm algorithm (w2,w3) it can generate the path for meeting flying condition.Wherein, the road that classical particle swarm algorithm generates
Diameter and the path difference that modified particle swarm optiziation generates are obvious.
It can be seen that from fitness curve when the negated linear fading function of Inertia Weight w, the value of fitness function is most
Small.This demonstrate modified particle swarm optiziations can generate the path for being better than conventional particle group algorithm, this also demonstrates this
The practicability and reasonability of invention.
In conclusion the present invention has provided newly for unmanned plane in the flight of complex environment after using above scheme
Obstacle avoidance method realizes that Dijkstra method is blended with particle swarm optimization algorithm, fast in a plurality of feasible path of generation
Speed filters out an optimal path, and is improved traditional particle swarm optimization algorithm, seeks out global optimum path all over,
With actual promotional value, it is worthy to be popularized.
Embodiment described above is only the preferred embodiments of the invention, and but not intended to limit the scope of the present invention, therefore
All shapes according to the present invention change made by principle, should all cover in protection scope of the present invention.
Claims (3)
1. based on Dijkstra and improve particle swarm algorithm rotor wing unmanned aerial vehicle paths planning method, which is characterized in that including with
Lower step:
1) by contrast echo wave sensor and laser sensor, suitable distance measuring sensor is selected for measuring around unmanned plane
The distance of barrier and direction construct the global map of flight environment of vehicle；
2) according to global map, the feasible path of a plurality of rotor wing unmanned aerial vehicle flight is planned using Dijkstra method；
3) traditional particle swarm algorithm is improved, global optimum path is searched for using improved particle swarm optimization algorithm,
And optimal path figure is generated, it is specific as follows:
In view of in conventional particle group's algorithm, the w of Inertia Weight is set as constant, for the optimization speed of accelerated particle group's algorithm
Degree, preferably converges on globally optimal solution, in modified particle swarm optiziation, linear attenuation has been set separately in Inertia Weight w
Function and nonlinear attenuation function:
The Inertia Weight of classical particle colony optimization algorithm:
W=C
In formula, C is constant；
The Inertia Weight of particle swarm optimization algorithm after improvement:
W=k* θi
In formula, k is proportionality coefficient, and θ is particle iteration radix, and i is particle the number of iterations；
Global optimum path is searched in resulting path tree using improved particle swarm optimization algorithm are as follows:
vid(t+1)=w*vid(t)+c1r1(pid(t)-xid(t))+c2r2(pgd(t)-xid(t))
xid(t+1)=vid(t+1)+xid(t)
In formula, vid(t) be particle i velocity vector in the t times iteration d dimensional vector, xidIt (t) is particle i in the t times iteration
The d dimensional vector of position vector, pid(t) be particle i optimal location vector in the t times iteration d dimensional vector, pgdIt (t) is entire
The optimal location of population, c1And c2It is the aceleration pulse for adjusting particle Learning Step, r1And r2It is uniformly to divide between 0 to 1
The random number of cloth, to increase the randomness of search, w is Inertia Weight, for the search range of adjustment algorithm.
2. the rotor wing unmanned aerial vehicle path planning side according to claim 1 based on Dijkstra and improvement particle swarm algorithm
Method, it is characterised in that: in step 1), ultrasonic sensor MB1043 and laser sensor are made into TFMini comparison, it is selected to make
Direction and distance with laser sensor TFMini measurement barrier, carry out barrier to the global context where rotor wing unmanned aerial vehicle
Perception, establishes the global map of rotor wing unmanned aerial vehicle flight environment of vehicle.
3. the rotor wing unmanned aerial vehicle path planning side according to claim 1 based on Dijkstra and improvement particle swarm algorithm
Method, it is characterised in that:, will in conjunction with the constructed flight environment of vehicle global map of laser sensor perception in step 2)
Dijkstra method is applied to the search of feasible path, plans the feasible path of a plurality of rotor wing unmanned aerial vehicle flight, including following step
It is rapid:
2.1) operating radius for considering rotor wing unmanned aerial vehicle, while the kinetic model for establishing quadrotor drone, barrier
It is also modeled as circle, the safe distance between unmanned plane and barrier is set；
2.2) the flight starting point and final of rotor wing unmanned aerial vehicle are established in global map；
2.3) the distance between all the points and starting point are calculated, signal source shortest path problem are solved using Dijkstra method, finally
Obtain feasible path tree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910246693.5A CN109947129A (en) | 2019-03-29 | 2019-03-29 | Rotor wing unmanned aerial vehicle paths planning method based on Dijkstra and improvement particle swarm algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910246693.5A CN109947129A (en) | 2019-03-29 | 2019-03-29 | Rotor wing unmanned aerial vehicle paths planning method based on Dijkstra and improvement particle swarm algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109947129A true CN109947129A (en) | 2019-06-28 |
Family
ID=67012779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910246693.5A Pending CN109947129A (en) | 2019-03-29 | 2019-03-29 | Rotor wing unmanned aerial vehicle paths planning method based on Dijkstra and improvement particle swarm algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109947129A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381284A (en) * | 2020-11-11 | 2021-02-19 | 成都信息工程大学 | Improved genetic algorithm for optimizing multi-station path of unmanned transfer vehicle |
| CN113049684A (en) * | 2021-03-23 | 2021-06-29 | 大连海洋大学 | Ultrasonic lamb wave defect signal identification method based on variational modal decomposition |
| CN113188547A (en) * | 2021-05-06 | 2021-07-30 | 国能朔黄铁路发展有限责任公司 | Unmanned aerial vehicle path planning method and device, controller and storage medium |
| CN117631689A (en) * | 2024-01-25 | 2024-03-01 | 成都航空职业技术学院 | Unmanned aerial vehicle obstacle avoidance flight method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104155974A (en) * | 2013-07-29 | 2014-11-19 | 深圳信息职业技术学院 | Path planning method and apparatus for robot fast collision avoidance |
| KR20150126265A (en) * | 2014-05-02 | 2015-11-11 | 조환 박 | An unmanned aerial system for creating aerial message |
| CN105527964A (en) * | 2015-12-28 | 2016-04-27 | 桂林电子科技大学 | Robot path planning method |
| CN105955273A (en) * | 2016-05-25 | 2016-09-21 | 速感科技（北京）有限公司 | Indoor robot navigation system and method |
| CN107356254A (en) * | 2017-06-07 | 2017-11-17 | 东南大学 | Suitable for the particle group optimizing method of geomagnetic auxiliary navigation trajectory planning |
| CN108664022A (en) * | 2018-04-27 | 2018-10-16 | 湘潭大学 | A kind of robot path planning method and system based on topological map |
-
2019
- 2019-03-29 CN CN201910246693.5A patent/CN109947129A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104155974A (en) * | 2013-07-29 | 2014-11-19 | 深圳信息职业技术学院 | Path planning method and apparatus for robot fast collision avoidance |
| KR20150126265A (en) * | 2014-05-02 | 2015-11-11 | 조환 박 | An unmanned aerial system for creating aerial message |
| CN105527964A (en) * | 2015-12-28 | 2016-04-27 | 桂林电子科技大学 | Robot path planning method |
| CN105955273A (en) * | 2016-05-25 | 2016-09-21 | 速感科技（北京）有限公司 | Indoor robot navigation system and method |
| CN107356254A (en) * | 2017-06-07 | 2017-11-17 | 东南大学 | Suitable for the particle group optimizing method of geomagnetic auxiliary navigation trajectory planning |
| CN108664022A (en) * | 2018-04-27 | 2018-10-16 | 湘潭大学 | A kind of robot path planning method and system based on topological map |
Non-Patent Citations (3)
| Title |
|---|
| 叶洪涛，等: "基于免疫粒子群算法的参数估计方法", 《自动化与仪表》 * |
| 王磊，杨思燕: "基于粒子群算法的电子地图路径规划软件设计", 《微型电脑应用》 * |
| 田思琪，郎百和，韩太林: "基于混沌-量子粒子群的分簇路由算法", 《吉林大学学报(信息科学版)》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381284A (en) * | 2020-11-11 | 2021-02-19 | 成都信息工程大学 | Improved genetic algorithm for optimizing multi-station path of unmanned transfer vehicle |
| CN112381284B (en) * | 2020-11-11 | 2023-12-01 | 成都信息工程大学 | Improved genetic algorithm for multi-station path optimization of unmanned connection vehicle |
| CN113049684A (en) * | 2021-03-23 | 2021-06-29 | 大连海洋大学 | Ultrasonic lamb wave defect signal identification method based on variational modal decomposition |
| CN113049684B (en) * | 2021-03-23 | 2023-07-28 | 大连海洋大学 | Ultrasonic lamb wave defect signal identification method based on variational modal decomposition |
| CN113188547A (en) * | 2021-05-06 | 2021-07-30 | 国能朔黄铁路发展有限责任公司 | Unmanned aerial vehicle path planning method and device, controller and storage medium |
| CN117631689A (en) * | 2024-01-25 | 2024-03-01 | 成都航空职业技术学院 | Unmanned aerial vehicle obstacle avoidance flight method |
| CN117631689B (en) * | 2024-01-25 | 2024-04-16 | 成都航空职业技术学院 | Unmanned aerial vehicle obstacle avoidance flight method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109947129A (en) | Rotor wing unmanned aerial vehicle paths planning method based on Dijkstra and improvement particle swarm algorithm | |
| CN109933086B (en) | Unmanned aerial vehicle environment perception and autonomous obstacle avoidance method based on deep Q learning | |
| CN106873599A (en) | Unmanned bicycle paths planning method based on ant group algorithm and polar coordinate transform | |
| CN111399541B (en) | Unmanned aerial vehicle whole-region reconnaissance path planning method of unsupervised learning type neural network | |
| CN109521794A (en) | A kind of multiple no-manned plane routeing and dynamic obstacle avoidance method | |
| CN103901892B (en) | The control method of unmanned plane and system | |
| CN109144102A (en) | A kind of Path Planning for UAV based on improvement bat algorithm | |
| CN102207736B (en) | Robot path planning method and apparatus thereof based on Bezier curve | |
| CN110031004A (en) | Unmanned plane static state and dynamic path planning method based on numerical map | |
| CN111240319A (en) | Outdoor multi-robot cooperative operation system and method thereof | |
| CN108897312A (en) | Lasting supervised path planing method of more unmanned vehicles to extensive environment | |
| KR20140076484A (en) | Tree metrology system | |
| CN109445456A (en) | A kind of multiple no-manned plane cluster air navigation aid | |
| CN108509820A (en) | Method for obstacle segmentation and device, computer equipment and readable medium | |
| CN110471426A (en) | Unmanned intelligent vehicle automatic Collision Avoidance method based on quantum wolf pack algorithm | |
| AU2022204569B2 (en) | Method for multi-agent dynamic path planning | |
| CN103697895A (en) | Method for determining optimal path of flight vehicle based on self-adaptive A star algorithm | |
| CN104406589B (en) | Flight method of aircraft passing through radar area | |
| CN108490939B (en) | Obstacle avoidance method of potential flow method under local perception capability | |
| CN115357031B (en) | Ship path planning method and system based on improved ant colony algorithm | |
| CN112666981A (en) | Unmanned aerial vehicle cluster dynamic route planning method based on dynamic group learning of original pigeon group | |
| Huan et al. | UAV path planning based on an improved ant colony algorithm | |
| Chen et al. | Obstacle avoidance strategy for quadrotor UAV based on improved particle swarm optimization algorithm | |
| Li et al. | Multi-mechanism swarm optimization for multi-UAV task assignment and path planning in transmission line inspection under multi-wind field | |
| CN108594241B (en) | A kind of AUV Sound stealth method for situation assessment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190628 |
|
| RJ01 | Rejection of invention patent application after publication |