CN117075484A - Underwater unmanned aerial vehicle return route planning method - Google Patents
Underwater unmanned aerial vehicle return route planning method Download PDFInfo
- Publication number
- CN117075484A CN117075484A CN202311344729.6A CN202311344729A CN117075484A CN 117075484 A CN117075484 A CN 117075484A CN 202311344729 A CN202311344729 A CN 202311344729A CN 117075484 A CN117075484 A CN 117075484A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- underwater unmanned
- individual
- planning
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000035772 mutation Effects 0.000 claims abstract description 24
- 230000033001 locomotion Effects 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- HOWHQWFXSLOJEF-MGZLOUMQSA-N systemin Chemical compound NCCCC[C@H](N)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](CC(O)=O)C(=O)OC(=O)[C@@H]1CCCN1C(=O)[C@H]1N(C(=O)[C@H](CC(O)=O)NC(=O)[C@H](CCCN=C(N)N)NC(=O)[C@H](CCCCN)NC(=O)[C@H](CO)NC(=O)[C@H]2N(CCC2)C(=O)[C@H]2N(CCC2)C(=O)[C@H](CCCCN)NC(=O)[C@H](CO)NC(=O)[C@H](CCC(N)=O)NC(=O)[C@@H](NC(=O)[C@H](C)N)C(C)C)CCC1 HOWHQWFXSLOJEF-MGZLOUMQSA-N 0.000 claims 1
- 108010050014 systemin Proteins 0.000 claims 1
- 230000033228 biological regulation Effects 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 230000014759 maintenance of location Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004088 simulation Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a method for planning a return path of an underwater unmanned aerial vehicle, which belongs to the technical field of navigation, electric digital data processing and general control or regulation systems and is used for planning the return path of the underwater unmanned aerial vehicle, and comprises the steps of obtaining a rough curve of a motion track of the underwater unmanned aerial vehicle under a certain azimuth angle and a certain pitch angle according to the sub-speeds of the underwater unmanned aerial vehicle in three directions under the action of water flow, initializing parameter setting by a differential evolution algorithm, initializing a first generation population and defining a fitness function; recording individuals with the minimum fitness value in the primary population, and performing mutation and crossover operations, individual evaluation selection operations and iterative control methods; and when the final solution meets the threshold value, obtaining the optimal return azimuth angle, pitch angle and path. According to the method, a kinematic equation of the underwater unmanned aerial vehicle is constructed, and the influence of environmental factors on a path is considered; the algorithm is improved, the accuracy and the convergence speed are increased, global searching capability and local individual feature retention are achieved, the optimal solution is found, and the method is suitable for more situations.
Description
Technical Field
The invention discloses a method for planning a return path of an underwater unmanned aerial vehicle, and belongs to the technical field of navigation, electric digital data processing and general control or regulation systems.
Background
With the development of technology, unmanned aerial vehicle technology is rapidly developed and widely applied, and the unmanned aerial vehicle can be applied to the ground and underwater. The underwater unmanned aerial vehicle has the characteristics of long voyage, long endurance, high flexibility and the like, and has wide application in the aspects of ocean resource development, underwater target search, underwater operation and the like. The underwater robot can travel in the ocean with different depths, can finish various works such as information detection, resource development, undersea salvage and the like, and after the existing underwater unmanned aerial vehicle is manually controlled to work at a designated position, the existing underwater unmanned aerial vehicle can return according to a preset return route, the return route is single, the influence of various environments such as water flow, pressure, water depth and the like can be received in actual conditions, and when the unmanned aerial vehicle needs to return to a moving return point, the return reliability can be greatly reduced, so that the demand for unmanned aerial vehicle track planning is more and more urgent. Through simulation, the initial position of the unmanned aerial vehicle is input into a three-dimensional coordinate system, the motion track of the return point is set, the three-dimensional track path of the unmanned aerial vehicle is planned, a proper azimuth angle and a proper pitch angle are searched, the optimal return path is planned, and whether the unmanned aerial vehicle can meet smoothly is judged, so that the reliability of the underwater unmanned aerial vehicle is improved.
For digital simulation, the traditional linear iterative simulation method needs to construct a motion track equation of the unmanned aerial vehicle, then randomly set a meeting point coordinate and start iterative operation. The linear iteration method generally needs to be iterated for many times to achieve convergence, and under different departure angles, the motion track equation of the unmanned aerial vehicle is changed, so that the time cost of simulation calculation is high. The linear iteration method is easy to fall into a local optimal solution when searching the optimal solution, and the linear iteration method simplifies a model and a control strategy, so that the linear iteration method can not jump out of the local optimal solution and can not find a global optimal solution. The linear iteration method needs to set an initial condition, and the selection of parameters has a relatively large influence on the accuracy of iteration, so that inaccurate or unstable return trajectory can be caused if the parameters are selected improperly. Therefore, the simulation algorithm needs to be improved, so that the simulation speed is high, the precision is high, and the simulation algorithm can adapt to more complex conditions.
Disclosure of Invention
The invention aims to provide a method for planning a return path of an underwater unmanned aerial vehicle, which aims to solve the problems that in the prior art, the speed of planning and resolving the return path of the unmanned aerial vehicle is low and an optimal solution is not easy to find.
A method for planning a return path of an underwater unmanned aerial vehicle comprises the following steps:
s1, constructing an underwater unmanned aerial vehicle dynamics equation and setting initial parameters;
s2, according to a dynamics equation and initial parameters of the underwater unmanned aerial vehicle, obtaining the sub-speeds of the underwater unmanned aerial vehicle in the x, y and z directions under the action of water flow, and obtaining a motion track curve of the underwater unmanned aerial vehicle under a certain azimuth angle and a certain pitch angle according to the sub-speeds;
s3, initializing parameter setting by a differential evolution algorithm;
s4, initializing a first generation population;
s5, defining a fitness function；
S6, recording individuals with the minimum fitness value in the primary population;
s7, mutation and crossover operation;
s8, individual evaluation;
s9, selecting operation;
s10, an iteration control method;
s11, when the final solution meets a threshold value, setting the following conditions in the path optimizing planning, and completing the path optimizing planning to obtain the optimal return azimuth angle, pitch angle and path:
。
constructing a kinetic equation under an underwater unmanned aerial vehicle body coordinate system:
；
in the method, in the process of the invention,，/>，/>for the components of the speed of the unmanned aerial vehicle in the body coordinate system for three axes, t represents time, +.>The rolling angle speed, the yaw angle speed and the pitch angle speed of the unmanned aerial vehicle are respectively, P is the thrust of the engine of the unmanned aerial vehicle, and +.>Respectively the pitch angle, the yaw angle and the roll angle of the unmanned aerial vehicle, m is the mass of the unmanned aerial vehicle, g is the gravitational acceleration,/g>Resistance, lift force and force measurement which are respectively decomposed by water flow power>The angle of attack and sideslip, respectively, of the unmanned vehicle's voyage.
Initial setting of population300, maximum iteration number->200, the number of required parameters isUpper limit set of azimuth and pitch angles->Lower limit set of azimuth and pitch angles->，/>And->Respectively represent the upper and lower limits of azimuth angle, +.>And->Representing the upper and lower limits of the pitch angle, respectively.
；
In the middle ofStore the ith individual in the representative generation population +.>The parameters of the parameters are set to be,，/>，/>is section->Is a random number of (a) and (b),the +.f representing the lower set of azimuth and pitch angles>Element(s)>The +.f. representing the set of azimuth and pitch upper limits>The elements.
When the return point makes uniform linear motion, the initial position of the return point is set，/>，/>) The movement speed is%，/>，/>) In->At time, there is a position of return point +.>；
In the middle of (a)，/>，/>) At t 0 Returning the position of the navigation point at moment;
initial position of underwater unmanned plane,/>,/>) The unmanned aerial vehicle is obtained by the dynamics equation of the underwater unmanned aerial vehicle at any +.>The time speed is (+)>,/>,/>) Then the unmanned aerial vehicle is at t 0 Time position；
In the middle of (a)，/>，/>) At t 0 The position of the underwater unmanned aerial vehicle at any moment;
according to the azimuth angle and pitch angle value calculated by each individual of each generation of population, calculating to obtain the return path of the underwater unmanned aerial vehicle under the azimuth angle and the pitch angle, and assuming that the water depth of the initial position of the underwater unmanned aerial vehicle is H, defining conditions must be provided in the path at the moment t；
Calculating the distance between any two points in the return path of the underwater unmanned aerial vehicle：
；
Then the fitness functionThe method comprises the following steps:
。
the individuals with the smallest fitness value in the primary population are：
，/>；
In the method, in the process of the invention,represents the +.>All parameters of the individual.
Performing mutation operation by using a position mutation operator, designating a mutation point according to mutation probability for all parameters of each individual, performing cross mutation on each designated mutation point by using parameter values of the same positions of other individuals, and generating a new individual;
s7.1 in each iteration, for the ith individual of each generation of population, three mutually different intervals different from i are generatedRandom number +.>；
S7.2. generating an intervalRandom integer +.>；
S7.3. definitionProbability of variationIs 0.7, crossover factor->0.6;
s7.4, traversing in path optimization of underwater unmanned aerial vehicleA parameter, generating a zone +.>Random number seed->；
S7.5. whenWhen the differential crossover operation is performed, a new individual is generatedThe method comprises the following steps:
；
s7.6, if the new individual exceeds the upper limit and the lower limit of the azimuth angle and the pitch angle, setting the new individual as:
；
when (when)The original individual is retained.
The selection algorithm uses a selection mechanism that combines tournaments and roulette bets;
s9.1, determining the size of the tournament, determining the number of individuals participating in competition in each tournament, and initially setting the size of the tournament to be 50% in path planning;
s9.2, randomly selecting individuals, and randomly selecting tournament scale individuals in the population to serve as competitors of the tournament;
s9.3, calculating the fitness value of each competitor through individual evaluation;
s9.4. select the individual with the best fitness from competitors as the parent.
S9.5, further selecting roulette for all tournament winners winning in the previous step;
s9.5.1. Assume that there are n individuals, and the fitness values are respectivelyFirst, calculate fitness sum +.>：
；
S9.5.2, calculating selection probability;
for the ith individual, choose probability P i The method comprises the following steps:
；
normalized selection probabilities are performed, and the sum of the selection probabilities is ensured to be 1, namely:
；
and obtaining the selection probability of each individual after normalization of the fitness value, creating a sector with a corresponding size on the wheel disc according to the selection probability of each individual, selecting a position as a pointer of the wheel disc by using a random number, and selecting the individual corresponding to the sector where the pointer is positioned as the final selected individual.
Compared with the prior art, the invention has the following beneficial effects: constructing a kinematic equation of the underwater unmanned aerial vehicle, and considering the influence of environmental factors on a path; the improved algorithm increases accuracy and convergence rate, has global searching capability and local individual feature retention, searches for an optimal solution, and adapts to more situations.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions in the present invention will be clearly and completely described below, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
A method for planning a return path of an underwater unmanned aerial vehicle comprises the following steps:
s1, constructing an underwater unmanned aerial vehicle dynamics equation and setting initial parameters;
s2, according to a dynamics equation and initial parameters of the underwater unmanned aerial vehicle, obtaining the sub-speeds of the underwater unmanned aerial vehicle in the x, y and z directions under the action of water flow, and obtaining a motion track curve of the underwater unmanned aerial vehicle under a certain azimuth angle and a certain pitch angle according to the sub-speeds;
s3, initializing parameter setting by a differential evolution algorithm;
s4, initializing a first generation population;
s5, defining a fitness function；
S6, recording individuals with the minimum fitness value in the primary population;
s7, mutation and crossover operation;
s8, individual evaluation;
s9, selecting operation;
s10, an iteration control method;
s11, when the final solution meets a threshold value, setting the following conditions in the path optimizing planning, and completing the path optimizing planning to obtain the optimal return azimuth angle, pitch angle and path:
。
constructing a kinetic equation under an underwater unmanned aerial vehicle body coordinate system:
；
in the method, in the process of the invention,，/>，/>for the components of the speed of the unmanned aerial vehicle in the body coordinate system for three axes, t represents time, +.>The rolling angle speed, the yaw angle speed and the pitch angle speed of the unmanned aerial vehicle are respectively, P is the thrust of the engine of the unmanned aerial vehicle, and +.>Respectively the pitch angle, the yaw angle and the roll angle of the unmanned aerial vehicle, m is the mass of the unmanned aerial vehicle, g is the gravitational acceleration,/g>Resistance, lift force and force measurement which are respectively decomposed by water flow power>The angle of attack and sideslip, respectively, of the unmanned vehicle's voyage.
Initial setting of population300, maximum iteration number->200, the number of required parameters isUpper limit set of azimuth and pitch angles->Lower limit set of azimuth and pitch angles->，/>And->Respectively represent the upper and lower limits of azimuth angle, +.>And->Representing the upper and lower limits of the pitch angle, respectively.
；
In the middle ofStore the ith individual in the representative generation population +.>The parameters of the parameters are set to be,，/>，/>is section->Is a random number of (a) and (b),the +.f representing the lower set of azimuth and pitch angles>Element(s)>The +.f. representing the set of azimuth and pitch upper limits>The elements.
When the return point makes uniform linear motion, the initial position of the return point is set，/>，/>) The movement speed is%，/>，/>) In->At time, there is a position of return point +.>；
In the middle of (a)，/>，/>) At t 0 Returning the position of the navigation point at moment;
initial position of underwater unmanned plane,/>,/>) The unmanned aerial vehicle is obtained by the dynamics equation of the underwater unmanned aerial vehicle at any +.>The time speed is (+)>,/>,/>) Then the unmanned aerial vehicle is at t 0 Time position；
In the middle of (a)，/>，/>) At t 0 The position of the underwater unmanned aerial vehicle at any moment;
according to the azimuth angle and pitch angle value calculated by each individual of each generation of population, calculating to obtain the return path of the underwater unmanned aerial vehicle under the azimuth angle and the pitch angle, and assuming that the water depth of the initial position of the underwater unmanned aerial vehicle is H, defining conditions must be provided in the path at the moment t；
Calculating the distance between any two points in the return path of the underwater unmanned aerial vehicle：
；
Then the fitness functionThe method comprises the following steps:
。
the individuals with the smallest fitness value in the primary population are：
，/>；
In the method, in the process of the invention,represents the +.>All parameters of the individual.
Performing mutation operation by using a position mutation operator, designating a mutation point according to mutation probability for all parameters of each individual, performing cross mutation on each designated mutation point by using parameter values of the same positions of other individuals, and generating a new individual;
s7.1 in each iteration, for the ith individual of each generation of population, three mutually different intervals different from i are generatedRandom number +.>；
S7.2. generating an intervalRandom integer +.>；
S7.3. defining mutation probabilityIs 0.7, crossover factor->0.6;
s7.4, traversing in path optimization of underwater unmanned aerial vehicleA parameter, generating a zone +.>Random number seed->；
S7.5. whenWhen the differential crossover operation is performed, a new individual is generatedThe method comprises the following steps:
；
s7.6, if the new individual exceeds the upper limit and the lower limit of the azimuth angle and the pitch angle, setting the new individual as:
；
when (when)The original individual is retained.
The selection algorithm uses a selection mechanism that combines tournaments and roulette bets;
s9.1, determining the size of the tournament, determining the number of individuals participating in competition in each tournament, and initially setting the size of the tournament to be 50% in path planning;
s9.2, randomly selecting individuals, and randomly selecting tournament scale individuals in the population to serve as competitors of the tournament;
s9.3, calculating the fitness value of each competitor through individual evaluation;
s9.4. select the individual with the best fitness from competitors as the parent.
S9.5, further selecting roulette for all tournament winners winning in the previous step;
s9.5.1. Assume that there are n individuals, and the fitness values are respectivelyFirst, calculate fitness sum +.>：
；
S9.5.2, calculating selection probability;
for the ith individual, choose probability P i The method comprises the following steps:
；
normalized selection probabilities are performed, and the sum of the selection probabilities is ensured to be 1, namely:
；
and obtaining the selection probability of each individual after normalization of the fitness value, creating a sector with a corresponding size on the wheel disc according to the selection probability of each individual, selecting a position as a pointer of the wheel disc by using a random number, and selecting the individual corresponding to the sector where the pointer is positioned as the final selected individual.
S10 comprises the following steps:
in the initial iteration, larger variation probabilities, crossover factors and tournament sizes are used;
in later iterations, the search step size is reduced by smaller variation probabilities, crossover factors, and tournament sizes.
Larger probability of variation in initial iterations: between 0.5 and 0.8;
larger crossover factor in early iterations: between 0.6 and 0.9;
larger tournament size in initial iterations: between 50% and 60%;
less probability of variation in late iterations: between 0.1 and 0.3;
smaller crossover factor in later iterations: between 0.3 and 0.5;
smaller tournament size in later iterations: between 10% and 25%;
the initial iteration searching step length is set to be 0.5 degree, the later iteration decreasing searching step length is set to be 0.01 degree, the searching range is increased in the initial stage, and the searching precision is increased in the later stage.
In an embodiment, the current generation population is the return path at the pitch and azimuth angles generated in the current iteration, and the ith individual is the ith path of all the return paths generated.
In the specific application of the invention, a kinetic equation is firstly constructed to obtain components of the speed of the unmanned aerial vehicle in a machine body coordinate system for three coordinate axes, at the moment, any azimuth angle and pitch angle are input, and all information in the kinetic equation, namely various navigation parameters of the unmanned aerial vehicle at each moment, can be obtained, so that the motion trail of the unmanned aerial vehicle is obtained, but the motion trail at the moment is only a rough trail. The return point is generally a ship which always moves forward with uniform linear motion, and the speed of the uniform linear motion of the return point is set very slowly, generally 0.22m/s. And inputting speed information of the unmanned aerial vehicle to the unmanned aerial vehicle, calculating and judging azimuth angle and pitch angle of the unmanned aerial vehicle in real time according to the speed information, and optimizing the azimuth angle and the pitch angle according to a differential evolution algorithm. And obtaining an optimal solution after the iterative control method, namely obtaining optimal return azimuth angle and pitch angle, and obtaining a return path by calculating the position of the unmanned aerial vehicle at a certain moment according to the speed and the angle. The optimal return azimuth, pitch angle, and minimum distance between the drone and the return point during return, calculated at several different initial speeds of the drone are shown in table 1. As shown in table 1, the initial value of the speed is between 2.6m/s and 7.5. 7.5 m/s, and the minimum distance is between 0.015m and 0.966m, and it is clear that the path planning method of the present invention can keep the distance between the unmanned aerial vehicle and the return point within 1m in the speed interval, and at this time, the unmanned aerial vehicle can be directly caught manually. And the distance between the unmanned aerial vehicle and the return point is kept to be minimum of 0.015m, so that collision can not occur. In conclusion, the invention can effectively realize the automatic return path planning of the unmanned aerial vehicle, does not have collision risk and cannot be far away from the return point.
TABLE 1 Return information at different initial speeds
。
The above embodiments are only for illustrating the technical aspects of the present invention, not for limiting the same, and although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may be modified or some or all of the technical features may be replaced with other technical solutions, which do not depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. The method for planning the return route of the underwater unmanned aerial vehicle is characterized by comprising the following steps of:
s1, constructing an underwater unmanned aerial vehicle dynamics equation and setting initial parameters;
s2, according to a dynamics equation and initial parameters of the underwater unmanned aerial vehicle, obtaining the sub-speeds of the underwater unmanned aerial vehicle in the x, y and z directions under the action of water flow, and obtaining a motion track curve of the underwater unmanned aerial vehicle under a certain azimuth angle and a certain pitch angle according to the sub-speeds;
s3, initializing parameter setting by a differential evolution algorithm;
s4, initializing a first generation population;
s5, defining a fitness function；
S6, recording individuals with the minimum fitness value in the primary population;
s7, mutation and crossover operation;
s8, individual evaluation;
s9, selecting operation;
s10, an iteration control method;
s11, when the final solution meets a threshold value, setting the following conditions in the path optimizing planning, and completing the path optimizing planning to obtain the optimal return azimuth angle, pitch angle and path:
。
2. the method for planning a return path of an underwater unmanned aerial vehicle according to claim 1, wherein S1 comprises: constructing a kinetic equation under an underwater unmanned aerial vehicle body coordinate system:
；
in the method, in the process of the invention,，/>，/>is the speed of the unmanned aerial vehicle in the machine body coordinate systemIn the components of the three axes, t represents time, < ->The rolling angle speed, the yaw angle speed and the pitch angle speed of the unmanned aerial vehicle are respectively, P is the thrust of the engine of the unmanned aerial vehicle, and +.>Respectively the pitch angle, the yaw angle and the roll angle of the unmanned aerial vehicle, m is the mass of the unmanned aerial vehicle, g is the gravitational acceleration,/g>Resistance, lift force and force measurement which are respectively decomposed by water flow power>The angle of attack and sideslip, respectively, of the unmanned vehicle's voyage.
3. The method for planning a return path of an underwater unmanned aerial vehicle according to claim 2, wherein S3 comprises: initial setting of population300, maximum iteration number->200, the number of required parameters is +.>Upper limit set of azimuth and pitch angles->Lower limit set of azimuth and pitch angles->，/>And->Representing the upper and lower limits of the azimuth angle respectively,and->Representing the upper and lower limits of the pitch angle, respectively.
4. A method for planning a return path of an underwater unmanned aerial vehicle according to claim 3, wherein S4 comprises:
；
in the middle ofStore the ith individual in the representative generation population +.>Parameters->，，/>Is section->Random number of->The +.f representing the lower set of azimuth and pitch angles>Element(s)>The +.f. representing the set of azimuth and pitch upper limits>The elements.
5. The method for planning a return path of an underwater unmanned aerial vehicle according to claim 4, wherein S5 comprises:
when the return point makes uniform linear motion, the initial position of the return point is set，/>，/>) The movement speed is (+)>，，/>) In->At time, there is a position of return point +.>；
In the middle of (a)，/>，/>) At t 0 Returning the position of the navigation point at moment;
initial position of underwater unmanned plane,/>,/>) The unmanned aerial vehicle is obtained by the dynamics equation of the underwater unmanned aerial vehicle at any +.>The time speed is (+)>,/>,/>) Then the unmanned aerial vehicle is at t 0 Time position；
In the middle of (a)，/>，/>) At t 0 The position of the underwater unmanned aerial vehicle at any moment;
according to the azimuth angle and pitch angle value calculated by each individual of each generation of population, calculating to obtain the return path of the underwater unmanned aerial vehicle under the azimuth angle and the pitch angle, and assuming that the water depth of the initial position of the underwater unmanned aerial vehicle is H, defining conditions must be provided in the path at the moment t；
Calculating the distance between any two points in the return path of the underwater unmanned aerial vehicle：
；
Then the fitness functionThe method comprises the following steps:
。
6. the method for planning a return path of an underwater unmanned aerial vehicle according to claim 5, wherein S6 comprises:
the individuals with the smallest fitness value in the primary population are：
，/>；
In the method, in the process of the invention,represents the +.>All parameters of the individual.
7. The method for planning a return path of an underwater unmanned aerial vehicle according to claim 6, wherein S7 comprises:
performing mutation operation by using a position mutation operator, designating a mutation point according to mutation probability for all parameters of each individual, performing cross mutation on each designated mutation point by using parameter values of the same positions of other individuals, and generating a new individual;
s7.1 in each iteration, for the ith individual of each generation of population, three mutually different intervals different from i are generatedRandom number +.>；
S7.2. generating an intervalRandom integer +.>；
S7.3. defining mutation probabilityIs 0.7, crossover factor->0.6;
s7.4, traversing in path optimization of underwater unmanned aerial vehicleA parameter of generating aIndividual interval->Random number seed->；
S7.5. whenWhen the differential crossover operation is performed, a new individual is generatedThe method comprises the following steps:
；
s7.6, if the new individual exceeds the upper limit and the lower limit of the azimuth angle and the pitch angle, setting the new individual as:
；
when (when)The original individual is retained.
8. The method for planning a return path of an underwater unmanned aerial vehicle according to claim 7, wherein S9 comprises:
the selection algorithm uses a selection mechanism that combines tournaments and roulette bets;
s9.1, determining the size of the tournament, determining the number of individuals participating in competition in each tournament, and initially setting the size of the tournament to be 50% in path planning;
s9.2, randomly selecting individuals, and randomly selecting tournament scale individuals in the population to serve as competitors of the tournament;
s9.3, calculating the fitness value of each competitor through individual evaluation;
s9.4. select the individual with the best fitness from competitors as the parent.
9. The method for planning a return path of an underwater unmanned aerial vehicle according to claim 8, wherein S9 comprises:
s9.5, further selecting roulette for all tournament winners winning in the previous step;
s9.5.1. Assume that there are n individuals, and the fitness values are respectivelyFirst, calculate fitness sum +.>：
；
S9.5.2, calculating selection probability;
for the ith individual, choose probability P i The method comprises the following steps:
；
normalized selection probabilities are performed, and the sum of the selection probabilities is ensured to be 1, namely:
；
and obtaining the selection probability of each individual after normalization of the fitness value, creating a sector with a corresponding size on the wheel disc according to the selection probability of each individual, selecting a position as a pointer of the wheel disc by using a random number, and selecting the individual corresponding to the sector where the pointer is positioned as the final selected individual.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311344729.6A CN117075484B (en) | 2023-10-18 | 2023-10-18 | Underwater unmanned aerial vehicle return route planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311344729.6A CN117075484B (en) | 2023-10-18 | 2023-10-18 | Underwater unmanned aerial vehicle return route planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117075484A true CN117075484A (en) | 2023-11-17 |
| CN117075484B CN117075484B (en) | 2024-01-30 |
Family
ID=88713863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311344729.6A Active CN117075484B (en) | 2023-10-18 | 2023-10-18 | Underwater unmanned aerial vehicle return route planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117075484B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105929848A (en) * | 2016-06-28 | 2016-09-07 | 南京邮电大学 | Track planning method for multi-unmanned plane system in three-dimensional environment |
| CN108919641A (en) * | 2018-06-21 | 2018-11-30 | 山东科技大学 | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm |
| CN110906936A (en) * | 2019-12-18 | 2020-03-24 | 哈尔滨工程大学 | Underwater robot path planning method |
| CN113159687A (en) * | 2021-04-29 | 2021-07-23 | 长安大学 | Workshop AGV-UAV cooperative material distribution path planning method and system |
| WO2022095067A1 (en) * | 2020-11-09 | 2022-05-12 | 深圳市大疆创新科技有限公司 | Path planning method, path planning device, path planning system, and medium thereof |
| CN114706404A (en) * | 2022-03-10 | 2022-07-05 | 江苏科技大学 | Search and rescue ROV control system and method with path planning function |
| CN115933715A (en) * | 2023-01-10 | 2023-04-07 | 莆田学院 | Marine garbage cleaning robot and path planning method, device and medium thereof |
-
2023
- 2023-10-18 CN CN202311344729.6A patent/CN117075484B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105929848A (en) * | 2016-06-28 | 2016-09-07 | 南京邮电大学 | Track planning method for multi-unmanned plane system in three-dimensional environment |
| CN108919641A (en) * | 2018-06-21 | 2018-11-30 | 山东科技大学 | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm |
| CN110906936A (en) * | 2019-12-18 | 2020-03-24 | 哈尔滨工程大学 | Underwater robot path planning method |
| WO2022095067A1 (en) * | 2020-11-09 | 2022-05-12 | 深圳市大疆创新科技有限公司 | Path planning method, path planning device, path planning system, and medium thereof |
| CN113159687A (en) * | 2021-04-29 | 2021-07-23 | 长安大学 | Workshop AGV-UAV cooperative material distribution path planning method and system |
| CN114706404A (en) * | 2022-03-10 | 2022-07-05 | 江苏科技大学 | Search and rescue ROV control system and method with path planning function |
| CN115933715A (en) * | 2023-01-10 | 2023-04-07 | 莆田学院 | Marine garbage cleaning robot and path planning method, device and medium thereof |
Non-Patent Citations (2)
| Title |
|---|
| 庄旭等: "基于改进选择操作的遗传算法的电力系统无功优化", 《电气自动化》, vol. 31, no. 2, pages 54 - 57 * |
| 曹江丽;孙潮义;: "多目标遗传算法在水下机器人路径规划中的应用", 武汉大学学报(信息科学版), no. 04, pages 441 - 444 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117075484B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106845716B (en) | Navigation error constraint-based water surface unmanned ship local hierarchical path planning method | |
| CN109375625B (en) | Intelligent ship path planning method based on rapid search genetic algorithm | |
| CN108871351B (en) | Dynamic path planning method for AUV (autonomous Underwater vehicle) submarine topography matching | |
| CN110544296B (en) | Intelligent planning method for three-dimensional global track of unmanned aerial vehicle in uncertain enemy threat environment | |
| CN110906934B (en) | Unmanned ship obstacle avoidance method and system based on collision risk coefficient | |
| CN109144102A (en) | A kind of Path Planning for UAV based on improvement bat algorithm | |
| CN114625151B (en) | Underwater robot obstacle avoidance path planning method based on reinforcement learning | |
| CN111238521A (en) | Path planning method and system for unmanned vehicle | |
| CN110906935B (en) | Unmanned ship path planning method | |
| CN109931943B (en) | Unmanned ship global path planning method and electronic equipment | |
| CN113534668B (en) | Maximum entropy based AUV (autonomous Underwater vehicle) motion planning method for actor-critic framework | |
| CN115357031B (en) | Ship path planning method and system based on improved ant colony algorithm | |
| CN110514567B (en) | Gas source searching method based on information entropy | |
| CN112506218B (en) | Reentry vehicle any no-fly zone around-flying method based on intelligent trajectory prediction | |
| CN110146087A (en) | A kind of ship paths planning method based on Dynamic Programming Idea | |
| CN110095788A (en) | A kind of RBPF-SLAM improved method based on grey wolf optimization algorithm | |
| CN113268087A (en) | Flight path planning method for cooperative work of multiple unmanned aerial vehicles based on improved ant colony algorithm in multi-constraint complex environment | |
| CN109976189A (en) | A kind of intelligence naval vessels automatic cruising analog simulation method | |
| CN113032896A (en) | Collision avoidance aid decision-making method based on ship driver preference | |
| CN113391633A (en) | Urban environment-oriented mobile robot fusion path planning method | |
| Yang et al. | A knowledge based GA for path planning of multiple mobile robots in dynamic environments | |
| CN113538973B (en) | Automatic ship collision avoidance method based on improved particle swarm optimization | |
| CN116151102A (en) | Intelligent determination method for space target ultra-short arc initial orbit | |
| CN113325867B (en) | Path planning method and device for searching of unmanned aircraft and unmanned aircraft | |
| CN117075484B (en) | Underwater unmanned aerial vehicle return route planning method |
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 |