CN112000126B - Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method - Google Patents

Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method Download PDF

Info

Publication number
CN112000126B
CN112000126B CN202010805685.2A CN202010805685A CN112000126B CN 112000126 B CN112000126 B CN 112000126B CN 202010805685 A CN202010805685 A CN 202010805685A CN 112000126 B CN112000126 B CN 112000126B
Authority
CN
China
Prior art keywords
target
whale
search
unmanned aerial
updating
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010805685.2A
Other languages
Chinese (zh)
Other versions
CN112000126A (en
Inventor
刘琨
黄大庆
韩玉洁
万思钰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN202010805685.2A priority Critical patent/CN112000126B/en
Publication of CN112000126A publication Critical patent/CN112000126A/en
Application granted granted Critical
Publication of CN112000126B publication Critical patent/CN112000126B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying

Abstract

The invention discloses a whale algorithm-based multi-unmanned aerial vehicle collaborative searching multi-dynamic target method. The method comprises the following steps: establishing an environment model, and initializing a target probability map; establishing an objective function; and (3) carrying out target search of an unknown environment by using an improved whale algorithm in combination with a new target probability map updating mode. The method provided by the invention designs the updating rule by fully utilizing the characteristics of the probability map of the existence of the targets in the sea area, and updates the target probability map based on the detected targets and the motion prediction targets, so that the whale algorithm can better complete the search of multiple unmanned aerial vehicles on the unknown sea area.

Description

Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method
Technical Field
The invention relates to collaborative search and group intelligent optimization, in particular to a method for collaboratively searching multiple dynamic targets in an unknown sea area by multiple unmanned aerial vehicles.
Background
In recent years, due to rapid development of sensors, microprocessors and information processing technologies, the functions of the unmanned cluster system are increasingly enhanced, and the application range of the unmanned cluster system is also continuously expanded. Due to the flexibility, expandability and strong cooperative operation capability, the research on unmanned cluster cooperative theory and application is more and more concerned by academic, industrial and defense circles. The multi-unmanned-aerial-vehicle collaborative search system can effectively improve search efficiency, especially under complex sea conditions of uncertainty, strong interference and the like. Therefore, the maritime multi-drone collaborative search is one of the important directions for the research of the drone cluster system. For a certain sea area, a plurality of homogeneous unmanned aerial vehicles enter the sea area needing to execute tasks, and each unmanned aerial vehicle independently searches for an unknown target by using a detection sensor of the unmanned aerial vehicle. Through collaborative search, multiple drones can find as many targets as possible in the shortest time at the minimum cost.
In the process of Unmanned Aerial Vehicles (UAVs) performing a target search task in an unknown environment, due to uncertainty of target and environment information, conventional advance flight path planning cannot adapt to such a dynamically changing environment, and a real-time online planning method needs to be researched to adapt to the characteristic that the UAV faces a time-varying environment. In order to reduce the uncertainty of the target motion, in the Prior art, Chunlei Zhang, Raul Ordonez, Corey Schumacher "Multi-Vehicle Cooperative Search with uncertainty information," AIAA Guidance Navigation and Control Conference, August 2004, proposes a target transition probability density function based on gaussian distribution, and adopts the maximum probability of discovery and the maximum coverage as a Search strategy to improve the Search efficiency, but needs continuous integral operation to increase the calculation load. The collaborative search method for the Markov moving target by the Namex navigation cluster comprises the steps of (J) systematic engineering and electronic technology, 2019(9), (2041) 2047) using a Markov chain to sign hidden motion of the target, predicting the position of the target, and solving the collaborative search track of the unmanned aerial vehicle by using a greedy iterative algorithm on the basis of distributed model prediction control. According to the method, the target position is predicted, the capture capacity of the unmanned aerial vehicle on the moving target is improved, but the problem of target misjudgment caused by sensor false alarm is not considered.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the defects of the prior art, the invention provides a method for cooperatively searching multiple dynamic targets by multiple unmanned aerial vehicles based on a whale algorithm, and solves the problems of large computation amount and sensor false alarm of the conventional multi-target motion prediction method.
The technical scheme is as follows: a method for cooperatively searching multiple dynamic targets by multiple unmanned aerial vehicles based on whale algorithm comprises the following steps:
(1) establishing an environment model, and initializing a target probability map;
(2) establishing a target function, and carrying out weighted summation on the unmanned aerial vehicle target search return function and the environment search return function;
(3) initializing a whale algorithm, setting the iteration number k to be 0, and setting the maximum iteration number kmax；
(4) Obtaining fitness values of whales at all positions by using an objective function, updating parameters, determining initial individual optimal positions and global optimal positions of whale populations, and then setting k to k + 1;
(5) generating a parameter epsilon, judging whether the parameter epsilon is smaller than a preset threshold value, if so, performing the step (6), and otherwise, performing the step (7);
(6) carrying out whale individual position vector iterative updating by adopting contraction surrounding and random search of a whale algorithm, and carrying out the step (8) after the updating is finished;
(7) carrying out whale individual position vector iteration updating by adopting spiral rising of a whale algorithm;
(8) calculating the fitness value of the individual position, and updating the individual optimal position and the global optimal position;
(9) updating an object probability map based on the detected object and the motion prediction object;
(10) judging whether the current iteration number k is less than the maximum iteration number kmaxIf so, performing the step (2), otherwise, performing the step (11);
(11) and outputting the global optimal solution, and ending.
Has the advantages that: the method utilizes an improved whale algorithm to carry out target search in an unknown environment in combination with a new target probability map updating mode, designs an updating rule by fully utilizing the characteristics of probability maps of targets in sea areas, and updates the target probability map based on the detected targets and the motion prediction targets, so that the whale algorithm can better complete the search of multiple unmanned aerial vehicles on the unknown sea areas.
Drawings
FIG. 1 is a flow chart of a method for cooperatively searching multiple dynamic targets by multiple unmanned aerial vehicles based on a whale algorithm.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
As shown in FIG. 1, the invention provides a method for cooperatively searching multiple dynamic targets in an unknown sea area by multiple unmanned aerial vehicles based on a whale algorithm, which comprises the following steps:
step 1, establishing an environment model and initializing a target probability map;
in the embodiment, a grid method is adopted to divide and label the search sea area, and the environment is modeled. Defining a sea area as E ═ Lx×Ly，LxFor the range in the x-axis direction of the sea area to be searched, LyThe range in the y direction of the sea area to be searched; mixing L withxUniform NxDividing into equal portions, mixing LyUniform NyDividing the sea area into N grids, where N is Nx×Ny. Cell i is defined as:
i＝nx+(ny-1)×Ny (1)
wherein n isx＝1...Nx，ny＝1...Ny，Nx＝Lx/Rs，Ny＝Ly/Ry。RsRepresenting the length of each grid in the x-axis direction; ryThe length in the y-axis direction of each grid is indicated.
And establishing a target probability graph model and initializing the target probability graph. Pi(t)∈[0,1]Representing the target existence probability of cell i at time t:
Pi＝∫∫sf(x,y)dxdy (2)
Figure BDA0002629044180000031
where s is the region where cell i is located and f (x, y) is the union and probability density function of the target.
Step 2, establishing a target function, and carrying out weighted summation on the unmanned aerial vehicle target search return function and the environment search return function;
establishing an objective function, mainly aiming at finding a target as much as possible in an unknown sea area, wherein the optimization objective function is as follows:
J(t)＝ω1J1(t)+ω2J2(t) (4)
wherein ω is1、ω2Is a weight coefficient, 0 is not less than omega1≤1，0≤ω2≤1。J1(t) is a target search return function, J2(t) is an environmental search reward function.
Defining the sum of the target discovery probabilities in the sea area as a target search return function:
Figure BDA0002629044180000032
wherein b isi(t) indicates finding the targetPossibility of (2)
Figure BDA0002629044180000033
Wherein deltaPRepresents a target threshold, which means that only if the probability of the target at the searched cell i is greater than a threshold δPThen, the target can be found.
Searching an area by using the airborne sensor, and gradually knowing the search area by the unmanned aerial vehicle along with the time, wherein the change of the environment entropy represents an environment search return function:
Figure BDA0002629044180000041
wherein ei(t) is the entropy of the information, representing the degree of uncertainty in cell i at time t:
Figure BDA0002629044180000042
step 3, initializing the whale algorithm, setting the iteration number k to be 0, and setting the maximum iteration number kmax；
Step 4, obtaining fitness values of whales at all positions by using a fitness function (an objective function), namely J (t) of the formula (4), updating parameters, determining initial individual optimal positions and global optimal positions of whale population, and then k being k + 1; wherein the position of the whale represents the area of the cell, the individual optimum is the optimum position of a whale individual, the global optimum is the optimum individual position in the whale population, and the parameters
Figure BDA0002629044180000043
Is a variable of the coefficient(s),
Figure BDA0002629044180000044
determining whether whale searches globally or locally, and taking the current parameter as
Figure BDA0002629044180000045
Time, algorithm with certain probabilityCarrying out random global search; when in use
Figure BDA0002629044180000046
In time, the algorithm is developed locally. a is a convergence factor.
Step 5, randomly generating an indication parameter epsilon by using a random generation function rand (0,1), wherein epsilon is less than 0.5, performing step 6, and epsilon is more than or equal to 0.5, and performing step 7;
step 6, carrying out whale individual position vector iterative updating by adopting contraction surrounding and random search of an improved whale algorithm, and carrying out step 8 after updating is finished;
step 7, carrying out whale individual position vector iterative updating by adopting spiral rising of an improved whale algorithm;
the above steps 5-7 describe the iterative process of the whale algorithm employed in the present invention. In the whale algorithm, the position of each whale represents a feasible solution. Group W ═ X composed of whales with N heads1,X2,...,XNDefine the position of the ith whale as
Figure BDA0002629044180000047
Wherein
Figure BDA0002629044180000048
The position of the ith whale in the d-dimension is represented, d represents the number of optimal solutions, and is a real number which can be randomly changed in a simulation experiment, for example: the results of simulation experiments can be compared when d is 10, d is 20 and d is 30. Each whale approached the prey location by continually iteratively updating the location. In the invention, the position updating mode of the whale predation process is divided into a development stage and a search stage. The development phase is based on epsilon to determine range, and the search phase is based on epsilon
Figure BDA0002629044180000049
The search mode is selected according to the range of (1).
Position updating mode in development stage:
Figure BDA00026290441800000410
where k is the current number of iterations,
Figure BDA0002629044180000051
is the prey (best solution) position.
ε<0.5 time, select shrink round surround prey, wherein
Figure BDA0002629044180000052
In order to have a reduced radius of curvature,
Figure BDA0002629044180000053
wherein epsilon1、ε2Is the interval [0,1]The convergence factor a decreases linearly from 2 to 0, k with increasing number of iterationsmaxThe maximum number of iterations is indicated.
And when the epsilon is more than or equal to 0.5, the optimal solution is expanded by adopting a search mode of a logarithmic spiral. b is a constant of the shape of a logarithmic spiral, and l is [ -1,1 ]]The random number of (2).
Figure BDA0002629044180000054
Represents the length of the ith whale from the prey, i.e. the distance between the ith solution and the current optimal solution.
Position update mode in exploration phase: when in use
Figure BDA0002629044180000055
In time, the current whale randomly selects the position X of other whales (not the current optimal solution)randThe target position is the whale
Figure BDA0002629044180000056
The location update formula of (a) is:
Figure BDA0002629044180000057
step 8, calculating the fitness value of the individual position, and updating the individual optimal position and the global optimal position; the individual optimal position refers to the optimal position of one whale, and the global optimal position is the optimal position under the comparison of all whale population individuals;
step 9, updating the target probability map based on the detection target and the motion prediction target;
when multiple unmanned aerial vehicles cooperatively search for targets in an unknown environment, uncertainty of the target state makes the searching process a probabilistic problem. As the search task progresses, the target probability map will be updated based on information detected by the unmanned aerial vehicle onboard sensors. After some cells are searched each time, the probability map of the target in the sea area to be searched is changed, and the probability map needs to be updated in time because moving targets exist in the area to be searched. In order to avoid repeated detection of multiple unmanned aerial vehicles in the subsequent search process, the updating methods of the target probability map are divided into the following three types:
(a) when the drone does not search cell i:
Pi(t)＝Pi(t-1) (11)
(b) when the unmanned plane searches the cell i and does not find any target:
Figure BDA0002629044180000058
(c) when the unmanned plane searches cell i and finds a target:
Figure BDA0002629044180000061
wherein P isd∈[0,1]The probability that the unmanned aerial vehicle finds the target when the target is located in the current cell is referred to. Pf∈[0,1]The false alarm probability represents the probability that the drone finds a target but does not have a target in the current cell.
When the search target is a moving target, the target probability map updating mechanism is as follows:
Figure BDA0002629044180000062
Niis the number of cells around cell i, δdAnd d (j) ═ d1(j),d2(j),d3(j),d4(j),d5(j),d6(j),d7(j),d8(j) Is constant and represents the speed and direction of diffusion in cell i, respectively. By utilizing the target probability map updating mechanism and the initial target distribution characteristics, the probability distribution of the targets after a period of time can be predicted, so that the unmanned aerial vehicle is guided to search cooperatively.
Step 10, judging whether the current iteration number k is less than the maximum iteration number kmaxIf yes, performing the step 2, otherwise, performing the step 11;
and 11, outputting the global optimal solution, namely the global optimal position obtained in the step 8, and ending.
The global optimal position, i.e. the area of the cell where the target is located, indicates that the search target exists in this cell.
According to the method, the updating rule is designed by fully utilizing the characteristics of the probability map of the existence of the targets in the sea area, and the target probability map is updated based on the detected targets and the motion prediction targets, so that the whale algorithm can better complete the search of multiple unmanned aerial vehicles on the unknown sea area.

Claims (7)

1. A method for cooperatively searching multiple dynamic targets by multiple unmanned aerial vehicles based on whale algorithm is characterized by comprising the following steps:
(1) establishing an environment model, and initializing a target probability map;
(2) establishing a target function, and carrying out weighted summation on the unmanned aerial vehicle target search return function and the environment search return function;
(3) initializing a whale algorithm, setting the iteration number k to be 0, and setting the maximum iteration number kmax；
(4) Obtaining fitness values of whales at all positions by using an objective function, updating parameters, determining initial individual optimal positions and global optimal positions of whale populations, and then setting k to k + 1;
(5) generating an indication parameter epsilon, judging whether the parameter epsilon is smaller than a preset threshold value, if so, performing the step (6), and otherwise, performing the step (7);
(6) carrying out whale individual position vector iterative updating by adopting contraction surrounding and random search of a whale algorithm, and carrying out the step (8) after the updating is finished;
(7) carrying out whale individual position vector iteration updating by adopting spiral rising of a whale algorithm;
(8) calculating the fitness value of the individual position, and updating the individual optimal position and the global optimal position;
(9) updating an object probability map based on the detected object and the motion prediction object;
(10) judging whether the current iteration number k is less than the maximum iteration number kmaxIf so, performing the step (2), otherwise, performing the step (11);
(11) and outputting the global optimal position.
2. The method for multi-unmanned aerial vehicle collaborative search for multi-dynamic target based on whale algorithm as claimed in claim 1, wherein the step (1) comprises:
dividing and marking the search sea area by adopting a grid method, and defining the search sea area as E-Lx×LyAnd dividing the sea area into N grids, N being Nx×NyCell i is defined as: n ═ ix+(ny-1)×NyWherein n isx＝1...Nx，ny＝1...Ny，Nx＝Lx/Rs，Ny＝Ly/Ry；
Establishing a target probability map model and initializing a target probability map, Pi(t)∈[0,1]Representing the target existence probability of cell i at time t:
Pi＝∫∫sf(x,y)dxdy
Figure FDA0003092030890000021
wherein S is the area where the cell i is located, and f (x, y) is the joint and probability density function of the target.
3. The method for multi-unmanned aerial vehicle collaborative search for multi-dynamic target based on whale algorithm as claimed in claim 2, wherein the objective function in the step (2) is:
J(t)＝ω1J1(t)+ω2J2(t)
wherein ω is1、ω2Is a weight coefficient, J1(t) is a target search return function, J2(t) searching for a reward function for the environment;
Figure FDA0003092030890000022
Figure FDA0003092030890000023
wherein b isi(t) represents the probability of finding the target
Figure FDA0003092030890000024
δPRepresents a target threshold; e.g. of the typei(t) is the entropy of the information, representing the degree of uncertainty in cell i at time t:
Figure FDA0003092030890000025
4. the method for multi-unmanned aerial vehicle collaborative search for multi-dynamic-target based on whale algorithm as claimed in claim 1, wherein the step (6) of shrinking the enclosing whale
Figure FDA0003092030890000026
The individual location update formula of (a) is:
Figure FDA0003092030890000027
wherein
Figure FDA0003092030890000028
In order to have a reduced radius of curvature,
Figure FDA0003092030890000029
ε1、ε2is the interval [0,1]A decreases linearly from 2 to 0 with increasing number of iterations,
Figure FDA00030920308900000210
is the position represented by the current optimal solution.
5. The method for multi-unmanned aerial vehicle collaborative search for multi-dynamic targets based on whale algorithm as claimed in claim 1, wherein the step (6) of randomly searching whales
Figure FDA00030920308900000211
The individual location update formula of (a) is:
Figure FDA00030920308900000212
wherein
Figure FDA00030920308900000213
For the randomly selected positions of other whales,
Figure FDA00030920308900000214
is a coefficient variable.
6. The method for multi-unmanned aerial vehicle collaborative search for multi-dynamic-target based on whale algorithm as claimed in claim 1, wherein the step (7) is that whales rise spirally
Figure FDA0003092030890000031
The individual location update formula of (a) is:
Figure FDA0003092030890000032
wherein b is a constant of the shape of a logarithmic spiral, and l is [ -1,1 ]]The random number of (a) is set,
Figure FDA0003092030890000033
the length of the ith whale from the prey, i.e. the distance between the ith solution and the current optimal solution,
Figure FDA0003092030890000034
is the position represented by the current optimal solution.
7. The method for multi-unmanned aerial vehicle collaborative search for multi-dynamic targets based on whale algorithm as claimed in claim 2, wherein the target probability map updating mechanism in step (9) is as follows:
Figure FDA0003092030890000035
wherein N isiIs the number of cells around cell i, δdAnd d (j) is a constant, representing the speed and direction of diffusion in cell i, respectively.
CN202010805685.2A 2020-08-12 2020-08-12 Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method Active CN112000126B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010805685.2A CN112000126B (en) 2020-08-12 2020-08-12 Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010805685.2A CN112000126B (en) 2020-08-12 2020-08-12 Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method

Publications (2)

Publication Number Publication Date
CN112000126A CN112000126A (en) 2020-11-27
CN112000126B true CN112000126B (en) 2021-08-06

Family

ID=73463549

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010805685.2A Active CN112000126B (en) 2020-08-12 2020-08-12 Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method

Country Status (1)

Country Link
CN (1) CN112000126B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113138609B (en) * 2020-12-25 2022-07-19 北京理工大学 Multi-unmanned aerial vehicle cooperative target searching method for anti-low-slow small targets
CN112905959B (en) * 2021-02-09 2022-09-09 辽宁警察学院 Police affair multi-unmanned aerial vehicle target searching method based on normal distribution probability graph
CN116989798B (en) * 2023-09-27 2023-12-26 北京理工大学 Unmanned aerial vehicle track planning method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103246289A (en) * 2013-05-07 2013-08-14 西北工业大学 Target assignment method used in cooperative search of multi-unmanned aerial vehicles with communication restriction
CN107844129A (en) * 2017-11-30 2018-03-27 北京大学深圳研究生院 Multiple no-manned plane collaboratively searching method and system based on path planning and information fusion
CN109299210A (en) * 2018-11-06 2019-02-01 哈尔滨工业大学（深圳） A kind of multiple no-manned plane distributed collaboration searching method based on information fusion

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DK2391863T3 (en) * 2009-02-02 2020-08-24 Aerovironment Inc MULTIMODAL DRIVERLESS AIRCRAFT

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103246289A (en) * 2013-05-07 2013-08-14 西北工业大学 Target assignment method used in cooperative search of multi-unmanned aerial vehicles with communication restriction
CN107844129A (en) * 2017-11-30 2018-03-27 北京大学深圳研究生院 Multiple no-manned plane collaboratively searching method and system based on path planning and information fusion
CN109299210A (en) * 2018-11-06 2019-02-01 哈尔滨工业大学（深圳） A kind of multiple no-manned plane distributed collaboration searching method based on information fusion

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"基于改进鲸鱼优化算法的无人机航路规划";吴坤 等;《航空学报》;20200630(第2期);第107-114页 *

Also Published As

Publication number Publication date
CN112000126A (en) 2020-11-27

Similar Documents

Publication Publication Date Title
CN112000126B (en) Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method
Yijing et al. Q learning algorithm based UAV path learning and obstacle avoidence approach
Kim et al. Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network
CN110058613B (en) Multi-unmanned-aerial-vehicle multi-ant-colony collaborative target searching method
CN111176334B (en) Multi-unmanned aerial vehicle cooperative target searching method
Wang et al. A hybrid metaheuristic DE/CS algorithm for UCAV three-dimension path planning
Tuba et al. Mobile robot path planning by improved brain storm optimization algorithm
Huang et al. A new dynamic path planning approach for unmanned aerial vehicles
CN102880186A (en) Flight path planning method based on sparse A* algorithm and genetic algorithm
CN110926477A (en) Unmanned aerial vehicle route planning and obstacle avoidance method
Liu et al. Potential odor intensity grid based UAV path planning algorithm with particle swarm optimization approach
Ru et al. Distributed cooperative search control method of multiple UAVs for moving target
Huang A novel three-dimensional path planning method for fixed-wing UAV using improved particle swarm optimization algorithm
CN113848919A (en) Ant colony algorithm-based indoor AGV path planning method
Yu et al. A novel sparrow particle swarm algorithm (SPSA) for unmanned aerial vehicle path planning
CN109118064B (en) Optimal resource allocation method for probe task planning
Peterson Dynamic grouping of cooperating vehicles using a receding horizon controller for ground target search and track missions
CN116400737B (en) Safety path planning system based on ant colony algorithm
CN113063419A (en) Unmanned aerial vehicle path planning method and system
CN115143970B (en) Obstacle avoidance method and system of underwater vehicle based on threat degree evaluation
Kim 3D path planner of an autonomous underwater vehicle to track an emitter using frequency and azimuth–elevation angle measurements
CN116048126A (en) ABC rapid convergence-based unmanned aerial vehicle real-time path planning method
CN116243717A (en) Underwater robot time optimal path planning method considering ocean current uncertainty
Ou et al. Hybrid path planning based on adaptive visibility graph initialization and edge computing for mobile robots
Sabra et al. Multi-objective Optimization of Confidence-Based Localization in Large-Scale Underwater Robotic Swarms

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