CN112966803A - Particle swarm algorithm-based multi-agent cooperative target searching method - Google Patents

Particle swarm algorithm-based multi-agent cooperative target searching method Download PDF

Info

Publication number
CN112966803A
CN112966803A CN202110145980.4A CN202110145980A CN112966803A CN 112966803 A CN112966803 A CN 112966803A CN 202110145980 A CN202110145980 A CN 202110145980A CN 112966803 A CN112966803 A CN 112966803A
Authority
CN
China
Prior art keywords
agent
particle swarm
particle
target
agents
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
Application number
CN202110145980.4A
Other languages
Chinese (zh)
Other versions
CN112966803B (en
Inventor
张军旗
卢烨昊
王成
臧笛
刘春梅
康琦
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.)
Tongji University
Original Assignee
Tongji University
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 Tongji University filed Critical Tongji University
Priority to CN202110145980.4A priority Critical patent/CN112966803B/en
Publication of CN112966803A publication Critical patent/CN112966803A/en
Application granted granted Critical
Publication of CN112966803B publication Critical patent/CN112966803B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Biomedical Technology (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Tourism & Hospitality (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Feedback Control In General (AREA)

Abstract

The invention provides a particle swarm algorithm-based multi-agent cooperative target searching method, which introduces a particle swarm algorithm to carry out virtual navigation and uses an entity agent with certain communication and perception capability to replace virtual particles in the particle swarm algorithm to realize source location searching. The moving distance and the searching time of the particles are considered in the particle swarm optimization for the first time, so that a weight cost function is established, and a path with the minimum cost is planned for the intelligent agent through a local searching strategy according to the target position generated by each generation of the particle swarm. Therefore, the multi-agent system can greatly reduce energy consumption, enhance endurance and improve search efficiency on the premise of not influencing target search accuracy. The invention is a universal multi-agent target searching method, and the particle swarm algorithm based on the method can be any particle swarm variant.

Description

Particle swarm algorithm-based multi-agent cooperative target searching method
Technical Field
The invention relates to the field of swarm intelligence and multi-agent target searching, in particular to a multi-agent cooperative target searching method based on a particle swarm algorithm.
Background
In recent years, the source localization problem has attracted much attention and has gradually developed into a research hotspot. This problem assumes that there is a static source in the unknown environment that will continue to emit signals to the outside world, and that the multi-agent needs to co-locate the source based on the signal strength detected in each area. Because the spatial signal has phenomena such as reflection and refraction and the sensor measurement has errors, noise with different degrees exists in the detection area, and the task difficulty is greatly increased. From another point of view analysis, this problem can be transformed into an optimization problem, modeling the signal strength of each position in the search space as a function value of the point, and then the position of the source is the position with the maximum function value, i.e. the maximum value of the search three-dimensional function. Meanwhile, due to space noise, the function is a multi-mode function, and a plurality of local optimal solutions exist.
The particle swarm algorithm is a swarm intelligence algorithm, which was proposed in 1995 by Kennedy and Eberhart inspired by bird swarm foraging to solve the global optimization problem. Due to the simplicity and the fast convergence of the parameters, the particle swarm optimization has become one of the mainstream global optimization technologies and is widely applied to various practical problems. But since the particle search has a certain randomness, the method is easy to fall into a local optimal solution. Therefore, numerous scholars continuously propose a variant algorithm of the particle swarm, and the optimization performance of the variant algorithm is further improved by balancing the global search capability and the local search capability of the swarm.
Many works in the swarm intelligence field and the multi-agent target search field have similarity and compatibility, and if an entity agent with certain communication and perception capability replaces virtual particles in a particle swarm algorithm, the swarm intelligence optimization algorithm can be popularized to the real world, namely, the problem of source positioning is solved. However, even if the particles in the particle swarm algorithm are virtual individuals, i.e., they do not consume energy, have unlimited speed, and can move instantly, if the particle swarm algorithm is directly used as a multi-agent control strategy to search and locate the target, the agent may stop working due to insufficient energy, or the task may fail due to too long moving time. Therefore, it is necessary to invent a particle swarm algorithm capable of optimizing energy consumption and search efficiency simultaneously aiming at multi-agent target search.
Disclosure of Invention
Aiming at the defects of the existing particle swarm algorithm in the field of multi-agent target search, the invention provides a multi-agent cooperative target search method based on a particle swarm algorithm, which realizes multi-agent cooperation through the swarm intelligence algorithm, simultaneously considers the moving distance and the working time of an agent, establishes a weight cost function, plans a path with the minimum cost for the agent according to the target position to be searched generated by each generation of the particle swarm, and realizes cooperative search of a multi-agent system through a local search strategy. Therefore, the multi-agent can greatly reduce energy consumption, enhance endurance and improve search efficiency on the premise of not influencing target search accuracy.
The invention is realized by the following technical scheme:
the invention relates to a particle swarm algorithm-based multi-agent cooperative target searching method, which comprises the following steps of:
step 1.1: in an application scene, multiple intelligent agents are distributed, the multiple intelligent agents are regarded as particle swarms, the intelligent agents are regarded as particles, environment modeling is carried out, and field source signal values detected by intelligent agent sensors are used as fitness indexes of a particle swarms.
Step 1.2: initializing particle swarm algorithm parameter setting: the particle swarm size n, the optimization dimension D and the maximum iteration number G.
Step 1.3: initializing the initial position x of n particles at random ═ { x ═ x1，x2，...，xnV and velocity v ═ v1，v2，...，vnInitializing the positions S ═ S of m agents1，S2，...，SmAnd velocity V.
Step 1.4: the multi-agent carries out optimal path planning through a local search strategy so as to traverse all current particle positionsx＝{x1，x2，...，xnAnd acquiring the field intensity f (x) of each target position by using a sensori) As a fitness value for that location.
Step 1.5: and updating the speed and the position of the particles by a particle swarm algorithm, wherein the updating formulas are respectively as follows:
Figure BDA0002929803170000021
Figure BDA0002929803170000022
wherein, c1、c2Is a constant acceleration factor, and c1＝c2＝2.05，r1、r2Is a D-dimensional random number vector, pbestiIndicating the historical optimum position of the ith particle, gbest indicating the historical optimum position of the particle population,
Figure BDA0002929803170000023
Figure BDA0002929803170000024
which represents the velocity of the ith particle,
Figure BDA0002929803170000025
indicating the position of the ith particle.
Step 1.6: and if the current iteration number is larger than the maximum iteration number G or the source target is successfully identified, executing the step 1.7, otherwise, returning to the step 1.4 to carry out the next iteration.
Step 1.7: all agents move to the optimal position gbest.
Further, in step 1.4, a local search strategy is used to plan a moving path for each agent, so that the group traverses all target positions, and the moving distance and the search time of the agents are optimized simultaneously, which specifically comprises the following steps:
step 1.4.1: dividing the multi-agent into m/n groups according to the following formula, wherein the number of the i-th group of agents is Λ (i), the number of the agents is m, and each group independently executes the search task:
Figure BDA0002929803170000031
step 1.4.2: initializing a time vector τ[1×m]And loss matrix F[m×n]The following were used:
τ[1×m]＝{0，...，0}；
Figure BDA0002929803170000032
wherein, tauiRepresenting the total time of movement of the ith agent in the current iteration, and F (i, j) representing the ith agent from the current location SiMove to the target position XjThe required cost, a ∈ [0, 1 ]]A weight constant for balancing the influence of the moving distance and the search time on the multi-agent performance,
Figure BDA0002929803170000033
denotes the position p1To p2V represents the moving speed of the agent.
Step 1.4.3: calculating the minimum value of the loss matrix, setting the minimum value as F (i, j), and moving the ith agent to the target position XiWherein, the accessed target position is not accessed again, and the update related parameters are as follows:
Figure BDA0002929803170000034
Figure BDA0002929803170000035
where f represents a set of target locations that are not accessed.
Step 1.4.4: step 2.3 is repeated until all target locations have been visited.
According to the invention, an interaction mechanism between intelligent agents is constructed through a particle swarm algorithm, so that group cooperation is realized; and performing multi-agent optimal path planning through a local search strategy in each iteration of the particle swarm, and performing multi-objective optimization on the cluster moving distance and the search time so as to reduce energy consumption, improve efficiency and realize the improvement of the cluster synergy.
The invention is a universal multi-agent target searching method, and the particle swarm algorithm based on the method can be any particle swarm variant.
The searching precision, the anti-interference capability and other performances of the method can be continuously improved along with the development of the intelligent optimization field of the particle swarm. The method is suitable for the environment with source signals, and the whole group cannot work due to the damage of part of agents, so the method is particularly suitable for search tasks in dangerous environments, such as disaster site rescue, harmful gas leakage source positioning and the like. The invention has reasonable design, introduces a local search strategy in the particle swarm optimization to plan the optimal path, and greatly reduces the moving distance and the search time of the multi-agent.
Drawings
FIG. 1 is a flow diagram of a multi-agent cooperative target searching method based on a particle swarm optimization.
Detailed Description
The invention simultaneously considers the moving distance and the working time of the intelligent agent, establishes a weight cost function, plans a path with the minimum cost for the intelligent agent through a neighborhood search strategy according to the target position generated by each generation of the particle swarm, and compared with the current latest technology, under the premise of allowing the intelligent agent to randomly fail, lose efficacy, damage and other severe conditions in the cluster, the invention not only does not influence the completion of the search task, but also greatly improves the target search precision and speed of the multi-intelligent agent, simultaneously reduces the energy consumption of the multi-intelligent agent by more than 66 percent, and reduces the search time by nearly 70 percent.
The technical scheme of the invention is explained in detail in the following by combining the drawings and the embodiment.
In the embodiments, the agent refers to a physical agent with communication and sensing capabilities, and is a non-virtual particle, such as, by way of example and not limitation, an unmanned aerial vehicle, an unmanned vehicle, and an unmanned underwater vehicle.
In the embodiment, a multi-agent target searching task, namely the technical scheme task of the invention, such as positioning of harmful gas leakage sources, by way of example and not limitation, is assumed as follows: harmful gas leakage exists in one area, but leakage source information is unknown, and a plurality of intelligent agents with local sensing and communication capabilities coordinate to locate the specific position where the leakage source is located and rescue after disaster according to the gas concentration values detected at different positions in a shared mode: in order to locate and rescue survivors in the ruins after disasters, the vital sign strength value of each position in the scene is detected by using an intelligent body with sensing equipment such as a radar life detector, and the position with the strongest vital sign is located through cooperative search of multiple intelligent bodies.
The embodiment models a multi-agent system construction process environment.
Examples
As shown in fig. 1, the multi-agent cooperative target searching method of the embodiment specifically includes the following steps:
step 1.1: in an application scene, multiple intelligent agents are distributed, the multiple intelligent agents are regarded as particle swarms, the intelligent agents are regarded as particles, environment modeling is carried out, and field source signal values detected by intelligent agent sensors are used as fitness indexes of a particle swarms.
Step 1.2: initializing particle swarm algorithm parameter setting: the particle swarm size n is 50, the optimization dimension D is 2, and the maximum iteration number G is 10000.
Step 1.3: initializing the initial position x of n particles at random ═ { x ═ x1，x2，...，xnV and velocity v ═ v1，v2，...，vnInitializing the positions S ═ S of m agents1，S2，...，SmAnd speed V-1.
Step 1.4: the multi-agent carries out optimal path planning through a local search strategy so as to traverse all current particle positions x ═ { x ═ x1，x2，...，xnAnd acquiring the field intensity f (x) of each target position by using a sensori) AsThe fitness value of the location.
Step 1.5: and updating the speed and the position of the particles by a particle swarm algorithm, wherein the updating formulas are respectively as follows:
Figure BDA0002929803170000051
Figure BDA0002929803170000052
wherein, c1、c2Is a constant acceleration factor, and c1＝c2＝2.05，r1、r2Is a D-dimensional random number vector, pbestiIndicating the historical optimum position of the ith particle, gbest indicating the historical optimum position of the particle population,
Figure BDA0002929803170000053
Figure BDA0002929803170000054
which represents the velocity of the ith particle,
Figure BDA0002929803170000055
indicating the position of the ith particle.
Step 1.6: and if the current iteration number is larger than the maximum iteration number G or the source target is successfully identified, executing the step 1.7, otherwise, returning to the step 1.4 to carry out the next iteration.
Step 1.7: all agents move to the optimal position gbest.
Further, in step 1.4 above, a multi-agent path planning method is proposed, where a local search strategy is used to plan a moving path for each agent, so that a group traverses all target positions, and the moving distance and the search time of the multi-agent are optimized at the same time, and the specific steps are as follows:
step 1.4.1: dividing the multi-agent into m/n groups according to the following formula, wherein the number of the i-th group of agents is Λ (i), the number of the agents is m, and each group independently executes the search task:
Figure BDA0002929803170000061
step 1.4.2: initializing a time vector τ[1×m]And loss matrix F[m×n]The following were used:
τ[1×m]＝{0，...，0}；
Figure BDA0002929803170000062
wherein, tauiRepresenting the total time of movement of the ith agent in the current iteration, and F (i, j) representing the ith agent from the current location SiMove to the target position XjThe required cost, a is 0.2, which is a weight constant used for balancing the influence of the moving distance and the searching time on the multi-agent performance,
Figure BDA0002929803170000063
denotes the position p1To p2V represents the moving speed of the agent, and the default value is 1.
Step 1.4.3: calculating the minimum value of the loss matrix, setting the minimum value as F (i, j), and moving the ith agent to the target position XjWherein, the accessed target position is not accessed again, and the update related parameters are as follows:
Figure BDA0002929803170000064
Figure BDA0002929803170000065
where f represents a set of target locations that are not accessed.
Step 1.4.4: step 1.4.3 is repeated until all target locations have been visited.
The invention is a multi-agent target search method with universality, in the proposed framework, the particle swarm algorithm based on can be any particle swarm variant, in each iteration process, the proposed local search algorithm is used for carrying out optimal path planning on the multi-agent, the moving distance and the search time of the multi-agent can be obviously reduced, and the reduction of energy consumption and the improvement of the search efficiency are realized. And the searching precision, the anti-interference capability and other performances of the method can be continuously improved along with the development of the intelligent optimization field of the particle swarm. The multi-agent system implementing the method can effectively complete the source positioning task through cooperation, allows the agents in the cluster to have random faults, failures, damages and other severe conditions, and has wide application prospect.
Authentication
To demonstrate the generality of this example, experiments were conducted with both smart sufficiency and smart deficiency, and in each case multi-agent path method deployment was conducted based on classical SPSO (d.branch and j.kennedy, "Defining a standard for particulate switch optimization," in proc.ieee switch integrity Symposium, pp.120-127, 2007.) and newer DEPSO (j.zhang, x.zhu, y.wang, and m.zhou, "Dual-environmental particulate switch optimization in noise and noise-environment," IEEE Transactions on Cybernetics, vol.49, No.6, pp.2011-2021, 2019.), respectively, to complete the multi-agent target search planning task.
In the case of sufficient agents, the number m of the agents is set to be 50, and compared with the direct application of the SPSO, after the method disclosed by the invention is adopted based on the SPSO, the moving distance of the agent cluster is reduced by 66.3%, and the search time is reduced by 69.1%. Compared with the direct application of DEPSO, after the method disclosed by the invention is adopted based on DEPSO, the moving distance of the intelligent cluster is reduced by 80.6%, and the search time is reduced by 73.1%.
In the absence of the agent, the number m of the agents is set to be 5, and compared with the direct application of the SPSO, after the method disclosed by the invention is adopted based on the SPSO, the moving distance of the agent cluster is reduced by 82.3%, and the search time is reduced by 77.6%. Compared with the direct application of DEPSO, after the method disclosed by the invention is adopted based on DEPSO, the moving distance of the intelligent cluster is reduced by 72.9%, and the search time is reduced by 70.9%.
The overall situation is shown in table 1:
TABLE 1 Algorithm comparative experimental data
Figure BDA0002929803170000071
The above is a further detailed description of the present invention, and it should not be considered that the embodiments of the present invention are limited thereto, and it will be apparent to those skilled in the art that various changes and modifications can be made without departing from the spirit and scope of the present invention.

Claims (2)

1. A multi-agent cooperative target searching method based on particle swarm optimization is characterized by comprising the following specific steps:
step 1.1: in an application scene, multiple intelligent agents are distributed, the multiple intelligent agents are regarded as particle swarms, the intelligent agents are regarded as particles, environment modeling is carried out, and field source signal values detected by intelligent agent sensors are used as fitness indexes of a particle swarms.
Step 1.2: initializing particle swarm algorithm parameter setting: the particle swarm size n, the optimization dimension D and the maximum iteration number G.
Step 1.3: initializing the initial position x of n particles at random ═ { x ═ x1，x2，...，xnV and velocity v ═ v1，v2，...，vnInitializing the positions S ═ S of m agents1，S2，...，SmAnd velocity V.
Step 1.4: the multi-agent carries out optimal path planning through a local search strategy so as to traverse all current particle positions x ═ { x ═ x1，x2，...，xnAnd acquiring the field intensity f (x) of each target position by using a sensori) As a fitness value for that location.
Step 1.5: and updating the speed and the position of the particles by a particle swarm algorithm, wherein the updating formulas are respectively as follows:
Figure FDA0002929803160000011
Figure FDA0002929803160000012
wherein, c1、c2Is a constant acceleration factor, and c1＝c2＝2.05，r1、r2Is a D-dimensional random number vector, pbestiIndicating the historical optimum position of the ith particle, gbest indicating the historical optimum position of the particle population,
Figure FDA0002929803160000013
Figure FDA0002929803160000014
which represents the velocity of the ith particle,
Figure FDA0002929803160000015
indicating the position of the ith particle.
Step 1.6: and if the current iteration number is larger than the maximum iteration number G or the source target is successfully identified, executing the step 1.7, otherwise, returning to the step 1.4 to carry out the next iteration.
Step 1.7: all agents move to the optimal position gbest.
2. A multi-agent path planning method based on the search method of claim 1, wherein in step 1.4, a local search strategy is used to plan a moving path for each agent, so that the agent traverses all particle positions, and optimizes the moving distance and the search time of the multi-agent simultaneously, which comprises the following specific steps:
step 1.4.1: dividing a plurality of intelligent agents into the following formulas
Figure FDA0002929803160000021
And the number of the i-th group of agents is Λ (i), the number of the agents is m, and each group independently executes the search task:
Figure FDA0002929803160000022
step 1.4.2: initializing a time vector τ[1×m]And loss matrix F[m×n]The following were used:
τ[1×m]＝{0，...，0}；
Figure FDA0002929803160000023
wherein, tauiRepresenting the total time of movement of the ith agent in the current iteration, and F (i, j) representing the ith agent from the current location SiMove to the target position XjThe required cost, a ∈ [0, 1 ]]A weight constant for balancing the influence of the moving distance and the search time on the multi-agent performance,
Figure FDA0002929803160000024
denotes the position p1To p2V represents the moving speed of the agent.
Step 1.4.3: calculating the minimum value of the loss matrix, setting the minimum value as F (i, j), and moving the ith agent to the target position XjWherein, the accessed target position is not accessed again, and the update related parameters are as follows:
Figure FDA0002929803160000025
Figure FDA0002929803160000026
where f represents a set of target locations that are not accessed.
Step 1.4.4: step 2.3 is repeated until all target locations have been visited.
CN202110145980.4A 2021-02-02 2021-02-02 Particle swarm algorithm-based multi-agent cooperative target searching method Active CN112966803B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110145980.4A CN112966803B (en) 2021-02-02 2021-02-02 Particle swarm algorithm-based multi-agent cooperative target searching method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110145980.4A CN112966803B (en) 2021-02-02 2021-02-02 Particle swarm algorithm-based multi-agent cooperative target searching method

Publications (2)

Publication Number Publication Date
CN112966803A true CN112966803A (en) 2021-06-15
CN112966803B CN112966803B (en) 2022-06-07

Family

ID=76272056

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110145980.4A Active CN112966803B (en) 2021-02-02 2021-02-02 Particle swarm algorithm-based multi-agent cooperative target searching method

Country Status (1)

Country Link
CN (1) CN112966803B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114371748A (en) * 2021-12-15 2022-04-19 同济大学 Greenhouse crop illumination carbon dioxide regulation and control method based on Gaussian curvature

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103278151A (en) * 2013-02-28 2013-09-04 中国矿业大学 Method for multirobot to search smell sources with cooperation under the dynamic smoke plumage environment
CN105425820A (en) * 2016-01-05 2016-03-23 合肥工业大学 Unmanned aerial vehicle cooperative search method for moving object with perception capability
CN108958028A (en) * 2018-05-24 2018-12-07 大连理工大学 Based on the group robot collaboratively searching method for improving particle swarm algorithm
CN111176334A (en) * 2020-01-16 2020-05-19 浙江大学 Multi-unmanned aerial vehicle cooperative target searching method
CN111487995A (en) * 2020-04-30 2020-08-04 湖南科技大学 Multi-target search cooperation method for group unmanned aerial vehicle based on three-dimensional simplified virtual model
CN111539511A (en) * 2020-04-28 2020-08-14 三峡大学 Particle swarm optimization algorithm based on multi-strategy fusion

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103278151A (en) * 2013-02-28 2013-09-04 中国矿业大学 Method for multirobot to search smell sources with cooperation under the dynamic smoke plumage environment
CN105425820A (en) * 2016-01-05 2016-03-23 合肥工业大学 Unmanned aerial vehicle cooperative search method for moving object with perception capability
CN108958028A (en) * 2018-05-24 2018-12-07 大连理工大学 Based on the group robot collaboratively searching method for improving particle swarm algorithm
CN111176334A (en) * 2020-01-16 2020-05-19 浙江大学 Multi-unmanned aerial vehicle cooperative target searching method
CN111539511A (en) * 2020-04-28 2020-08-14 三峡大学 Particle swarm optimization algorithm based on multi-strategy fusion
CN111487995A (en) * 2020-04-30 2020-08-04 湖南科技大学 Multi-target search cooperation method for group unmanned aerial vehicle based on three-dimensional simplified virtual model

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
JUNQI ZHANG ET.AL: "Moving-Distance-Minimized PSO for Mobile Robot Swarm", 《IEEE TRANSACTIONS ON CYBERNETICS》 *
张勇 等: "室内噪声环境下气味源的多机器人微粒群搜索方法", 《电子学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114371748A (en) * 2021-12-15 2022-04-19 同济大学 Greenhouse crop illumination carbon dioxide regulation and control method based on Gaussian curvature
CN114371748B (en) * 2021-12-15 2022-09-20 同济大学 Greenhouse crop illumination carbon dioxide regulation and control method based on Gaussian curvature

Also Published As

Publication number Publication date
CN112966803B (en) 2022-06-07

Similar Documents

Publication Publication Date Title
Pomerleau et al. Long-term 3D map maintenance in dynamic environments
CN110110763B (en) Grid map fusion method based on maximum public subgraph
CN105865449A (en) Laser and vision-based hybrid location method for mobile robot
US6577906B1 (en) Distributed optimization system and method
CN110471426A (en) Unmanned intelligent vehicle automatic Collision Avoidance method based on quantum wolf pack algorithm
Bhat et al. Is localization of wireless sensor networks in irregular fields a challenge?
CN113131985B (en) Multi-unmanned-aerial-vehicle data collection method based on information age optimal path planning
CN102325370A (en) High-precision three-dimensional positioner for wireless sensor network node
Wu et al. Robust LiDAR-based localization scheme for unmanned ground vehicle via multisensor fusion
CN112966803B (en) Particle swarm algorithm-based multi-agent cooperative target searching method
Zamora et al. Recent advances on simultaneous localization and mapping for mobile robots
CN117270545A (en) Convolutional neural network-based substation wheel type inspection robot and method
CN111163479A (en) Node optimization deployment method suitable for wireless locatable sensor network
Ye et al. Robot indoor positioning and navigation based on improved wifi location fingerprint positioning algorithm
Wu et al. UWB base station cluster localization for unmanned ground vehicle guidance
CN116611468A (en) Particle swarm search method based on communication-free robots
Scherer et al. Efficient C-space and cost function updates in 3D for unmanned aerial vehicles
CN103777200A (en) RFID positioning node arrangement method for mobile robot, and RFID auxiliary positioning navigation method for mobile robot
Zhang et al. Exploration with global consistency using real-time re-integration and active loop closure
CN114596360A (en) Double-stage active instant positioning and graph building algorithm based on graph topology
Lu et al. ONavi: Data-driven based multi-sensor fusion positioning system in indoor environments
CN117007047A (en) Particle swarm algorithm multi-source positioning method based on virtual target and virtual population
Li et al. Path Planning of UAV Navigation Mark Inspection Using a K-means Clustering ACA
Li et al. Research on Rao-Blackwellized Particle Filter SLAM Based On Grey Wolf Optimizer
Deng et al. Study on LiDAR Obstacle Detection for FSAC Racing Car Chiji

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