CN110750095A - Robot cluster motion control optimization method and system based on 5G communication - Google Patents
Robot cluster motion control optimization method and system based on 5G communication Download PDFInfo
- Publication number
- CN110750095A CN110750095A CN201910832918.5A CN201910832918A CN110750095A CN 110750095 A CN110750095 A CN 110750095A CN 201910832918 A CN201910832918 A CN 201910832918A CN 110750095 A CN110750095 A CN 110750095A
- Authority
- CN
- China
- Prior art keywords
- grid
- mobile robot
- robot
- path
- pheromone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004891 communication Methods 0.000 title claims abstract description 52
- 230000033001 locomotion Effects 0.000 title claims abstract description 48
- 238000005457 optimization Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 26
- 239000002245 particle Substances 0.000 claims abstract description 73
- 239000003016 pheromone Substances 0.000 claims description 73
- 241000257303 Hymenoptera Species 0.000 claims description 30
- 230000007704 transition Effects 0.000 claims description 11
- 230000002787 reinforcement Effects 0.000 claims description 8
- VWDWKYIASSYTQR-UHFFFAOYSA-N sodium nitrate Chemical compound [Na+].[O-][N+]([O-])=O VWDWKYIASSYTQR-UHFFFAOYSA-N 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000007423 decrease Effects 0.000 claims description 4
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000003491 array Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 241001652065 Trigonopeltastes delta Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003638 chemical reducing agent Substances 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000011089 mechanical engineering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- XOOUIPVCVHRTMJ-UHFFFAOYSA-L zinc stearate Chemical compound [Zn+2].CCCCCCCCCCCCCCCCCC([O-])=O.CCCCCCCCCCCCCCCCCC([O-])=O XOOUIPVCVHRTMJ-UHFFFAOYSA-L 0.000 description 1
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
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0287—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling
-
- 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
- G05D1/0011—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot associated with a remote control arrangement
- G05D1/0022—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot associated with a remote control arrangement characterised by the communication link
-
- 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
- G05D1/0011—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot associated with a remote control arrangement
- G05D1/0027—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot associated with a remote control arrangement involving a plurality of vehicles, e.g. fleet or convoy travelling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- 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
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention discloses a robot cluster motion control optimization method and system based on 5G communication. The system comprises a mobile robot control module, a mobile robot communication module and a mobile robot positioning module. Aiming at the motion control of a robot cluster in an environment, a central control system in the environment performs cluster division on robots in the environment by using information such as environment data and robot data, then calculates optimal path information by using a particle swarm optimization-ant colony optimization algorithm, then sends a motion control command to a robot cluster control module, and determines a motion strategy to be performed by a mobile robot communication module and controls the motion of the robot cluster by using the mobile robot control module after the mobile robot communication module receives the motion control command and in combination with position information of a mobile robot positioning module of the mobile robot communication module. The system is a high-speed, ubiquitous network (the network in an environment area is wide), low-power-consumption and low-time-delay system established by carrying a 5G communication module.
Description
Technical Field
The invention relates to the technical field of robot control, in particular to a robot cluster motion control optimization method and system based on 5G communication.
Background
The mobile robot is a comprehensive system integrating multiple functions of environment perception, dynamic decision and planning, behavior control and execution and the like. The method integrates the research results of multiple subjects such as sensor technology, mechanical engineering, electronic engineering, computer engineering, automatic control engineering, artificial intelligence and the like, represents the highest achievement of mechanical-electrical integration, and is one of the most active fields of scientific and technical development at present. With the continuous improvement of the performance of the robot, the application range of the mobile robot is greatly expanded, and the mobile robot is not only widely applied to industries such as industry, agriculture, national defense, medical treatment, service and the like, but also well applied to harmful and dangerous occasions such as mine clearance, search and catch, rescue, radiation, space fields and the like. Therefore, mobile robotics has gained widespread attention in countries around the world.
With the rapid development of the 5G technology and the continuous and deep research of the intelligent robot, the intelligent robot product based on the 5G communication has become a hot spot of current social attention. The 5G communication is used as a communication mode of the intelligent mobile robot, so that communication information can be transmitted in a high-speed and low-delay mode. Aiming at the scene of cooperative control of a large number of robots in the environment, the robots need to be clustered, and then by utilizing the characteristics of high speed (high information communication transmission speed), ubiquitous network (wide network in an environment area), low power consumption, low time delay and large bandwidth of a 5G network, a central control system in the area establishes control over robot groups through the 5G network, which is the key point of future robot technical development.
Therefore, there is a need to develop a control system and method based on 5G communication for remotely controlling the motion of a robot cluster, which is significant for the development of robot technology.
Disclosure of Invention
In view of this, the present application provides a robot cluster motion control optimization method and system based on 5G communication. The intelligent mobile robot cluster is controlled to run more safely and efficiently through the remote control center in a high-speed and low-delay communication mode.
The application is realized by the following technical scheme:
a robot cluster motion control optimization system based on 5G communication comprises: the mobile robot system comprises a mobile robot control module, a mobile robot communication module and a mobile robot positioning module;
the mobile robot control module is respectively connected with the mobile robot communication module and the mobile robot positioning module, combines a motion control instruction obtained from the mobile robot communication module with position information obtained from the mobile robot positioning module, realizes path planning of the mobile robot through an ant colony-particle swarm intelligent algorithm, and controls a motion track of the mobile robot;
the mobile robot communication module is respectively connected with the mobile robot control module and the mobile robot positioning module, and the mobile robot communication module completes internal communication of the mobile robot through one or more communication modes of a GPIO module, an RS485, an IIC and a CAN bus and completes external communication between the mobile robot and a central control system;
the mobile robot positioning module is respectively connected with the mobile robot control module and the mobile robot positioning module, and the mobile robot positioning module is used for positioning the mobile robot.
Further, the implementing the path planning of the mobile robot through the ant colony-particle swarm intelligent algorithm to control the motion trajectory of the mobile robot specifically includes:
step1, initializing an environment map;
step2, carrying out rough path search on the cluster of the mobile robots in the environment map by utilizing a particle swarm optimization algorithm to generate an optimized path, wherein the cluster of the mobile robots is a set of robots which have the same position information and the same target position information and the same motion characteristics in a control area of the same central control system;
and 3, further searching the cluster of the mobile robot in the environment map by using an ant colony optimization algorithm to generate an optimal path.
Further, the initializing the environment map specifically includes:
the method comprises the steps of importing an environment map, rasterizing the environment map, establishing a rectangular coordinate system in the environment, setting a unit step length of a robot to be R, dividing grids by taking R as a unit respectively for an x axis and a y axis of the established rectangular coordinate system, wherein each grid is provided with a corresponding coordinate and a corresponding serial number, completing the mapping relation between the coordinates and the serial numbers of the grids, and representing a limited number of obstacles in the environment as a free-passing area and an obstacle area through 0 and 1 respectively.
Further, the mapping relationship between the coordinates of the completion grid and the serial number is calculated by the following formula:
wherein x isp，ypRespectively, the abscissa and ordinate of the grid with the serial number p, mod is the remainder calculation, m is the number of grids in each row, and int is the rounding operation.
Further, the particle swarm optimization algorithm specifically includes:
step1, obtaining a two-dimensional array table of grid environment information in a rasterization environment;
step2, setting parameters including particle population size NpMaximum inertial weight ωmaxMinimum inertial weight ωminLearning factor c1And c2And a maximum number of iterations Niter,maxMaximum velocity Vmax；
Step3, randomly generating a position vector x of the particle i in a corresponding rangei＝(xi1,xi2,…,xiD) And velocity vector Vi＝(vi1,vi2,…,viD) For the historical optimum Pb of the particleiInitializing the global optimal value Gb of the particle swarm to enable Pb to bei＝xi，
Wherein i is 1,2, …, NpD represents the size of the dimension within the particle;
step4, calculating the current fitness f (x) of each particle ii) If f (x)i)＜f(Pbi) Then let Pb standi＝xi，f(xi)＝min(f(Pbi) ); if f (x)i) < f (Gb), let Gb ═ xi；
Step5, the velocity V of the particle is updated according to the following formula, if Vi>VmaxThen V isi＝Vmax(ii) a If Vi<-VmaxThen V isi＝-Vmax；
Vi′＝ωVi+c1·rand(0,1)(Pi-Xi)+c2·rand(0,1)(Gb-Xi)
Wherein, Vi' updated speed, ViFor pre-update speed, ω is the inertial weight, c1And c2For the learning factor, rand (0,1) is a random number between the (0,1) range, PiIn order to represent the individual extremum searched by the ith particle so far, Gb represents the global optimal value of the particle swarm, and omega is a weighting coefficient;
step6, update the particle according to the following formula:
x′i＝xi+v′i
wherein x' i is the updated particle, xiIs speed before update, v'iIs the updated velocity of the particle;
step7, if the algorithm reaches the maximum iteration times or the calculated fitness value reaches a certain precision requirement, the algorithm is ended; otherwise go to Step 4.
Further, the weighting coefficient is calculated according to the following formula:
ω＝ωmax-Niter(ωmax-ωmin)/Niter,max
where ω is the particle velocity pair used to control the previous timeThe weighting factor of the velocity contribution at the current moment, which decreases with increasing number of iterations, NiterFor the current update iteration algebra, Niter,maxFor maximum update iteration algebra, omegamaxIs a preset maximum weighting coefficient, omegaminIs a preset minimum weighting factor, ωmaxAnd omegaminAre all real numbers between the (0,1) range.
Further, after the performing the coarse search of the path to generate an optimized path, the method further includes:
setting pheromone reinforcement values for grids passed by the optimized path, and setting the pheromone reinforcement value from grid i to grid j on the optimized path to be delta tauijObtaining initial value of pheromone according to environment information, setting initial pheromone from grid i to grid j
For the initial pheromone distributed on the path from each grid to the adjacent grid, ants search from the grid where the robot cluster initial position area S is located, for the position difference of each grid, the grid is divided into a boundary grid and a middle grid, for the middle grid, assuming that no obstacle exists around the middle grid, next, search can be performed to 8 adjacent directions, wherein the 8 directions are respectively: the distance definitions of the lower right, upper left, lower right, the current grid and its adjacent 8 orientations are represented by the following arrays:
for the boundary grid, the serial numbers of grids which cannot be reached because the grid is at the boundary are removed from the next searching direction;
initial value tau of pheromone from grid i to grid jijDetermined according to the following formula:
wherein, tauijThe initial value of pheromone from grid i to grid j, a is a set constant, and j is the grid adjacent to i;
determining an initial value of the pheromone and a reinforcement value of the pheromone, then performing redistribution of the pheromone, and determining the redistribution of the pheromone according to the following formula:
wherein, tau'ijFor a new distribution of pheromones from grid i to grid j, τijFor the initial value of the pheromone from grid i to grid j, Δ τijReinforcement values for pheromones from grid i to grid j;
setting the distance d from the center point of the grid i to the center of the grid of the target position to which the robot cluster is to be locatedi；
Defining 4 grids on the left, right, top and bottom adjacent to the grid i as directly adjacent grids, and 4 grids on the left, top left, bottom left, top right and bottom right as indirectly adjacent grids, wherein the reachable grids are determined according to the following rules:
dj<dij is directly adjacent to i and is a free grid;
dj<dij is indirectly adjacent to i and j and both the two directly adjacent grids adjacent to i that tend to j are free grids.
When an ant is on a boundary grid, the search considers only the free grid adjacent to it.
Further, the ant colony optimization algorithm specifically includes the following steps:
step1, setting the number N of ants in the ant colony algorithmaAnd maximum number of cycles MaObtaining a global optimized path Gb ═ x by using a particle swarm algorithm1,x2,…,xD) Calculating each initial pheromone in the environment, and setting the initial position of an ant in the ant colony algorithm as a position grid where the robot cluster is located;
step2, starting the ant colony, wherein each ant selects the next path point according to the state transition rulek the transition probability of selecting the next reachable grid j when grid i is at time t is
Determining the transition probability for ant k to select the next reachable grid j when it is at grid i at time t according to:
in the formula (I), the compound is shown in the specification,
selecting the transition probability, τ, of the next reachable grid j for ant k when it is at grid i at time tij(t) the amount of information remaining on the route from grid i to grid j at time t, α the relative importance of the pheromone, β the relative importance of the distance information, Dj＝Q/djQ is a set constant, djThe distance from the center point of the grid j to the center of the grid of target positions to which the robot cluster is to be located. T isallowed,kThe system is a tabu watch and is used for storing the grid position where the kth ant has walked;
step3 repeats Step2 until all the set ants reach the target position grid to which the robot cluster is going.
Step4, calculating the path length L of each ant, and recording the current optimal path.
Step5, updating the path information of the week-trip optimal ants and the global optimal ants by using pheromones on each path;
step6, if the ant colony is totally converged to a path or reaches the maximum cycle number MaIf yes, the circulation is ended, otherwise, the Step2 is executed;
and Step7, outputting the passing grid serial number information of the current global optimal path, converting the information into a motion command, and sending the motion command to each robot in the robot cluster through the important controller.
Further, in Step2, ant k generates tabu table T in the process of searching for pathallowed,kStore the institute's experienceAfter the ants search for a cycle, the ants determine which ant searched for a better path according to the objective function value.
Further, in Step5, when each ant walks through 1 designated position, that is, a unit time, the pheromone is updated, and the pheromone amount on the path from i to j at the time t +1 can be adjusted according to the following formula:
τi,j(t+1)＝(1-ρ)τi,j(t)+Δτi,j(t)
in the formula, τi,j(t +1) is the pheromone amount on the path from i to j at the time of t +1, rho is the pheromone volatilization coefficient, rho belongs to (0,1), and 1-rho represents the pheromone amount residual factor; tau isi,j(t) the amount of pheromones on the path from the i position to the j position at time t; delta taui,j(t) information increment of ants on the path in the cycle; a isk,bkThe integer variable respectively represents the weight of updating pheromone by week-tour optimal ants and global optimal ants, and the sum of the weights is a constant; l iscPath length, L, for optimal path of the circumambulated antsωPath length of the optimal path for the global ant.
The invention can obtain the following beneficial effects:
1) aiming at the motion control of a robot cluster in an environment, a central control system in the environment performs cluster division on robots in the environment by utilizing information such as environment data and robot data, then calculates optimal path information by utilizing a particle swarm optimization-ant colony optimization algorithm, then sends a motion control command to a robot cluster control module, and determines a motion strategy to be performed by a mobile robot communication module and utilizes the mobile robot control module to control the motion of the robot cluster by combining position information of a mobile robot positioning module after the mobile robot communication module receives the motion control command;
2) the system is a system which is built by carrying a 5G communication module, has high speed (high information communication transmission speed), ubiquitous network (the network in an environment area is wide), low power consumption and low time delay.
Drawings
FIG. 1 is a schematic diagram of a robot cluster motion control system based on 5G communication according to the present invention;
FIG. 2 is a diagram illustrating an exemplary application of the present invention;
FIG. 3 is an exemplary diagram of robot cluster division and robot cluster path optimization according to the present invention;
fig. 4 is a flowchart of the ant colony-particle swarm optimization algorithm for the path optimization of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
The invention will be described in further detail below with reference to the drawings and examples.
The invention provides a robot cluster motion control optimization method and system based on 5G communication, wherein the system comprises a mobile robot control module, a mobile robot communication module and a mobile robot positioning module;
the mobile robot control module is connected with the mobile robot communication module and the mobile robot positioning module, and controls the mobile robot to move according to a specified instruction by combining a motion control instruction obtained by the mobile robot communication module and the position information of the mobile robot positioning module;
the mobile robot communication module is connected with the mobile robot control module and the mobile robot positioning module, and the module CAN complete the internal communication of the robot in one or more communication modes of the GPIO module, the RS485, the IIC and the CAN bus and complete the external communication between the mobile robot end and the regional central control system through the 5G communication module.
The mobile robot positioning module is connected with the mobile robot control module and the mobile robot positioning module, and is used for positioning the mobile robot, and sensing and fusing various equipment information such as a camera, an ultrasonic radar, a laser radar, an encoder and an IMU (inertial navigation module) to realize the positioning of the robot.
The robot comprises a robot encoder, a depth camera, an ultrasonic radar, an inertial navigation module IMU and a laser radar, wherein the depth camera carried by the robot detects depth camera information of an environment, the ultrasonic radar obtains ultrasonic feedback information of the environment, the laser radar obtains laser radar information of the environment, the inertial navigation module IMU obtains yaw angle information of the robot, and the robot encoder acquires speed information of the robot. And the yaw angle information output by the inertial navigation device is fused with the speed information acquired by the encoder, so that the offset of the robot relative to the driving route is calculated. The robot motion system is formed by independently driving independent wheels by two direct current motors with speed reducers and encoders. The rotation angular velocity of the driving wheel can be measured by installing an additional layer to install necessary equipment, and an inertia measuring unit and a two-dimensional laser radar are installed at the same time. The lidar "scans" the environment to build up an environment map. The laser radar scans obstacle distance data within the range of 180 degrees, and polar coordinates are adopted to represent the distance data, so that a view is obtained by scanning the laser radar. Self-positioning is carried out by combining with the encoder distance information in the running process of the robot, so that an incremental map is generated, a robot view is further generated, and a global map is created through multiple map updating. A RaoBlackwell particle filter is mainly used when an environment map is built, and the core idea of the method is that firstly, a particle filter is used for estimating the track of a robot, and then the track estimation is used for calculating the posterior estimation of the environment map, so that the map building and the self positioning are realized.
A robot cluster movement control optimization method based on 5G communication is characterized in that a robot cluster division process is that a robot in an environment transmits position information and task information of the robot to a central control system through a 5G communication module, the central control system plans a cluster matrix of the robot in a unified mode, the central control system determines a boundary range of a unit area, and all robots in the environment are divided into different robot clusters according to a current position area and a target position area to be reached.
A robot cluster motion control optimization method based on 5G communication is characterized in that an ant colony-particle swarm intelligent algorithm considering obstacle avoidance comprises the following steps:
1) the method comprises the steps of importing an environment map, rasterizing the environment map, establishing a rectangular coordinate system in the environment, setting the robot to divide grids by a certain step length (the unit step length is set as R), wherein the x axis and the y axis of the established rectangular coordinate system respectively divide the grids by taking R as a unit, each grid has corresponding coordinates and serial numbers, a limited number of obstacles exist in the environment, the attribute of whether each grid is an obstacle area is represented by binary information, and the attribute is respectively represented as a free-passing area and an obstacle area by 0 and 1.
The algorithm utilizes the following formula to complete the mapping relation between the coordinates and the serial number of the grid.
In the formula: x is the number ofp，ypRespectively the abscissa and ordinate of the grid with the serial number p, mod is the remainder calculation, m is the number of grids in each row, and int is the indexAnd (6) performing integer operation.
The robot cluster is to avoid an obstacle in the environment and move from a current position area to a target position area, the shortest optimized path can be obtained by considering an ant colony-particle swarm intelligent algorithm for obstacle avoidance, the length of the path is calculated by the following formula in the algorithm, and the minimum value of the path is used as an objective function of the algorithm;
where L is the length of the path, npFor the total number of grid points on the selected path, (x)i,yi) Is the grid position information on the selected path.
2) And carrying out coarse search on the paths of the mobile robot cluster in the environment by utilizing a particle swarm optimization algorithm to generate an optimized path.
The mobile robot cluster is a robot set which has the same position information and target position information in the same central controller control area and has certain same motion characteristics;
the particle swarm optimization algorithm is characterized in that:
in a particle swarm algorithm system, each individual particle represents a path for a robot cluster to make a decision, such as x, from a current location area to a target location areai＝(xi1,xi2,…,xiD) Wherein D represents the dimension of the particle, i.e. the number of grids that the robot cluster to be decided passes through on a path from the current position area to the target position area, each dimension represents a grid, the first dimension of the particle represents the grid number of the area of the current position of the robot cluster, the last dimension of the particle represents the grid number of the area of the target position that the robot cluster will go through, and the grid numbers in the particle are sequentially connected to form the path that the robot cluster will pass through.
The method is characterized in that an adaptive value function is properly selected in a particle swarm optimization algorithm system to ensure that an optimal path is obtained, the shortest path is taken as an evaluation standard, and the fitness function is selected as follows:
wherein f is a fitness function in the particle swarm optimization algorithm, n is the number of grids passed by a path, and L is the path length of the path.
The particle swarm optimization algorithm comprises the following specific steps:
step1, obtaining a two-dimensional array table of grid environment information in a rasterization environment;
step2 parameter set, including particle population size (set to N)p) Maximum inertial weight (set to ω)max) Minimum inertial weight (set to ω)min) Learning factor (set to c)1And c2) And maximum number of iterations (set to N)iter,max) Maximum speed (set as V)max)。
Step3 randomly generates a position vector x of particle i in a corresponding rangei＝(xi1,xi2,…,xiD) And velocity vector Vi＝(vi1,vi2,…,viD) For the historical optimum Pb of the particleiInitializing the global optimal value Gb of the particle swarm to enable Pb to bei＝xi，
Wherein i is 1,2, …, Np。
Step4 calculates the current fitness f (x) of each particle ii). If f (x)i)<f(Pbi) Then let Pb standi＝xi，
If f (x)i)<f (Gb), let Gb be xi。
Step5 the velocity V of the particle is updated according to the following formula if Vi>VmaxThen V isi＝Vmax(ii) a If Vi<-VmaxThen V isi＝-Vmax。
V′i＝ωVi+c1·rand(0,1)(Pi-Xi)+c2·rand(0,1)(Gb-Xi)
V 'in formula'iFor updated speed, ViFor pre-update speed, ω is the inertial weight, c1And c2For the learning factor, rand (0,1) is a random number between the (0,1) range, PiGb indicates the global optimum of the particle population in order to indicate the individual extremum searched so far for the ith particle. Omega is a weighting coefficient, the weighting coefficient omega is used for controlling the influence of the particle update speed at the previous moment on the particle update speed at the current moment, the motion inertia of the particles can be kept, the particles are promoted to have enough capacity to explore a new space, the omega value is reduced along with the particle update speed in the continuous iteration process of the algorithm, the individual extreme value and the global value are continuously updated, the global optimum is finally achieved, and the expression of the weighting coefficient is as follows:
ω＝ωmax-Niter(ωmax-ωmin)/Niter,max
where ω is a weighting factor for controlling the influence of the particle velocity at the previous time on the velocity at the current time, which decreases as the number of iterations increases, and NiterFor the current update iteration algebra, Niter,maxFor maximum update iteration algebra, omegamaxIs a preset maximum weighting coefficient, omegaminIs a preset minimum weighting factor, ωmaxAnd omegaminAre all real numbers between the (0,1) range.
Step6 updates the particle according to the following equation.
x′i＝xi+v′i
X 'in the formula'iFor renewed particles, xiIs speed before update, v'iIs the updated velocity of the particle.
Step7, if the algorithm reaches the maximum iteration times or the calculated fitness value reaches a certain precision requirement, the algorithm is ended; otherwise go to Step 4.
3) And further searching the mobile robot cluster in the environment by using an ant colony optimization algorithm to generate an optimal path.
The ant colony optimization algorithm is characterized in that:
after obtaining an optimized path after the rough search, a certain pheromone reinforcement value is set for the grid which the optimized path passes through (the pheromone reinforcement value from grid i to grid j on the optimized path is set to be delta tauij) Obtaining initial value of pheromone according to environment information (setting grid i to grid j initial pheromone)
For the initial pheromone distributed on the path from each grid to the adjacent grid, ants search from the grid where the robot cluster initial position area S is located, for the position difference of each grid, the grid can be divided into a boundary grid and a middle grid, for the middle grid, assuming that no obstacles exist around the middle grid, next, search can be performed to 8 adjacent directions, wherein the 8 directions are respectively: right lower, right upper, upper left, left upper, left lower and lower. It can be seen that the distance definition of the current grid and its adjacent 8 orientations can be represented by the following array:
for the boundary grid, the next step is to remove the sequence number of the grid that is not reachable because it is at the boundary.
Initial value tau of pheromone from grid i to grid jijThe determination can be made according to the following formula.
In the formula, τijThe initial value of the pheromone from grid i to grid j is a set constant, and j is the grid adjacent to i.
Determining an initial value of the pheromone and an enhanced value of the pheromone, then implementing redistribution of the pheromone, and determining new initial pheromone distribution according to the following formula;
in formula (II) is τ'ijFor a new distribution of pheromones from grid i to grid j, τijFor the initial value of the pheromone from grid i to grid j, Δ τijThe pheromone from grid i to grid j is emphasized.
Setting the distance d from the center point of the grid i to the center of the grid of the target position to which the robot cluster is to be locatedi。
Defining 4 grids on the left, right, top and bottom adjacent to the grid i as directly adjacent grids, and 4 grids on the left, top left, bottom left, top right and bottom right as indirectly adjacent grids, wherein the reachable grids are determined according to the following rules:
if d isj<diJ is directly adjacent to i and is a free grid;
if it is
dj<diJ is indirectly adjacent to i and j and both the two directly adjacent grids adjacent to i that tend to j are free grids.
When the ant is in the boundary grid, the search only needs to consider the free grid adjacent to the ant, so that the search point of each step of the ant is limited to the grid which is closer to the target position grid than the current grid point.
The main steps of the ant colony-particle swarm algorithm can be described as follows:
step1, setting the number N of ants in the ant colony algorithmaAnd maximum number of cycles MaObtaining a global optimized path Gb ═ x by using a particle swarm algorithm1,x2,…,xD) And calculating each initial pheromone in the environment, and setting the initial position of the ant in the ant colony algorithm as a position grid where the robot cluster is located.
Step2 starts the ant colony, and each ant selects the next path point according to the state transition rule. Because the search range of each step of the ant is only limited to the adjacent grid of the grid where the ant is currently located, the problem of overlarge search calculation amount of each step is solved, and the algorithm directly follows the transfer outlineThe next waypoint is selected by the roulette method. In the algorithm, the transfer probability of selecting the next reachable grid j when the ant k is on the grid i at the time t is
The transition probability for ant k to select the next reachable grid j when it is at grid i at time t is determined according to the following equation.
In the formula (I), the compound is shown in the specification,
selecting the transition probability, τ, of the next reachable grid j for ant k when it is at grid i at time tij(t) the amount of information remaining on the route from grid i to grid j at time t, α the relative importance of the pheromone, β the relative importance of the distance information, Dj＝Q/djQ is a set constant, djThe distance from the center point of the grid j to the center of the grid of target positions to which the robot cluster is to be located. T isallowed,kThe ant is a tabu watch and is used for storing the grid positions where the kth ant has walked. Taboo list T generated by ant k in path searching processallowed,kThe serial number information of the passed grid point position information is stored, and the ants determine which ant has searched a better path according to the objective function value after searching a cycle.
In order to avoid deadlock of ants in the process of path searching, ants enter such grids when searching for path points: it is zero to the pheromone of the grid adjacent to it, at this time, a feedback message is added to make the ant return to the path point searched last time, and this grid is set as the barrier grid, and then the grid is not searched. Therefore, the condition of path deadlock formed when meeting a dead angle environment is effectively avoided, and the searching efficiency of the algorithm is improved.
Step3 repeats Step2 until all the set ants reach the target position grid to which the robot cluster is going.
Step4, calculating the path length L of each ant, and recording the current optimal path.
Step5, updating the path information of the week-trip optimal ants and the global optimal ants by the pheromone on each path.
In order to avoid that the residual information is too much to cause the residual information to inundate the heuristic information, the pheromone is updated every time each ant walks 1 designated position, namely walks a unit time, so that the pheromone amount on the path from i to j at the time of t +1 can be adjusted according to the following formula:
τi,j(t+1)＝(1-ρ)τi,j(t)+Δτi,j(t)
in the formula, τi,j(t +1) is the pheromone quantity on the path from i to j at time t +1, ρ is the pheromone volatility coefficient, ρ ∈ (0,1), and 1- ρ represents the pheromone quantity residual factor. Tau isi,j(t) is the amount of pheromone on the path from the i position to the j position at time t. Delta taui,jAnd (t) is the information increment of the ant on the path (from i to j) in the current cycle. The ants finish a search period, and one round trip is finished from a starting point to an end point. a isk,bkFor integer variables, represent the weights for updating pheromones with week-optimal ants and global-optimal ants, respectively, the sum of which is a constant (a)kThe value of (b) gradually decreases as the number of searches increases, bkThe value of (c) gradually increases as the number of searches increases). L iscPath length, L, for optimal path of the circumambulated antsωPath length of the optimal path for the global ant.
Step6, if the ant colony is totally converged to a path or reaches the maximum cycle number MaThe loop ends, otherwise Step2 is executed.
And Step7, outputting the passing grid serial number information of the current global optimal path, converting the information into a motion command, and sending the motion command to each robot in the robot cluster through the important controller.
It will be understood by those skilled in the art that all or part of the steps of the above methods may be implemented by instructing the relevant hardware through a program, and the program may be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, and the like. Alternatively, all or part of the steps of the foregoing embodiments may also be implemented by using one or more integrated circuits, and accordingly, each module/unit in the foregoing embodiments may be implemented in the form of hardware, and may also be implemented in the form of a software functional module. The present invention is not limited to any specific form of combination of hardware and software.
It should be noted that the present invention can be embodied in other specific forms, and various changes and modifications can be made by those skilled in the art without departing from the spirit and scope of the invention.
Claims (10)
1. A robot cluster motion control optimization system based on 5G communication is characterized by comprising: the mobile robot system comprises a mobile robot control module, a mobile robot communication module and a mobile robot positioning module;
the mobile robot control module is respectively connected with the mobile robot communication module and the mobile robot positioning module, combines a motion control instruction obtained from the mobile robot communication module with position information obtained from the mobile robot positioning module, realizes path planning of the mobile robot through an ant colony-particle swarm intelligent algorithm, and controls a motion track of the mobile robot;
the mobile robot communication module is respectively connected with the mobile robot control module and the mobile robot positioning module, and the mobile robot communication module completes internal communication of the mobile robot through one or more communication modes of a GPIO module, an RS485, an IIC and a CAN bus and completes external communication between the mobile robot and a central control system;
the mobile robot positioning module is respectively connected with the mobile robot control module and the mobile robot positioning module, and the mobile robot positioning module is used for positioning the mobile robot.
2. The robot cluster motion control optimization system according to claim 1, wherein the path planning of the mobile robot is implemented through an ant colony-particle swarm intelligent algorithm, and the motion trajectory of the mobile robot is controlled, specifically including:
step1, initializing an environment map;
step2, carrying out rough path search on the cluster of the mobile robots in the environment map by utilizing a particle swarm optimization algorithm to generate an optimized path, wherein the cluster of the mobile robots is a set of robots which have the same position information and the same target position information and the same motion characteristics in a control area of the same central control system;
and 3, further searching the cluster of the mobile robot in the environment map by using an ant colony optimization algorithm to generate an optimal path.
3. The robot cluster motion control optimization system of claim 2, wherein the initialization of the environment map specifically comprises:
the method comprises the steps of importing an environment map, rasterizing the environment map, establishing a rectangular coordinate system in the environment, setting a unit step length of a robot to be R, dividing grids by taking R as a unit respectively for an x axis and a y axis of the established rectangular coordinate system, wherein each grid is provided with a corresponding coordinate and a corresponding serial number, completing the mapping relation between the coordinates and the serial numbers of the grids, and representing a limited number of obstacles in the environment as a free-passing area and an obstacle area through 0 and 1 respectively.
4. The robot cluster motion control optimization system of claim 3, wherein the mapping between the coordinates of the completion grid and the serial number is calculated by the following formula:
wherein x isp，ypRespectively, the abscissa and ordinate of the grid with the serial number p, mod is the remainder calculation, m is the number of grids in each row, and int is the rounding operation.
5. The robot cluster motion control optimization system of claim 2, wherein the particle swarm optimization algorithm specifically comprises:
step1, obtaining a two-dimensional array table of grid environment information in the grid environment;
step2, setting parameters including particle population size NpMaximum inertial weight ωmaxMinimum inertial weight ωminLearning factor c1And c2And a maximum number of iterations Niter,maxMaximum velocity Vmax；
Step3, randomly generating a position vector x of the particle i in a corresponding rangei＝(xi1,xi2,…,xiD) And velocity vector Vi＝(vi1,vi2,…,viD) For the historical optimum Pb of the particleiInitializing the global optimal value Gb of the particle swarm to enable Pb to bei＝xi，Wherein i is 1,2, …, NpD represents the size of the dimension within the particle;
step4, calculating the current fitness f (x) of each particle ii) If f (x)i)＜f(Pbi) Then let Pb standi＝xi，f(xi)＝min(f(Pbi) ); if f (x)i) < f (Gb), let Gb ═ xi；
Step5, the velocity V of the particle is updated according to the following formula, if Vi>VmaxThen V isi＝Vmax(ii) a If Vi<-VmaxThen V isi＝-Vmax；
Vi′＝ωVi+c1·rand(0,1)(Pi-Xi)+c2·rand(0,1)(Gb-Xi)
Wherein, Vi' updated speed, ViFor pre-update speed, ω is the inertial weight, c1And c2For the learning factor, rand (0,1) is a random number between the (0,1) range, PiIn order to represent the individual extremum searched by the ith particle so far, Gb represents the global optimal value of the particle swarm, and omega is a weighting coefficient;
step6, update the particle according to the following formula:
x′i＝xi+v′i
x 'in the formula'iFor renewed particles, xiIs speed before update, v'iIs the updated velocity of the particle;
step7, if the algorithm reaches the maximum iteration times or the calculated fitness value reaches a certain precision requirement, the algorithm is ended; otherwise go to Step 4.
6. The robot cluster motion control optimization system of claim 5, wherein the weighting coefficients are calculated by the formula:
ω＝ωmax-Niter(ωmax-ωmin)/Niter,max
where ω is a weighting factor for controlling the influence of the particle velocity at the previous time on the velocity at the current time, which decreases as the number of iterations increases, and NiterFor the current update iteration algebra, Niter,maxFor maximum update iteration algebra, omegamaxIs a preset maximum weighting coefficient, omegaminIs a preset minimum weighting factor, ωmaxAnd omegaminAre all real numbers between the (0,1) range.
7. The robot cluster motion control optimization system of claim 2, further comprising, after the performing the coarse search of paths to generate an optimized path:
setting pheromone reinforcement values for grids passed by the optimized path, and setting the pheromone reinforcement value from grid i to grid j on the optimized path to be delta tauijObtaining initial value of pheromone according to environment information, setting initial pheromone from grid i to grid j
For the initial pheromone distributed on the path from each grid to the adjacent grid, ants search from the grid where the robot cluster initial position area S is located, for the position difference of each grid, the grid is divided into a boundary grid and a middle grid, for the middle grid, assuming that no obstacle exists around the middle grid, next, search can be performed to 8 adjacent directions, wherein the 8 directions are respectively: the distance definitions of the lower right, upper left, lower right, the current grid and its adjacent 8 orientations are represented by the following arrays:
for the boundary grid, the serial numbers of grids which cannot be reached because the grid is at the boundary are removed from the next searching direction;
initial value tau of pheromone from grid i to grid jijDetermined according to the following formula:
wherein, tauijThe initial value of pheromone from grid i to grid j, a is a set constant, and j is the grid adjacent to i;
determining an initial value of the pheromone and a reinforcement value of the pheromone, then performing redistribution of the pheromone, and determining the redistribution of the pheromone according to the following formula:
wherein, tau'ijFor a new distribution of pheromones from grid i to grid j, τijFor the initial value of the pheromone from grid i to grid j, Δ τijReinforcement values for pheromones from grid i to grid j;
setting the distance d from the center point of the grid i to the center of the grid of the target position to which the robot cluster is to be locatedi；
Defining 4 grids on the left, right, top and bottom adjacent to the grid i as directly adjacent grids, and 4 grids on the left, top left, bottom left, top right and bottom right as indirectly adjacent grids, wherein the reachable grids are determined according to the following rules:
dj<dij is directly adjacent to i and is a free grid;
dj<dij is indirectly adjacent to i and j and both the two directly adjacent grids adjacent to i that tend to j are free grids.
When an ant is on a boundary grid, the search considers only the free grid adjacent to it.
8. The robot cluster motion control optimization system of claim 2, wherein the ant colony optimization algorithm specifically comprises the steps of:
step1, setting the number N of ants in the ant colony algorithmaAnd maximum number of cycles MaObtaining a global optimized path Gb ═ x by using a particle swarm algorithm1,x2,…,xD) Calculating each initial pheromone in the environment, and setting the initial position of an ant in the ant colony algorithm as a position grid where the robot cluster is located;
step2, starting the ant colony, each ant selects the next path point according to the state transition rule, and the transition probability of the ant k selecting the next reachable grid j when the ant k is on the grid i at the time t is
According to the formulaDetermining a transition probability that ant k selects the next reachable grid j when it is at grid i at time t:
in the formula (I), the compound is shown in the specification,
selecting the transition probability, τ, of the next reachable grid j for ant k when it is at grid i at time tij(t) the amount of information remaining on the route from grid i to grid j at time t, α the relative importance of the pheromone, β the relative importance of the distance information, Dj＝Q/djQ is a set constant, djThe distance from the center point of the grid j to the center of the grid of target positions to which the robot cluster is to be located. T isallowed,kThe system is a tabu watch and is used for storing the grid position where the kth ant has walked;
step3 repeats Step2 until all the ants set up reach the target location grid for the robot cluster to reach.
Step4, calculating the path length L of each ant, and recording the current optimal path.
Step5, updating pheromones on each path according to the path information of the week-tour optimal ants and the global optimal ants;
step6 if the ant colony is totally converged to a path or reaches the maximum number of circulation MaIf yes, the loop is ended, otherwise, the Step2 is executed;
step7 outputs the passing grid serial number information of the current global optimal path, and the information is converted into motion commands and sent to each robot in the robot cluster through the important controller.
9. The robot cluster motion control optimization system of claim 8, wherein in Step2, ant k generates tabu table T in the process of searching pathallowed,kThe serial number information of the passed grid point position information is stored, and ants search for one cycle according to the target functionThe values determine which ant searched for a better path.
10. The robot cluster motion control optimization system of claim 8, wherein in Step5, the pheromone is updated every time each ant walks 1 designated position, i.e. a unit time, and the amount of pheromone on the path from i to j at time t +1 is adjusted according to the following formula:
τi,j(t+1)＝(1-ρ)τi,j(t)+Δτi,j(t)
in the formula, τi,j(t +1) is the pheromone amount on the path from i to j at the time of t +1, rho is the pheromone volatilization coefficient, rho belongs to (0,1), and 1-rho represents the pheromone amount residual factor; tau isi,j(t) the amount of pheromones on the path from the i position to the j position at time t; delta taui,j(t) information increment of ants on the path in the cycle; a isk,bkThe integer variable respectively represents the weight of updating pheromone by week-tour optimal ants and global optimal ants, and the sum of the weights is a constant; l iscPath length, L, for optimal path of the circumambulated antsωPath length of the optimal path for the global ant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910832918.5A CN110750095A (en) | 2019-09-04 | 2019-09-04 | Robot cluster motion control optimization method and system based on 5G communication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910832918.5A CN110750095A (en) | 2019-09-04 | 2019-09-04 | Robot cluster motion control optimization method and system based on 5G communication |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110750095A true CN110750095A (en) | 2020-02-04 |
Family
ID=69276153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910832918.5A Pending CN110750095A (en) | 2019-09-04 | 2019-09-04 | Robot cluster motion control optimization method and system based on 5G communication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110750095A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116400737A (en) * | 2023-06-02 | 2023-07-07 | 中国传媒大学 | Safety path planning system based on ant colony algorithm |
| CN116820110A (en) * | 2023-08-28 | 2023-09-29 | 武汉市自然资源保护利用中心 | Ecological environment monitoring task planning method and device based on intelligent optimization algorithm |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070019865A1 (en) * | 2005-03-04 | 2007-01-25 | Yuri Owechko | Object recognition using a congnitive swarm vision framework with attention mechanisms |
| CN102637023A (en) * | 2012-03-23 | 2012-08-15 | 王效波 | Remote unmanned aerial vehicle cluster control method and system based on 3G (the 3rd Generation Telecommunication) and GPRS (General Packet Radio Service) cell phone communication |
| CN102778229A (en) * | 2012-05-31 | 2012-11-14 | 重庆邮电大学 | Mobile Agent path planning method based on improved ant colony algorithm under unknown environment |
| CN103472828A (en) * | 2013-09-13 | 2013-12-25 | 桂林电子科技大学 | Mobile robot path planning method based on improvement of ant colony algorithm and particle swarm optimization |
| CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
| CN106444755A (en) * | 2016-09-22 | 2017-02-22 | 江苏理工学院 | Mobile robot path planning method and system based on improved genetic algorithm |
| CN106909980A (en) * | 2015-12-22 | 2017-06-30 | 哈尔滨欧润瑞德科技有限公司 | A kind of colony's paths planning method based on change dimension ABC algorithms |
| CN107368077A (en) * | 2017-08-15 | 2017-11-21 | 西京学院 | A kind of robot path planning method based on GACA algorithm |
| CN107402018A (en) * | 2017-09-21 | 2017-11-28 | 北京航空航天大学 | A kind of apparatus for guiding blind combinatorial path planing method based on successive frame |
| CN107450563A (en) * | 2017-09-21 | 2017-12-08 | 景德镇陶瓷大学 | A kind of adaptive information feedback population robot path system of selection and system based on more subgroups |
| CN107702723A (en) * | 2017-11-27 | 2018-02-16 | 安徽工程大学 | A kind of robot path planning method, storage medium and equipment |
| US20180059685A1 (en) * | 2016-08-23 | 2018-03-01 | King Fahd University Of Petroleum And Minerals | Gps-free robots |
| CN109079792A (en) * | 2018-09-05 | 2018-12-25 | 顺德职业技术学院 | A kind of target based on multirobot surrounds and seize method and system |
| CN109164810A (en) * | 2018-09-28 | 2019-01-08 | 昆明理工大学 | It is a kind of based on the adaptive dynamic path planning method of ant colony-clustering algorithm robot |
| CN109343569A (en) * | 2018-11-19 | 2019-02-15 | 南京航空航天大学 | Multiple no-manned plane cluster self-organizing collaboration, which is examined, beats mission planning method |
| CN109685286A (en) * | 2019-01-14 | 2019-04-26 | 哈尔滨工程大学 | USV is based on the collision-avoidance planning method for improving ant group optimization under unknown static-obstacle environment |
| US20190146474A1 (en) * | 2016-05-09 | 2019-05-16 | Strong Force Iot Portfolio 2016, Llc | Methods and systems of industrial production line with self organizing data collectors and neural networks |
| CN109803341A (en) * | 2018-09-29 | 2019-05-24 | 江苏开放大学（江苏城市职业学院） | Adaptive path planning method in wireless sensor network |
| CN110174118A (en) * | 2019-05-29 | 2019-08-27 | 北京洛必德科技有限公司 | Robot multiple-objective search-path layout method and apparatus based on intensified learning |
-
2019
- 2019-09-04 CN CN201910832918.5A patent/CN110750095A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070019865A1 (en) * | 2005-03-04 | 2007-01-25 | Yuri Owechko | Object recognition using a congnitive swarm vision framework with attention mechanisms |
| CN102637023A (en) * | 2012-03-23 | 2012-08-15 | 王效波 | Remote unmanned aerial vehicle cluster control method and system based on 3G (the 3rd Generation Telecommunication) and GPRS (General Packet Radio Service) cell phone communication |
| CN102778229A (en) * | 2012-05-31 | 2012-11-14 | 重庆邮电大学 | Mobile Agent path planning method based on improved ant colony algorithm under unknown environment |
| CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
| CN103472828A (en) * | 2013-09-13 | 2013-12-25 | 桂林电子科技大学 | Mobile robot path planning method based on improvement of ant colony algorithm and particle swarm optimization |
| CN106909980A (en) * | 2015-12-22 | 2017-06-30 | 哈尔滨欧润瑞德科技有限公司 | A kind of colony's paths planning method based on change dimension ABC algorithms |
| US20190146474A1 (en) * | 2016-05-09 | 2019-05-16 | Strong Force Iot Portfolio 2016, Llc | Methods and systems of industrial production line with self organizing data collectors and neural networks |
| US20180059685A1 (en) * | 2016-08-23 | 2018-03-01 | King Fahd University Of Petroleum And Minerals | Gps-free robots |
| CN106444755A (en) * | 2016-09-22 | 2017-02-22 | 江苏理工学院 | Mobile robot path planning method and system based on improved genetic algorithm |
| CN107368077A (en) * | 2017-08-15 | 2017-11-21 | 西京学院 | A kind of robot path planning method based on GACA algorithm |
| CN107402018A (en) * | 2017-09-21 | 2017-11-28 | 北京航空航天大学 | A kind of apparatus for guiding blind combinatorial path planing method based on successive frame |
| CN107450563A (en) * | 2017-09-21 | 2017-12-08 | 景德镇陶瓷大学 | A kind of adaptive information feedback population robot path system of selection and system based on more subgroups |
| CN107702723A (en) * | 2017-11-27 | 2018-02-16 | 安徽工程大学 | A kind of robot path planning method, storage medium and equipment |
| CN109079792A (en) * | 2018-09-05 | 2018-12-25 | 顺德职业技术学院 | A kind of target based on multirobot surrounds and seize method and system |
| CN109164810A (en) * | 2018-09-28 | 2019-01-08 | 昆明理工大学 | It is a kind of based on the adaptive dynamic path planning method of ant colony-clustering algorithm robot |
| CN109803341A (en) * | 2018-09-29 | 2019-05-24 | 江苏开放大学（江苏城市职业学院） | Adaptive path planning method in wireless sensor network |
| CN109343569A (en) * | 2018-11-19 | 2019-02-15 | 南京航空航天大学 | Multiple no-manned plane cluster self-organizing collaboration, which is examined, beats mission planning method |
| CN109685286A (en) * | 2019-01-14 | 2019-04-26 | 哈尔滨工程大学 | USV is based on the collision-avoidance planning method for improving ant group optimization under unknown static-obstacle environment |
| CN110174118A (en) * | 2019-05-29 | 2019-08-27 | 北京洛必德科技有限公司 | Robot multiple-objective search-path layout method and apparatus based on intensified learning |
Non-Patent Citations (8)
| Title |
|---|
| MD AZHARUDDIN: "Particle swarm optimization for maximizing lifetime of wireless sensor networks", 《COMPUTERS & ELECTRICAL ENGINEERING》 * |
| MD AZHARUDDIN: "Particle swarm optimization for maximizing lifetime of wireless sensor networks", 《COMPUTERS & ELECTRICAL ENGINEERING》, vol. 51, 30 April 2016 (2016-04-30), pages 26 - 42, XP029593557, DOI: 10.1016/j.compeleceng.2016.03.002 * |
| PENG CHEN: "Hybrid chaos-based particle swarm optimization-ant colony optimization algorithm with asynchronous pheromone updating strategy for path planning of landfill inspection robots", 《INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS》 * |
| PENG CHEN: "Hybrid chaos-based particle swarm optimization-ant colony optimization algorithm with asynchronous pheromone updating strategy for path planning of landfill inspection robots", 《INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS》, vol. 16, no. 4, 31 August 2019 (2019-08-31), pages 1 - 11 * |
| QI-LEI XU: "The robot path planning based on ant colony and particle swarm fusion algorithm", 《2017 CHINESE AUTOMATION CONGRESS 》, 31 January 2018 (2018-01-31), pages 411 - 415 * |
| 张国良: "《自主移动机器人设计与制作》", 北京航空航天大学出版社, pages: 182 - 185 * |
| 袁杨: "基于群集智能算法的移动机器人路径规划研究", 《计算机工程与应用》 * |
| 袁杨: "基于群集智能算法的移动机器人路径规划研究", 《计算机工程与应用》, no. 5, 31 March 2007 (2007-03-31), pages 52 - 55 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116400737A (en) * | 2023-06-02 | 2023-07-07 | 中国传媒大学 | Safety path planning system based on ant colony algorithm |
| CN116400737B (en) * | 2023-06-02 | 2023-08-25 | 中国传媒大学 | Safety path planning system based on ant colony algorithm |
| CN116820110A (en) * | 2023-08-28 | 2023-09-29 | 武汉市自然资源保护利用中心 | Ecological environment monitoring task planning method and device based on intelligent optimization algorithm |
| CN116820110B (en) * | 2023-08-28 | 2023-11-28 | 武汉市自然资源保护利用中心 | Ecological environment monitoring task planning method and device based on intelligent optimization algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Mobile robot path planning using ant colony algorithm and improved potential field method | |
| CN109489667A (en) | A kind of improvement ant colony paths planning method based on weight matrix | |
| WO2018176595A1 (en) | Unmanned bicycle path planning method based on ant colony algorithm and polar coordinate transformation | |
| CN111240319A (en) | Outdoor multi-robot cooperative operation system and method thereof | |
| CN101837591B (en) | Robot path planning method based on two cooperative competition particle swarms and Ferguson spline | |
| CN110220525A (en) | A kind of paths planning method based on potential field ant group algorithm | |
| CN110544296A (en) | intelligent planning method for three-dimensional global flight path of unmanned aerial vehicle in environment with uncertain enemy threat | |
| CN110750095A (en) | Robot cluster motion control optimization method and system based on 5G communication | |
| CN112824998A (en) | Multi-unmanned aerial vehicle collaborative route planning method and device in Markov decision process | |
| CN113703450B (en) | Mobile robot path planning method based on smoothing factor improved ant colony algorithm | |
| Chen et al. | Research on path planning for mobile robots based on improved ACO | |
| Huang et al. | Robot path planning using improved ant colony algorithm in the environment of internet of things | |
| CN112484732B (en) | IB-ABC algorithm-based unmanned aerial vehicle flight path planning method | |
| CN114063614A (en) | Rapid convergence method for mixed formation of multi-small robot system based on airborne monocular visual perception | |
| CN114740849B (en) | Mobile robot autonomous navigation method and device based on pedestrian walking decision rule | |
| Peng et al. | Cooperative area search for multiple UAVs based on RRT and decentralized receding horizon optimization | |
| Wang et al. | An improved NSGA-II algorithm for UAV path planning problems | |
| Zhou et al. | Routing optimization of intelligent vehicle in automated warehouse | |
| CN114413896A (en) | Composite navigation method, device, equipment and storage medium for mobile robot | |
| CN114578845A (en) | Unmanned aerial vehicle flight path planning method based on improved ant colony algorithm | |
| CN109141438A (en) | A kind of fork truck global path planning method | |
| Atas et al. | Navigating in 3D Uneven Environments through Supervoxels and Nonlinear MPC | |
| Zhou et al. | The route planning for AMR based on combined ant colony and genetic algorithm | |
| Fan et al. | A 3D Path Planning Method Based on Improved Artificial Bee Colony Algorithm | |
| Fan et al. | Improved Q-Learning Method for Multirobot Formation and Path Planning with Concave Obstacles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200204 |
|
| RJ01 | Rejection of invention patent application after publication |