CN105911992B - A kind of automatic path planning method and mobile robot of mobile robot - Google Patents
A kind of automatic path planning method and mobile robot of mobile robot Download PDFInfo
- Publication number
- CN105911992B CN105911992B CN201610423883.6A CN201610423883A CN105911992B CN 105911992 B CN105911992 B CN 105911992B CN 201610423883 A CN201610423883 A CN 201610423883A CN 105911992 B CN105911992 B CN 105911992B
- Authority
- CN
- China
- Prior art keywords
- firefly
- mobile robot
- path
- planning
- population
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 61
- 241000131894 Lampyris noctiluca Species 0.000 claims abstract description 34
- 230000007613 environmental effect Effects 0.000 claims abstract description 28
- 230000004888 barrier function Effects 0.000 claims abstract description 13
- 230000008929 regeneration Effects 0.000 claims abstract description 9
- 238000011069 regeneration method Methods 0.000 claims abstract description 9
- 241000254158 Lampyridae Species 0.000 claims description 130
- 238000010521 absorption reaction Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 11
- 238000009826 distribution Methods 0.000 description 8
- 238000005457 optimization Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000031700 light absorption Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000004020 luminiscence type Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000000455 protein structure prediction Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a kind of automatic path planning method of mobile robot and using the mobile robot of this method, method includes the following steps: acquisition environmental information;It is modeled by the region that collected environmental information is ready for path planning to mobile robot to construct two-dimensional plane coordinate figure, and determines the coordinate position of starting point, terminal and barrier;Based on two-dimensional plane coordinate figure, path optimizing is carried out by the glowworm swarm algorithm of initialization of population based on Sobol sequence and dynamic adjustment coefficient of disturbance Population Regeneration from the path of origin-to-destination to mobile robot, thus in two-dimensional plane coordinate figure planning plan to implement into path optimizing;According to the path optimizing that planning is completed, mobile robot is driven to be moved.The present invention overcomes the insufficient problems of existing glowworm swarm algorithm constringency performance, enable mobile robot quickly and accurately automatic path planning, improve the ability that mobile robot carries out path planning.
Description
Technical field
The present invention relates to electronic robot technical fields, are to be related to a kind of automatic rule of mobile robot more specifically
Draw Path Method and mobile robot.
Background technique
Mobile robot (Mobile robot) is a kind of by sensor, remote manipulator and the mobile vehicle of automatic control
The robot system of composition, is the product of the integrated application of an interdisciplinary study developed in recent years, it has concentrated mechanical, electricity
The multidisciplinary newest research results such as son, computer, automatic control and artificial intelligence, represent the highest of electromechanical integration at
Just.Mobile robot has locomotive function, and dangerous, operation and the environment work less than people under adverse circumstances are being engaged in instead of people
Aspect has bigger mobility, flexibility than general robot.Mobile robot gradually using with industrial production agricultural,
The different industries such as medical treatment.
In the research of mobile robot the relevant technologies, airmanship is its core, and path planning is navigation research
One important link and project.So-called path planning refers to mobile robot according to a certain performance indicator (such as distance, time, energy
Source consumption etc.) optimal or sub-optimal path of the search one from initial state to dbjective state.The problem of path planning relates generally to
Including: (1) establishes relatively reasonable model using the mobile robot environmental information of acquisition, then with certain algorithm find one from
Initial state is to optimal or near-optimization the collisionless path of dbjective state;(2) it is capable of handling uncertain in environmental model
The error occurred in factor and path trace is minimized influence of the external object to robot;(3) using known all
Information carrys out the movement of guided robot, to obtain more preferably behaviour decision making relatively.Currently, for mobile robot path planning
The research of technology has been achieved for a large amount of achievement, and many scientists are studied from different aspect.Wherein, from robot pair
The research of the angle of environment sensing, method for planning path for mobile robot is divided into three types: the planning side based on environmental model
The paths planning method of method, the planing method of vision based and Behavior-based control;The journey that environmental information is grasped from robot
Degree, and global path planning based on environment priori Complete Information can be divided into and based on the local paths planning of sensor information;
From the aspect of whether changing over time from planning environment, it can also be divided into static path planning and active path planning;From mobile machine
On the specific algorithm of people's path planning and strategy, planning technology can be divided into following four classes: stencil matching Path Planning Technique, artificial
Potential field Path Planning Technique, map structuring Path Planning Technique and artificial intelligence Path Planning Technique.Artificial intelligence path planning
Technology be by modern artificial intelligence technology be applied to mobile robot path planning in, as artificial neural network, evolutionary computation,
Fuzzy logic and swarm intelligence algorithm etc..Wherein, the Path Planning Technique based on artificial intelligence is research hotspot in recent years.
Glowworm swarm algorithm (Firefly Algorithm) is a kind of new intelligence proposed by Yang Xin-she in 2008
Can optimization algorithm, the biological characteristics of fire fly luminescence develop in the algorithm simulation nature, with particle swarm algorithm and
Ant group algorithm is the same and a kind of naturally heuristic Stochastic Optimization Algorithms based on group.The algorithm is once proposition, by the country
The concern of outer scholar becomes a new research hotspot of computational intelligence research field, and the algorithm has been applied in function at present
Optimization, image procossing, Combinatorial Optimization, feature selecting, clustering, Stock Price Forecasting, protein structure prediction and dynamic city
The research fields such as field price.The computational efficiency of existing firefly group algorithm is high, and memory overhead is small, and the parameter of adjusting is few, simply
It is easily achieved, but the coefficient of disturbance α in existing glowworm swarm algorithm is usually fixed constant, this is for the search of algorithm
Be it is defective, there is also Premature convergences as other random search algorithms.
Summary of the invention
It is an object of the invention to overcome drawbacks described above in the prior art, a kind of automatic planning of mobile robot is provided
Path Method and mobile robot adjust the strategy of coefficient of disturbance based on Sobol sequence initialization population and dynamic, by right
Coefficient of disturbance in glowworm swarm algorithm carries out adaptive adjustment to enhance convergence energy, to improve mobile robot
Carry out the ability of path planning.
To achieve the above object, first aspect present invention provides a kind of automatic path planning method of mobile robot,
The following steps are included:
Acquire environmental information;
It is modeled by the region that collected environmental information is ready for path planning to mobile robot to construct
Two-dimensional plane coordinate figure, and determine the coordinate position of starting point, terminal and barrier;
Based on two-dimensional plane coordinate figure, mobile robot is passed through from the path of origin-to-destination based on Sobol sequence
Initialization of population and the glowworm swarm algorithm of dynamic adjustment coefficient of disturbance Population Regeneration carry out path optimizing, to sit in two-dimensional surface
Mark on a map it is middle planning plan to implement into path optimizing;
According to the path optimizing that planning is completed, mobile robot is driven to be moved.
Preferably, in the above-mentioned methods, described to be based on two-dimensional plane coordinate figure, to mobile robot from
Point passes through the firefly of initialization of population and dynamic adjustment coefficient of disturbance Population Regeneration based on Sobol sequence to the path of terminal
Algorithm carry out path optimizing, thus in two-dimensional plane coordinate figure planning plan to implement into path optimizing the step of specifically include:
The basic parameter of glowworm swarm algorithm is imported, and initializes each basic parameter of glowworm swarm algorithm;
Using Sobol sequence initialization population, the position of popN firefly is generated, calculates the target letter of every firefly
Number selects brightness maximum as optimal location to obtain corresponding brightness;
The Attraction Degree for calculating every firefly is guided the movement of other fireflies by the firefly with maximum brightness,
The position of every firefly is updated, and recalculates the brightness of firefly;
It when reaching maximum search number, then exports optimum individual and stops algorithm, otherwise, recalculate every firefly
Attraction Degree.
Preferably, in the above-mentioned methods, the Sobol sequence is with 2 for base, by one group of direction number V1,
V2, V3..., Vi..., VnIt generates, wherein Vi∈ (0,1), in Sobol sequence, the value of i-th of element jth dimension can be obtained by formula
It arrives:
Preferably, in the above-mentioned methods, the calculation formula of the Attraction Degree of the firefly are as follows:
In formula, β0Attraction when be two firefly distances being zero, γ is the absorption coefficient of light, dijIt is firefly i and firefly
The distance between fireworm j.
Preferably, in the above-mentioned methods, the location update formula of the firefly are as follows:
Xj(t+1)=Xj(t)+βij(Xi(t)-Xj(t))+α(t)*εj;
In formula, Xi(t) and XjIt (t) is the spatial position of firefly i and firefly j in the t times iteration respectively, α is disturbance
Coefficient, εjIt is random number vector, T is the number of iterations.
Second aspect of the present invention provides a kind of mobile robot of automatic path planning characterized by comprising
Environment information acquisition module, for acquiring environmental information;
Environmental information modeling module, for being ready for path planning to mobile robot by collected environmental information
Region modeled to construct two-dimensional plane coordinate figure, and determine the coordinate position of starting point, terminal and barrier;
Path planning module, it is logical from the path of origin-to-destination to mobile robot for being based on two-dimensional plane coordinate figure
The glowworm swarm algorithm progress path for crossing the initialization of population based on Sobol sequence and dynamic adjustment coefficient of disturbance Population Regeneration is sought
It is excellent, thus in two-dimensional plane coordinate figure planning plan to implement into path optimizing;
Mobile drive module, the path optimizing for being completed according to planning, drives mobile robot to be moved.
Preferably, in the scheme of above-mentioned mobile robot, the path planning module is specifically included:
Basic parameter input unit for importing the basic parameter of glowworm swarm algorithm, and initializes each of glowworm swarm algorithm
A basic parameter;
Sobol sequence initialization kind group unit generates popN firefly for using Sobol sequence initialization population
Position;
Dynamic disturbances coefficient path optimizing unit obtains corresponding bright for calculating the objective function of every firefly
Degree, and select brightness maximum as optimal location;And the Attraction Degree of every firefly is calculated, by the firefly with maximum brightness
Fireworm guides the movements of other fireflies, updates the position of every firefly, and recalculate the brightness of firefly;When reaching
Maximum search number then exports optimum individual and stops algorithm, otherwise, recalculates the Attraction Degree of every firefly.
Preferably, in the scheme of above-mentioned mobile robot, the Sobol sequence is with 2 for base, by one
Group direction number V1, V2, V3..., Vi..., VnIt generates, wherein Vi∈ (0,1), in Sobol sequence, the value of i-th of element jth dimension
It can be obtained by formula:
Preferably, in the scheme of above-mentioned mobile robot, the calculating of the Attraction Degree of the firefly is public
Formula are as follows:
In formula, β0Attraction when be two firefly distances being zero, γ is the absorption coefficient of light, dijIt is firefly i and firefly
The distance between fireworm j.
Preferably, in the scheme of above-mentioned mobile robot, the location update formula of the firefly are as follows:
Xj(t+1)=Xj(t)+βij(Xi(t)-Xj(t))+α(t)*εj;
In formula, Xi(t) and XjIt (t) is the spatial position of firefly i and firefly j in the t times iteration respectively, α is disturbance
Coefficient, εjIt is random number vector, T is the number of iterations.
Compared with prior art, the beneficial effects of the present invention are:
1, the present invention can construct two-dimensional plane coordinate figure according to collected environmental information, and initialization component is called to adopt
With Sobol sequence initialization population, dynamic disturbances coefficient update population is then based on to plan in two-dimensional plane coordinate figure
Plan to implement into path, finally two-dimensional plane coordinate figure and the path planned is combined to be moved.The present invention is based on Sobol sequences
Initialization population and dynamic adjust the strategy of coefficient of disturbance, by carrying out to the key parameter in glowworm swarm algorithm-coefficient of disturbance
Adaptive adjustment overcomes the insufficient problem of existing glowworm swarm algorithm constringency performance, makes to move to enhance convergence energy
Mobile robot can quickly and accurately automatic path planning, improve the ability that mobile robot carries out path planning.
2, the present invention initializes firefly population using Sobol sequence, preferable sampling coverage rate can be obtained, to protect
Demonstrate,prove the uniformity of initial population distribution.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of flow chart of the automatic path planning method of mobile robot provided by the invention;
Fig. 2 is the schematic diagram of two-dimensional plane coordinate figure provided by the invention;
Fig. 3 is a kind of structural block diagram of the mobile robot of automatic path planning provided by the invention;
Fig. 4 is the structural block diagram of path planning module provided by the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Embodiment one
The embodiment of the present invention one provides a kind of automatic path planning method of mobile robot, right with reference to the accompanying drawing
The present embodiment is described in detail.Fig. 1 is the method flow diagram of the embodiment of the present invention one, referring to FIG. 1, the embodiment of the present invention
Method the following steps are included:
Step S1, environmental information is acquired;
Wherein, mobile robot can obtain external environmental information by infrared sensor or the scanning of other acquisition devices.
Step S2, it is modeled by the region that collected environmental information is ready for path planning to mobile robot
To construct two-dimensional plane coordinate figure, and determine the coordinate position of starting point, terminal and barrier;
Path planning refer in the working environment for having barrier find one from origin-to-destination, bypass without collision
The motion path (that is: finding out the collisionless shortest path from A point to B point) of all barriers.
As shown in Fig. 2, the environmental information modeling module of mobile robot can when two-dimensional plane coordinate figure constructs completion
Identify the position coordinates of barrier (such as: a, b, c) in the global area of quasi- exploration.It is more due to having from A point to the path of B point
Item, it is therefore desirable to therefrom identify shortest path using the improved glowworm swarm algorithm of the present invention.
Step S3, it is based on two-dimensional plane coordinate figure, to mobile robot from the path of origin-to-destination by being based on Sobol
The initialization of population of sequence and the glowworm swarm algorithm of dynamic adjustment coefficient of disturbance Population Regeneration carry out path optimizing, thus in two dimension
In plane coordinates figure planning plan to implement into path optimizing;
Furthermore, step S3 specifically includes the following steps:
Step S31, the basic parameter of glowworm swarm algorithm is imported, and initializes each basic parameter of glowworm swarm algorithm;
Wherein, the basic parameter may include population quantity popN, the number of iterations T, initial Attraction Degree β0, light absorption system
Number γ, coefficient of disturbance α etc..Their initial value can be as shown in following table one:
Step S32, using Sobol sequence initialization population, the position of popN firefly is generated, calculates every firefly
Objective function to obtain corresponding brightness, and select brightness maximum as optimal location;
Specifically, the Sobol sequence is with 2 for base, by one group of direction number V1, V2, V3..., Vi ..., VnIt generates,
In, Vi ∈ (0,1).Assuming that mono- group of sequence of Sobol is x1, x2, x3..., xi..., xn,Indicate i-th of element in Sobol sequence
The value of jth dimension, can be obtained by formula:
There is sample distribution and be really distributed inconsistent, Sobol stochastic ordering in pseudo-random number sequence common at present
Column are that ((low-discrepancy sequences) is a stable random sequence, and distribution is equal for a kind of low diversity sequence
Even property is good.The present invention initializes firefly population using Sobol sequence, preferable sampling coverage rate can be obtained, to guarantee
The uniformity of initial population distribution.
Glowworm swarm algorithm is a kind of heuritic approach, and the algorithm simulation weaker firefly of brightness is to the stronger light of firefly of brightness
The mobile random search of worm, usually represents target function value, i.e. f (x with the absolute brightness of firefly in glowworm swarm algorithm*)=
maxx∈sF (x), which solves this optimization problem by iteration using the firefly population that quantity is popN, at the beginning of algorithm
Stage beginning, all fireflies are probabilistically assigned in the s of search space.xiIndicate one of i-th of firefly in the t times iteration
A solution, f (xi) mean that the absolute brightness of its corresponding firefly.
Step S33, the Attraction Degree for calculating every firefly, other fireflies are guided by the firefly with maximum brightness
Movement, update the position of every firefly, and recalculate the brightness of firefly;
Every firefly has an attraction β to other fireflies, if the absolute brightness of firefly i is greater than firefly
The absolute brightness of j, then firefly j will be attracted mobile to i by firefly i.Attraction β of the firefly i to firefly jijPublic affairs
Formula is defined as:
Wherein, β0Attraction when be two firefly distances being zero, γ is the absorption coefficient of light (Light Absorption
Coefficient), dijIt is the distance between firefly i and firefly j.
If firefly j is mobile to firefly i, then the location update formula of firefly j in the t times iteration are as follows:
Xj(t+1)=Xj(t)+βij(Xi(t)-Xj(t))+α(t)*εj (2)
In formula, Xi(t) and XjIt (t) is the spatial position of firefly i and firefly j in the t times iteration respectively, α is disturbance
Coefficient, εjIt is random number vector.
The more new formula that the present invention uses α is as follows:
From the point of view of the operation of algorithm, a biggish α value is conducive to global search, and a lesser α value is conducive to office
Portion's search, therefore convergence energy is improved by carrying out dynamic adjustment to α.
Step S34, it when reaching maximum search number, then exports optimum individual and stops algorithm, otherwise, return step S33
Recalculate the Attraction Degree of every firefly.
Wherein, maximum search number refers to the optimizing number of glowworm swarm algorithm, i.e. the number of iterations T.
The pseudocode of the algorithm is as follows:
Step S4, the path optimizing completed according to planning, drives mobile robot to be moved.
Wherein, the path that optimum individual is passed by is exactly optimal path, when path planning module determines an optimal path
Afterwards, mobile robot will be moved along the paths.
Method of the invention adjusts the strategy of coefficient of disturbance based on Sobol sequence initialization population and dynamic, by firefly
Coefficient of disturbance in fireworm algorithm carries out adaptive adjustment to enhance convergence energy, overcomes existing glowworm swarm algorithm and receives
The insufficient problem for holding back performance, enables mobile robot quickly and accurately automatic path planning, improve mobile robot into
The ability of row path planning.
Embodiment two
The embodiment of the present invention two provides a kind of mobile robot of automatic path planning, referring to FIG. 3, the present invention is real
The mobile robot for applying example includes environmental perception module 1, path planning module 2 and mobile drive module 3, wherein environment sensing
Module 1 is equipped with environment information acquisition module 11 and environmental information modeling module 12, will carry out below to the function of above-mentioned module detailed
Thin explanation.
Environment information acquisition module 11, for acquiring environmental information.
Wherein, environment information acquisition module 11 can be set to infrared sensor or other acquisition devices, mobile robot
External environmental information can be obtained by infrared sensor or the scanning of other acquisition devices.
Environmental information modeling module 12, for being ready for path rule to mobile robot by collected environmental information
The region drawn is modeled to construct two-dimensional plane coordinate figure, and determines the coordinate position of starting point, terminal and barrier.
Path planning refer in the working environment for having barrier find one from origin-to-destination, bypass without collision
The motion path (that is: finding out the collisionless shortest path from A point to B point) of all barriers.
As shown in Fig. 2, when two-dimensional plane coordinate figure constructs completion, 12 energy of environmental information modeling module of mobile robot
Enough identify the position coordinates of barrier (such as: a, b, c) in the global area of quasi- exploration.It is more due to having from A point to the path of B point
Item, it is therefore desirable to therefrom identify shortest path using path planning module 2.
Path planning module 2, it is logical from the path of origin-to-destination to mobile robot for being based on two-dimensional plane coordinate figure
The glowworm swarm algorithm progress path for crossing the initialization of population based on Sobol sequence and dynamic adjustment coefficient of disturbance Population Regeneration is sought
It is excellent, thus in two-dimensional plane coordinate figure planning plan to implement into path optimizing.
As shown in figure 4, furthermore, in the present embodiment, the path planning module 2 specifically includes:
Basic parameter input unit 21 for importing the basic parameter of glowworm swarm algorithm, and initializes glowworm swarm algorithm
Each basic parameter;
Wherein, the basic parameter may include population quantity popN, the number of iterations T, initial Attraction Degree β0, light absorption system
Number γ, coefficient of disturbance α etc..Their initial value can be as shown in following table one:
Sobol sequence initialization kind group unit 22 generates the popN light of firefly for using Sobol sequence initialization population
The position of worm;
Specifically, the Sobol sequence is with 2 for base, by one group of direction number V1, V2, V3..., Vi ..., VnIt generates,
In, Vi ∈ (0,1).Assuming that mono- group of sequence of Sobol is x1, x2, x3..., xi..., xn,Indicate i-th of element in Sobol sequence
The value of jth dimension, can be obtained by formula:
There is sample distribution and be really distributed inconsistent, Sobol stochastic ordering in pseudo-random number sequence common at present
Column are that ((low-discrepancy sequences) is a stable random sequence, and distribution is equal for a kind of low diversity sequence
Even property is good.The present invention initializes firefly population using Sobol sequence, preferable sampling coverage rate can be obtained, to guarantee
The uniformity of initial population distribution.
Dynamic disturbances coefficient path optimizing unit 23 obtains corresponding for calculating the objective function of every firefly
Brightness, and select brightness maximum as optimal location;And the Attraction Degree of every firefly is calculated, by with maximum brightness
Firefly guides the movements of other fireflies, updates the position of every firefly, and recalculate the brightness of firefly;When reaching
It to maximum search number, then exports optimum individual and stops algorithm, otherwise, recalculate the Attraction Degree of every firefly.
Glowworm swarm algorithm is a kind of heuritic approach, and the algorithm simulation weaker firefly of brightness is to the stronger light of firefly of brightness
The mobile random search of worm, usually represents target function value, i.e. f (x with the absolute brightness of firefly in glowworm swarm algorithm*)=
maxx∈sF (x), which solves this optimization problem by iteration using the firefly population that quantity is popN, at the beginning of algorithm
Stage beginning, all fireflies are probabilistically assigned in the s of search space.xiIndicate one of i-th of firefly in the t times iteration
A solution, f (xi) mean that the absolute brightness of its corresponding firefly.
Every firefly has an attraction β to other fireflies, if the absolute brightness of firefly i is greater than firefly
The absolute brightness of j, then firefly j will be attracted mobile to i by firefly i.Attraction β of the firefly i to firefly jijPublic affairs
Formula is defined as:
Wherein, β0Attraction when be two firefly distances being zero, γ is the absorption coefficient of light (Light Absorption
Coefficient), dijIt is the distance between firefly i and firefly j.
If firefly j is mobile to firefly i, then the location update formula of firefly j in the t times iteration are as follows:
Xj(t+1)=Xj(t)+βij(Xi(t)-Xj(t))+α(t)*εj (2)
In formula, Xi(t) and XjIt (t) is the spatial position of firefly i and firefly j in the t times iteration respectively, α is disturbance
Coefficient, εjIt is random number vector.
The more new formula that the present invention uses α is as follows:
From the point of view of the operation of algorithm, a biggish α value is conducive to global search, and a lesser α value is conducive to office
Portion's search, therefore convergence energy is improved by carrying out dynamic adjustment to α.
Mobile drive module 3, the path optimizing for being completed according to planning, drives mobile robot to be moved.
Wherein, the path that optimum individual is passed by is exactly optimal path, when path planning module 2 determines an optimal path
Afterwards, mobile drive module 3 will drive mobile robot to move along the paths.
Shifter people of the invention adjusts the strategy of coefficient of disturbance based on Sobol sequence initialization population and dynamic, passes through
Adaptive adjustment is carried out to enhance convergence energy to the coefficient of disturbance in glowworm swarm algorithm, existing firefly is overcome and calculates
The insufficient problem of method constringency performance, can quickly and accurately automatic path planning, improve path planning ability.
It should be noted that a kind of mobile robot of automatic path planning provided by the above embodiment, only with above-mentioned each
The division progress of functional module can according to need and for example, in practical application by above-mentioned function distribution by different function
Energy module is completed, i.e., the internal structure of system is divided into different functional modules, to complete whole described above or portion
Divide function.
Those of ordinary skill in the art will appreciate that implement the method for the above embodiments be can be with
Relevant hardware is instructed to complete by program, the program can be stored in a computer-readable storage medium
In, the storage medium, such as ROM/RAM, disk, CD.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (4)
1. a kind of automatic path planning method of mobile robot, which is characterized in that method includes the following steps:
Acquire environmental information;
It is modeled by the region that collected environmental information is ready for path planning to mobile robot to construct two dimension
Plane coordinates figure, and determine the coordinate position of starting point, terminal and barrier;
Based on two-dimensional plane coordinate figure, the population based on Sobol sequence is passed through from the path of origin-to-destination to mobile robot
The glowworm swarm algorithm of initialization and dynamic adjustment coefficient of disturbance Population Regeneration carries out path optimizing, thus in two-dimensional plane coordinate figure
It is middle planning plan to implement into path optimizing;
According to the path optimizing that planning is completed, mobile robot is driven to be moved;
Wherein, described to be based on two-dimensional plane coordinate figure, to mobile robot from the path of origin-to-destination by being based on Sobol sequence
The initialization of population of column and the glowworm swarm algorithm of dynamic adjustment coefficient of disturbance Population Regeneration carry out path optimizing, thus flat in two dimension
In areal coordinate figure planning plan to implement into path optimizing the step of specifically include:
The basic parameter of glowworm swarm algorithm is imported, and initializes each basic parameter of glowworm swarm algorithm;
Using Sobol sequence initialization population, generate the position of popN firefly, the objective function of every firefly of calculating with
Corresponding brightness is obtained, and selects brightness maximum as optimal location;
The Attraction Degree for calculating every firefly is guided the movement of other fireflies by the firefly with maximum brightness, is updated
The position of every firefly, and recalculate the brightness of firefly;
It when reaching maximum search number, then exports optimum individual and stops algorithm, otherwise, recalculate the attraction of every firefly
Degree;
The calculation formula of the Attraction Degree of the firefly are as follows:
In formula, β0Attraction when be two firefly distances being zero, γ is the absorption coefficient of light, dijIt is firefly i and firefly j
The distance between;
The location update formula of the firefly are as follows:
Xj(t+1)=Xj(t)+βij(Xi(t)-Xj(t))+α(t)*εj;
In formula, Xi(t) and XjIt (t) is the spatial position of firefly i and firefly j in the t times iteration respectively, α is disturbance system
Number, εjIt is random number vector, T is the number of iterations.
2. the automatic path planning method of mobile robot according to claim 1, which is characterized in that the Sobol sequence
Column are with 2 for base, by one group of direction number V1, V2, V3..., Vi..., VnIt generates, wherein Vi∈ (0,1), in Sobol sequence, the
The value of i element jth dimension can be obtained by formula:
3. a kind of mobile robot of automatic path planning characterized by comprising
Environment information acquisition module, for acquiring environmental information;
Environmental information modeling module, for being ready for the area of path planning to mobile robot by collected environmental information
Domain is modeled to construct two-dimensional plane coordinate figure, and determines the coordinate position of starting point, terminal and barrier;
Path planning module passes through base from the path of origin-to-destination to mobile robot for being based on two-dimensional plane coordinate figure
Path optimizing is carried out in the initialization of population of Sobol sequence and the glowworm swarm algorithm of dynamic adjustment coefficient of disturbance Population Regeneration, from
And in two-dimensional plane coordinate figure planning plan to implement into path optimizing;
Mobile drive module, the path optimizing for being completed according to planning, drives mobile robot to be moved;
Wherein, the path planning module specifically includes:
Basic parameter input unit for importing the basic parameter of glowworm swarm algorithm, and initializes each base of glowworm swarm algorithm
This parameter;
Sobol sequence initialization kind group unit generates the position of popN firefly for using Sobol sequence initialization population
It sets;
Dynamic disturbances coefficient path optimizing unit, for calculating the objective function of every firefly to obtain corresponding brightness,
And select brightness maximum as optimal location;And the Attraction Degree of every firefly is calculated, by the light of firefly with maximum brightness
Worm guides the movements of other fireflies, updates the position of every firefly, and recalculate the brightness of firefly;When reaching most
Big searching times then export optimum individual and stop algorithm, otherwise, recalculate the Attraction Degree of every firefly;
The calculation formula of the Attraction Degree of the firefly are as follows:
In formula, β0Attraction when be two firefly distances being zero, γ is the absorption coefficient of light, dijIt is firefly i and firefly j
The distance between;
The location update formula of the firefly are as follows:
Xj(t+1)=Xj(t)+βij(Xi(t)-Xj(t))+α(t)*εj;
In formula, Xi(t) and XjIt (t) is the spatial position of firefly i and firefly j in the t times iteration respectively, α is disturbance system
Number, εjIt is random number vector, T is the number of iterations.
4. the mobile robot of automatic path planning according to claim 3, which is characterized in that the Sobol sequence is
It is base with 2, by one group of direction number V1, V2, V3..., Vi..., VnIt generates, wherein Vi∈ (0,1), in Sobol sequence, i-th
The value of element jth dimension can be obtained by formula:
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610423883.6A CN105911992B (en) | 2016-06-14 | 2016-06-14 | A kind of automatic path planning method and mobile robot of mobile robot |
PCT/CN2016/087911 WO2017215044A1 (en) | 2016-06-14 | 2016-06-30 | Automatic path planning method for mobile robot and mobile robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610423883.6A CN105911992B (en) | 2016-06-14 | 2016-06-14 | A kind of automatic path planning method and mobile robot of mobile robot |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105911992A CN105911992A (en) | 2016-08-31 |
CN105911992B true CN105911992B (en) | 2019-02-22 |
Family
ID=56751116
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610423883.6A Active CN105911992B (en) | 2016-06-14 | 2016-06-14 | A kind of automatic path planning method and mobile robot of mobile robot |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN105911992B (en) |
WO (1) | WO2017215044A1 (en) |
Families Citing this family (53)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106371446A (en) * | 2016-12-03 | 2017-02-01 | 河池学院 | Navigation and positioning system of indoor robot |
CN107219858B (en) * | 2017-04-26 | 2020-04-03 | 西北工业大学 | Multi-unmanned aerial vehicle cooperative coupling task allocation method for improving firefly algorithm |
CN107341442B (en) * | 2017-05-22 | 2023-06-06 | 腾讯科技(上海)有限公司 | Motion control method, motion control device, computer equipment and service robot |
CN107390701B (en) * | 2017-09-07 | 2018-10-02 | 南京昱晟机器人科技有限公司 | A kind of small space mobile robot orientation management method |
CN108647770A (en) * | 2018-04-19 | 2018-10-12 | 东华大学 | A kind of optimization method in the multiple no-manned plane disaster rescue searching path based on particle cluster algorithm |
CN109164810B (en) * | 2018-09-28 | 2021-08-10 | 昆明理工大学 | Robot self-adaptive dynamic path planning method based on ant colony-clustering algorithm |
CN109489667A (en) * | 2018-11-16 | 2019-03-19 | 楚天智能机器人(长沙)有限公司 | A kind of improvement ant colony paths planning method based on weight matrix |
CN109542106A (en) * | 2019-01-04 | 2019-03-29 | 电子科技大学 | A kind of paths planning method under mobile robot multi-constraint condition |
CN109613921B (en) * | 2019-01-08 | 2021-07-30 | 智慧航海(青岛)科技有限公司 | Unmanned ship local path planning method based on fast moving firefly algorithm |
CN109839107A (en) * | 2019-03-21 | 2019-06-04 | 深圳市三宝创新智能有限公司 | A kind of intelligent robot navigation method and its navigation device |
CN109945873B (en) * | 2019-04-04 | 2022-07-15 | 东南大学 | Hybrid path planning method for indoor mobile robot motion control |
CN110119705B (en) * | 2019-05-09 | 2023-04-18 | 哈尔滨工程大学 | Line feature data association method based on improved ant colony optimization for robot |
CN110389587A (en) * | 2019-05-20 | 2019-10-29 | 长沙理工大学 | A kind of robot path planning's new method of target point dynamic change |
CN111813100B (en) * | 2019-07-04 | 2022-07-15 | 中国科学技术大学 | Local path planning algorithm and device |
CN110412982B (en) * | 2019-07-31 | 2022-07-15 | 长沙理工大学 | Robot path robustness planning method based on monocular camera ranging uncertainty |
CN110531767A (en) * | 2019-08-27 | 2019-12-03 | 广州蓝胖子机器人有限公司 | It is a kind of for the scheduling of AGV cluster and the method and system of pathfinding algorithm |
CN110553660B (en) * | 2019-08-31 | 2023-03-24 | 武汉理工大学 | Unmanned vehicle trajectory planning method based on A-star algorithm and artificial potential field |
CN110647162B (en) * | 2019-10-16 | 2022-10-14 | 厦门理工学院 | Route planning method for tour guide unmanned aerial vehicle, terminal equipment and storage medium |
CN110850880A (en) * | 2019-11-20 | 2020-02-28 | 中电科技集团重庆声光电有限公司 | Automatic driving system and method based on visual sensing |
CN110823229B (en) * | 2019-12-16 | 2023-07-07 | 湖北工业大学 | Mobile robot path planning method system based on optimized firefly algorithm |
CN111121807A (en) * | 2019-12-18 | 2020-05-08 | 安徽机电职业技术学院 | Mobile robot path planning method |
CN110986957B (en) * | 2019-12-24 | 2023-05-12 | 中国人民解放军空军工程大学 | Unmanned aerial vehicle three-dimensional track planning method and device |
CN111238366B (en) * | 2020-01-09 | 2021-10-22 | 天远三维(天津)科技有限公司 | Three-dimensional scanning path planning method and device |
CN111273664B (en) * | 2020-02-11 | 2023-06-30 | 西北工业大学深圳研究院 | Multi-robot path collaborative planning method for space truss structure on-orbit assembly |
CN110986954B (en) * | 2020-02-18 | 2023-08-22 | 中国人民解放军空军工程大学 | Military transport plane route planning method based on gray wolf optimization algorithm |
CN111539506A (en) * | 2020-03-16 | 2020-08-14 | 中国石油天然气集团有限公司 | Firefly algorithm-based longitudinal wave time difference real-time extraction method |
US11967063B2 (en) | 2020-03-30 | 2024-04-23 | Industrial Technology Research Institute | Automatic bio-specimen inspection system and inspection method thereof |
TWI756996B (en) * | 2020-03-30 | 2022-03-01 | 財團法人工業技術研究院 | Automatic bio-specimen inspection system and inspection method thereof as well as non-volatile computer readable storage media |
CN111562786B (en) * | 2020-05-19 | 2023-03-28 | 智慧航海(青岛)科技有限公司 | Multi-stage optimized unmanned ship path planning method and device |
CN111796597A (en) * | 2020-07-16 | 2020-10-20 | 云南电网有限责任公司昭通供电局 | Robot multi-target path optimization method based on novel firefly group optimization |
CN111982118B (en) * | 2020-08-19 | 2023-05-05 | 合肥工业大学 | Robot walking track determining method and device, computer equipment and storage medium |
CN112099498A (en) * | 2020-09-08 | 2020-12-18 | 合肥学院 | Path planning method and system based on parameterized Thiele continuous fractional interpolation |
CN112101655B (en) * | 2020-09-11 | 2023-04-28 | 长沙理工大学 | Population dynamic regulation strategy and implementation of firefly algorithm in path planning application |
CN112184007B (en) * | 2020-09-27 | 2024-01-19 | 浙江工业大学 | Workshop equipment remote diagnosis method based on digital twin |
CN112180934B (en) * | 2020-10-09 | 2023-10-27 | 广州大学 | Control method, system and device of loading robot and readable storage medium |
CN112364450B (en) * | 2020-10-28 | 2023-11-03 | 东北大学 | Multi-pipeline layout optimization method and system for aero-engine |
CN112731969B (en) * | 2020-12-29 | 2022-11-25 | 合肥一森电子科技有限公司 | River-oriented multi-unmanned-aerial-vehicle water quality sampling and monitoring path optimization method |
CN112859855A (en) * | 2021-01-11 | 2021-05-28 | 金陵科技学院 | Robot multi-target path planning based on locust optimization algorithm |
CN112987721B (en) * | 2021-02-01 | 2022-12-13 | 哈尔滨工业大学 | Multi-AGV scheduling device and fusion method of global planning and local planning thereof |
CN113359859B (en) * | 2021-07-16 | 2023-09-08 | 广东电网有限责任公司 | Combined navigation obstacle avoidance method, system, terminal equipment and storage medium |
CN113919771B (en) * | 2021-09-24 | 2023-09-01 | 成都信息工程大学 | Multi-target intelligent distribution method for unmanned aerial vehicle |
CN114065614B (en) * | 2021-11-01 | 2024-04-30 | 哈尔滨工业大学 | Gym crowd evacuation simulation method, system, electronic equipment and medium based on sparrow search algorithm |
CN114347041B (en) * | 2022-02-21 | 2024-03-08 | 汕头市快畅机器人科技有限公司 | Group robot control and pattern generation method |
CN114905506A (en) * | 2022-04-15 | 2022-08-16 | 北京航空航天大学杭州创新研究院 | Robot navigation system based on visual perception and spatial cognitive neural mechanism |
CN115132296A (en) * | 2022-05-23 | 2022-09-30 | 成都信息工程大学 | Quality assessment method based on double-layer thickness optimization deep learning framework |
CN115454070B (en) * | 2022-09-15 | 2024-04-05 | 安徽工程大学 | K-Means ant colony algorithm multi-robot path planning method |
CN115951683B (en) * | 2023-01-29 | 2023-11-28 | 南京理工大学紫金学院 | Artificial potential field path planning method for mixed gradient descent and longhorn beetle whisker search |
CN115826590B (en) * | 2023-02-21 | 2023-06-02 | 山东大学 | Mobile robot local path planning method and system with self-adaptive parameters |
CN116147636B (en) * | 2023-04-20 | 2023-07-07 | 甘肃省公安厅 | Automatic path finding calculation method for optimal distance based on geographic space |
CN116518979B (en) * | 2023-06-26 | 2023-08-29 | 深圳市森歌数据技术有限公司 | Unmanned plane path planning method, unmanned plane path planning system, electronic equipment and medium |
CN117146833B (en) * | 2023-10-31 | 2024-01-05 | 北京卓翼智能科技有限公司 | Unmanned aerial vehicle path planning method and device based on improved bat algorithm |
CN117850213B (en) * | 2024-03-08 | 2024-05-24 | 羽禾人工智能(嘉兴)有限公司 | Enhanced PID control optimization method for killing robot |
CN118071333A (en) * | 2024-04-17 | 2024-05-24 | 中用科技有限公司 | Industrial equipment emergency supervision method and system based on industrial Internet of things |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0340006A (en) * | 1989-07-07 | 1991-02-20 | Hitachi Ltd | Product manufacturing facility having fa line |
JP2006277556A (en) * | 2005-03-30 | 2006-10-12 | Yaskawa Electric Corp | Multi-axis network drive controller |
CN102768536A (en) * | 2012-07-20 | 2012-11-07 | 哈尔滨工程大学 | Route planning method based on multi-target glowworm swarm algorithm |
CN103034123A (en) * | 2012-12-11 | 2013-04-10 | 中国科学技术大学 | Dynamic model parameter identification based parallel robot control method |
CN105005301A (en) * | 2015-05-25 | 2015-10-28 | 湘潭大学 | Method for planning operation point sequence and path of industrial robot based on swarm intelligence algorithm |
CN105116886A (en) * | 2015-08-11 | 2015-12-02 | 余路 | Robot autonomous walking method |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5335551B2 (en) * | 2009-05-14 | 2013-11-06 | 本田技研工業株式会社 | Robot hand and its control system, control method and control program |
KR101667031B1 (en) * | 2009-11-02 | 2016-10-17 | 삼성전자 주식회사 | Path planning apparatus of robot and method thereof |
KR101203897B1 (en) * | 2011-02-25 | 2012-11-23 | 동국대학교 산학협력단 | Apparatus and method of cell-based path planning for a mobile body |
CN102520718B (en) * | 2011-12-02 | 2013-06-05 | 上海大学 | Physical modeling-based robot obstacle avoidance path planning method |
CN102799179B (en) * | 2012-07-06 | 2014-12-31 | 山东大学 | Mobile robot path planning algorithm based on single-chain sequential backtracking Q-learning |
JP5990453B2 (en) * | 2012-12-14 | 2016-09-14 | セコム株式会社 | Autonomous mobile robot |
WO2016067467A1 (en) * | 2014-10-31 | 2016-05-06 | 三菱電機株式会社 | Robot control device, robot system, robot control method, and program |
GB201419883D0 (en) * | 2014-11-07 | 2014-12-24 | F Robotics Acquisitions Ltd | Domestic robotic system and method |
-
2016
- 2016-06-14 CN CN201610423883.6A patent/CN105911992B/en active Active
- 2016-06-30 WO PCT/CN2016/087911 patent/WO2017215044A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0340006A (en) * | 1989-07-07 | 1991-02-20 | Hitachi Ltd | Product manufacturing facility having fa line |
JP2006277556A (en) * | 2005-03-30 | 2006-10-12 | Yaskawa Electric Corp | Multi-axis network drive controller |
CN102768536A (en) * | 2012-07-20 | 2012-11-07 | 哈尔滨工程大学 | Route planning method based on multi-target glowworm swarm algorithm |
CN103034123A (en) * | 2012-12-11 | 2013-04-10 | 中国科学技术大学 | Dynamic model parameter identification based parallel robot control method |
CN105005301A (en) * | 2015-05-25 | 2015-10-28 | 湘潭大学 | Method for planning operation point sequence and path of industrial robot based on swarm intelligence algorithm |
CN105116886A (en) * | 2015-08-11 | 2015-12-02 | 余路 | Robot autonomous walking method |
Non-Patent Citations (5)
Title |
---|
《一种改进的新颖的粒子群优化算法》;顾大为等;《计算机工程与应用》;20110214;第47卷(第6期);第49-51,85页 |
《基于sobol序列的量子粒子群求解电力经济调度》;许磊等;《西南师范大学学报(自然科学版)》;20130420;第38卷(第4期);第98-101页 |
基于变参数萤火虫算法和Maklink 图的路径规划研究;李明富等;《机械科学与技术》;20151019;第34卷(第11期);全文 |
基于多子群协同进化的自适应萤火虫算法;张毅等;《纺织高校基础科学学报》;20160304;第29卷(第01期);全文 |
基于改进型萤火虫算法的动态自动聚集路径规划方法;刘鹏等;《计算机应用研究》;20111115;第28卷(第11期);全文 |
Also Published As
Publication number | Publication date |
---|---|
CN105911992A (en) | 2016-08-31 |
WO2017215044A1 (en) | 2017-12-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105911992B (en) | A kind of automatic path planning method and mobile robot of mobile robot | |
Gupta et al. | Cognitive mapping and planning for visual navigation | |
CN106970615B (en) | A kind of real-time online paths planning method of deeply study | |
CN113110509B (en) | Warehousing system multi-robot path planning method based on deep reinforcement learning | |
CN112356830B (en) | Intelligent parking method based on model reinforcement learning | |
CN104121903B (en) | A kind of rolling Route planner based on boundary value problem | |
CN106127121A (en) | A kind of built-up areas intellectuality extracting method based on nighttime light data | |
Arie et al. | Imitating others by composition of primitive actions: A neuro-dynamic model | |
CN109813304A (en) | A kind of sectioning search earth magnetism bionic navigation method based on evolution strategy | |
Pardhi et al. | Vehicle motion prediction for autonomous navigation system using 3 dimensional convolutional neural network | |
Ugur et al. | Unsupervised learning of object affordances for planning in a mobile manipulation platform | |
Chen et al. | A comprehensive survey of convergence analysis of beetle antennae search algorithm and its applications | |
Sellers et al. | Deep learning-based heterogeneous system for autonomous navigation | |
CN101477689B (en) | Aerial robot vision layered matching process based adaptive ant colony intelligence | |
CN115327926A (en) | Multi-agent dynamic coverage control method and system based on deep reinforcement learning | |
Nápoles et al. | Aggregation of partial rankings-an approach based on the Kemeny ranking problem | |
CN114663982A (en) | Human hand trajectory prediction and intention recognition method based on multi-feature fusion | |
Li et al. | A novel path planning algorithm based on Q-learning and adaptive exploration strategy | |
Jeong et al. | Goal-oriented behavior sequence generation based on semantic commands using multiple timescales recurrent neural network with initial state correction | |
Ning et al. | A survey on multi-agent reinforcement learning and its application | |
Lin et al. | Medical image registration based on an improved ant colony optimization algorithm | |
Faulkner et al. | Dyna planning using a feature based generative model | |
Hauser | Large Motion Libraries: Toward a “Google” for Robot Motions | |
Yue et al. | LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updating | |
Zhang et al. | Path Planning Model of Intelligent Robot based on Computer Vision Recognition Algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: 510000 No. 293, Zhongshan Avenue, Tianhe District, Guangdong, Guangzhou Patentee after: Guangdong Normal University of Technology Address before: 293 No. 510000 Guangdong city of Guangzhou province Tianhe District Zhongshan Avenue Patentee before: Guangdong Technical Normal College |