CN113837049B - Intelligent pavement cleaning method based on convolutional neural network and genetic algorithm - Google Patents
Intelligent pavement cleaning method based on convolutional neural network and genetic algorithm Download PDFInfo
- Publication number
- CN113837049B CN113837049B CN202111090784.8A CN202111090784A CN113837049B CN 113837049 B CN113837049 B CN 113837049B CN 202111090784 A CN202111090784 A CN 202111090784A CN 113837049 B CN113837049 B CN 113837049B
- Authority
- CN
- China
- Prior art keywords
- road surface
- grid
- path
- garbage
- convolutional neural
- 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
- 238000004140 cleaning Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 48
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 45
- 230000002068 genetic effect Effects 0.000 title claims abstract description 40
- 238000009826 distribution Methods 0.000 claims abstract description 55
- 238000012549 training Methods 0.000 claims abstract description 18
- 240000007651 Rubus glaucus Species 0.000 claims abstract description 11
- 235000011034 Rubus glaucus Nutrition 0.000 claims abstract description 11
- 235000009122 Rubus idaeus Nutrition 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 15
- 230000035772 mutation Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000010187 selection method Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 9
- 238000000605 extraction Methods 0.000 description 6
- 238000011176 pooling Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009396 hybridization Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 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, 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
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Genetics & Genomics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent road surface cleaning method based on a convolutional neural network and a genetic algorithm, which belongs to the technical field of artificial intelligence, and aims to solve the technical problem of how to clean a road surface by using artificial intelligence so as to achieve the aim of cleaning an unmanned road surface, and adopts the following technical scheme: s1, constructing a road surface garbage distribution model through a convolutional neural network; s2, recognizing the garbage distribution situation on the road surface by using a classification method in the convolutional neural network, and training a road surface garbage distribution model; s3, planning a path through a genetic algorithm according to the distribution condition of the road surface garbage; s4, embedding the road surface garbage model and the path planning into a raspberry group, and embedding the raspberry group and the unmanned camera into a mobile road cleaning machine, wherein the mobile road cleaning machine performs road cleaning.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an intelligent pavement cleaning method based on a convolutional neural network and a genetic algorithm.
Background
Neural networks (networks) are part of the field of artificial intelligence research, the most popular of which is currently deep convolutional neural networks (deep convolutional neural networks, CNNs), which, although they also have a shallow structure, are rarely used for reasons of accuracy and expressivity. At present, CNNs and convolutional neural networks are mentioned, and academia and industry are not specially distinguished any more, and generally refer to convolutional neural networks with deep structures, and the number of layers is variable from a few layers to tens of hundreds of layers. CNNs have now achieved great success in many research fields, such as speech recognition, image segmentation, natural language processing, etc. Although the problems addressed in these fields are not the same, these methods of application can be generalized in that CNNs can automatically learn features from (typically large-scale) data and generalize the results to the same type of unknown data. The general steps for implementing the task of image recognition using CNN are: the input layer reads in the regularized (uniformly sized) image, each neuron of each layer takes as input a small set of local neighbor cells of the previous layer, i.e. local receptive fields and weight sharing, the neurons extract some basic visual features such as edges, corner points, etc., which are then used by higher layer neurons. The convolutional neural network obtains feature maps through convolutional operation, and each position, the units from different feature maps obtain different types of features respectively. A convolutional layer typically contains multiple feature maps with different weight vectors so that the richer features of the image can be preserved. The back of the convolution layer is connected with the pooling layer to carry out downsampling operation, so that on one hand, the resolution of an image can be reduced, the number of parameters is reduced, and on the other hand, the robustness of translation and deformation can be obtained. The convolution layer and the pooling layer are alternately distributed, so that the number of the feature images is gradually increased, and the resolution is gradually reduced, and the double pyramid structure is formed.
The genetic algorithm (Genetic Algorithm, GA) is a search algorithm used to solve the optimization in computational mathematics, and is one of the evolutionary algorithms. Evolutionary algorithms were originally developed with reference to a number of phenomena in evolutionary biology, including genetics, mutations, natural selection, and hybridization. Genetic algorithms are typically implemented as a kind of computer simulation. For an optimization problem, a population of abstract representations (called chromosomes) of a certain number of candidate solutions (called individuals) evolve toward a better solution. Traditionally, the solution is represented in binary (i.e., a string of 0 and 1), but other representation methods are possible. Evolution starts from a population of completely random individuals, with the next generation occurring. In each generation, the fitness of the entire population is evaluated, a number of individuals are randomly selected from the current population (based on their fitness), and a new living population is generated by natural selection and mutation, which becomes the current population in the next iteration of the algorithm.
Many lifestyles exist, mainly by manpower, but artificial intelligence technology has been rapidly developed in recent years. The artificial intelligence should be more service life, let people save the time of doing life to enjoy higher quality of life, for example clean the health of street road surface this kind of work that wastes time and energy should utilize the manual work to go intelligent solution more.
Therefore, how to clean the road surface of the street by using artificial intelligence and achieve the aim of cleaning the road surface of an unmanned engineering is a technical problem to be solved urgently at present.
Disclosure of Invention
The invention aims to provide an intelligent road surface cleaning method based on a convolutional neural network and a genetic algorithm, which solves the problem of how to clean the road surface of a street by using artificial intelligence and realize self-service road surface cleaning.
The intelligent road surface cleaning method based on the convolutional neural network and the genetic algorithm is realized in the following manner, the garbage distribution condition on the road surface is identified through the convolutional neural network, the path planning is carried out through the genetic algorithm, and the road surface cleaning is carried out by utilizing a mobile road surface cleaning machine; the method comprises the following steps:
s1, constructing a road surface garbage distribution model through a convolutional neural network;
s2, recognizing the garbage distribution situation on the road surface by using a classification method in the convolutional neural network, and training a road surface garbage distribution model;
s3, planning a path through a genetic algorithm according to the distribution condition of the road surface garbage;
s4, embedding the road surface garbage model and the path planning into a raspberry group, and embedding the raspberry group and an unmanned camera into a mobile road cleaning machine, wherein the mobile road cleaning machine performs road cleaning, so that the purpose of road cleaning is achieved.
Preferably, the training of the road surface garbage distribution model in step S2 is specifically as follows:
s201, constructing a pavement data set: the method comprises the steps of dividing a training set and a testing set;
s202, training a road surface garbage distribution model: putting the garbage distribution model into a processed horizontal plane training set, and training the pavement garbage distribution model through a server;
s203, testing a road surface garbage distribution model: putting the trained model into a test set for polarity test;
s204, optimizing a road surface garbage distribution model: and according to the pavement garbage distribution model test result, re-acquiring the pavement data set to train or finely tune the pavement garbage distribution model until the model is fitted.
More preferably, the construction of the pavement data set in step S201 is specifically as follows:
s20101, collecting pictures: under different light environments, taking photos and recording the road surface through the unmanned aerial vehicle, and obtaining road surface pictures;
s20102, tag label: observing whether the pictures of the pavement contain garbage or not by naked eyes, and marking the pictures with labels, wherein the content of the labels is whether the garbage exists or not;
s20103, preprocessing the picture: the existing photo is selectively cut, rotated, enlarged or reduced;
s20104, manufacturing a pavement data set: all tagged photographs were made into one pavement data set.
Preferably, the path planning in step S3 by a genetic algorithm is specifically as follows:
s301, building a map: constructing a grid map by adopting a grid algorithm;
s302, initializing a population: randomly generating a plurality of feasible paths, wherein the feasible paths represent paths which do not collide with the barrier grid;
s303, calculating a fitness function: the path is optimized by iterating the fitness function.
More preferably, the grid map is that a rectangular coordinate system is established by taking the first grid at the lower left corner of the map as the origin of coordinates, each grid is represented by the (x, y) coordinate form, and each grid is numbered, and a path is represented by the grid number.
More preferably, the initialization population in step S302 is specifically as follows:
s30201, generating an intermittent path: randomly taking out an unobstructed grating from each row in sequence to form an intermittent path; wherein the first grid of the path and the last grid of the path are a starting position and a target position respectively;
s30202, connecting the discontinuous path to the continuous path, specifically as follows:
s3020201, determining from the first grid whether two adjacent grids are consecutive grids:
if the grid is continuous, executing step S3020202;
s3020202, judging whether the new grid is an obstacle grid:
(1) if the new grid is an obstacle grid, step S3020203 is executed;
(2) if the new grid is an unobstructed grid, the process goes to step S3020205;
s3020203, fetching adjacent grids of the new grid in order of up, down, left, and right, and judging whether the adjacent grids of the new grid are already in the path (preventing trapping dead loops):
if the neighboring grid of the new grid is an unobstructed grid and is not in the path, then step S3020204 is performed;
s3020204, inserting into the path, and executing the step S3020207 next;
s3020205, inserting the two discontinuous grids, and executing the step S3020206 next;
s3020206, continuously judging whether the newly inserted grid and the previous grid of the newly inserted grid are continuous:
(1) if not, the steps S3020201 to S3020206 are looped to find new grids until the two grids are continuous, and the next step is to execute step S3020207;
s3020207, when two grids are continuous, then take the next grid, and loop through steps S3020201 to S3020206 to find the next grid until the whole path is continuous.
More preferably, the path optimization by iterating the fitness function in step S303 is specifically as follows:
s30301, a selection method comprises the following steps: calculating the sum of fitness functions of all individuals, calculating the ratio of each individual, and selecting the next generation of individuals in a roulette mode according to the probability of each individual;
s30302, cross mode: determining a cross probability pc, generating a random number between 0 and 1, and comparing the random number with the cross probability pc; if the value is smaller than pc, performing cross operation; the method comprises the following steps:
finding out all the same points in the two paths, randomly selecting one point, and performing cross operation on the subsequent paths;
s30303, variant mode: determining a variation probability pm, generating a random number between 0 and 1, and comparing the random number with the variation probability pm; if the value is less than pm, performing mutation operation; the method comprises the following steps:
randomly selecting two grids except a starting point and an end point in the path, removing the path between the two grids, and connecting the discontinuous paths into continuous paths by using the two grids as adjacent points for continuous operation in the step S30202; when the continuous path cannot be generated, the two points are reselected to perform the mutation operation until the mutation operation is completed.
Preferably, the road cleaning performed by the mobile road cleaning machine in step S4 is specifically as follows:
s401, arranging a road cleaning machine at a proper position of a road to be cleaned, integrally shooting the road by using an unmanned aerial vehicle, transmitting a picture into a raspberry pie, and judging whether garbage exists or not through a road garbage distribution model:
(1) if the garbage model exists, executing step S402;
(2) if no garbage exists, no treatment is carried out;
s402, the pavement garbage distribution model processes the processed result through a genetic algorithm to obtain a path planning chart, and the path planning chart is sent to a pavement cleaning machine;
s403, the road surface cleaning machine performs cleaning work according to the path planning chart until the road surface is free of garbage;
s404, returning the road surface cleaning machine to the original position after the cleaning work is completed.
An electronic device, comprising: a memory and at least one processor;
wherein the memory has a computer program stored thereon;
the at least one processor executes the computer program stored by the memory, causing the at least one processor to perform the intelligent road surface cleaning method based on convolutional neural network and genetic algorithm as described above.
A computer readable storage medium having stored therein a computer program executable by a processor to implement a method of intelligent road surface cleaning based on a convolutional neural network and a genetic algorithm as described above.
The intelligent pavement cleaning method based on the convolutional neural network and the genetic algorithm has the following advantages:
firstly, the invention respectively judges the distribution of the road surface garbage and plans the path based on the convolutional neural network and the genetic algorithm in the deep learning so as to achieve the aim of cleaning the road surface;
the invention relates to two events, namely, confirming the distribution of garbage on the road surface and confirming the specific route analysis of disposing garbage after the distribution of the garbage is confirmed; the two events respectively relate to two artificial intelligence technologies: convolutional neural networks and genetic algorithms; the garbage distribution on the road surface is identified through the convolutional neural network, then the route planning is carried out through the genetic algorithm, and finally the road cleaning is carried out through the machine until no garbage exists on the road surface, so that the labor intensity is reduced, the labor force is saved, and the road cleaning efficiency is improved.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of an intelligent road surface cleaning method based on a convolutional neural network and a genetic algorithm;
FIG. 2 is a schematic diagram of a road surface garbage distribution model;
FIG. 3 is a flow chart of path planning by genetic algorithm;
fig. 4 is a block diagram of a process for road cleaning by a mobile road cleaning machine.
Detailed Description
The intelligent road surface cleaning method based on the convolutional neural network and the genetic algorithm of the present invention is described in detail below with reference to the accompanying drawings and specific embodiments of the specification.
Example 1:
as shown in figure 1, the intelligent road surface cleaning method based on the convolutional neural network and the genetic algorithm provided by the invention is characterized in that the garbage distribution condition on the road surface is identified through the convolutional neural network, the path planning is carried out through the genetic algorithm, and the road surface cleaning is carried out by utilizing a mobile road surface cleaning machine; the method comprises the following steps:
s1, constructing a road surface garbage distribution model through a convolutional neural network; as shown in fig. 2, the road surface garbage distribution model comprises an input unit, a feature extraction unit and a feature output unit; the feature extraction unit comprises a convolution layer, a pooling layer, a convolution layer, a pooling layer and a full communication layer; the road surface picture input by the input unit is processed by the feature extraction unit, the feature extraction is sequentially performed by the convolution layer, the pooling layer, the convolution layer, the pooling layer and the full communication layer, and after the feature extraction, the feature extraction unit outputs the feature by the feature output unit.
S2, recognizing the garbage distribution situation on the road surface by using a classification method in the convolutional neural network, and training a road surface garbage distribution model;
s3, planning a path through a genetic algorithm according to the distribution condition of the road surface garbage;
s4, embedding the road surface garbage model and the path planning into a raspberry group, and embedding the raspberry group and an unmanned camera into a mobile road cleaning machine, wherein the mobile road cleaning machine performs road cleaning, so that the purpose of road cleaning is achieved.
The training of the road surface garbage distribution model in step S2 in this embodiment is specifically as follows:
s201, constructing a pavement data set: the method comprises the steps of dividing a training set and a testing set;
s202, training a road surface garbage distribution model: putting the garbage distribution model into a processed horizontal plane training set, and training the pavement garbage distribution model through a server;
s203, testing a road surface garbage distribution model: putting the trained model into a test set for polarity test;
s204, optimizing a road surface garbage distribution model: and according to the pavement garbage distribution model test result, re-acquiring the pavement data set to train or finely tune the pavement garbage distribution model until the model is fitted.
The construction of the road surface data set in step S201 of the present embodiment is specifically as follows:
s20101, collecting pictures: under different light environments, taking photos and recording the road surface through the unmanned aerial vehicle, and obtaining road surface pictures;
s20102, tag label: observing whether the pictures of the pavement contain garbage or not by naked eyes, and marking the pictures with labels, wherein the content of the labels is whether the garbage exists or not;
s20103, preprocessing the picture: the existing photo is selectively cut, rotated, enlarged or reduced;
s20104, manufacturing a pavement data set: all tagged photographs were made into one pavement data set.
As shown in fig. 3, the path planning by the genetic algorithm in step S3 in this embodiment is specifically as follows:
s301, building a map: constructing a grid map by adopting a grid algorithm;
s302, initializing a population: randomly generating a plurality of feasible paths, wherein the feasible paths represent paths which do not collide with the barrier grid;
s303, calculating a fitness function: the path is optimized by iterating the fitness function.
The smaller the grid area, the more accurate the representation of various environmental information in the space, but the larger the memory space occupied at the same time, the larger the search time used by the algorithm. If the grid area is larger, various environmental information in the space cannot be accurately represented, and collision problems are likely to occur. Therefore, when building an environment model, the following needs to be made: the problem of obstacle height is not considered, and the robot walking space is a two-dimensional plane space; the size, location of the obstacle are known and no dynamic obstacle exists; robots can be considered particle processing at the time of planning. To facilitate the setting of the grid area, we usually represent the walking space of the robot by a square. If the area of the obstacle is smaller than the square area, the obstacle can be enlarged to be square; if the barrier area is larger than the square area, two squares may be used to represent the barrier area; if the obstacle area is larger, it can be represented by a plurality of squares. The grid map is characterized in that a rectangular coordinate system is established by taking the first grid at the left lower corner of the map as a coordinate origin, each grid is expressed in a (x, y) coordinate form, and numbering is carried out on each grid, and a path is expressed through the grid number.
The initialization population in step S302 of the present embodiment is specifically as follows:
s30201, generating an intermittent path: randomly taking out an unobstructed grating from each row in sequence to form an intermittent path; wherein the first grid of the path and the last grid of the path are a starting position and a target position respectively;
s30202, connecting the discontinuous path to the continuous path, specifically as follows:
s3020201, determining from the first grid whether two adjacent grids are consecutive grids:
if the grid is continuous, executing step S3020202;
s3020202, judging whether the new grid is an obstacle grid:
(1) if the new grid is an obstacle grid, step S3020203 is executed;
(2) if the new grid is an unobstructed grid, the process goes to step S3020205;
s3020203, fetching adjacent grids of the new grid in order of up, down, left, and right, and judging whether the adjacent grids of the new grid are already in the path (preventing trapping dead loops):
if the neighboring grid of the new grid is an unobstructed grid and is not in the path, then step S3020204 is performed;
s3020204, inserting into the path, and executing the step S3020207 next;
s3020205, inserting the two discontinuous grids, and executing the step S3020206 next;
s3020206, continuously judging whether the newly inserted grid and the previous grid of the newly inserted grid are continuous:
(1) if not, the steps S3020201 to S3020206 are looped to find new grids until the two grids are continuous, and the next step is to execute step S3020207;
s3020207, when two grids are continuous, then take the next grid, and loop through steps S3020201 to S3020206 to find the next grid until the whole path is continuous.
For example: the starting position is grid 0 and the target position is grid 99. Initializing a population requires randomly generating a plurality of viable paths that represent paths that do not collide with the obstacle grid.
The path optimization by the iterative fitness function in step S303 of the present embodiment is specifically as follows:
s30301, a selection method comprises the following steps: calculating the sum of fitness functions of all individuals, calculating the ratio of each individual, and selecting the next generation of individuals in a roulette mode according to the probability of each individual, wherein the roulette mode ensures partial non-optimal individuals and can effectively prevent the algorithm from falling into a local optimal solution. The fitness function is divided into two parts, which are respectively used for judging the length and the smoothness of the path. The robot is not suitable to turn too much when traveling due to the constraints of kinematics and dynamics, and a relatively smooth path is beneficial to the traveling of the robot, so that the generated path has the requirement of smoothness.
S30302, cross mode: determining a cross probability pc, generating a random number between 0 and 1, and comparing the random number with the cross probability pc; if the value is smaller than pc, performing cross operation; the method comprises the following steps:
finding out all the same points in the two paths, randomly selecting one point, and performing cross operation on the subsequent paths;
s30303, variant mode: determining a variation probability pm, generating a random number between 0 and 1, and comparing the random number with the variation probability pm; if the value is less than pm, performing mutation operation; the method comprises the following steps:
randomly selecting two grids except a starting point and an end point in the path, removing the path between the two grids, and connecting the discontinuous paths into continuous paths by using the two grids as adjacent points for continuous operation in the step S30202; when the continuous path cannot be generated, the two points are reselected to perform the mutation operation until the mutation operation is completed.
As shown in fig. 4, in step S4 of this embodiment, the road cleaning by the mobile road cleaning machine is specifically as follows:
s401, arranging a road cleaning machine at a proper position of a road to be cleaned, integrally shooting the road by using an unmanned aerial vehicle, transmitting a picture into a raspberry pie, and judging whether garbage exists or not through a road garbage distribution model:
(1) if the garbage model exists, executing step S402;
(2) if no garbage exists, no treatment is carried out;
s402, the pavement garbage distribution model processes the processed result through a genetic algorithm to obtain a path planning chart, and the path planning chart is sent to a pavement cleaning machine;
s403, the road surface cleaning machine performs cleaning work according to the path planning chart until the road surface is free of garbage;
s404, returning the road surface cleaning machine to the original position after the cleaning work is completed.
Example 2:
the embodiment of the invention also provides electronic equipment, which comprises: a memory and a processor;
wherein the memory stores computer-executable instructions;
the processor executes the computer-executable instructions stored by the memory, so that the processor executes the intelligent road surface cleaning method based on the convolutional neural network and the genetic algorithm in any embodiment of the invention.
Example 3:
the embodiment of the invention also provides a computer readable storage medium, wherein a plurality of instructions are stored, and the instructions are loaded by a processor, so that the processor executes the intelligent pavement cleaning method based on the convolutional neural network and the genetic algorithm in any embodiment of the invention. Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code form part of the present invention.
Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RYM, DVD-RWs, DVD+RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer by a communication network.
Further, it should be apparent that the functions of any of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform part or all of the actual operations based on the instructions of the program code.
Further, it is understood that the program code read out by the storage medium is written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion unit connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion unit is caused to perform part and all of actual operations based on instructions of the program code, thereby realizing the functions of any of the above embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (7)
1. The intelligent road surface cleaning method based on the convolutional neural network and the genetic algorithm is characterized in that the method is characterized in that the garbage distribution condition on the road surface is identified through the convolutional neural network, the path planning is carried out through the genetic algorithm, and the road surface cleaning is carried out by utilizing a mobile road surface cleaning machine; the method comprises the following steps:
s1, constructing a road surface garbage distribution model through a convolutional neural network;
s2, recognizing the garbage distribution situation on the road surface by using a classification method in the convolutional neural network, and training a road surface garbage distribution model;
s3, planning a path through a genetic algorithm according to the distribution condition of the road surface garbage; the method comprises the following steps:
s301, building a map: constructing a grid map by adopting a grid algorithm;
s302, initializing a population: randomly generating a plurality of feasible paths, wherein the feasible paths represent paths which do not collide with the barrier grid; the method comprises the following steps:
s30201, generating an intermittent path: randomly taking out an unobstructed grating from each row in sequence to form an intermittent path; wherein the first grid of the path and the last grid of the path are a starting position and a target position respectively;
s30202, connecting the discontinuous path to the continuous path, specifically as follows:
s3020201, determining from the first grid whether two adjacent grids are consecutive grids:
if the grid is continuous, executing step S3020202;
s3020202, judging whether the new grid is an obstacle grid:
(1) if the new grid is an obstacle grid, step S3020203 is executed;
(2) if the new grid is an unobstructed grid, the process goes to step S3020205;
s3020203, taking adjacent grids of the new grid in the sequence of up, down, left and right, and judging whether the adjacent grids of the new grid are in the path or not:
if the neighboring grid of the new grid is an unobstructed grid and is not in the path, then step S3020204 is performed;
s3020204, inserting into the path, and executing the step S3020207 next;
s3020205, inserting the two discontinuous grids, and executing the step S3020206 next;
s3020206, continuously judging whether the newly inserted grid and the previous grid of the newly inserted grid are continuous:
(1) if not, the steps S3020201 to S3020206 are looped to find new grids until the two grids are continuous, and the next step is to execute step S3020207;
s3020207, when two grids are continuous, taking down one grid, and circulating the steps S3020201 to S3020206 to search for the next grid until the whole path is continuous;
s303, calculating a fitness function: optimizing the path through an iterative fitness function; the method comprises the following steps:
s30301, a selection method comprises the following steps: calculating the sum of fitness functions of all individuals, calculating the ratio of each individual, and selecting the next generation of individuals in a roulette mode according to the probability of each individual;
s30302, cross mode: determining a cross probability pc, generating a random number between 0 and 1, and comparing the random number with the cross probability pc; if the value is smaller than pc, performing cross operation; the method comprises the following steps:
finding out all the same points in the two paths, randomly selecting one point, and performing cross operation on the subsequent paths;
s30303, variant mode: determining a variation probability pm, generating a random number between 0 and 1, and comparing the random number with the variation probability pm; if the value is less than pm, performing mutation operation; the method comprises the following steps:
randomly selecting two grids except a starting point and an end point in the path, removing the path between the two grids, and connecting the discontinuous paths into continuous paths by using the two grids as adjacent points for continuous operation in the step S30202; when the continuous path cannot be generated, reselecting the two points to perform mutation operation until the mutation operation is completed;
s4, embedding the road surface garbage model and the path planning into a raspberry group, and embedding the raspberry group and an unmanned camera into a mobile road cleaning machine, wherein the mobile road cleaning machine performs road cleaning, so that the purpose of road cleaning is achieved.
2. The intelligent pavement cleaning method based on convolutional neural network and genetic algorithm as set forth in claim 1, wherein the pavement garbage distribution model in step S2 is trained specifically as follows:
s201, constructing a pavement data set: the method comprises the steps of dividing a training set and a testing set;
s202, training a road surface garbage distribution model: putting the garbage distribution model into a processed horizontal plane training set, and training the pavement garbage distribution model through a server;
s203, testing a road surface garbage distribution model: putting the trained model into a test set for polarity test;
s204, optimizing a road surface garbage distribution model: and according to the pavement garbage distribution model test result, re-acquiring the pavement data set to train or finely tune the pavement garbage distribution model until the model is fitted.
3. The intelligent road surface cleaning method based on convolutional neural network and genetic algorithm as set forth in claim 2, wherein the construction of the road surface data set in step S201 is specifically as follows:
s20101, collecting pictures: under different light environments, taking photos and recording the road surface through the unmanned aerial vehicle, and obtaining road surface pictures;
s20102, tag label: observing whether the pictures of the pavement contain garbage or not by naked eyes, and marking the pictures with labels, wherein the content of the labels is whether the garbage exists or not;
s20103, preprocessing the picture: the existing photo is selectively cut, rotated, enlarged or reduced;
s20104, manufacturing a pavement data set: all tagged photographs were made into one pavement data set.
4. The intelligent road surface cleaning method based on convolutional neural network and genetic algorithm as claimed in claim 1, wherein the grid map is a rectangular coordinate system established by taking the first grid at the lower left corner of the map as the origin of coordinates, each grid is represented by the form of coordinates of (x, y), and numbering is carried out for each grid, and a path is represented by the grid number.
5. The intelligent road surface cleaning method based on convolutional neural network and genetic algorithm as set forth in claim 1, wherein the road cleaning by moving the road surface cleaning machine in step S4 is specifically as follows:
s401, arranging a road cleaning machine at a proper position of a road to be cleaned, integrally shooting the road by using an unmanned aerial vehicle, transmitting a picture into a raspberry pie, and judging whether garbage exists or not through a road garbage distribution model:
(1) if the garbage model exists, executing step S402;
(2) if no garbage exists, no treatment is carried out;
s402, the pavement garbage distribution model processes the processed result through a genetic algorithm to obtain a path planning chart, and the path planning chart is sent to a pavement cleaning machine;
s403, the road surface cleaning machine cleans according to the path planning chart until the road surface is free of garbage;
s404, returning the road surface cleaning machine to the original position after the cleaning work is completed.
6. An electronic device, comprising: a memory and at least one processor;
wherein the memory has a computer program stored thereon;
the at least one processor executing the computer program stored by the memory causes the at least one processor to perform the intelligent road surface cleaning method based on a convolutional neural network and a genetic algorithm as claimed in any one of claims 1 to 5.
7. A computer readable storage medium, characterized in that it has stored therein a computer program executable by a processor to implement the intelligent road surface cleaning method based on convolutional neural network and genetic algorithm as claimed in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111090784.8A CN113837049B (en) | 2021-09-17 | 2021-09-17 | Intelligent pavement cleaning method based on convolutional neural network and genetic algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111090784.8A CN113837049B (en) | 2021-09-17 | 2021-09-17 | Intelligent pavement cleaning method based on convolutional neural network and genetic algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113837049A CN113837049A (en) | 2021-12-24 |
CN113837049B true CN113837049B (en) | 2023-06-20 |
Family
ID=78959715
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111090784.8A Active CN113837049B (en) | 2021-09-17 | 2021-09-17 | Intelligent pavement cleaning method based on convolutional neural network and genetic algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113837049B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116681195A (en) * | 2023-06-06 | 2023-09-01 | 深圳启示智能科技有限公司 | Robot road-finding device based on artificial intelligence |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10242264B1 (en) * | 2018-04-25 | 2019-03-26 | Imagry (Israel) Ltd. | System and method for training a machine-learning model to identify real-world elements |
CN110097139A (en) * | 2019-05-13 | 2019-08-06 | 济南浪潮高新科技投资发展有限公司 | A kind of intelligence rice washing method and device based on convolutional neural networks |
CN111985316A (en) * | 2020-07-10 | 2020-11-24 | 上海富洁科技有限公司 | Road surface garbage sensing method for intelligent road cleaning |
-
2021
- 2021-09-17 CN CN202111090784.8A patent/CN113837049B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10242264B1 (en) * | 2018-04-25 | 2019-03-26 | Imagry (Israel) Ltd. | System and method for training a machine-learning model to identify real-world elements |
CN110097139A (en) * | 2019-05-13 | 2019-08-06 | 济南浪潮高新科技投资发展有限公司 | A kind of intelligence rice washing method and device based on convolutional neural networks |
CN111985316A (en) * | 2020-07-10 | 2020-11-24 | 上海富洁科技有限公司 | Road surface garbage sensing method for intelligent road cleaning |
Non-Patent Citations (1)
Title |
---|
基于深度学习技术的巡检视频图像智能理解算法研究;孙干余;《中国优秀硕士论文全文数据库》;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113837049A (en) | 2021-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109446970B (en) | Transformer substation inspection robot road scene recognition method based on deep learning | |
CN114067160B (en) | Small sample remote sensing image scene classification method based on embedded smooth graph neural network | |
Ruiz et al. | Learning to simulate | |
Jeong et al. | Image preprocessing for efficient training of YOLO deep learning networks | |
CN107203781B (en) | End-to-end weak supervision target detection method based on significance guidance | |
CN112465738B (en) | Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images | |
CN109785385B (en) | Visual target tracking method and system | |
CN110569901A (en) | Channel selection-based countermeasure elimination weak supervision target detection method | |
WO2020046213A1 (en) | A method and apparatus for training a neural network to identify cracks | |
JP6980289B2 (en) | Learning method and learning device that can detect lanes using a lane model, and test method and test device using this {LEARNING METHOD, LEARNING DEVICE FOR DETECTING LANE USING LANE MODEL AND TEST METHOD, TEST DEVICE | |
CN106133756A (en) | For filtering, split and identify the system without the object in constraint environment | |
JP2020038660A (en) | Learning method and learning device for detecting lane by using cnn, and test method and test device using the same | |
CN115563674B (en) | Initial planar arrangement generating method and device, electronic equipment and storage medium | |
CN112766170B (en) | Self-adaptive segmentation detection method and device based on cluster unmanned aerial vehicle image | |
CN112052818A (en) | Unsupervised domain adaptive pedestrian detection method, unsupervised domain adaptive pedestrian detection system and storage medium | |
CN113673482B (en) | Cell antinuclear antibody fluorescence recognition method and system based on dynamic label distribution | |
CN112148028A (en) | Environment monitoring method and system based on unmanned aerial vehicle shooting image | |
CN113837049B (en) | Intelligent pavement cleaning method based on convolutional neural network and genetic algorithm | |
CN114511077A (en) | Training point cloud processing neural networks using pseudo-element based data augmentation | |
CN115526316A (en) | Knowledge representation and prediction method combined with graph neural network | |
CN117948976B (en) | Unmanned platform navigation method based on graph sampling and aggregation | |
Tomoe et al. | Long-term knowledge distillation of visual place classifiers | |
Hwang et al. | Object Detection for Cargo Unloading System Based on Fuzzy C Means. | |
Mosalam et al. | NEW DIRECTIONS IN STRUCTURAL HEALTH MONITORING. | |
CN116362294B (en) | Neural network searching method and device and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |