CN114610030B - Operation allocation path planning method and system based on combined intelligent algorithm - Google Patents
Operation allocation path planning method and system based on combined intelligent algorithm Download PDFInfo
- Publication number
- CN114610030B CN114610030B CN202210227656.1A CN202210227656A CN114610030B CN 114610030 B CN114610030 B CN 114610030B CN 202210227656 A CN202210227656 A CN 202210227656A CN 114610030 B CN114610030 B CN 114610030B
- Authority
- CN
- China
- Prior art keywords
- path
- algorithm
- fish
- result
- optimal
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 129
- 238000000034 method Methods 0.000 title claims abstract description 43
- 241000251468 Actinopterygii Species 0.000 claims abstract description 122
- 238000005457 optimization Methods 0.000 claims abstract description 23
- 239000004575 stone Substances 0.000 claims description 38
- 230000006399 behavior Effects 0.000 claims description 33
- 238000009412 basement excavation Methods 0.000 claims description 19
- 239000011435 rock Substances 0.000 claims description 15
- 241000257303 Hymenoptera Species 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 230000000007 visual effect Effects 0.000 claims description 9
- 230000007704 transition Effects 0.000 claims description 5
- 230000002431 foraging effect Effects 0.000 claims description 4
- 230000019637 foraging behavior Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000010276 construction Methods 0.000 description 13
- 239000003016 pheromone Substances 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 238000003306 harvesting Methods 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000000638 solvent extraction 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
- 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
- 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
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for planning an operation allocation path based on a combined intelligent algorithm, wherein the method comprises the following steps: adopting an ant colony algorithm to perform path optimization, and obtaining a first convergence result of the ant colony algorithm iteration when the relative error of the comprehensive cost of the current optimal scheme and the optimal scheme formed by the last iteration is smaller than a set threshold value; adopting an artificial fish swarm algorithm to perform swarm and rear-end collision to obtain a first optimizing result of the artificial fish swarm algorithm; if the first convergence result is better than the first optimizing result of the artificial fish swarm algorithm, continuing optimizing by adopting the ant colony algorithm on the basis of the first optimizing result until convergence to obtain a second convergence result; selecting smaller results from the first convergence result and the second convergence result as optimal paths; otherwise, continuing path optimization to convergence by adopting an artificial fish swarm algorithm, and taking the obtained result as an optimal path. The method and the device can avoid the problem that a single algorithm falls into local optimum, so that the planning result is more accurate and reliable.
Description
Technical Field
The invention relates to the technical field of operation allocation path planning, in particular to an operation allocation path planning method and system based on a combined intelligent algorithm.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The operation path planning is widely applied to integrated construction, unmanned farm crop harvesting and material allocation in a digital workshop. This patent uses the soil-stone formula to allocate in the construction of an organic whole as the illustrative innovation point. The earth and stone party allocation is widely used in engineering construction projects such as roads, flat sites, earth and stone dams, mines and the like, and the reasonable selection of the earth and stone party allocation construction order has important significance for the series connection of all construction links. Researchers try to determine the construction flow by adopting some intelligent algorithms, and an accurate and reasonable construction scheme is formed quickly while manpower and material resources are saved.
When the traditional construction process carries out the transportation and the allocation of the earthwork in the construction area, the earthwork allocation path is selected by relying on the experience of constructors, and the earthwork allocation path determined in the mode wastes manpower and material resources to a certain extent, so that the method has a large optimized space. In the present era, various intelligent algorithms are applied to the engineering field, but single intelligent algorithms such as an ant colony algorithm, a genetic algorithm and the like are adopted, and the single algorithms tend to be in local optimum easily, so that the planning of the whole operation path is not facilitated.
Disclosure of Invention
In order to solve the problems, the invention provides a method and a system for planning an operation allocation path based on a combined intelligent algorithm, which are used for forming the combined intelligent algorithm by combining an ant colony algorithm and an artificial fish swarm algorithm on the basis of completing the working area division and the earth and stone allocation cost calculation mode, so as to obtain the optimal earth and stone allocation path in the engineering mechanical operation process.
In some embodiments, the following technical scheme is adopted:
a job scheduling path planning method based on a combined intelligent algorithm comprises the following steps:
dividing grids in a working area, and calculating the cost of land and stone deployment among the grids;
Adopting an ant colony algorithm to perform path optimization, and obtaining a first convergence result of the ant colony algorithm iteration when the relative error of the comprehensive cost of the current optimal scheme and the optimal scheme formed by the last iteration is smaller than a set threshold value;
adopting an artificial fish swarm algorithm to perform swarm and rear-end collision to obtain a first optimizing result of the artificial fish swarm algorithm;
If the first convergence result is better than the first optimizing result of the artificial fish swarm algorithm, continuing optimizing by adopting the ant colony algorithm on the basis of the first optimizing result until convergence to obtain a second convergence result; selecting smaller results from the first convergence result and the second convergence result as optimal paths; otherwise, continuing path optimization to convergence by adopting an artificial fish swarm algorithm, and taking the obtained result as an optimal path.
As an alternative embodiment, the working area is divided into grids, which specifically includes:
dividing a working area into a digging grid, a filling grid, a borrowing grid, a discarding grid and an obstacle grid; wherein the excavation grid and the borrowing grid belong to the excavation area, and the filling grid and the discarding grid belong to the filling area; the obstacle grid belongs to an obstacle region.
As an alternative embodiment, an ant colony algorithm is adopted to perform path optimization, specifically:
and searching an earth and stone deployment path with the lowest cost by adopting an ant colony algorithm, and simultaneously avoiding an obstacle region from a digging region to a filling region in the operation of the engineering machinery.
As an optional implementation manner, the process of path optimization by adopting the ant colony algorithm specifically comprises the following steps:
setting initial parameters of an ant colony algorithm, and randomly distributing n ants to a excavation areas;
Each ant explores a land and stone deployment path in the iteration process, and when the kth ant enters the iteration, the tabu table is updated according to the position of the area i; if the transition probability meets the set condition, the ant moves to the next area and updates the earthwork quantity of the related area; repeating the process, when the earthwork quantity required to be transported in each area is zero, completing the exploration of the earthwork deployment path of the ants, and carrying out the iteration of the next ants until all the ants are explored, and ending the iteration;
and performing the next iteration until the algorithm converges.
As an alternative implementation scheme, an artificial fish swarm algorithm is adopted to perform swarm and rear-end collision, and a first optimizing result of the artificial fish swarm algorithm is obtained, specifically:
initializing parameters of an artificial fish swarm algorithm, wherein each artificial fish represents an earth-rock deployment path, and the distance between two artificial fish is defined as the number of different nodes in the corresponding path;
Calculating and accumulating the distance between each fish and other fish, and calculating the fish with the lowest comprehensive cost as a central fish;
when each fish iterates, firstly, judging a clustering behavior and a rear-end collision behavior;
If the clustering behavior and the rear-end collision behavior are judged to be successful, selecting a better solution in two paths generated by the two behaviors as an optimal path; if only one behavior is judged to be successful, selecting a path generated by the behavior as an optimal path; if the two behaviors are judged to be unsuccessful, entering a foraging behavior; randomly transforming the node sequence of the path of the fish, and selecting the path as an optimal path if the comprehensive cost is lower after transformation;
If no lower comprehensive cost is generated in multiple foraging, a random behavior is entered, and the original path is changed randomly.
As an alternative embodiment, the determination of the clustering behavior is specifically:
if the ratio of the fitness of the center fish to the number of the center fish in the visual field is larger than the product of the crowding degree and the fitness of the fish, successful clustering is achieved; the earth-rock deployment path of the fish deviates from the earth-rock deployment path of the center fish, and a path closer to the center fish is generated.
As an alternative embodiment, the determination of the rear-end collision behavior is specifically:
The optimal fish is artificial fish with the lowest comprehensive cost in the visual field range, and if the ratio of the fitness of the optimal fish to the number of the optimal fish in the visual field is greater than the product of the crowding degree and the fitness of the fish, the rear-end collision is successful; the earth-rock mixing path of the fish deviates to the earth-rock mixing path of the optimal fish, so that a path closer to the optimal fish is generated.
In other embodiments, the following technical solutions are adopted:
a job deployment path planning system based on a combined intelligent algorithm, comprising:
The grid dividing module is used for dividing grids of the working area and calculating the cost of earth and stone deployment among the grids;
The ant colony algorithm optimizing module is used for carrying out path optimization by adopting an ant colony algorithm, and when the relative error of the comprehensive cost of the current optimal scheme and the optimal scheme formed by the last iteration is smaller than a set threshold value, a first convergence result of the ant colony algorithm iteration is obtained;
the artificial fish swarm algorithm optimizing module is used for gathering and overtaking the tail end by adopting the artificial fish swarm algorithm to obtain a first optimizing result of the artificial fish swarm algorithm;
The optimal path determining module is used for continuing optimizing until convergence by adopting an ant colony algorithm on the basis of the first optimizing result when the first converging result is better than the first optimizing result of the artificial fish swarm algorithm to obtain a second converging result; selecting smaller results from the first convergence result and the second convergence result as optimal paths; otherwise, continuing path optimization to convergence by adopting an artificial fish swarm algorithm, and taking the obtained result as an optimal path.
In other embodiments, the following technical solutions are adopted:
A terminal device comprising a processor and a memory, the processor being configured to implement instructions; the memory is used for storing a plurality of instructions which are suitable for being loaded by the processor and executing the job scheduling path planning method based on the combined intelligent algorithm.
In other embodiments, the following technical solutions are adopted:
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the above-described job scheduling path planning method based on a combined intelligent algorithm.
Compared with the prior art, the invention has the beneficial effects that:
(1) According to the invention, the ant colony algorithm and the artificial fish swarm algorithm are combined to form the combined intelligent algorithm, so that the operation path plan with lower comprehensive cost is obtained, the algorithm selected for the next iteration is determined according to the convergence result of the algorithm, the problem that a single algorithm falls into local optimum can be avoided, and the planning result is more accurate and reliable.
Additional features and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1 is a flowchart of a method for planning a job scheduling path based on a combined intelligent algorithm in an embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Example 1
In one or more embodiments, a job scheduling path planning method based on a combined intelligent algorithm is disclosed, and referring to fig. 1, the method specifically includes the following steps:
s101: dividing grids in a working area, and calculating the cost of land and stone deployment among the grids;
Specifically, according to the embodiment, according to actual requirements, the area is divided into different grids, and for calculating the land and stone deployment cost of a construction area, the working area is divided into five grids, namely, the area needing to excavate the land and stone; filling grids, namely areas needing to be filled with earth and stones; the borrowing grid can borrow the area of the earth and stone, such as a borrowing field; discarding grid, namely discarding the area of the earth and stone, such as discarding the stock ground; obstacle grids, i.e. areas through which the work machine cannot pass. Wherein the excavation grid and the borrowing grid both belong to the excavation area, and the filling grid and the discarding grid both belong to the filling area.
After the partitioning is completed, the engineering machinery operation cost is proposed, and the monetary cost M ij from the earth and stone deployment of the grid i to the grid j per day specifically comprises: the construction area is the earth and stone transportation cost, the earth and stone filling cost, the earth and stone excavation cost, the earth and stone borrowing cost and the earth and stone abandoning cost; the time cost of the operation process is the number of days from the deployment of the earth and stone from grid i to grid j. The composite cost C ij is the product of construction days and monetary cost/day.
The construction machine to which the cost calculation should be applied should be clarified. The engineering machinery for carrying out earth and stone deployment mainly comprises an excavator and a bulldozer. The excavator is used for achieving the function of digging and filling in a working area, the bulldozer is used for achieving the function of transporting earth and stones in a short distance, and the scraper is used for achieving the function of transporting earth and stones in a long distance.
S102: adopting an ant colony algorithm to perform path optimization, and obtaining a first convergence result of the ant colony algorithm iteration when the relative error of the comprehensive cost of the current optimal scheme and the optimal scheme formed by the last iteration is smaller than a set threshold value;
In this embodiment, the ant colony algorithm is used to find the land and stone deployment path with the lowest cost, and the engineering machinery is moved from the excavation area to the filling area during operation, while avoiding the obstacle area. The excavation area is a set of excavation grids and borrowing grids, the filling area is a set of filling grids and abandoning grids, and the obstacle area is a set of obstacle grids. And defining the earthwork quantity required to be transported in each excavation area and each filling area, wherein the earthwork quantity in the excavation area is positive, the earthwork quantity in the filling area is negative, and the total excavation quantity and the total filling quantity are equal.
The ant moves each time and needs to update a tabu table, and when the ant is currently positioned on the square digging grid, the tabu table comprises a borrowing grid and an obstacle grid; when ants are currently in the filling grid, the tabu list comprises a discarding grid and an obstacle grid; when ants are currently in the borrower grid, the tabu list comprises a digging grid, a discarding grid and an obstacle grid; when ants are currently in the discarding grid, the tabu list includes the filling grid, the borrowing grid and the obstacle grid.
The concrete steps of carrying out the planning of the earth and stone deployment path by adopting the ant colony algorithm are as follows:
(1) And initializing parameters. The method comprises the following parameters of ant number n=50, pheromone importance factor alpha=1, comprehensive cost importance factor beta=7, pheromone tau ij on the paths of the excavation area i and the filling area j, pheromone volatilization coefficient rho=0.5, heuristic function eta ij, namely the reciprocal of comprehensive cost C ij, current area s, tabu table of the current area k, current iteration time t, maximum iteration time maxgen =200 and the like.
(2) The path pheromone between each excavation area and each filling area is set to be constant, n ants are randomly distributed to a excavation areas, namely, the initial area of each ant is the excavation area.
(3) The iterative process starts, each time with t=t+1. In the iterative process, each ant explores a clay-stone deployment path, the ant numbers are 1 to n, and k represents the current ant. When ant k enters iteration, updating a tabu table according to the position of region i, and calculating transition probability according to the following formula:
When ants will move, traversing all the possible moving areas, selecting the area with the highest transition probability in the traversing area to move, and updating the soil volume of the related area. And (5) carrying out probability calculation of the next transition. When the earthwork quantity required to be transported in each area is zero, the earthwork deployment path of the ants is explored, and a complete earthwork deployment scheme is obtained, wherein k=k+1. When k is less than n, the next ant exploring process is entered, and when k=n, the iteration is ended.
After the iteration is finished, recording the optimal scheme in all earth and stone deployment schemes, and updating the pheromone on each path according to the pheromone updating formula, wherein the pheromone updating formula is as follows:
Where τ ij (t+1) is the pheromone on the path of the land i and the fill j in the t+1 iteration, τ ij (t) is the pheromone on the path of the land i and the fill j in the t iteration, and Δτ ij is the pheromone increment on the path of the land i and the fill j.
And when the iteration times t is greater than 1, calculating the relative error between the comprehensive cost of the optimal scheme of the iteration and the optimal scheme of the last iteration. The calculation formula is as follows:
Wherein A_f t (x) represents the reciprocal of the comprehensive cost of the earth and stone deployment path obtained by the t-th iteration of the ant colony algorithm, and A_f t-1 (x) represents the reciprocal of the comprehensive cost of the earth and stone deployment path obtained by the t-1 th iteration of the ant colony algorithm. And setting a relative error threshold value of 0.01, and if the relative error is smaller than the threshold value, indicating that the change between the iteration and the last iteration is smaller, and converging the algorithm. If the relative error is greater than the threshold, a convergence space still exists, and the optimization calculation is continued.
S103: adopting an artificial fish swarm algorithm to perform swarm and rear-end collision to obtain a first optimizing result of the artificial fish swarm algorithm;
in this embodiment, an artificial fish swarm algorithm is adopted to generate a land and stone formula allocation scheme, and parameter initialization is performed first. Each artificial fish represents an earth-rock deployment path, and the distance between two artificial fish is defined as the number of different nodes in the corresponding path;
One artificial fish passing through n regions is denoted as a= { a 1,a2,…,an }, the other artificial fish passing through m regions is denoted as b= { B 1,b2,…,bm }, and given that n is less than or equal to m, the distance between a and B is defined as:
Wherein,
X is |a i-bi |, and view is the visual field of the artificial fish.
If dis (A, B) < view, then the two artificial fish A and B are considered to be in view of each other. Taking most common or nearest values of the plurality of fishes as centers of the plurality of fishes, calculating and accumulating the distances between each fish and other fishes, taking the fish with the smallest total distance as the center of the plurality of fishes, and taking the fish with the lowest comprehensive cost as the center of the plurality of fishes if the total distances of different fishes are the smallest.
When each fish iterates, firstly, judging a clustering behavior and a rear-end collision behavior;
the clustering behavior determination formula is as follows:
Wherein η z represents the fitness of the center fish in the field of view, i.e. the reciprocal of the integrated cost; n z represents the number of center fish; delta represents the congestion level, which is set to 0.618 in the present invention; η i represents the fitness of the present fish. If the method is established, the aggregation is successful, and the earth-rock mixing path of the fish deviates from the earth-rock mixing path of the center fish, so that a path closer to the center fish is generated.
The judgment formula of the rear-end collision behavior is as follows:
Wherein, the optimal fish is artificial fish with the lowest comprehensive cost in the visual field range, and eta min represents the adaptability of the optimal fish in the visual field; n z represents the number of optimal fish; delta represents the degree of congestion; η i represents the fitness of the present fish. If the method is established, the rear-end collision is successful, and the earth-rock mixing path of the fish deviates to the earth-rock mixing path of the optimal fish, so that a path closer to the optimal fish is generated.
If the group behavior and the rear-end behavior are judged to be successful, the better solutions of the two paths generated by the two behaviors are selected as the results. If just one behavior determination is successful, the path generated by that behavior is selected as the result. If the judgment of the two behaviors is unsuccessful, the foraging behavior is entered, the node sequence of the path of the fish is randomly changed, the path is selected as a result after the comprehensive cost is lower, and otherwise foraging is continued. If no better solution is generated in multiple foraging, the random behavior is entered, and the original path is changed randomly.
After all fish iterations are completed, the first iteration is ended, and a first path optimizing result is obtained.
S104: if the first convergence result of the ant colony algorithm iteration is better than the first optimizing result of the artificial fish swarm algorithm, continuing optimizing until convergence by adopting the ant colony algorithm on the basis of the first optimizing result to obtain a second convergence result; selecting smaller results from the first convergence result and the second convergence result as optimal paths; otherwise, continuing path optimization to convergence by adopting an artificial fish swarm algorithm, and taking the obtained result as an optimal path.
In this embodiment, the ant colony algorithm is first adopted to perform optimization, and if the relative error H is less than 0.01, it is explained that the ant colony algorithm may fall into local optimization, so as to obtain a convergence result a_f (x) of the ant colony algorithm iteration. And (3) performing swarm and rear-end collision by using an artificial fish swarm algorithm, and playing the global searching capability of the artificial fish swarm algorithm to obtain a first optimizing result FA_f 1 (x) of the artificial fish swarm algorithm.
Comparing the sizes of A_f (x) and FA_f 1 (x), if the optimizing result of the artificial fish swarm algorithm is better than the optimizing result of the ant colony algorithm, adopting the artificial fish swarm algorithm to optimize until convergence, wherein the iteration number is r, and the iteration number is expressed as FA_f r (x), and the result is the optimal solution of the iteration process;
If the artificial fish swarm optimization result is worse than the ant swarm optimization result, then the ant swarm algorithm is used for optimizing, the ant swarm algorithm is used for optimizing until convergence to obtain a convergence result FA_f l (x), the iteration times are l, the sizes of A_f (x) and FA_f l (x) are compared, and the smaller value is the optimal solution.
It should be noted that, the method of the embodiment is not only applied to the operation allocation of the earthwork, but also is applicable to the operation allocation of other occasions, such as: unmanned farm crop harvesting, material allocation operation in a digital workshop, and the like.
Example two
In one or more embodiments, a job deployment path planning system based on a combined intelligent algorithm is disclosed, comprising:
The grid dividing module is used for dividing grids of the working area and calculating the cost of earth and stone deployment among the grids;
The ant colony algorithm optimizing module is used for carrying out path optimization by adopting an ant colony algorithm, and when the relative error of the comprehensive cost of the current optimal scheme and the optimal scheme formed by the last iteration is smaller than a set threshold value, a first convergence result of the ant colony algorithm iteration is obtained;
the artificial fish swarm algorithm optimizing module is used for gathering and overtaking the tail end by adopting the artificial fish swarm algorithm to obtain a first optimizing result of the artificial fish swarm algorithm;
The optimal path determining module is used for continuing optimizing until convergence by adopting an ant colony algorithm on the basis of the first optimizing result when the first converging result is better than the first optimizing result of the artificial fish swarm algorithm to obtain a second converging result; selecting smaller results from the first convergence result and the second convergence result as optimal paths; otherwise, continuing path optimization to convergence by adopting an artificial fish swarm algorithm, and taking the obtained result as an optimal path.
It should be noted that, the specific implementation manner of each module has been described in the first embodiment, and will not be described in detail herein.
Example III
In one or more embodiments, a terminal device is disclosed, including a server, where the server includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the processor implements the job deployment path planning method based on the combined intelligent algorithm in the first embodiment. For brevity, the description is omitted here.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic device, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include read only memory and random access memory and provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software.
Example IV
In one or more embodiments, a computer-readable storage medium is disclosed, in which a plurality of instructions are stored, the instructions being adapted to be loaded by a processor of a terminal device and to perform the job deployment path planning method based on a combinatorial intelligent algorithm described in embodiment one.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (10)
1. The operation allocation path planning method based on the combined intelligent algorithm is characterized by comprising the following steps of:
dividing grids in a working area, and calculating the cost of land and stone deployment among the grids;
Adopting an ant colony algorithm to perform path optimization, and obtaining a first convergence result of the ant colony algorithm iteration when the relative error of the comprehensive cost of the current optimal scheme and the optimal scheme formed by the last iteration is smaller than a set threshold value;
adopting an artificial fish swarm algorithm to perform swarm and rear-end collision to obtain a first optimizing result of the artificial fish swarm algorithm;
If the first convergence result is better than the first optimizing result of the artificial fish swarm algorithm, continuing optimizing by adopting the ant colony algorithm on the basis of the first optimizing result until convergence to obtain a second convergence result; selecting smaller results from the first convergence result and the second convergence result as optimal paths; otherwise, continuing path optimization to convergence by adopting an artificial fish swarm algorithm, and taking the obtained result as an optimal path.
2. The method for planning a job scheduling path based on a combined intelligent algorithm according to claim 1, wherein the method for planning the job scheduling path comprises the steps of:
dividing a working area into a digging grid, a filling grid, a borrowing grid, a discarding grid and an obstacle grid; wherein the excavation grid and the borrowing grid belong to the excavation area, and the filling grid and the discarding grid belong to the filling area; the obstacle grid belongs to an obstacle region.
3. The method for planning the operation allocation path based on the combined intelligent algorithm as claimed in claim 1, wherein the method for path optimization by adopting the ant colony algorithm is specifically as follows:
and searching an earth and stone deployment path with the lowest cost by adopting an ant colony algorithm, and simultaneously avoiding an obstacle region from a digging region to a filling region in the operation of the engineering machinery.
4. The method for planning a path of job deployment based on a combined intelligent algorithm as set forth in claim 3, wherein the process of path optimization by adopting an ant colony algorithm comprises the following steps:
setting initial parameters of an ant colony algorithm, and randomly distributing n ants to a excavation areas;
Each ant explores a land and stone deployment path in the iteration process, and when the kth ant enters the iteration, the tabu table is updated according to the position of the area i; if the transition probability meets the set condition, the ant moves to the next area and updates the earthwork quantity of the related area; repeating the process, when the earthwork quantity required to be transported in each area is zero, completing the exploration of the earthwork deployment path of the ants, and carrying out the iteration of the next ants until all the ants are explored, and ending the iteration;
and performing the next iteration until the algorithm converges.
5. The method for planning an operation allocation path based on a combined intelligent algorithm according to claim 1, wherein the artificial fish swarm algorithm is adopted for clustering and rear-end collision, and a first optimizing result of the artificial fish swarm algorithm is obtained, specifically:
initializing parameters of an artificial fish swarm algorithm, wherein each artificial fish represents an earth-rock deployment path, and the distance between two artificial fish is defined as the number of different nodes in the corresponding path;
Calculating and accumulating the distance between each fish and other fish, and calculating the fish with the lowest comprehensive cost as a central fish;
when each fish iterates, firstly, judging a clustering behavior and a rear-end collision behavior;
If the clustering behavior and the rear-end collision behavior are judged to be successful, selecting a better solution in two paths generated by the two behaviors as an optimal path; if only one behavior is judged to be successful, selecting a path generated by the behavior as an optimal path; if the two behaviors are judged to be unsuccessful, entering a foraging behavior; randomly transforming the node sequence of the path of the fish, and selecting the path as an optimal path if the comprehensive cost is lower after transformation;
If no lower comprehensive cost is generated in multiple foraging, a random behavior is entered, and the original path is changed randomly.
6. The method for planning a job scheduling path based on a combined intelligent algorithm as set forth in claim 5, wherein the determining of the clustering behavior is specifically:
if the ratio of the fitness of the center fish to the number of the center fish in the visual field is larger than the product of the crowding degree and the fitness of the fish, successful clustering is achieved; the earth-rock deployment path of the fish deviates from the earth-rock deployment path of the center fish, and a path closer to the center fish is generated.
7. The method for planning a job scheduling path based on a combined intelligent algorithm as set forth in claim 5, wherein the determining of the rear-end collision behavior is specifically:
The optimal fish is artificial fish with the lowest comprehensive cost in the visual field range, and if the ratio of the fitness of the optimal fish to the number of the optimal fish in the visual field is greater than the product of the crowding degree and the fitness of the fish, the rear-end collision is successful; the earth-rock mixing path of the fish deviates to the earth-rock mixing path of the optimal fish, so that a path closer to the optimal fish is generated.
8. An operation allocation path planning system based on a combined intelligent algorithm is characterized by comprising:
The grid dividing module is used for dividing grids of the working area and calculating the cost of earth and stone deployment among the grids;
The ant colony algorithm optimizing module is used for carrying out path optimization by adopting an ant colony algorithm, and when the relative error of the comprehensive cost of the current optimal scheme and the optimal scheme formed by the last iteration is smaller than a set threshold value, a first convergence result of the ant colony algorithm iteration is obtained;
the artificial fish swarm algorithm optimizing module is used for gathering and overtaking the tail end by adopting the artificial fish swarm algorithm to obtain a first optimizing result of the artificial fish swarm algorithm;
The optimal path determining module is used for continuing optimizing until convergence by adopting an ant colony algorithm on the basis of the first optimizing result when the first converging result is better than the first optimizing result of the artificial fish swarm algorithm to obtain a second converging result; selecting smaller results from the first convergence result and the second convergence result as optimal paths; otherwise, continuing path optimization to convergence by adopting an artificial fish swarm algorithm, and taking the obtained result as an optimal path.
9. A terminal device comprising a processor and a memory, the processor being configured to implement instructions; a memory for storing a plurality of instructions adapted to be loaded by a processor and to perform the combined intelligent algorithm-based job scheduling method of any one of claims 1-7.
10. A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the job deployment path planning method based on a combinatorial intelligent algorithm as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210227656.1A CN114610030B (en) | 2022-03-08 | 2022-03-08 | Operation allocation path planning method and system based on combined intelligent algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210227656.1A CN114610030B (en) | 2022-03-08 | 2022-03-08 | Operation allocation path planning method and system based on combined intelligent algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114610030A CN114610030A (en) | 2022-06-10 |
| CN114610030B true CN114610030B (en) | 2024-05-28 |
Family
ID=81861381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210227656.1A Active CN114610030B (en) | 2022-03-08 | 2022-03-08 | Operation allocation path planning method and system based on combined intelligent algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114610030B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106200650A (en) * | 2016-09-22 | 2016-12-07 | 江苏理工学院 | Based on method for planning path for mobile robot and the system of improving ant group algorithm |
| CN108413976A (en) * | 2018-01-23 | 2018-08-17 | 大连理工大学 | A kind of climbing robot intelligence paths planning method and system towards multi-state |
| WO2018176595A1 (en) * | 2017-03-31 | 2018-10-04 | 深圳市靖洲科技有限公司 | Unmanned bicycle path planning method based on ant colony algorithm and polar coordinate transformation |
| CN110220525A (en) * | 2019-05-14 | 2019-09-10 | 昆明理工大学 | A kind of paths planning method based on potential field ant group algorithm |
| CN110414584A (en) * | 2019-07-22 | 2019-11-05 | 山东大学 | The motor road spectral clustering synthetic method and system of hybrid particle swarm and artificial fish-swarm algorithm |
| CN112650287A (en) * | 2020-12-22 | 2021-04-13 | 泉州云卓科技有限公司 | Unmanned aerial vehicle path planning method based on artificial fish school |
| CN113050426A (en) * | 2021-03-22 | 2021-06-29 | 山东大学 | Genetic ant colony algorithm fused thermal management control method and system |
| CN113901932A (en) * | 2021-10-13 | 2022-01-07 | 山东大学 | Engineering machinery image recognition method and system fusing artificial fish and particle swarm algorithm |
-
2022
- 2022-03-08 CN CN202210227656.1A patent/CN114610030B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106200650A (en) * | 2016-09-22 | 2016-12-07 | 江苏理工学院 | Based on method for planning path for mobile robot and the system of improving ant group algorithm |
| WO2018176595A1 (en) * | 2017-03-31 | 2018-10-04 | 深圳市靖洲科技有限公司 | Unmanned bicycle path planning method based on ant colony algorithm and polar coordinate transformation |
| CN108413976A (en) * | 2018-01-23 | 2018-08-17 | 大连理工大学 | A kind of climbing robot intelligence paths planning method and system towards multi-state |
| CN110220525A (en) * | 2019-05-14 | 2019-09-10 | 昆明理工大学 | A kind of paths planning method based on potential field ant group algorithm |
| CN110414584A (en) * | 2019-07-22 | 2019-11-05 | 山东大学 | The motor road spectral clustering synthetic method and system of hybrid particle swarm and artificial fish-swarm algorithm |
| CN112650287A (en) * | 2020-12-22 | 2021-04-13 | 泉州云卓科技有限公司 | Unmanned aerial vehicle path planning method based on artificial fish school |
| CN113050426A (en) * | 2021-03-22 | 2021-06-29 | 山东大学 | Genetic ant colony algorithm fused thermal management control method and system |
| CN113901932A (en) * | 2021-10-13 | 2022-01-07 | 山东大学 | Engineering machinery image recognition method and system fusing artificial fish and particle swarm algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 基于改进型蚁群算法的灭火机器人路径规划研究;何少佳;邓子信;高韵沣;石旅光;陈志丹;闫伟;微型机与应用;20141231(第013期);全文 * |
| 基于蚁群与鱼群的混合优化算法;修春波;张雨虹;;计算机工程;20080720(第14期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114610030A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102778229A (en) | Mobile Agent path planning method based on improved ant colony algorithm under unknown environment | |
| CN114815802A (en) | Unmanned overhead traveling crane path planning method and system based on improved ant colony algorithm | |
| CN112686424A (en) | Flat ground path range determining method, flat ground path planning method and related device | |
| CN111310999A (en) | Warehouse mobile robot path planning method based on improved ant colony algorithm | |
| CN113985888B (en) | Forklift path planning method and system based on improved ant colony algorithm | |
| CN115014362B (en) | Cattle-ploughing type full-coverage path planning method and device based on synthesis unit | |
| CN114167865B (en) | Robot path planning method based on countermeasure generation network and ant colony algorithm | |
| CN112436971B (en) | Global instruction control network cooperative topology generation method based on Monte Carlo tree search | |
| CN115639828B (en) | Robot path planning method and device based on improved artificial fish swarm algorithm | |
| CN114610030B (en) | Operation allocation path planning method and system based on combined intelligent algorithm | |
| CN116257057A (en) | Agricultural machinery operation path planning method and system based on region division | |
| Bai et al. | Design and Simulation of a Collision-free Path Planning Algorithm for Mobile Robots Based on Improved Ant Colony Optimization. | |
| CN113327322B (en) | Inversion method and device of surface wave frequency dispersion curve and computer readable storage medium | |
| CN113778090A (en) | Mobile robot path planning method based on ant colony optimization and PRM algorithm | |
| CN113110431A (en) | Real-time planning method for field test path of unmanned target vehicle | |
| CN112036537B (en) | Three-dimensional path planning method and system for land leveler navigation | |
| CN108629036A (en) | A kind of road Generalization Method and device | |
| Demetriou et al. | LandParcelS: A module for automated land partitioning | |
| Tiwari et al. | A survey of metaheuristic algorithms for travelling salesman problem | |
| CN116764225A (en) | Efficient path-finding processing method, device, equipment and medium | |
| CN115454070A (en) | K-Means ant colony algorithm multi-robot path planning method | |
| CN114996278A (en) | Road network shortest path distance calculation method based on reinforcement learning | |
| CN114625137A (en) | AGV-based intelligent parking path planning method and system | |
| Ding et al. | Path Planning of Omnidirectional mobile vehicle based on road condition | |
| Wellhausen et al. | Efficient grid map data structures for autonomous driving in large-scale environments |
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 |