CN113703472B - Path optimization method and device for collaborative inspection of multiple unmanned aerial vehicles and vehicles - Google Patents
Path optimization method and device for collaborative inspection of multiple unmanned aerial vehicles and vehicles Download PDFInfo
- Publication number
- CN113703472B CN113703472B CN202110838000.9A CN202110838000A CN113703472B CN 113703472 B CN113703472 B CN 113703472B CN 202110838000 A CN202110838000 A CN 202110838000A CN 113703472 B CN113703472 B CN 113703472B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- node
- path planning
- task allocation
- unmanned aerial
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000005457 optimization Methods 0.000 title claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 26
- 230000002068 genetic effect Effects 0.000 claims abstract description 25
- 210000000349 chromosome Anatomy 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 17
- 230000008901 benefit Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 101100390771 Danio rerio fitm1l gene Proteins 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 101150112906 fitm-2 gene Proteins 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 4
- 230000035772 mutation Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 241000073677 Changea Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002759 chromosomal effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013209 evaluation strategy Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Biology (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Genetics & Genomics (AREA)
- Evolutionary Computation (AREA)
- Remote Sensing (AREA)
- Physiology (AREA)
- Radar, Positioning & Navigation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Automation & Control Theory (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a path optimization method and device for collaborative inspection of multiple unmanned aerial vehicles and vehicles, and relates to the field of task allocation. The invention acquires the information of the target point to be inspected and the information of the inspection resource; based on the information of the target point to be inspected and the information of the inspection resource, constructing an open-type vehicle-machine cooperative path model by taking the shortest time as a target; and solving the open vehicle-machine cooperative path model through a genetic algorithm with a double fitness function to obtain an optimal task allocation path planning scheme for cooperative access of the vehicle and the unmanned aerial vehicle. The genetic algorithm provided by the invention adopts the double fitness function, so that the operation time for obtaining the approximate optimal solution can be effectively reduced, and the satisfactory solution of the problem can be obtained, thereby reducing the total time for the vehicle and the unmanned aerial vehicle to cooperatively complete the task.
Description
Technical Field
The invention relates to the technical field of task allocation, in particular to a path optimization method and device for collaborative inspection of multiple unmanned aerial vehicles and vehicles.
Background
The unmanned aerial vehicle has good maneuvering characteristics and strong timeliness, can monitor great scope, and at present, unmanned aerial vehicle has generally used in numerous fields such as traffic patrol, emergent processing, geological investigation and safety in production, but because unmanned aerial vehicle has the restriction of duration, cause unmanned aerial vehicle flight range to receive certain restriction, only can carry out limited inspection task. In order to complete tasks with tight time, heavy tasks and large scale, a large number of unmanned aerial vehicles are often required to be invested to complete specified tasks, so that the cost is greatly increased.
In the process of executing the inspection task, the vehicle and the unmanned aerial vehicle unit complex are cooperated to complete the inspection task, the vehicle and the unmanned aerial vehicle can respectively execute the inspection task, meanwhile, the moving vehicle can be used as a take-off and landing platform of the unmanned aerial vehicle, and each time the vehicle and the unmanned aerial vehicle are converged and replaced, the flight duration of each frame of the unmanned aerial vehicle can reach the maximum duration. The inspection task can be completed in a short time, and the maximum working efficiency of the vehicle and the unmanned aerial vehicle can be brought into full play.
However, the problem of vehicle-to-machine collaborative mission allocation path planning has proven to be an NP-hard problem, and it is difficult for the existing method to obtain the optimal solution of the path planning scheme in a shorter time.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a path optimization method and a path optimization device for collaborative inspection of multiple unmanned aerial vehicles and vehicles, which solve the technical problem that the operation time of the existing method for solving the approximate optimal solution is too long.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme:
in a first aspect, the present invention provides a path optimization method for collaborative inspection of multiple unmanned aerial vehicles and vehicles, the method comprising:
s1, acquiring information of a target point to be inspected and information of inspection resources;
s2, constructing an open type vehicle-machine cooperative path model by taking the shortest time as a target based on the target point information and the patrol resource information which need to be patrol;
and S3, solving the open type vehicle-machine cooperative path model through a genetic algorithm with a double fitness function, and obtaining an optimal task allocation path planning scheme for cooperative access of the vehicle and the unmanned aerial vehicle.
Preferably, the open vehicle-machine cooperative path model includes an objective function, as shown in formula (1):
wherein h, i and o are node numbers, and N is a node set; k is the number of the vehicle, and K is the set of vehicles; d is the number of the unmanned aerial vehicle, and D is the unmanned aerial vehicle set;for the driving time of the vehicle with the number k from node h to node i, < >>The flight time length from the node h to the node i of the unmanned plane with the number d is set; />For decision variables, the path of the vehicle numbered k from node h to node i is denoted +.>For the decision variables, the path of the unmanned aerial vehicle numbered d from node h to node i and merging with the vehicle numbered d at node o is represented.
Preferably, the open vehicle-machine cooperative path model includes constraint conditions, expressed by formulas (4) to (10):
wherein:
equation (4) shows that each node is accessed only once;
equation (5) shows that each vehicle starts from the warehouse;
equation (6) represents the ingress and egress balance constraint of each node;
equation (7) represents the relationship between the time the vehicle arrives at the node and the time the node starts to service;
equation (8) shows that the flight duration of each unmanned aerial vehicle cannot exceed the maximum duration of the unmanned aerial vehicle;
the formulas (9) to (10) represent decision variable value taking constraints;
d is the number of the unmanned aerial vehicle, and D is the unmanned aerial vehicle set; h. i and o are node numbers, N is a node set, and T is a patrol target point set; k is the number of the vehicle, and K is the set of vehicles;for decision variables, the path of the vehicle numbered k from node h to node i is denoted +.>As a decision variable, a path from node h to node i and merging with the vehicle numbered d at node o is represented by the unmanned aerial vehicle numbered d; />As a decision variable, a path of a vehicle numbered k from the warehouse 0 to the patrol destination i is represented;as a decision variable, a path of a vehicle numbered k from a patrol target point i to a warehouse point is represented; />As a decision variable, representing the path of a vehicle numbered k from node i to node j; />The running time of the vehicle with the number k from the node h to the node i; />Arrival time for vehicle numbered k to reach node i, +.>The arrival time of the vehicle with the number k to the node h;for the flight duration of the unmanned aerial vehicle numbered d from warehouse 0 to inspection target point l, +.>The flight time of the unmanned plane with the number d from the inspection target point l to the inspection target point m is set; />For the decision variables, the path of the unmanned plane numbered d from warehouse point 0 to patrol destination point l and merging with the vehicle numbered d at node o is indicated, +.>For decision-making changeA quantity representing a path of the unmanned aerial vehicle numbered d from the patrol destination l to the patrol destination m and merging with the vehicle numbered d at the node o; p (P) d The maximum flight duration of the unmanned aerial vehicle with the number d capable of executing the inspection task.
Preferably, the open-type vehicle-machine cooperative path model is solved through a genetic algorithm, and an optimal task allocation path planning scheme for cooperative access of a vehicle and an unmanned aerial vehicle is obtained, which comprises the following steps:
s301, setting coding rules;
s302, generating an initial task allocation path planning scheme set according to the coding rule;
and S303, optimizing the initial task allocation path planning scheme set by adopting a genetic algorithm to obtain an optimal task allocation path planning scheme cooperatively accessed by the vehicle and the unmanned aerial vehicle.
Preferably, the generating the initial task allocation path planning scheme set according to the coding rule includes:
s302a, starting from a warehouse, distributing inspection target points for the vehicles to form a first row of chromosomes;
s302b, starting from a warehouse, the unmanned aerial vehicle distributes inspection task points for the unmanned aerial vehicle, and completes tasks in cooperation with the vehicle to form a second row of chromosomes;
s302c, generating a third row of chromosomes according to the numbers of the vehicle and the unmanned aerial vehicle, and forming a task allocation path planning scheme of the vehicle and the unmanned aerial vehicle;
s302d, generating task allocation path planning schemes of the remaining vehicles and unmanned aerial vehicles according to the number of the vehicles and the unmanned aerial vehicles and the steps S302 a-S302 c, and splicing to form a complete task allocation path planning scheme, wherein the vehicles and the unmanned aerial vehicles cooperate with each other to finish inspection of the last inspection target point;
s302e, repeating the steps S302a to S302d to obtain an initial task allocation path planning scheme set.
Preferably, the dual fitness function includes:
wherein:
the fit1 fitness value of the formula (12) represents the total time length of the task path allocation planning scheme for completing the task, the smaller the fitness value is, the better the task allocation scheme is, the fit2 fitness value of the formula (13) represents the expected income of the task path allocation planning scheme, and the larger the fitness value is, the higher the useful information of the scheme is, and the better the task allocation scheme is;
h and i are node numbers, r is a patrol target point, N is a node set, and T is a patrol target point set; w (w) r The weight of the inspection target point r is D, the number of the unmanned aerial vehicle is D, and the number of the unmanned aerial vehicle is D; k is the number of the vehicle, and K is the set of vehicles;for decision variables, the path of the vehicle numbered k from node h to node i is denoted +.>As a decision variable, a path of the unmanned aerial vehicle with the number d from the patrol target point r to the patrol target point s and merging with the vehicle with the number d at the node o is represented; e, e d The detection error of the sensor carried by the unmanned aerial vehicle numbered d.
Preferably, the optimizing the initial task allocation path planning scheme set by adopting a genetic algorithm to obtain an optimal task allocation path planning scheme cooperatively accessed by the vehicle and the unmanned aerial vehicle includes:
s303a, setting execution parameters of a genetic algorithm and calculating an adaptability value of a task allocation path planning scheme through a formula (12), wherein the execution parameters comprise the maximum iteration times and the crossover probability;
s303b, selecting a roulette strategy for the initial task path planning scheme set according to the calculated fitness value of the step S303a, and selecting two chromosomes, wherein the smaller the fitness value is, the larger the selected probability is;
s303c, performing single-point crossing operation on the two selected chromosomes according to the crossing probability;
s303d, performing mutation operation on the chromosome subjected to the cross operation to obtain two new task allocation path planning schemes;
s303e, calculating the fitness value of two new task allocation path planning schemes by using a formula (12), namely executing task total time length, comparing the task total time length of the two new task allocation path planning schemes with the task total time length of the two task allocation path planning schemes obtained in the step S303d, if the total time length of flight of the new task allocation path planning schemes is smaller than the total time length of flight of one of the original task allocation path planning schemes selected by a roulette mechanism, replacing the original task allocation path planning scheme by the new task allocation path planning scheme in a task allocation path planning scheme set, if the total time length of flight of the original task allocation path planning scheme is equal to the total time length of flight of the new task allocation path planning scheme in the comparison process, calculating expected benefits of the two task allocation path planning schemes by using a formula (13), and if the expected benefits of the new task allocation path planning scheme are greater than the original task allocation path planning scheme, replacing the original task allocation path planning scheme by the new task allocation path planning scheme in the task allocation path planning scheme set;
s303f, repeating the steps S303b to S303e until the maximum iteration number is reached, stopping the operation, and obtaining the vehicle-machine collaborative optimal task allocation path planning scheme.
In a second aspect, the present invention provides a path optimization device for collaborative inspection of multiple unmanned aerial vehicles and vehicles, the device comprising the following steps:
the information acquisition module is used for acquiring information of target points and patrol resource information required to be patrol;
the model construction module is used for constructing an open type vehicle-machine cooperative path model by taking the shortest time as a target based on the target point information and the patrol resource information which need to be patrol;
and the model solving module is used for solving the open vehicle-machine collaborative path model through a genetic algorithm with a double fitness function to obtain an optimal task allocation path planning scheme for collaborative access of the vehicle and the unmanned aerial vehicle.
In a third aspect, the present invention provides a computer readable storage medium, which stores a computer program for path optimization for collaborative inspection of multiple unmanned aerial vehicles and vehicles, wherein the computer program causes a computer to execute the path optimization method for collaborative inspection of multiple unmanned aerial vehicles and vehicles as described above.
In a fourth aspect, the present invention provides an electronic device comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising a path optimization method for performing the multi-drone with vehicle co-inspection as described above.
(III) beneficial effects
The invention provides a path optimization method and device for collaborative inspection of multiple unmanned aerial vehicles and vehicles. Compared with the prior art, the method has the following beneficial effects:
the genetic algorithm provided by the invention adopts the double fitness function, so that the operation time for obtaining the approximate optimal solution can be effectively reduced, and the satisfactory solution of the problem can be obtained, thereby reducing the total time for the vehicle and the unmanned aerial vehicle to cooperatively complete the task.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a block diagram of a path optimization method for collaborative inspection of multiple unmanned aerial vehicles and vehicles according to an embodiment of the invention;
FIG. 2 is a schematic representation of a chromosome format;
fig. 3 is a schematic diagram of a path of a patrol task completed by two vehicles and two unmanned aerial vehicles in cooperation.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the application solves the technical problem that the operation time of solving the approximate optimal solution is too long in the existing method by providing the path optimization method and the device for collaborative inspection of the multiple unmanned aerial vehicles and the vehicles, and reduces the operation time for obtaining the approximate optimal solution.
The technical scheme in the embodiment of the application aims to solve the technical problems, and the overall thought is as follows:
in the prior art, the inspection task completed by the unmanned aerial vehicle is limited in range, and the number of unmanned aerial vehicles capable of completing work is insufficient. The unmanned aerial vehicle and the vehicle are cooperated, so that the inspection range can be enlarged, and the inspection cost can be effectively reduced. The problem of path planning of multi-unmanned aerial vehicle and vehicle collaborative inspection has proved to be NP-hard problem, the accurate algorithm is difficult to obtain the optimal solution of the path planning scheme in a short time, the genetic algorithm is used for solving the multi-constraint problem, and the high-quality approximate optimal solution is obtained in a short time.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
The embodiment of the invention provides a path optimization method for collaborative inspection of multiple unmanned aerial vehicles and vehicles, which comprises the following steps as shown in fig. 1:
s1, acquiring information of a target point to be inspected and information of inspection resources;
s2, constructing an open type vehicle-machine cooperative path model by taking the shortest time as a target based on the target point information and the patrol resource information which need to be patrol;
and S3, solving the open type vehicle-machine cooperative path model through a genetic algorithm with a double fitness function, and obtaining an optimal task allocation path planning scheme for cooperative access of the vehicle and the unmanned aerial vehicle.
The genetic algorithm of the embodiment of the invention can effectively reduce the operation time for obtaining the approximate optimal solution and obtain the satisfactory solution of the problem by adopting the double fitness function, thereby reducing the total time for the vehicle and the unmanned plane to cooperatively complete the task.
The implementation process of the embodiment of the invention is described in detail below:
in step S1, the target point information and the patrol resource information required for patrol are obtained, specifically:
the computer acquires the information of the target point to be inspected and the information of the inspection resource
The target point information comprises coordinates of the target point and weights of the target point;
the patrol resource information comprises unmanned aerial vehicle information, vehicle information and warehouse information.
The unmanned aerial vehicle information includes: unmanned aerial vehicle serial number, unmanned aerial vehicle flight speed, unmanned aerial vehicle duration and unmanned aerial vehicle carry the sensor error.
The vehicle information includes: vehicle number and vehicle travel speed.
The warehouse information includes warehouse coordinates.
In step S2, based on the target point information and the patrol resource information, an open vehicle-machine cooperative path model is constructed with the shortest time as a target, and the implementation process is as follows:
wherein h, i and o are node numbers, and N is a node set; k is the number of the vehicle and K is the set of vehiclesThe method comprises the steps of carrying out a first treatment on the surface of the D is the number of the unmanned aerial vehicle, and D is the unmanned aerial vehicle set;for the driving time of the vehicle with the number k from node h to node i, < >>The flight time length from the node h to the node i of the unmanned plane with the number d is set; />For decision variables, the path of the vehicle numbered k from node h to node i is denoted +.>As a decision variable, a path from node h to node i and merging with the vehicle numbered d at node o is represented by the unmanned aerial vehicle numbered d;
wherein, the liquid crystal display device comprises a liquid crystal display device,
wherein v is d The flying speed of the unmanned aerial vehicle is numbered d; x is x h Is the abscissa of node h, y h Is the ordinate of node h, x i Is the abscissa of node i, y i Is the ordinate of node i.
Wherein v is k The running speed of the vehicle numbered k; x is x h Is the abscissa of node h, y h Is the ordinate of node h, x i Is the abscissa of node i, y i Is the ordinate of node i.
The constraint is expressed by formulas (4) to (10):
wherein:
equation (4) shows that each node is accessed only once;
equation (5) shows that each vehicle starts from the warehouse;
equation (6) represents the ingress and egress balance constraint of each node;
equation (7) represents the relationship between the time the vehicle arrives at the node and the time the node starts to service;
equation (8) shows that the flight duration of each unmanned aerial vehicle cannot exceed the maximum duration of the unmanned aerial vehicle;
the formulas (9) to (10) represent decision variable value taking constraints;
d is the number of the unmanned aerial vehicle, and D is the unmanned aerial vehicle set; h. i and o are node numbers, N is a node set, and T is a patrol target point set; k is the number of the vehicle, and K is the set of vehicles;for decision variables, the path of the vehicle numbered k from node h to node i is denoted +.>As a decision variable, a path from node h to node i and merging with the vehicle numbered d at node o is represented by the unmanned aerial vehicle numbered d; />As a decision variable, a path of a vehicle numbered k from the warehouse 0 to the patrol destination i is represented; />As a decision variable, a path of a vehicle numbered k from a patrol target point i to a warehouse point is represented; />As a decision variable, representing the path of a vehicle numbered k from node i to node j; />The running time of the vehicle with the number k from the node h to the node i; />Arrival time for vehicle numbered k to reach node i, +.>The arrival time of the vehicle with the number k to the node h; />For the flight duration of the unmanned aerial vehicle numbered d from warehouse 0 to inspection target point l, +.>Unmanned aerial vehicle slave patrol with number dThe flight time from the inspection target point l to the inspection target point m; />For the decision variables, the path of the unmanned plane numbered d from warehouse point 0 to patrol destination point l and merging with the vehicle numbered d at node o is indicated,/>As a decision variable, a path of the unmanned plane with the number d from the patrol target point l to the patrol target point m and merging with the vehicle with the number d at the node o is represented; p (P) d The unmanned aerial vehicle with the number d can execute the maximum flight duration of the inspection task.
In step S3, the open-type vehicle-machine cooperative path model is solved by a genetic algorithm provided with a double fitness function, and an optimal task allocation path planning scheme for cooperative access of the vehicle and the unmanned aerial vehicle is obtained, and the specific implementation process is as follows:
s301, setting a coding rule, wherein the coding rule is as follows:
the method comprises the steps that a chromosome represents an initial task path planning scheme of a combination body formed by a vehicle and an unmanned aerial vehicle, the chromosome adopts a three-dimensional integer coding mode and is formed by three rows, a first row of the chromosome is formed by a patrol target point path accessed by the vehicle, the first row and a second row of the chromosome are combined to represent the patrol target point path accessed by the unmanned aerial vehicle, and a third row of the chromosome is formed by the number of the combination body formed by the vehicle and the unmanned aerial vehicle. The chromosomal form is shown in FIG. 2.
The chromosome representation shown in fig. 2: and the two vehicles and the two unmanned aerial vehicles cooperatively complete the inspection task. The vehicle with the number 1 sequentially goes to the inspection target point 2, the inspection target point 4 and the inspection target point 3 from the warehouse, the unmanned plane with the number 1 goes to the inspection target point 2 together with the vehicle with the number 1, and takes off from the vehicle with the number 1 at the inspection target point 2 and goes to the inspection target point 5 for inspection, then goes to the inspection target point 4 for merging with the vehicle with the number 1, then goes to the inspection target point 7 for inspection, and then goes to the inspection target point 3 for merging with the vehicle with the number 1. The vehicle with the number of 2 sequentially goes to the inspection target point 9 and the inspection target point 8 for inspection after starting from the warehouse, the unmanned aerial vehicle with the number of 2 goes to the inspection target point 1 for inspection after starting from the warehouse, then merges with the vehicle with the number of 2 at the inspection target point 9, goes to the inspection target point 6 for inspection, and then merges with the vehicle at the inspection target point 8. The corresponding path is shown in fig. 3.
S302, generating an initial task allocation path planning scheme set according to the coding rule, wherein the method specifically comprises the following four steps:
s302a, the vehicle starts from a warehouse, and a patrol target point is allocated to the vehicle to form a first row of chromosomes.
S302b, the unmanned aerial vehicle starts from a warehouse, patrol task points are distributed to the unmanned aerial vehicle, tasks are completed in cooperation with the vehicle, and a second row of chromosomes is formed.
S302c, generating a third row of chromosomes according to the numbers of the vehicle and the unmanned aerial vehicle, so as to form a task allocation path planning scheme of the vehicle and the unmanned aerial vehicle.
S302d, generating task allocation path planning schemes of the remaining vehicles and unmanned aerial vehicles according to the number of the vehicles and the unmanned aerial vehicles and the steps S302 a-S302 c, and splicing to form a complete task allocation path planning scheme. According to the scheme, the vehicle and the unmanned aerial vehicle cooperate to finish the inspection of the last inspection target point.
S302e, repeating the steps S302a to S302d to obtain an initial task allocation path planning scheme set.
In the specific implementation process, the planning schemes in the initial task allocation path planning scheme set do not necessarily meet the constraint conditions of the open vehicle-machine collaborative path model, so that constraint inspection is needed to be carried out on each chromosome in the initial task allocation path planning scheme set, and the chromosomes which do not meet the constraint conditions are deleted.
S303, optimizing an initial task allocation path planning scheme set by adopting a genetic algorithm (genetic algorithm, GA), wherein the genetic algorithm adopts a double-fitness function, so as to obtain an optimal task allocation path planning scheme cooperatively accessed by a vehicle and an unmanned aerial vehicle, and the method comprises the following steps:
it should be noted that, in the embodiment of the present invention, the merits of the task allocation path planning scheme may be represented by the fitness value of the chromosome, and according to the optimization objective of the open vehicle-machine collaborative path model, the smaller the fitness value of the task allocation path planning scheme calculated by the formula (12), the better the planning scheme is described. However, as a plurality of course angles can be selected when the unmanned aerial vehicle patrols and examines the target points, the unmanned aerial vehicle patrols and examines the target points differently, the investigation errors of the scheme are also different, and the expected benefits of the path planning scheme for completing the patrol task are different.
The method designs a chromosome double-fitness evaluation strategy, namely the total time length of executing tasks is fit1, the expected benefit is fit2, and the calculation formula is as follows:
wherein h and i are node numbers, r is a patrol target point, N is a node set, and T is a patrol target point set; w (w) r The weight of the inspection target point r is D, the number of the unmanned aerial vehicle is D, and the number of the unmanned aerial vehicle is D; k is the number of the vehicle, and K is the set of vehicles;for decision variables, the path of the vehicle numbered k from node h to node i is denoted +.>As a decision variable, a path of the unmanned aerial vehicle with the number d from the patrol target point r to the patrol target point s and merging with the vehicle with the number d at the node o is represented; e, e d The detection error of the sensor carried by the unmanned aerial vehicle numbered d.
The fit1 fitness value of the formula (12) represents the total task completion time of the task path allocation planning scheme, the smaller the fitness value is, the better the task allocation scheme is, the fit2 fitness value of the formula (13) represents the expected benefit of the task path allocation planning scheme, and the larger the fitness value is, the higher the useful information of the scheme is, and the better the task allocation scheme is. When the fit1 values of the two chromosomes are identical, fit2 values are calculated for comparison.
S303a, setting execution parameters of a genetic algorithm and calculating an adaptability value of a task allocation path planning scheme through a formula (12); the execution parameters include a maximum iteration number of 500 and a crossover probability of 0.7, and in the embodiment of the present invention, the maximum iteration number is 500, and the crossover probability is 0.7.
S303b, selecting a roulette strategy for the initial task path planning scheme set according to the calculated fitness value in the step S303a to select two chromosomes, wherein the smaller the fitness value is, the larger the probability of being selected is.
S303c, performing single-point crossing operation on the two selected chromosomes according to the crossing probability;
s303d, performing mutation operation on the chromosome subjected to the cross operation to obtain two new task allocation path planning schemes;
s303e, calculating the fitness value of two new task allocation path planning schemes by using a formula (12), namely executing task total time length, comparing the task total time length of executing the two task allocation path planning schemes obtained in the step S303d with the task total time length of executing the two task allocation path planning schemes, if the total time length of flight of the new task allocation path planning schemes is smaller than the total time length of flight of the original task allocation path planning scheme selected by a roulette mechanism, replacing the original task allocation path planning scheme by the new task allocation path planning scheme in a task allocation path planning scheme set, if the total time length of flight of the original task allocation path planning scheme is equal to the total time length of the new task allocation path planning scheme in the comparison process, calculating expected benefits of the two task allocation path planning schemes by using a formula (13), and if the expected benefits of the new task allocation path planning scheme are greater than the original task allocation path planning scheme, and replacing the original task allocation path planning scheme by the new task allocation path planning scheme in the task allocation path planning scheme set.
S303f, repeating the steps S303b to S303e until the maximum iteration number is 500, stopping operation, and obtaining the vehicle-machine cooperative optimal task allocation path planning scheme.
The embodiment of the invention provides a path optimization device for collaborative inspection of multiple unmanned aerial vehicles and vehicles, which comprises the following components:
the information acquisition module is used for acquiring information of target points and patrol resource information required to be patrol;
the model construction module is used for constructing an open type vehicle-machine cooperative path model by taking the shortest time as a target based on the target point information and the patrol resource information which need to be patrol;
and the model solving module is used for solving the open vehicle-machine collaborative path model through a genetic algorithm with a double fitness function to obtain an optimal task allocation path planning scheme for collaborative access of the vehicle and the unmanned aerial vehicle.
It may be understood that the path optimization device for collaborative inspection of multiple unmanned aerial vehicles and vehicles provided in the embodiments of the present invention corresponds to the path optimization method for collaborative inspection of multiple unmanned aerial vehicles and vehicles, and the explanation, the examples, the beneficial effects, and other parts of the related content may refer to the corresponding content in the path optimization method for collaborative inspection of multiple unmanned aerial vehicles and vehicles, which is not described herein.
The embodiment of the invention also provides a computer readable storage medium which stores a computer program for path optimization of the multi-unmanned aerial vehicle and the vehicle collaborative inspection, wherein the computer program enables a computer to execute the path optimization method of the multi-unmanned aerial vehicle and the vehicle collaborative inspection.
The embodiment of the invention also provides electronic equipment, which comprises:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising a path optimization method for performing the multi-drone with vehicle co-inspection as described above.
In summary, compared with the prior art, the method has the following beneficial effects:
1. the genetic algorithm of the embodiment of the invention can effectively reduce the operation time for obtaining the approximate optimal solution and obtain the satisfactory solution of the problem by adopting the double fitness function, thereby reducing the total time for the vehicle and the unmanned plane to cooperatively complete the task.
2. The existing optimization schemes assume that vehicles and unmanned aerial vehicles are isomorphic, and the method provided by the embodiment of the invention considers a path planning method for cooperatively completing the inspection task by heterogeneous vehicles and unmanned aerial vehicles. The vehicle and the unmanned aerial vehicle are isomorphic, the bearing capacity of the vehicle is the same as the duration of the unmanned aerial vehicle, the number of the inspection task points is different through different path planning schemes, the required vehicle and the unmanned aerial vehicle resources are different, the heterogeneous vehicle and the unmanned aerial vehicle are selected to finish tasks in a cooperative mode, the resource utilization rate is increased, and no-load phenomenon is avoided.
It should be noted that in the embodiments of the present invention, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; 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 technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. The path optimization method for collaborative inspection of multiple unmanned aerial vehicles and vehicles is characterized by comprising the following steps:
s1, acquiring information of a target point to be inspected and information of inspection resources;
s2, constructing an open type vehicle-machine cooperative path model by taking the shortest time as a target based on the target point information and the patrol resource information which need to be patrol; the open vehicle-machine collaborative path model comprises an objective function, as shown in formula (1):
wherein h, i and o are node numbers, and N is a node set; k is the number of the vehicle, and K is the set of vehicles; d is the number of the unmanned aerial vehicle, and D is the unmanned aerial vehicle set;the running time of the vehicle with the number k from the node h to the node i; />The flight time length from the node h to the node i of the unmanned plane with the number d is set; />As a decision variable, representing the path of a vehicle numbered k from node h to node i;for decision variables, the unmanned plane with the number d starts from the node h to reach the node i and is coded with the node oA path where vehicles numbered d meet;
s3, solving the open type vehicle-machine cooperative path model through a genetic algorithm with a double fitness function to obtain an optimal task allocation path planning scheme for cooperative access of the vehicle and the unmanned aerial vehicle, wherein the method comprises the following steps:
s301, setting coding rules;
s302, generating an initial task allocation path planning scheme set according to the coding rule;
s303, optimizing the initial task allocation path planning scheme set by adopting a genetic algorithm to obtain an optimal task allocation path planning scheme cooperatively accessed by the vehicle and the unmanned aerial vehicle;
wherein the dual fitness function comprises:
wherein:
the fit1 fitness value of the formula (12) represents the total time length of the task path allocation planning scheme for completing the task, the smaller the fitness value is, the better the task allocation scheme is, the fit2 fitness value of the formula (13) represents the expected income of the task path allocation planning scheme, and the larger the fitness value is, the higher the useful information of the scheme is, and the better the task allocation scheme is;
r is a patrol target point, and T is a patrol target point set; w (w) r The weight of the inspection target point r;as a decision variable, a path of the unmanned aerial vehicle with the number d from the patrol target point r to the patrol target point s and merging with the vehicle with the number d at the node o is represented; e, e d The detection error of the sensor carried by the unmanned aerial vehicle with the number d;
the step S303 includes:
s303a, setting execution parameters of a genetic algorithm and calculating an adaptability value of a task allocation path planning scheme through a formula (12), wherein the execution parameters comprise the maximum iteration times and the crossover probability;
s303b, selecting a roulette strategy for the initial task path planning scheme set according to the calculated fitness value of the step S303a, and selecting two chromosomes, wherein the smaller the fitness value is, the larger the selected probability is;
s303c, performing single-point crossing operation on the two selected chromosomes according to the crossing probability;
s303d, performing mutation operation on the chromosome subjected to the cross operation to obtain two new task allocation path planning schemes;
s303e, calculating the fitness value of two new task allocation path planning schemes by using a formula (12), namely executing task total time length, comparing the task total time length of the two new task allocation path planning schemes with the task total time length of the two task allocation path planning schemes obtained in the step S303d, if the total time length of flight of the new task allocation path planning schemes is smaller than the total time length of flight of one of the original task allocation path planning schemes selected by a roulette mechanism, replacing the original task allocation path planning scheme by the new task allocation path planning scheme in a task allocation path planning scheme set, if the total time length of flight of the original task allocation path planning scheme is equal to the total time length of flight of the new task allocation path planning scheme in the comparison process, calculating expected benefits of the two task allocation path planning schemes by using a formula (13), and if the expected benefits of the new task allocation path planning scheme are greater than the original task allocation path planning scheme, replacing the original task allocation path planning scheme by the new task allocation path planning scheme in the task allocation path planning scheme set;
s303f, repeating the steps S303b to S303e until the maximum iteration number is reached, stopping the operation, and obtaining the vehicle-machine collaborative optimal task allocation path planning scheme.
2. The path optimization method for collaborative inspection of multiple unmanned aerial vehicles and vehicles according to claim 1, wherein the open vehicle-machine collaborative path model includes constraints represented by formulas (4) to (10):
wherein:
equation (4) shows that each node is accessed only once;
equation (5) shows that each vehicle starts from the warehouse;
equation (6) represents the ingress and egress balance constraint of each node;
equation (7) represents the relationship between the time the vehicle arrives at the node and the time the node starts to service;
equation (8) shows that the flight duration of each unmanned aerial vehicle cannot exceed the maximum duration of the unmanned aerial vehicle;
the formulas (9) to (10) represent decision variable value taking constraints;
d is the number of the unmanned aerial vehicle, and D is the unmanned aerial vehicle set; h. i and o are node numbers, N is a node set, and T is a patrol target point set; k is the number of the vehicle, and K is the set of vehicles;as a decision variable, representing the path of a vehicle numbered k from node h to node i; />As a decision variable, a path from node h to node i and merging with the vehicle numbered d at node o is represented by the unmanned aerial vehicle numbered d; />As a decision variable, a path of a vehicle numbered k from the warehouse 0 to the patrol destination i is represented;as a decision variable, a path of a vehicle numbered k from a patrol target point i to a warehouse point is represented; />As a decision variable, representing the path of a vehicle numbered k from node i to node j; />The running time of the vehicle with the number k from the node h to the node i; />The arrival time for the vehicle numbered k to reach node i; />Is a braidingThe arrival time of the vehicle with the number k to the node h;the flight time length from the warehouse 0 to the inspection target point l of the unmanned aerial vehicle with the number d is set; />The flight time of the unmanned plane with the number d from the inspection target point l to the inspection target point m is set; />As a decision variable, a path of the unmanned aerial vehicle with the number d from the warehouse point 0 to the patrol target point l and merging with the vehicle with the number d at the node o is represented; />As a decision variable, a path of the unmanned plane with the number d from the patrol target point l to the patrol target point m and merging with the vehicle with the number d at the node o is represented; p (P) d The unmanned aerial vehicle with the number d can execute the maximum flight duration of the inspection task.
3. The path optimization method for collaborative inspection of multiple unmanned aerial vehicles and vehicles according to claim 1, wherein the generating an initial set of mission allocation path planning schemes according to the encoding rules comprises:
s302a, starting from a warehouse, distributing inspection target points for the vehicles to form a first row of chromosomes;
s302b, starting from a warehouse, the unmanned aerial vehicle distributes inspection task points for the unmanned aerial vehicle, and completes tasks in cooperation with the vehicle to form a second row of chromosomes;
s302c, generating a third row of chromosomes according to the numbers of the vehicle and the unmanned aerial vehicle, and forming a task allocation path planning scheme of the vehicle and the unmanned aerial vehicle;
s302d, generating task allocation path planning schemes of the remaining vehicles and unmanned aerial vehicles according to the number of the vehicles and the unmanned aerial vehicles and the steps S302 a-S302 c, and splicing to form a complete task allocation path planning scheme, wherein the vehicles and the unmanned aerial vehicles cooperate with each other to finish inspection of the last inspection target point;
s302e, repeating the steps S302a to S302d to obtain an initial task allocation path planning scheme set.
4. The path optimizing device for the collaborative inspection of the multiple unmanned aerial vehicles and the vehicles is characterized by comprising the following steps:
the information acquisition module is used for acquiring information of target points and patrol resource information required to be patrol;
the model construction module is used for constructing an open type vehicle-machine cooperative path model by taking the shortest time as a target based on the target point information and the patrol resource information which need to be patrol; the open vehicle-machine collaborative path model comprises an objective function, as shown in formula (1):
wherein h, i and o are node numbers, and N is a node set; k is the number of the vehicle, and K is the set of vehicles; d is the number of the unmanned aerial vehicle, and D is the unmanned aerial vehicle set;the running time of the vehicle with the number k from the node h to the node i; />The flight time length from the node h to the node i of the unmanned plane with the number d is set; />As a decision variable, representing the path of a vehicle numbered k from node h to node i; />As a decision variable, a path from node h to node i and merging with the vehicle numbered d at node o is represented by the unmanned aerial vehicle numbered d;
the model solving module is used for solving the open-type vehicle-machine cooperative path model through a genetic algorithm with a double fitness function, and obtaining an optimal task allocation path planning scheme for cooperative access of the vehicle and the unmanned aerial vehicle, and comprises the following steps:
s301, setting coding rules;
s302, generating an initial task allocation path planning scheme set according to the coding rule;
s303, optimizing the initial task allocation path planning scheme set by adopting a genetic algorithm to obtain an optimal task allocation path planning scheme cooperatively accessed by the vehicle and the unmanned aerial vehicle;
wherein the dual fitness function comprises:
wherein:
the fit1 fitness value of the formula (12) represents the total time length of the task path allocation planning scheme for completing the task, the smaller the fitness value is, the better the task allocation scheme is, the fit2 fitness value of the formula (13) represents the expected income of the task path allocation planning scheme, and the larger the fitness value is, the higher the useful information of the scheme is, and the better the task allocation scheme is;
r is an inspection target point; w (w) r The weight of the inspection target point r;as a decision variable, a path of the unmanned aerial vehicle with the number d from the patrol target point r to the patrol target point s and merging with the vehicle with the number d at the node o is represented; e, e d No matter numbered dDetecting errors of sensors carried by the human-machine;
the step S303 includes:
s303a, setting execution parameters of a genetic algorithm and calculating an adaptability value of a task allocation path planning scheme through a formula (12), wherein the execution parameters comprise the maximum iteration times and the crossover probability;
s303b, selecting a roulette strategy for the initial task path planning scheme set according to the calculated fitness value of the step S303a, and selecting two chromosomes, wherein the smaller the fitness value is, the larger the selected probability is;
s303c, performing single-point crossing operation on the two selected chromosomes according to the crossing probability;
s303d, performing mutation operation on the chromosome subjected to the cross operation to obtain two new task allocation path planning schemes;
s303e, calculating the fitness value of two new task allocation path planning schemes by using a formula (12), namely executing task total time length, comparing the task total time length of the two new task allocation path planning schemes with the task total time length of the two task allocation path planning schemes obtained in the step S303d, if the total time length of flight of the new task allocation path planning schemes is smaller than the total time length of flight of one of the original task allocation path planning schemes selected by a roulette mechanism, replacing the original task allocation path planning scheme by the new task allocation path planning scheme in a task allocation path planning scheme set, if the total time length of flight of the original task allocation path planning scheme is equal to the total time length of flight of the new task allocation path planning scheme in the comparison process, calculating expected benefits of the two task allocation path planning schemes by using a formula (13), and if the expected benefits of the new task allocation path planning scheme are greater than the original task allocation path planning scheme, replacing the original task allocation path planning scheme by the new task allocation path planning scheme in the task allocation path planning scheme set;
s303f, repeating the steps S303b to S303e until the maximum iteration number is reached, stopping the operation, and obtaining the vehicle-machine collaborative optimal task allocation path planning scheme.
5. A computer-readable storage medium, characterized in that it stores a computer program for path optimization of multi-drone with vehicle cooperative inspection, wherein the computer program causes a computer to execute the path optimization method of multi-drone with vehicle cooperative inspection as claimed in any one of claims 1 to 3.
6. An electronic device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising a path optimization method for performing the multi-drone with vehicle co-inspection of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110838000.9A CN113703472B (en) | 2021-07-23 | 2021-07-23 | Path optimization method and device for collaborative inspection of multiple unmanned aerial vehicles and vehicles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110838000.9A CN113703472B (en) | 2021-07-23 | 2021-07-23 | Path optimization method and device for collaborative inspection of multiple unmanned aerial vehicles and vehicles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113703472A CN113703472A (en) | 2021-11-26 |
| CN113703472B true CN113703472B (en) | 2023-08-01 |
Family
ID=78650352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110838000.9A Active CN113703472B (en) | 2021-07-23 | 2021-07-23 | Path optimization method and device for collaborative inspection of multiple unmanned aerial vehicles and vehicles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113703472B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326800B (en) * | 2021-12-28 | 2024-05-03 | 北京神星科技有限公司 | Unmanned aerial vehicle task planning method for comprehensive tasks |
| CN114413921B (en) * | 2022-01-19 | 2022-12-16 | 广东工业大学 | Excitation mechanism-based internet vehicle running path planning method, system and equipment |
| CN115130791B (en) * | 2022-08-30 | 2023-01-03 | 广东翼景信息科技有限公司 | Unmanned aerial vehicle and vehicle cooperative scheduling method and device for vehicle-mounted intelligent airport |
| CN116484996B (en) * | 2022-10-31 | 2023-09-08 | 广东电网有限责任公司佛山供电局 | Three-dimensional goods shelf material quick inventory method and system based on unmanned aerial vehicle inventory |
| CN116088540B (en) * | 2023-04-07 | 2023-06-27 | 电子科技大学中山学院 | Unmanned aerial vehicle and unmanned aerial vehicle cooperated cable channel inspection method and medium |
| CN116382099A (en) * | 2023-06-02 | 2023-07-04 | 上海数字大脑科技研究院有限公司 | Robot path scheduling planning method and system |
| CN117970932B (en) * | 2024-04-01 | 2024-06-07 | 中数智科(杭州)科技有限公司 | Task allocation method for collaborative inspection of multiple robots of rail train |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107807665A (en) * | 2017-11-29 | 2018-03-16 | 合肥工业大学 | Unmanned plane formation detection mission collaborative allocation and device |
| US10140875B1 (en) * | 2017-05-27 | 2018-11-27 | Hefei University Of Technology | Method and apparatus for joint optimization of multi-UAV task assignment and path planning |
| CN111352417A (en) * | 2020-02-10 | 2020-06-30 | 合肥工业大学 | Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301473B (en) * | 2017-06-12 | 2018-06-15 | 合肥工业大学 | Similar parallel machine based on improved adaptive GA-IAGA batch dispatching method and system |
-
2021
- 2021-07-23 CN CN202110838000.9A patent/CN113703472B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10140875B1 (en) * | 2017-05-27 | 2018-11-27 | Hefei University Of Technology | Method and apparatus for joint optimization of multi-UAV task assignment and path planning |
| CN107807665A (en) * | 2017-11-29 | 2018-03-16 | 合肥工业大学 | Unmanned plane formation detection mission collaborative allocation and device |
| CN111352417A (en) * | 2020-02-10 | 2020-06-30 | 合肥工业大学 | Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113703472A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113703472B (en) | Path optimization method and device for collaborative inspection of multiple unmanned aerial vehicles and vehicles | |
| CN111862579B (en) | Taxi scheduling method and system based on deep reinforcement learning | |
| CN108594858B (en) | Unmanned aerial vehicle searching method and device for Markov moving target | |
| CN111047087B (en) | Intelligent optimization method and device for path under cooperation of unmanned aerial vehicle and vehicle | |
| CN111007874B (en) | Unmanned aerial vehicle and vehicle cooperative power inspection method and device | |
| CN112835333A (en) | Multi-AGV obstacle avoidance and path planning method and system based on deep reinforcement learning | |
| CN113705982A (en) | Scheduling decision method for vehicle-mounted machine cooperative power patrol | |
| CN113359702B (en) | Intelligent warehouse AGV operation optimization scheduling method based on water wave optimization-tabu search | |
| Luo et al. | A* guiding DQN algorithm for automated guided vehicle pathfinding problem of robotic mobile fulfillment systems | |
| CN114399095A (en) | Cloud-side-cooperation-based dynamic vehicle distribution path optimization method and device | |
| CN111737826B (en) | Rail transit automatic simulation modeling method and device based on reinforcement learning | |
| CN114237222A (en) | Method for planning route of delivery vehicle based on reinforcement learning | |
| Liang et al. | A three stage optimal scheduling algorithm for AGV route planning considering collision avoidance under speed control strategy | |
| CN104537446A (en) | Bilevel vehicle routing optimization method with fuzzy random time window | |
| CN115329683A (en) | Aviation luggage online loading planning method, device, equipment and medium | |
| Zhang et al. | UAV trajectory planning for complex open storage environments based on an improved RRT algorithm | |
| Ma et al. | Solving heterogeneous USV scheduling problems by problem-specific knowledge based meta-heuristics with Q-learning | |
| Yang et al. | Path planning of UAV base station based on deep reinforcement learning | |
| CN116306216A (en) | Multi-vehicle type path planning method, system, equipment and medium for column generation | |
| Ou et al. | Adaptive visibility graph initialization on edge computing to accelerate hybrid path planning for mobile robots | |
| CN115187056A (en) | Multi-agent cooperative resource allocation method considering fairness principle | |
| CN113487264A (en) | Logistics distribution method and system based on heterogeneous multi-unmanned aerial vehicles | |
| Zhang et al. | Intelligent path planning algorithm for cooperative traversal task of multiple unmanned ground vehicles | |
| Bo et al. | AGV Real-time Scheduling Based on Multi-feature and Tree-Convolutional Neural Network | |
| Yu et al. | Research on Operation and Maintenance Route Planning of Offshore Wind Farm Based on Multiagent |
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 |