CN116993246A - Intelligent management method and system for unmanned delivery vehicle - Google Patents
Intelligent management method and system for unmanned delivery vehicle Download PDFInfo
- Publication number
- CN116993246A CN116993246A CN202311246766.3A CN202311246766A CN116993246A CN 116993246 A CN116993246 A CN 116993246A CN 202311246766 A CN202311246766 A CN 202311246766A CN 116993246 A CN116993246 A CN 116993246A
- Authority
- CN
- China
- Prior art keywords
- update
- distance
- target
- particles
- local
- 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.)
- Granted
Links
- 238000012384 transportation and delivery Methods 0.000 title claims abstract description 33
- 238000007726 management method Methods 0.000 title claims abstract description 31
- 239000002245 particle Substances 0.000 claims abstract description 217
- 238000005457 optimization Methods 0.000 claims abstract description 40
- 238000013439 planning Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 10
- 230000000694 effects Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to the technical field of distribution path planning, in particular to an intelligent management method and system for an unmanned distribution vehicle. According to the position change distance of the target particle, the position change distance difference between the target particle and all the participated optimization particles and the relative distance between the target particle and the optimization particles in the local search range under each update, a position update coefficient is obtained; obtaining the element change degree of the difference sequence according to the distance difference between the selected reference updating position and the position of the local history optimal solution; thereby obtaining an inertial weight update coefficient; and adjusting initial inertia weight parameters of the target particles under each update by combining the position distance between the destination and the target particles to obtain inertia weight update parameters and planning a distribution path. According to the invention, the initial inertia weight parameter is adjusted according to the position change characteristic of the target particle under each update, so that the optimizing efficiency of the target particle path is accelerated, and the accuracy of unmanned delivery vehicle path planning management is improved.
Description
Technical Field
The invention relates to the technical field of distribution path planning, in particular to an intelligent management method and system for an unmanned distribution vehicle.
Background
Unmanned delivery is a convenient, quick efficient novel delivery mode, can alleviate urban terminal delivery pressure, improves the delivery efficiency of express delivery, but in the delivery process, can receive local regional characteristic and global regional characteristic's influence, leads to unable timely delivery, and there is uncertainty in the route of delivery.
In the prior art, in order to optimize a delivery path and improve unmanned delivery efficiency, a particle swarm optimization algorithm and other traditional path planning algorithms can be adopted for optimization, but the problems of poor local autonomous planning capacity, poor global path planning instantaneity and easy sinking into local optimization of an unmanned delivery vehicle are caused, an accurate optimal solution cannot be obtained, the error of path planning is large, and the efficiency and the accuracy of intelligent path planning management are poor.
Disclosure of Invention
In order to solve the technical problem that the change condition of local information features and global information features is not considered in the prior art, and an optimal path can not be planned by determining proper inertia weight update parameters, the invention aims to provide an intelligent management method and system for an unmanned delivery vehicle, and the adopted technical scheme is as follows:
the invention provides an intelligent management method of an unmanned delivery vehicle, which comprises the following steps:
acquiring a to-be-distributed vehicle and a historical distribution vehicle which contain distribution information; the to-be-distributed vehicles serve as target particles, and the historical distribution vehicles serve as participatory optimization particles; executing a particle swarm optimization algorithm according to the distribution information;
calculating the position change distances of all particles under each update, and obtaining a position update coefficient according to the position change distances of the target particles, the position change distance differences between the target particles and all the participated optimized particles and the relative distances between the target particles and all the participated optimized particles in a local search range;
obtaining a local historical optimal solution according to the position change distance of the participated optimized particles in the local search range; acquiring reference update positions, and calculating the distance difference between each reference update position and the position of the local historical optimal solution to acquire a difference sequence; acquiring an inertia weight update coefficient according to the element change degree of the difference sequence and the position update coefficient;
acquiring initial inertial weight parameters of target particles under each update, acquiring the position distance between a destination and the target particles, and adjusting the initial inertial weight parameters according to the inertial weight update coefficients and the position distance of the target particles to acquire inertial weight update parameters; and planning and managing the distribution path according to the inertia weight updating parameters.
Further, the location update coefficients include:
in the local search range, calculating Euclidean distance average values between the target particles and all the participated optimized particle positions as the relative distances;
obtaining a position update coefficient according to the position change distance of the target particle, the position change distance difference and the relative distance;
the position change distance difference and the position update coefficient are in positive correlation, and the position change distance, the relative distance and the position update coefficient are in negative correlation.
Further, the position change distance includes:
and under each update, calculating the Euclidean distance between the positions before and after the particle update to obtain the position change distance.
Further, the method for obtaining the local history optimal solution comprises the following steps:
and in the local search range, acquiring a local historical optimal solution from the position where the position change distance of the participated optimization particles is minimum.
Further, the method for acquiring the difference sequence comprises the following steps:
acquiring the positions of a preset number of updated processes before each updating process of the target particles as the reference updated positions;
and calculating the distance between the reference updating position and the position of the local history optimal solution as the distance difference, and sequencing the distance difference from big to small to obtain the difference sequence.
Further, the method for acquiring the inertial weight update coefficient comprises the following steps:
the element variation degree comprises a first element variation degree and a second element variation degree;
calculating the extremely poor in the difference sequence to obtain the degree of change of the first element;
calculating the difference between the average value and the minimum value of the difference sequence to obtain the variation degree of the second element;
acquiring an inertia weight update coefficient according to the element change degree and the position update coefficient;
the first element change degree and the second element change degree are in positive correlation with the inertia weight update coefficient; the position update coefficient and the inertial weight update coefficient are in a negative correlation.
Further, the method for acquiring the inertial weight update parameter comprises the following steps:
judging whether the local search range of the target particle is a target range according to the position distance between the target particle and the destination;
normalizing the inertia weight updating coefficient, if the inertia weight updating coefficient is larger than a preset judging threshold value and the local searching range of the target particle is the target range, reducing the initial inertia weight parameter, and if the inertia weight updating coefficient is smaller than or equal to the preset judging threshold value, increasing the initial inertia weight parameter to obtain the inertia weight updating parameter.
Further, the method for judging whether the local search range of the target particle is a target range according to the position distance between the target particle and the destination comprises the following steps:
and if the position distance is smaller than or equal to the size of the local search range of the target particle, judging that the corresponding local search range is the target range.
Further, the preset judgment threshold value is set to 0.3.
The invention also provides an intelligent management system of the unmanned delivery vehicle, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the intelligent management methods of the unmanned delivery vehicle when executing the computer program.
The invention has the following beneficial effects:
according to the position change distance of the target particle, the position change distance difference between the target particle and all the participated optimization particles and the relative distance between the target particle and the optimization particles in the local search range, a position update coefficient is obtained; whether a large number of other optimizing paths participating in optimizing particles exist around the target particles can be judged, so that the optimizing effect of the target particles is poor, and the possibility of trapping in local optimization exists; obtaining element change degrees of a difference sequence according to the distance difference between each selected reference updating position and the position of the local historical optimal solution, determining the position relation between the target particles and the local historical optimal solution, judging the possibility of sinking into the local optimal solution, and further obtaining an inertia weight updating coefficient; in order to more efficiently find the optimal path of the target particle, acquiring an initial inertial weight parameter of the target particle under each update, acquiring a position distance between a destination and the target particle, adjusting the initial inertial weight parameter according to an inertial weight update coefficient and the position distance of the target particle, and planning a distribution path by acquiring the inertial weight update parameter. According to the invention, the particle swarm optimization algorithm is carried out by continuously and adaptively adjusting the inertia weight updating parameters of the target particles, so that the problem that the target particles are easy to sink into local optimum is further solved, and the efficiency and accuracy of path planning management are improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an intelligent management method for an unmanned delivery vehicle according to an embodiment of the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the intelligent management method and system for the unmanned distribution vehicle according to the invention with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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 invention belongs.
The invention provides a method and a system for intelligent management of an unmanned delivery vehicle, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of an intelligent management method for an unmanned delivery vehicle according to an embodiment of the invention is shown, which specifically includes:
step S1: acquiring a to-be-distributed vehicle and a historical distribution vehicle which contain distribution information; the to-be-distributed vehicles serve as target particles, and the historical distribution vehicles serve as participatory optimization particles; and executing a particle swarm optimization algorithm according to the distribution information.
In the unmanned delivery management center, delivery information of each time of the unmanned delivery vehicle is recorded and managed, and the delivery information comprises information such as a starting point, an ending point, a route point, electric quantity and the like of delivery. In the distribution area, the optimal path in the distribution process can be analyzed by acquiring the distribution information of the historical distribution vehicle, and the path planning management is carried out on the vehicle to be distributed.
The particle swarm optimization algorithm is used for solving the optimization problem and can be used for searching an optimal path in path planning. In an embodiment of the invention, performing a particle swarm optimization algorithm includes:
obtainingA historical delivery vehicle containing delivery information is used as a participatory optimization particle; and taking the to-be-delivered vehicle as a target particle. And (3) moving the target particles to the optimal solution direction by analyzing the position and the position change degree of the target particles relative to the participated optimal particles in the updating process until the preset iteration times or the optimal solution of the target particles are reached, and stopping updating the positions of the target particles.
It should be noted that, in an embodiment of the present invention, the path planning by using the particle swarm optimization algorithm is a technical means well known to those skilled in the art, and will not be described herein. In one embodiment of the invention, particles are optimized50; the preset number of iterations is 100.
Step S2: and calculating the position change distances of all particles under each update, and obtaining a position update coefficient according to the position change distances of the target particles, the position change distance difference between the target particles and all the participated optimized particles and the relative distance between the target particles and the optimized particles in the local search range.
And considering whether the target particles have local optimal conditions when the path planning is carried out in the local search range, iterating continuously, and analyzing the position change distance of each updating of the particles. In the local search range, the smaller the position change distance of the target particles is, the smaller the relative distance between the target particles and the participated optimization particles is, which indicates that more optimizing paths exist nearby, the new position cannot be updated, the optimizing capability is reduced, and the more the situation of local optimization is likely to be involved; calculating the difference of the position change distances between the target particle and all the participated optimization particles, wherein the larger the difference is, the smaller the position change of the target particle relative to the participated optimization particles is, and the more likely the situation that an optimal path cannot be found exists; in order to judge whether the target particle falls into the local optimum condition in the local search range, a position update coefficient is obtained according to the position change distance of the target particle, the position change distance difference between the target particle and all the participated optimization particles and the relative distance between the target particle and the optimization particles in the local search range.In one embodiment of the present invention, the local search range of the target particle is a radiusIs defined in the specification. In other embodiments, the local search range may be specifically set according to specific situations, which is not limited and described herein.
Preferably, in one embodiment of the present invention, the method for acquiring the position change distance includes:
in order to judge the searching capability of the particles for searching the optimal path, under each update, calculating Euclidean distance between the positions before and after the particle update to obtain a position change distance; the smaller the position change distance is, the worse the searching capability of the particle to the optimal path is, the larger the position change distance is, and the better the searching capability of the particle to the optimal path is. The formula for the position change distance in one embodiment of the invention is:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing target particlesIn the first placeThe position change distance after the secondary updating;representing target particlesIn the first placeThe position after the secondary update;representing target particlesIn the first placeThe position after the secondary update;representing calculation target particlesFirst, thePost update and the firstEuclidean distance between positions after the second update.
It should be noted that, in one embodiment of the invention,the value range of (5) is [0,99 ]]。
Preferably, in one embodiment of the present invention, the method for acquiring a location update coefficient includes:
in the local search range, calculating Euclidean distance average values between the target particles and all the participated optimized particle positions as relative distances; the smaller the relative distance is, the more participated optimization particles exist in the local search range of the target particles, and the situation of local optimization is easier to trap; the formula for the relative distance in one embodiment of the invention is:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing target particlesOptimizing the distance between particles relative to all the participants in the local search range;representing target particlesIn the first placeThe position after the secondary update;representing target particlesLocal search in rangeThe participated optimization particles are at the firstThe position after the secondary update;representing calculation target particlesOptimizing particles with participationEuclidean distance between locations. In one embodiment of the present invention, the target particlesIs included in the local search range of (1)Participated in optimizing particles, soThe range of the values is as follows。
Obtaining a position update coefficient according to the position change distance, the position change distance difference and the relative distance of the target particles; the smaller the position change distance of the target particle is, the smaller the relative distance between the target particle and the participated optimization particle is, and the larger the difference between the position change distance and the participated optimization particle is, the larger the position update coefficient is, which indicates that the target particle is harder to find an optimal path in a local search range, so that new position update cannot be performed; the difference of the position change distance and the position update coefficient are in positive correlation, and the position change distance, the relative distance and the position update coefficient are in negative correlation. The formula for the location update coefficients in one embodiment of the invention is:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing target particlesIn the first placeThe position update coefficient in the secondary update;representing target particlesIn the first placeThe position change distance after the secondary updating;representing participated optimized particlesIn the first placeThe position change distance after the secondary updating;representing target particlesOptimizing the relative distance between particles with respect to all the participants in the local search range,is a natural constant.
In the formula for the location update coefficients,representing the difference of the position change distances between the target particles and the participated optimization particles, and averaging the position change distances, wherein the larger the average value is, the smaller the optimizing capability of the target particles is, and the more likely the target particles are trapped into local optimization; by exponential function based on natural constantThe position change distance of the target particles is smaller, the relative distance is smaller, the influence of the participated optimization particles in the local search range is more likely, the target particles are trapped into local optimum, and an optimum path cannot be found.
It should be noted that, in other embodiments of the present invention, positive and negative correlation and normalization methods may be constructed by other basic mathematical operations, and specific means are technical means well known to those skilled in the art, and are not described herein. In one embodiment of the invention the number of particles involved in optimization isTherefore, it isThe value of (2) is。
Step S3: obtaining a local historical optimal solution according to the position change distance of the participated optimized particles in the local search range; obtaining reference updated positions, and calculating the distance difference between each reference updated position and the position of the local historical optimal solution to obtain a difference sequence; and obtaining an inertia weight update coefficient according to the element change degree of the difference sequence and the position update coefficient.
In the local search range, the acquisition of the local history optimal solution can guide the target particles to search in a better direction, so that the search process of an optimal path is accelerated; a plurality of paths participating in optimizing particles intersect at a local historical optimal solution position, a path pointed by a target particle at a current position is a local historical optimal solution path, a plurality of reference updating positions are selected, the position difference between the reference updating positions and the local historical optimal solution is compared, whether the target particle falls into the local optimal solution is judged, and the distance difference between each reference updating position and the position of the local historical optimal solution is calculated to obtain a difference sequence; and obtaining an inertia weight update coefficient according to the element change degree of the difference sequence and the position update coefficient. The smaller the element change degree of the difference sequence is, the larger the position update coefficient is, the smaller the inertia weight update coefficient is, the target particles possibly sink into local optimum, the searching capability of the target particles needs to be enlarged, and the searching of the optimum path is quickened.
Preferably, in one embodiment of the present invention, the method for acquiring a difference sequence includes:
and in the local search range, participating in optimizing the position where the position change distance of the particles is minimum, and acquiring a local historical optimal solution. Selecting the positions of a preset number of updated processes before each updating process of the target particles as reference updating positions; and calculating the distance between the reference updating position and the position of the local history optimal solution as a distance difference, and sequencing the distance difference from large to small to obtain a difference sequence. In one embodiment of the invention, the predetermined number is takenTarget particlesIn the first placeThe next updated local search range contains a local historical optimal solution,selecting target particlesFront partThe location of the secondary update is used as a reference update location. In one embodiment of the present invention, the target particlesIn the first placeThe next update is the current update,the range of the values is as follows。
Preferably, in one embodiment of the present invention, the method for acquiring the inertial weight update coefficient includes:
the degree of element variation of the difference sequence includes a first degree of element variation and a second degree of element variation; calculating the extreme difference in the difference sequence to obtain the variation degree of the first element; calculating the difference between the average value and the minimum value of the difference sequence to obtain the second element change degree; the smaller the first element change degree is, the smaller the change range of the reference updating position of the target particle in the local history optimal solution range is, and the local optimal solution cannot be trended; the smaller the difference degree of the second element is, the more the updated reference update position is far from the local optimal solution, the more the target particles are likely to fall into the local optimal solution, and the path planning is poorer; acquiring an inertia weight update coefficient according to the element change degree and the position update coefficient; the smaller the inertia weight updating parameter is, the farther the target particle is from the local history optimal solution in the local searching range, the smaller the variation range between the reference updating positions is, and the worse the optimizing capability on the path is; the change degree of the first element and the change degree of the second element are in positive correlation with the inertia weight updating coefficient; the position update coefficient and the inertia weight update coefficient are in negative correlation.
In one embodiment of the invention the formula for the inertial weight update coefficients is:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing calculated difference sequencesIs extremely bad in (3);representing differential sequencesMaximum value of (2);representing differential sequencesIs the minimum value of (a);representing target particlesIn the first placeThe inertia weight updating coefficient after the secondary updating;representing differential sequencesMiddle (f)A value;representing target particlesIn the first placeThe position in the secondary update updates the coefficients. In one embodiment of the present invention, the difference sequenceThe number of (3) is。
In the inertial weight update coefficient formula,representing the difference between the minimum value in the difference sequence and the mean value of the difference sequence, i.e. the firstCompared with the change of the continuously repeated updating position of the target particle, the minimum value after the secondary updating has smaller difference, and the position of the target particle after the updating is larger from the position of the local historical optimal solution, so that the situation of local optimal is easily trapped.
It should be noted that, in other embodiments of the present invention, the positive-negative correlation may be constructed by other basic mathematical operations, and specific means are technical means well known to those skilled in the art, which are not described herein.
Step S4: acquiring initial inertial weight parameters of target particles under each update, acquiring the position distance between a destination and the target particles, and adjusting the initial inertial weight parameters according to the inertial weight update coefficients and the position distance of the target particles to acquire inertial weight update parameters; and planning the distribution path according to the inertia weight updating parameters.
In the particle swarm optimization algorithm, the movement mode of the target particles in the local search range can be influenced by changing the size of the inertia weight parameter, so that the target particles are prevented from falling into local optimum. Acquiring initial inertial weight parameters of target particles under each update, acquiring the position distance between a destination and the target particles, considering that the destination is in a local search range of the target particles, if the inertial weight update coefficient is large, the target particles cannot approach an optimal solution, the initial inertial weight parameters of the target particles need to be reduced, the search range of the target particles is reduced, and the shortest path reaching the destination is found; if the inertia weight update coefficient is smaller, the local search range of the target particle does not contain a destination, the target particle is trapped in local optimum and cannot find an optimum path, the initial inertia weight update parameter of the target particle needs to be increased, the search range of the target particle is enlarged, and the optimum path is found more quickly. And adjusting the initial inertia weight parameters according to the inertia weight updating coefficient and the position distance of the target particles to obtain the inertia weight updating parameters.
Preferably, in one embodiment of the present invention, the method for acquiring the inertial weight update parameter includes:
the inertial weight updating parameters can influence the searching capability of the optimal path of the target particles, and the target particles are more prone to exploring unknown areas due to the larger inertial weight updating parameters; smaller inertial weight update parameters may make the target particles more prone to track the current optimal solution, resulting in insufficient search capability. Judging whether the local search range of the target particle is a target range according to the position distance between the target particle and the destination; and normalizing the inertia weight updating coefficient, if the normalized inertia weight updating coefficient is larger than a preset judging threshold value and the local searching range of the target particles is a target range, reducing the initial inertia weight parameter, and if the normalized inertia weight updating coefficient is smaller than or equal to the preset judging threshold value, increasing the initial inertia weight parameter to obtain the inertia weight updating parameter.
In one embodiment of the invention the inertial weight update parameters are formulated as:
wherein, the liquid crystal display device comprises a liquid crystal display device,the inertial weight update coefficient after each update of the position of the target particle is represented;representing initial inertial weight parameters of the target particles under each update;representing a normalization function;indicating particlesIn the first placeNormalized inertial weight update coefficient after secondary update;representing target particlesIn the first placeThe inertia weight update coefficient after the secondary update.
It should be noted that, in other embodiments of the present invention, the positive-negative correlation and normalization method may be constructed by other basic mathematical operations, and specific means are technical means well known to those skilled in the art, and will not be described herein. In one embodiment of the invention, a judgment threshold is presetIs thatInitial inertial weight parametersIs of the size ofThe method comprises the steps of carrying out a first treatment on the surface of the In other embodiments, the preset determination threshold and the initial inertial weight parameter may be specifically set according to specific situations, which are not limited and described herein.
Preferably, in one embodiment of the present invention, the method for determining whether the local search range of the target particle is a target range according to the location distance of the target particle from the destination includes:
and if the position distance is smaller than or equal to the size of the local search range of the target particle, judging that the corresponding local search range is the target range. The target range is determined, so that under the condition that the target particles already contain the destination in the local search range, the target particles still have strong search capability to search for the unknown region, and the time is long, and therefore, when the target particles are already in the target range, the search range can be reduced, and the optimal path can be found more quickly.
And planning and managing the distribution path according to the inertia weight updating parameters, properly adjusting the inertia weight updating parameters, optimizing the searching range of the target particles, quickly searching the distribution time of the target particles or the shortest path of the path, obtaining the optimal solution of path planning, and improving the efficiency and the accuracy of intelligent path planning and management of the target particles.
In summary, in the embodiment of the present invention, the position update coefficient is obtained according to the position change distance of the target particle under each update, the difference of the position change distances between the target particle and all the participating optimization particles, and the relative distance between the target particle and the participating optimization particles in the local search range; obtaining the element change degree of the difference sequence according to the distance difference between each selected reference updating position and the position of the local history optimal solution; thereby obtaining an inertial weight update coefficient; and adjusting initial inertia weight parameters of the target particles under each update by combining the position distance between the destination and the target particles to obtain inertia weight update parameters and planning a distribution path. According to the invention, the initial inertia weight parameter is adjusted according to the position change characteristic of the target particle under each update, so that the search range of the target particle is changed, the optimizing efficiency of the target particle path is accelerated, and the accuracy of the unmanned distribution vehicle path planning management is improved.
The invention also provides an intelligent management system of the unmanned delivery vehicle, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes any one step of the intelligent management method of the unmanned delivery vehicle when executing the computer program.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. An intelligent management method for an unmanned delivery vehicle, which is characterized by comprising the following steps:
acquiring a to-be-distributed vehicle and a historical distribution vehicle which contain distribution information; the to-be-distributed vehicles serve as target particles, and the historical distribution vehicles serve as participatory optimization particles; executing a particle swarm optimization algorithm according to the distribution information;
calculating the position change distances of all particles under each update, and obtaining a position update coefficient according to the position change distances of the target particles, the position change distance differences between the target particles and all the participated optimized particles and the relative distances between the target particles and all the participated optimized particles in a local search range;
obtaining a local historical optimal solution according to the position change distance of the participated optimized particles in the local search range; acquiring reference update positions, and calculating the distance difference between each reference update position and the position of the local historical optimal solution to acquire a difference sequence; acquiring an inertia weight update coefficient according to the element change degree of the difference sequence and the position update coefficient;
acquiring initial inertial weight parameters of target particles under each update, acquiring the position distance between a destination and the target particles, and adjusting the initial inertial weight parameters according to the inertial weight update coefficients and the position distance of the target particles to acquire inertial weight update parameters; and planning and managing the distribution path according to the inertia weight updating parameters.
2. The unmanned aerial vehicle intelligent management method of claim 1, wherein the location update coefficients comprise:
in the local search range, calculating Euclidean distance average values between the target particles and all the participated optimized particle positions as the relative distances;
obtaining a position update coefficient according to the position change distance of the target particle, the position change distance difference and the relative distance;
the position change distance difference and the position update coefficient are in positive correlation, and the position change distance, the relative distance and the position update coefficient are in negative correlation.
3. The unmanned aerial vehicle intelligent management method of claim 2, wherein the location change distance comprises:
and under each update, calculating the Euclidean distance between the positions before and after the particle update to obtain the position change distance.
4. The intelligent management method for unmanned distribution vehicles according to claim 1, wherein the method for obtaining the local history optimal solution comprises the following steps:
and in the local search range, acquiring a local historical optimal solution from the position where the position change distance of the participated optimization particles is minimum.
5. The intelligent management method of an unmanned distribution vehicle according to claim 1, wherein the method for acquiring the difference sequence comprises:
acquiring the positions of a preset number of updated processes before each updating process of the target particles as the reference updated positions;
and calculating the distance between the reference updating position and the position of the local history optimal solution as the distance difference, and sequencing the distance difference from big to small to obtain the difference sequence.
6. The intelligent management method for the unmanned distribution vehicle according to claim 1, wherein the method for acquiring the inertial weight update coefficient comprises the steps of:
the element variation degree comprises a first element variation degree and a second element variation degree;
calculating the extremely poor in the difference sequence to obtain the degree of change of the first element;
calculating the difference between the average value and the minimum value of the difference sequence to obtain the variation degree of the second element;
acquiring an inertia weight update coefficient according to the element change degree and the position update coefficient;
the first element change degree and the second element change degree are in positive correlation with the inertia weight update coefficient; the position update coefficient and the inertial weight update coefficient are in a negative correlation.
7. The intelligent management method for the unmanned distribution vehicle according to claim 1, wherein the method for acquiring the inertial weight update parameters comprises the steps of:
judging whether the local search range of the target particle is a target range according to the position distance between the target particle and the destination;
normalizing the inertia weight updating coefficient, if the inertia weight updating coefficient is larger than a preset judging threshold value and the local searching range of the target particle is the target range, reducing the initial inertia weight parameter, and if the inertia weight updating coefficient is smaller than or equal to the preset judging threshold value, increasing the initial inertia weight parameter to obtain the inertia weight updating parameter.
8. The unmanned aerial vehicle intelligent management method of claim 7, wherein the method of determining whether the local search range of the target particle is a target range based on the location distance of the target particle from the destination comprises:
and if the position distance is smaller than or equal to the size of the local search range of the target particle, judging that the corresponding local search range is the target range.
9. The intelligent management method of an unmanned aerial vehicle according to claim 7, wherein the preset determination threshold is set to 0.3.
10. An unmanned delivery vehicle intelligent management system, the system comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of an unmanned delivery vehicle intelligent management method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311246766.3A CN116993246B (en) | 2023-09-26 | 2023-09-26 | Intelligent management method and system for unmanned delivery vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311246766.3A CN116993246B (en) | 2023-09-26 | 2023-09-26 | Intelligent management method and system for unmanned delivery vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116993246A true CN116993246A (en) | 2023-11-03 |
| CN116993246B CN116993246B (en) | 2023-12-05 |
Family
ID=88530510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311246766.3A Active CN116993246B (en) | 2023-09-26 | 2023-09-26 | Intelligent management method and system for unmanned delivery vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116993246B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108615069A (en) * | 2018-03-25 | 2018-10-02 | 哈尔滨工程大学 | A kind of optimized calculation method based on improved adaptable quanta particle swarm optimization |
| CN111381600A (en) * | 2018-12-28 | 2020-07-07 | 陕西师范大学 | UUV path planning method based on particle swarm optimization |
| JP2021051736A (en) * | 2019-09-24 | 2021-04-01 | ▲広▼州大学 | Vehicle travel route planning method, apparatus, system, medium and device |
| CN114399043A (en) * | 2021-06-16 | 2022-04-26 | 北京理工大学 | Vehicle position routing method based on non-dominated sorting particle swarm genetic algorithm |
| CN116380110A (en) * | 2023-06-07 | 2023-07-04 | 上海伯镭智能科技有限公司 | Real-time path planning method based on big data unmanned vehicle |
| WO2023123642A1 (en) * | 2021-12-29 | 2023-07-06 | 中国矿业大学 | Drivable area detection and autonomous obstacle avoidance method for unmanned transportation device for deep, confined spaces |
-
2023
- 2023-09-26 CN CN202311246766.3A patent/CN116993246B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108615069A (en) * | 2018-03-25 | 2018-10-02 | 哈尔滨工程大学 | A kind of optimized calculation method based on improved adaptable quanta particle swarm optimization |
| CN111381600A (en) * | 2018-12-28 | 2020-07-07 | 陕西师范大学 | UUV path planning method based on particle swarm optimization |
| JP2021051736A (en) * | 2019-09-24 | 2021-04-01 | ▲広▼州大学 | Vehicle travel route planning method, apparatus, system, medium and device |
| CN114399043A (en) * | 2021-06-16 | 2022-04-26 | 北京理工大学 | Vehicle position routing method based on non-dominated sorting particle swarm genetic algorithm |
| WO2023123642A1 (en) * | 2021-12-29 | 2023-07-06 | 中国矿业大学 | Drivable area detection and autonomous obstacle avoidance method for unmanned transportation device for deep, confined spaces |
| CN116380110A (en) * | 2023-06-07 | 2023-07-04 | 上海伯镭智能科技有限公司 | Real-time path planning method based on big data unmanned vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 熊华捷;蔚保国;何成龙;: "基于改进粒子群算法的UAV航迹规划方法", 计算机测量与控制, no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116993246B (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9594150B2 (en) | Determining device locations using movement, signal strength | |
| CN107247961B (en) | Track prediction method applying fuzzy track sequence | |
| CN109798896B (en) | Indoor robot positioning and mapping method and device | |
| CN109144056A (en) | The global method for self-locating and equipment of mobile robot | |
| CN110530388B (en) | Multi-AGV path planning method and system | |
| US9674656B2 (en) | Wireless-based localization using a zonal framework | |
| CN113299085A (en) | Traffic signal lamp control method, equipment and storage medium | |
| Liu et al. | Multi-task-oriented vehicular crowdsensing: A deep learning approach | |
| WO2019080711A1 (en) | Road segment speed prediction method, device, server, medium and program product | |
| CN110617819B (en) | Unmanned aerial vehicle terrain auxiliary navigation method based on ant colony algorithm path planning | |
| CN114117878B (en) | Target motion trajectory segmented compression method based on improved particle swarm optimization | |
| US20190187296A1 (en) | Method and system for processing trajectory data | |
| CN110909303B (en) | Adaptive space-time heterogeneity inverse distance interpolation method | |
| CN110830915B (en) | Method and device for determining starting point position | |
| US20070201425A1 (en) | Method Of Selecting Operational Parameters In A Communication Network | |
| CN116805785A (en) | Power load hierarchy time sequence prediction method based on random clustering | |
| CN116993246B (en) | Intelligent management method and system for unmanned delivery vehicle | |
| Du et al. | Digital twin based trajectory prediction for platoons of connected intelligent vehicles | |
| CN112612275A (en) | Complex path planning system and method for database machine room | |
| US10209086B2 (en) | Route search system, method, and program | |
| Chandio et al. | An approach for map-matching strategy of GPS-trajectories based on the locality of road networks | |
| CN115526267A (en) | Power distribution network operation scene extraction method and device | |
| CN114646313A (en) | User track positioning method, electronic equipment and computer storage medium | |
| CN112991080A (en) | Key node calculation method, system, electronic equipment and storage medium | |
| Zoubert-Ousseni et al. | Comparison of post-processing algorithms for indoor navigation trajectories |
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 |