CN116151506B - Weather-based method and device for determining real-time operation route of unmanned vehicle - Google Patents
Weather-based method and device for determining real-time operation route of unmanned vehicle Download PDFInfo
- Publication number
- CN116151506B CN116151506B CN202310430741.2A CN202310430741A CN116151506B CN 116151506 B CN116151506 B CN 116151506B CN 202310430741 A CN202310430741 A CN 202310430741A CN 116151506 B CN116151506 B CN 116151506B
- Authority
- CN
- China
- Prior art keywords
- route
- unmanned vehicle
- real
- historical operation
- hot spot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012545 processing Methods 0.000 claims description 78
- 239000002245 particle Substances 0.000 claims description 51
- 238000004422 calculation algorithm Methods 0.000 claims description 30
- 238000004458 analytical method Methods 0.000 claims description 25
- 238000005457 optimization Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 9
- 238000012098 association analyses Methods 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000012800 visualization Methods 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a weather-based real-time operation route determining method and device for an unmanned vehicle, and relates to the technical field of unmanned vehicles.
Description
Technical Field
The invention relates to the technical field of unmanned vehicles, in particular to a weather-based method and device for determining a real-time operating route of an unmanned vehicle.
Background
Along with the development of society, unmanned vehicles are popularized, the unmanned vehicles are not manually controlled, the determination of the operation route of the unmanned vehicles often needs manual input in the operation process, and the operation route cannot be adjusted according to real-time conditions due to manual control, so that the conditions of slow running of the vehicles, overlong transportation time and the like are caused, and therefore, the method and the device for automatically adjusting the operation route of the unmanned vehicles based on real-time weather environment are not required to be manually operated, so that the labor cost is reduced, and the operation efficiency is increased.
Disclosure of Invention
The invention aims to provide a weather-based method and a weather-based device for determining a real-time operating route of an unmanned vehicle, so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in one aspect, the present application provides a weather-based method for determining a real-time operating route of an unmanned vehicle, including:
acquiring real-time weather information, city map data and historical operation data of an unmanned vehicle, wherein the real-time weather information comprises temperature information, humidity information, atmospheric pressure information, wind intensity information and wind direction information;
establishing a longitude and latitude coordinate map based on the urban map data, and carrying out data processing on the historical operation data of the unmanned vehicle and the longitude and latitude coordinate map to obtain operation hot spot areas of at least two categories of commodities in the historical operation data, wherein the operation hot spot areas of the commodities in the at least two categories in the historical operation data are operation hot spot areas of commodities with each value in the historical operation data;
the operation hot spot areas of all types of commodities in the historical operation data and the preset historical operation route of the unmanned vehicle are sent to a route prediction model to be processed, and the operation route of the unmanned vehicle is obtained;
and sending the real-time weather information and the urban map data to a route adjustment module for real-time adjustment of the operation route of the unmanned vehicle, so as to obtain the adjusted real-time operation route of the unmanned vehicle.
On the other hand, the application also provides a weather-based unmanned vehicle real-time operation route determining device, which comprises:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring real-time weather information, urban map data and historical operation data of unmanned vehicles, and the real-time weather information comprises temperature information, humidity information, barometric pressure information, wind intensity information and wind direction information;
the first processing unit is used for establishing a longitude and latitude coordinate map based on the urban map data, and carrying out data processing on the historical operation data of the unmanned vehicle and the longitude and latitude coordinate map to obtain operation hot spot areas of at least two types of commodities in the historical operation data, wherein the operation hot spot areas of the at least two types of commodities in the historical operation data are operation hot spot areas of commodities with each value in the historical operation data;
the second processing unit is used for sending the operation hot spot areas of all types of commodities in the historical operation data and the preset historical operation route of the unmanned vehicle to the route prediction model for processing to obtain the operation route of the unmanned vehicle;
and the third processing unit is used for sending the real-time weather information and the urban map data to the route adjustment module to adjust the operation route of the unmanned vehicle in real time, so as to obtain the adjusted real-time operation route of the unmanned vehicle.
The beneficial effects of the invention are as follows:
according to the invention, through establishing a longitude and latitude coordinate map, historical operation data of an unmanned vehicle are analyzed, different value operation commodity categories are determined, operation hot spot positions of each value operation commodity are determined, operation areas of each value operation commodity are determined, the operation areas are reduced, then, the overlapping areas of each commodity are subjected to association analysis with the historical operation route, association values obtained through association analysis are used as initial weight values for predicting the current operation route, the accuracy of neural network prediction is increased, the neural network is optimized based on a particle swarm algorithm, the optimal operation route is selected, and operation cost is reduced.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for determining a real-time operating route of a weather-based unmanned vehicle according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a real-time operation route determining device for a weather-based unmanned vehicle according to an embodiment of the invention.
The marks in the figure: 701. an acquisition unit; 702. a first processing unit; 703. a second processing unit; 704. a third processing unit; 7021. a first processing subunit; 7022. a first analysis subunit; 7023. a second processing subunit; 7031. a third processing subunit; 7032. a fourth processing subunit; 7033. a second analysis subunit; 7034. a fifth processing subunit; 70341. a sixth processing subunit; 70342. a seventh processing subunit; 70343. an eighth processing subunit; 70344. a ninth processing subunit; 7041. a third analysis subunit; 7042. a fourth analysis subunit; 7043. tenth processing subunit.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a weather-based method for determining a real-time operation route of an unmanned vehicle.
Referring to fig. 1, the method is shown to include steps S1, S2, S3 and S4.
Step S1, acquiring real-time weather information, city map data and historical operation data of an unmanned vehicle, wherein the real-time weather information comprises temperature information, humidity information, barometric pressure information, wind intensity information and wind direction information;
it can be understood that the real-time weather information is acquired based on the weather information acquired by the sensors installed on the unmanned vehicle and the weather monitoring devices installed in different areas, the urban map data is urban map data acquired based on Beidou satellites, the historical operation data of the unmanned vehicle is the historical operation data of all unmanned vehicles stored based on a database and the Internet of things, and the step is to process the big data and call the data in the database to analyze and process the big data so as to quickly determine the real-time operation route of the unmanned vehicle.
Step S2, a longitude and latitude coordinate map is established based on the urban map data, and the historical operation data of the unmanned vehicle and the longitude and latitude coordinate map are subjected to data processing to obtain operation hot spot areas of at least two types of commodities in the historical operation data, wherein the operation hot spot areas of the at least two types of commodities in the historical operation data are operation hot spot areas of commodities with each value in the historical operation data;
it can be understood that in this step, a longitude and latitude coordinate map is established for urban map data, and then, operation hot spot areas of the commodity are determined based on the coordinate map, wherein the commodity is classified according to different values, and then, the grades of different operation hot spots are determined based on the commodity value, and the operation hot spot areas are areas with operation times larger than a preset threshold or areas with the largest operation times. In this step, step S2 includes step S21, step S22, and step S23.
S21, carrying out coordinate conversion on the urban map data to obtain a longitude and latitude coordinate map corresponding to the urban map data;
step S22, performing hierarchical analysis on the historical operation data of the unmanned vehicle, wherein the operation data of the commodities with different values are classified according to the classification of the operation commodities to obtain at least two types of historical operation data;
it will be appreciated that this step determines the number of items of different value by analytic hierarchy process and then determines the category of the items based on the range of different values.
Step S23, at least two types of historical operation data and longitude and latitude coordinate maps are sent to a clustering model for processing, wherein starting point coordinates on the historical operation data of each type are determined, clustering analysis is carried out on all the starting point coordinates on the longitude and latitude coordinate maps based on an OPTICS clustering algorithm, and operation hot spot areas corresponding to the historical operation data of each type are determined.
It can be understood that the operation starting point coordinates of the commodities in each category are clustered through a clustering algorithm, and operation hot spot areas corresponding to the historical operation data in each category are determined, so that the operation hot spot areas of the commodities in each category can be determined, data is provided for the subsequent operation routes, the accuracy of determining the operation routes is improved, the operation quality is ensured, too much time is required in the commodity submitting process, and further the customer satisfaction is reduced.
Step S3, the operation hot spot areas of all types of commodities in the historical operation data and the preset historical operation route of the unmanned vehicle are sent to a route prediction model to be processed, and the operation route of the unmanned vehicle is obtained;
it can be understood that the operation route prediction is performed by the present step based on the operation hot spot areas of all the types of commodities and the preset historical operation route of the unmanned vehicle, so that the operation route of the unmanned vehicle is rapidly determined, and the operation efficiency is improved, and in the present step, step S3 includes step S31, step S32, step S33 and step S34.
Step S31, marking operation hot spot areas of all types of commodities in the historical operation data based on the map visualization tool, carrying out image recognition based on a Yolov3 network, and marking operation hot spot area overlapping parts of the commodities in each type to obtain the overlapping layer number of the hot spot overlapping areas in the historical operation data;
step S32, grading the demand level of the unmanned vehicle according to the superposition layer number of the hot spot superposition area in the historical operation data, wherein the demand level is graded according to a rule that the demand level is higher when the superposition layer number is larger, and hot spot superposition areas with different levels are obtained;
the method comprises the steps of carrying out image processing through a map visualization tool and a Yolov3 network, marking overlapping parts of operation hot spot areas of commodities of each category, determining the overlapping layer number of each overlapping area, wherein the total value of different commodity values in the overlapping layer number represents the total value of the commodities in the area, grading the demand level according to the total value of each area, determining the area through which a route passes according to different demand levels, further reducing the length of the route, improving the operation efficiency, reducing the cost expense, and improving the accuracy of the neural network prediction route.
Step S33, carrying out association analysis on the hot spot overlapping areas of different grades and the historical operation route of the unmanned vehicle, wherein the outlines of the hot spot overlapping areas of different grades and the historical operation route of the unmanned vehicle are subjected to coordinate transformation, and coordinate points of the outlines of the hot spot overlapping areas of different grades obtained through the coordinate transformation and coordinate points of the historical operation route of the unmanned vehicle are subjected to association degree value calculation to obtain association degree values of the coordinate points of the outlines of the hot spot overlapping areas of each grade and the coordinate points of the historical operation route;
and step S34, based on the relevance value and the historical operation route of the unmanned vehicle, sending the historical operation route to the trained route prediction model to predict the operation route of the unmanned vehicle, and obtaining the operation route of the unmanned vehicle.
It can be understood that the correlation analysis method is used for analyzing the correlation between the hot spot overlapping areas of different levels and the historical operation route of the unmanned vehicle, determining the correlation between the hot spot overlapping areas and the historical operation route of the unmanned vehicle, taking the correlation as a prediction weight, inputting the prediction weight into the neural network for prediction, improving the accuracy of the neural network prediction, and guaranteeing the robustness of the neural network prediction, and the step S34 comprises the steps S341, S342, S343 and S344.
Step S341, dividing the relevance value, the hot spot overlapping areas of different grades and the coordinate points of the historical operation route into a training set and a verification set;
step S342, inputting the training set into a BP neural network for training, and optimizing the BP neural network based on a particle swarm optimization algorithm, wherein initial weight parameters of a BP neural network model are initialized, coordinate points of a historical operation route are obtained through prediction based on hot spot overlapping areas of different grades and the coordinate points of the historical operation route, particle fitness values are obtained through calculation of the particle swarm optimization algorithm, the initial weight parameters are the relevance values, and the particle swarm parameters are the coordinate points of the historical operation route obtained through prediction of the BP neural network;
step S343, determining an individual optimal position and a global optimal position of particles according to the fitness of the particles in the particle swarm and a particle swarm optimization algorithm, and dynamically tracking the individual optimal position and the global optimal position to continuously update the speeds and positions of all the particles until the particle swarm optimization algorithm reaches the maximum iteration times, so as to obtain a coordinate point of an optimal historical operation route;
it can be understood that in this step, the correlation value is taken as an initial weight parameter, then the historical operation route is predicted based on the BP neural network, and the prediction result is optimally selected through the particle swarm algorithm, so as to obtain the coordinate point of the optimal historical operation route, and when the prediction efficiency is improved, the route close to the hot spot overlapping areas of different grades is selected as the optimal historical operation route, so that the commodity submitting distance and time of the customer are reduced, the customer cost is reduced, the customer satisfaction is improved, and the fitness calculation formula in the particle swarm optimization algorithm is as follows:
wherein,,for fitness value, +_>For the actual value of the a-th historical operating route coordinate,/->And N is the number of groups of data in the training set, wherein the number is the predicted value of the a-th historical operation route coordinate.
The calculation formula of the updated position in the particle swarm optimization algorithm is as follows:
wherein,,for updated speed, ++>For the current speed, +.>And->For learning factors, 2, +.>For the current position of the particles, a is the total number of particles, < >>To take a random number between 0 and 1, < >>For the best position found by the present particle up to now, < >>For the best position found by all particles to the current position, < > where>Is an inertial factor.
Wherein,,for the updated position of the particle +.>For the position of the particle before updating, +.>The position before the particle update.
And step 344, comparing the verification set with the coordinate points of the optimal historical operation route, and if the verification set is consistent with the coordinate points of the optimal historical operation route, obtaining a trained route prediction model.
And S4, transmitting the real-time weather information and the urban map data to a route adjustment module for real-time adjustment of the operation route of the unmanned vehicle, and obtaining the adjusted real-time operation route of the unmanned vehicle.
It can be understood that this step is performed by acquiring real-time weather information and performing route adjustment based on the real-time weather information, where step S4 includes step S41, step S42, and step S43.
Step S41, analyzing the real-time weather information and the average running speed information of the vehicle based on a correlation analysis method in the SLP method to obtain a linear relation between the real-time weather information and the average running speed information of the vehicle;
it can be understood that the present step provides data for the subsequent kalman filter estimation by analyzing the linear relationship between each real-time weather information and the average running speed information of the vehicle, ensuring the accuracy of the estimation.
Step S42, a relation model is established based on the linear relation between the real-time weather information and the average running speed information of the vehicle, and the real-time speed of each position of the unmanned vehicle on the operation route is predicted and obtained based on a Kalman filtering algorithm;
it can be understood that the real-time position of the unmanned vehicle and the real-time speed corresponding to the real-time position are estimated through the Kalman filtering algorithm, so that the running efficiency of the vehicle is estimated, and the situation that the running efficiency is too low and the transportation time is too long is prevented.
And step S43, the real-time speed and the urban map data of each position of the unmanned vehicle on the operation route are obtained based on the prediction, the operation route of the unmanned vehicle is adjusted in real time, the real-time position and the speed of the unmanned vehicle are repeatedly predicted, and the real-time route adjustment is carried out, so that the real-time operation route of the unmanned vehicle with the shortest running time is obtained.
The real-time position and speed of the vehicle are estimated continuously, then the real-time running route of the unmanned vehicle is adjusted based on the position and the speed, so that the transportation efficiency is improved, the transportation time is shortened, the customer satisfaction is improved, and the transportation time is ensured to meet the requirements.
Example 2:
as shown in fig. 2, the present embodiment provides a weather-based unmanned vehicle real-time operation route determination apparatus including an acquisition unit 701, a first processing unit 702, a second processing unit 703, and a third processing unit 704.
An acquisition unit 701 for acquiring real-time weather information including temperature information, humidity information, barometric pressure information, wind intensity information, and wind direction information, city map data, and historical operation data of an unmanned vehicle;
the first processing unit 702 is configured to establish a latitude and longitude coordinate map based on the urban map data, and perform data processing on the historical operation data of the unmanned vehicle and the latitude and longitude coordinate map to obtain operation hot spot areas of at least two types of commodities in the historical operation data, where the operation hot spot areas of the at least two types of commodities in the historical operation data are operation hot spot areas of each value commodity in the historical operation data;
the first processing unit 702 includes a first processing subunit 7021, a first analysis subunit 7022, and a second processing subunit 7023.
The first processing subunit 7021 is configured to perform coordinate transformation on the urban map data to obtain a longitude and latitude coordinate map corresponding to the urban map data;
a first analysis subunit 7022, configured to perform hierarchical analysis on the historical operation data of the unmanned vehicle, where the operation data of the commercial products with different values are classified by performing hierarchical analysis according to the types of the commercial products, so as to obtain at least two types of historical operation data;
the second processing subunit 7023 is configured to send the historical operation data of at least two categories and the longitude and latitude coordinate map to a clustering model for processing, where a start point coordinate on the historical operation data of each category is determined, and cluster analysis is performed on the longitude and latitude coordinate map on all start point coordinates based on an OPTICS clustering algorithm, so as to determine an operation hotspot area corresponding to the historical operation data of each category.
A second processing unit 703, configured to send the operation hot spot areas of all the types of commodities in the historical operation data and the preset historical operation route of the unmanned vehicle to the route prediction model for processing, so as to obtain an operation route of the unmanned vehicle;
the second processing unit 703 includes a third processing subunit 7031, a fourth processing subunit 7032, a second analysis subunit 7033, and a fifth processing subunit 7034.
The third processing subunit 7031 is configured to mark operation hot spot areas of all types of commodities in the historical operation data based on the map visualization tool, and perform image recognition based on the Yolov3 network, mark operation hot spot area overlapping portions of the commodities in each type, and obtain the overlapping layer number of the hot spot overlapping areas in the historical operation data;
a fourth processing subunit 7032, configured to rank the demand level of the unmanned vehicle according to the number of overlapping layers of the hot spot overlapping areas in the historical operation data, where the demand level is ranked according to a rule that the higher the number of overlapping layers is, the higher the demand level is, so as to obtain hot spot overlapping areas with different levels;
a second analysis subunit 7033, configured to perform association analysis on the hotspot overlapping areas of different levels and the historical operating route of the unmanned vehicle, where coordinate transformation is performed on the profiles of the hotspot overlapping areas of different levels and the historical operating route of the unmanned vehicle, and association value calculation is performed on coordinate points of the profiles of the hotspot overlapping areas of different levels and coordinate points of the historical operating route of the unmanned vehicle obtained by the coordinate transformation, so as to obtain association values of coordinate points of the profiles of the hotspot overlapping areas of each level and coordinate points of each historical operating route;
and a fifth processing subunit 7034, configured to predict the operation route of the unmanned vehicle based on the relevance value and the historical operation route of the unmanned vehicle, and obtain the operation route of the unmanned vehicle.
The fifth processing subunit 7034 includes a sixth processing subunit 70341, a seventh processing subunit 70342, an eighth processing subunit 70343, and a ninth processing subunit 70344.
A sixth processing subunit 70341, configured to divide the association value, the hotspot overlapping areas of different grades, and the coordinate points of the historical operating route into a training set and a verification set;
a seventh processing subunit 70342, configured to input the training set to a BP neural network for training, and perform optimization processing on the BP neural network based on a particle swarm optimization algorithm, where an initial weight parameter of a BP neural network model is initialized, coordinate points of a historical operation route are obtained by prediction based on hot spot overlapping areas of different levels and coordinate points of the historical operation route, a particle fitness value is obtained by calculation through the particle swarm optimization algorithm, the initial weight parameter is the relevance value, and the particle swarm parameter is a coordinate point of the historical operation route obtained by prediction by the BP neural network;
an eighth processing subunit 70343, configured to determine an individual optimal position and a global optimal position of the particles according to the fitness of the particles in the particle swarm and a particle swarm optimization algorithm, dynamically track the individual optimal position and the global optimal position to continuously update the speeds and positions of all the particles until the particle swarm optimization algorithm reaches the maximum iteration number, and obtain a coordinate point of an optimal historical operation route;
and a ninth processing subunit 70344, configured to compare the verification set with the coordinate points of the optimal historical operating route, and obtain a trained route prediction model if the verification set is consistent with the coordinate points of the optimal historical operating route.
And the third processing unit 704 is configured to send the real-time weather information and the city map data to a route adjustment module to perform real-time adjustment on the operation route of the unmanned vehicle, so as to obtain the adjusted real-time operation route of the unmanned vehicle.
Wherein the third processing unit 704 includes a third analysis subunit 7041, a fourth analysis subunit 7042, and a tenth processing subunit 7043.
A third analysis subunit 7041, configured to analyze the real-time weather information and the average running speed information of the vehicle based on a correlation analysis method in the SLP method, so as to obtain a linear relationship between the real-time weather information and the average running speed information of the vehicle;
a fourth analysis subunit 7042, configured to establish a relationship model based on a linear relationship between the real-time weather information and the average running speed information of the vehicle, and predict, based on a kalman filtering algorithm, a real-time speed of each position of the unmanned vehicle on an operation route;
the tenth processing subunit 7043 is configured to adjust the operation route of the unmanned vehicle in real time based on the real-time speed and the city map data of each position of the unmanned vehicle on the operation route obtained by the prediction, repeatedly predict the real-time position and speed of the unmanned vehicle, and perform real-time route adjustment to obtain the real-time operation route of the unmanned vehicle with the shortest driving time.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. A weather-based method for determining a real-time operating route of an unmanned vehicle, comprising:
acquiring real-time weather information, city map data and historical operation data of an unmanned vehicle, wherein the real-time weather information comprises temperature information, humidity information, atmospheric pressure information, wind intensity information and wind direction information;
establishing a longitude and latitude coordinate map based on the urban map data, and carrying out data processing on the historical operation data of the unmanned vehicle and the longitude and latitude coordinate map to obtain operation hot spot areas of at least two categories of commodities in the historical operation data, wherein the operation hot spot areas of the commodities in the at least two categories in the historical operation data are operation hot spot areas of commodities with each value in the historical operation data;
the operation hot spot areas of all types of commodities in the historical operation data and the preset historical operation route of the unmanned vehicle are sent to a route prediction model to be processed, and the operation route of the unmanned vehicle is obtained;
the real-time weather information and the urban map data are sent to a route adjustment module to adjust the operation route of the unmanned vehicle in real time, and the adjusted real-time operation route of the unmanned vehicle is obtained;
the method for real-time adjustment of the operation route of the unmanned vehicle by sending the real-time weather information and the city map data to a route adjustment module comprises the following steps:
analyzing the real-time weather information and the average running speed information of the vehicle based on a correlation analysis method in the SLP method to obtain a linear relation between the real-time weather information and the average running speed information of the vehicle;
establishing a relation model based on the linear relation between the real-time weather information and the average running speed information of the vehicle, and predicting the real-time speed of each position of the unmanned vehicle on an operation route based on a Kalman filtering algorithm;
and based on the prediction, real-time speed and city map data of each position of the unmanned vehicle on the operation route are obtained, the operation route of the unmanned vehicle is adjusted in real time, the real-time position and speed of the unmanned vehicle are repeatedly predicted, and the real-time route adjustment is carried out, so that the real-time operation route of the unmanned vehicle with the shortest running time is obtained.
2. The weather-based real-time operation route determination method of an unmanned vehicle according to claim 1, wherein creating a latitude and longitude coordinate map based on the urban map data and performing data processing on the historical operation data of the unmanned vehicle and the latitude and longitude coordinate map comprises:
coordinate conversion is carried out on the urban map data to obtain a longitude and latitude coordinate map corresponding to the urban map data;
performing hierarchical analysis on the historical operation data of the unmanned vehicle, wherein the operation data of the commodities with different values are classified according to the classification of the operation commodities to obtain at least two types of historical operation data;
and sending the historical operation data of at least two categories and the longitude and latitude coordinate map to a clustering model for processing, wherein the starting point coordinates on the historical operation data of each category are determined, and clustering analysis is carried out on all the starting point coordinates on the longitude and latitude coordinate map based on an OPTICS clustering algorithm to determine operation hot spot areas corresponding to the historical operation data of each category.
3. The method for determining a real-time operation route of a weather-based unmanned vehicle according to claim 1, wherein the step of transmitting the operation hot spot areas of all kinds of commodities in the historical operation data and the preset historical operation route of the unmanned vehicle to the route prediction model for processing comprises the steps of:
marking operation hot spot areas of all types of commodities in the historical operation data based on a map visualization tool, carrying out image recognition based on a Yolov3 network, marking operation hot spot area overlapping parts of the commodities in each type, and obtaining the overlapping layer number of the hot spot overlapping areas in the historical operation data;
classifying the demand grades of the unmanned vehicles according to the superposition layers of the hot spot superposition areas in the historical operation data, wherein the demand grades are classified according to a rule that the demand grades are higher as the superposition layers are more, so that the hot spot superposition areas with different grades are obtained;
performing association analysis on the hot spot overlapping areas of different grades and the historical operating route of the unmanned vehicle, wherein the outlines of the hot spot overlapping areas of different grades and the historical operating route of the unmanned vehicle are subjected to coordinate transformation, and coordinate points of the outlines of the hot spot overlapping areas of different grades obtained through the coordinate transformation and coordinate points of the historical operating route of the unmanned vehicle are subjected to association value calculation to obtain association values of the coordinate points of the outlines of the hot spot overlapping areas of each grade and the coordinate points of the historical operating route;
and based on the correlation value and the historical operation route of the unmanned vehicle, sending the correlation value and the historical operation route of the unmanned vehicle to a trained route prediction model to predict the operation route of the unmanned vehicle, and obtaining the operation route of the unmanned vehicle.
4. The method for determining a real-time operation route of a weather-based unmanned vehicle according to claim 3, wherein the method for constructing the trained route prediction model comprises the steps of:
dividing the association degree value, the hot spot overlapping areas with different grades and the coordinate points of the historical operating route into a training set and a verification set;
inputting the training set into a BP neural network for training, and optimizing the BP neural network based on a particle swarm optimization algorithm, wherein initial weight parameters of a BP neural network model are initialized, coordinate points of a historical operation route are obtained through prediction based on hot spot overlapping areas of different grades and the coordinate points of the historical operation route, particle fitness values are obtained through calculation of the particle swarm optimization algorithm, the initial weight parameters are the relevance values, and the particle swarm parameters are the coordinate points of the historical operation route obtained through prediction of the BP neural network;
determining individual optimal positions and global optimal positions of particles according to the fitness of the particles in the particle swarm and a particle swarm optimization algorithm, and dynamically tracking the individual optimal positions and the global optimal positions to continuously update the speeds and the positions of all the particles until the particle swarm optimization algorithm reaches the maximum iteration times, so as to obtain a coordinate point of an optimal historical operation route;
comparing the verification set with the coordinate points of the optimal historical operation route, and if the coordinate points of the verification set and the optimal historical operation route are consistent, obtaining a trained route prediction model.
5. A weather-based real-time operational route determination device for an unmanned vehicle, comprising:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring real-time weather information, urban map data and historical operation data of unmanned vehicles, and the real-time weather information comprises temperature information, humidity information, barometric pressure information, wind intensity information and wind direction information;
the first processing unit is used for establishing a longitude and latitude coordinate map based on the urban map data, and carrying out data processing on the historical operation data of the unmanned vehicle and the longitude and latitude coordinate map to obtain operation hot spot areas of at least two types of commodities in the historical operation data, wherein the operation hot spot areas of the at least two types of commodities in the historical operation data are operation hot spot areas of commodities with each value in the historical operation data;
the second processing unit is used for sending the operation hot spot areas of all types of commodities in the historical operation data and the preset historical operation route of the unmanned vehicle to the route prediction model for processing to obtain the operation route of the unmanned vehicle;
the third processing unit is used for sending the real-time weather information and the urban map data to the route adjustment module to adjust the operation route of the unmanned vehicle in real time, so as to obtain the adjusted real-time operation route of the unmanned vehicle;
wherein the third processing unit includes:
a third analysis subunit, configured to analyze the real-time weather information and the average running speed information of the vehicle based on a correlation analysis method in the SLP method, so as to obtain a linear relationship between the real-time weather information and the average running speed information of the vehicle;
a fourth analysis subunit, configured to establish a relationship model based on a linear relationship between the real-time weather information and the average running speed information of the vehicle, and predict and obtain a real-time speed of each position of the unmanned vehicle on an operation route based on a kalman filtering algorithm;
and the tenth processing subunit is used for obtaining the real-time speed and the urban map data of each position of the unmanned vehicle on the operation route based on the prediction, adjusting the operation route of the unmanned vehicle in real time, repeatedly predicting the real-time position and the speed of the unmanned vehicle, and carrying out real-time route adjustment to obtain the real-time operation route of the unmanned vehicle with the shortest running time.
6. The weather-based unmanned vehicle real-time operational route determination apparatus according to claim 5, wherein the apparatus comprises:
the first processing subunit is used for carrying out coordinate conversion on the urban map data to obtain a longitude and latitude coordinate map corresponding to the urban map data;
a first analysis subunit, configured to perform hierarchical analysis on historical operation data of the unmanned vehicle, where the operation data of the commercial products with different values are classified by performing hierarchical analysis according to the types of the commercial products, so as to obtain historical operation data of at least two types;
and the second processing subunit is used for sending the historical operation data of at least two categories and the longitude and latitude coordinate map to the clustering model for processing, wherein the starting point coordinates on the historical operation data of each category are determined, and clustering analysis is carried out on all the starting point coordinates on the longitude and latitude coordinate map based on an OPTICS clustering algorithm to determine operation hot spot areas corresponding to the historical operation data of each category.
7. The weather-based unmanned vehicle real-time operational route determination apparatus according to claim 5, wherein the apparatus comprises:
the third processing subunit is used for marking the operation hot spot areas of all types of commodities in the historical operation data based on the map visualization tool, carrying out image recognition based on the Yolov3 network, marking the overlapping parts of the operation hot spot areas of the commodities in each type, and obtaining the overlapping layer number of the hot spot overlapping areas in the historical operation data;
a fourth processing subunit, configured to rank demand levels of the unmanned vehicle according to the number of overlapping layers of the hot spot overlapping areas in the historical operation data, where the demand levels are ranked according to a rule that the demand levels are higher as the number of overlapping layers is greater, so as to obtain hot spot overlapping areas with different levels;
the second analysis subunit is used for carrying out association analysis on the hot spot overlapping areas of different grades and the historical operation route of the unmanned vehicle, wherein the outlines of the hot spot overlapping areas of different grades and the historical operation route of the unmanned vehicle are subjected to coordinate transformation, and coordinate points of the outlines of the hot spot overlapping areas of different grades obtained through the coordinate transformation and coordinate points of the historical operation route of the unmanned vehicle are subjected to association degree value calculation to obtain association degree values of the coordinate points of the outlines of the hot spot overlapping areas of each grade and the coordinate points of the historical operation route;
and the fifth processing subunit is used for predicting the operation route of the unmanned vehicle based on the association degree value and the historical operation route of the unmanned vehicle and sending the association degree value and the historical operation route of the unmanned vehicle to the trained route prediction model to obtain the operation route of the unmanned vehicle.
8. The weather-based unmanned vehicle real-time operational route determination apparatus according to claim 7, wherein the apparatus comprises:
a sixth processing subunit, configured to divide the association value, the hotspot coincidence areas of different levels, and the coordinate points of the historical operating route into a training set and a verification set;
a seventh processing subunit, configured to input the training set to a BP neural network for training, and perform optimization processing on the BP neural network based on a particle swarm optimization algorithm, where an initial weight parameter of a BP neural network model is initialized, coordinate points of a historical operation route are obtained by prediction based on hot spot overlapping areas of different levels and coordinate points of the historical operation route, a particle fitness value is obtained by calculation of the particle swarm optimization algorithm, the initial weight parameter is the relevance value, and the particle swarm parameter is a coordinate point of the historical operation route obtained by prediction of the BP neural network;
an eighth processing subunit, configured to determine an individual optimal position and a global optimal position of the particles according to the fitness of the particles in the particle swarm and a particle swarm optimization algorithm, and dynamically track the individual optimal position and the global optimal position to continuously update the speeds and positions of all the particles until the particle swarm optimization algorithm reaches the maximum iteration number, so as to obtain a coordinate point of an optimal historical operation route;
and the ninth processing subunit is used for comparing the verification set with the coordinate points of the optimal historical operation route, and if the coordinate points of the verification set and the optimal historical operation route are consistent, a trained route prediction model is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310430741.2A CN116151506B (en) | 2023-04-21 | 2023-04-21 | Weather-based method and device for determining real-time operation route of unmanned vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310430741.2A CN116151506B (en) | 2023-04-21 | 2023-04-21 | Weather-based method and device for determining real-time operation route of unmanned vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116151506A CN116151506A (en) | 2023-05-23 |
CN116151506B true CN116151506B (en) | 2023-06-27 |
Family
ID=86356513
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310430741.2A Active CN116151506B (en) | 2023-04-21 | 2023-04-21 | Weather-based method and device for determining real-time operation route of unmanned vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116151506B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116628446A (en) * | 2023-05-24 | 2023-08-22 | 成都工业职业技术学院 | Intelligent analysis method and system for turnout health standard value based on clustering algorithm |
CN116485063B (en) * | 2023-06-20 | 2023-08-18 | 成都工业职业技术学院 | Unmanned rolling machine group control method and device based on big data |
CN117196266B (en) * | 2023-11-07 | 2024-01-23 | 成都工业职业技术学院 | Unmanned shared automobile area scheduling method and device based on neural network |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008015612A (en) * | 2006-07-03 | 2008-01-24 | Hitachi Ltd | Regular-route bus operation management system, regular-route bus operation management method, regular-route bus operation management program |
CN103426297A (en) * | 2012-05-18 | 2013-12-04 | 李志恒 | System and method for enabling bus rapid transit dispatch to be corrected to seconds at time of sudden change of weather or road condition |
CN107909815A (en) * | 2017-12-07 | 2018-04-13 | 浙江工业大学 | A kind of car speed Forecasting Methodology based on adaptive Kalman filter |
CN111047859A (en) * | 2019-11-28 | 2020-04-21 | 刘宏隆 | Unmanned taxi operation method |
CN115243952A (en) * | 2020-03-20 | 2022-10-25 | 伟摩有限责任公司 | Weather-based speed and route planning |
CN115790636A (en) * | 2023-02-01 | 2023-03-14 | 西华大学 | Unmanned retail vehicle cruise path planning method and device based on big data |
-
2023
- 2023-04-21 CN CN202310430741.2A patent/CN116151506B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008015612A (en) * | 2006-07-03 | 2008-01-24 | Hitachi Ltd | Regular-route bus operation management system, regular-route bus operation management method, regular-route bus operation management program |
CN103426297A (en) * | 2012-05-18 | 2013-12-04 | 李志恒 | System and method for enabling bus rapid transit dispatch to be corrected to seconds at time of sudden change of weather or road condition |
CN107909815A (en) * | 2017-12-07 | 2018-04-13 | 浙江工业大学 | A kind of car speed Forecasting Methodology based on adaptive Kalman filter |
CN111047859A (en) * | 2019-11-28 | 2020-04-21 | 刘宏隆 | Unmanned taxi operation method |
CN115243952A (en) * | 2020-03-20 | 2022-10-25 | 伟摩有限责任公司 | Weather-based speed and route planning |
CN115790636A (en) * | 2023-02-01 | 2023-03-14 | 西华大学 | Unmanned retail vehicle cruise path planning method and device based on big data |
Non-Patent Citations (4)
Title |
---|
B-Planner: Planning Bidirectional Night Bus Routes Using Large-Scale Taxi GPS Traces;Chao Chen 等;《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》;第15卷(第4期);1451-1464 * |
基于出租车 GPS 数据的超市班车路线规划方法;张翔;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第4期);C034-827 * |
基于出租车历史轨迹挖掘的公交路线优化研究;张鹏飞;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第5期);C034-695 * |
基于短时交通速度预测的网约车行驶路线优化研究;林倩;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第3期);C034-336 * |
Also Published As
Publication number | Publication date |
---|---|
CN116151506A (en) | 2023-05-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116151506B (en) | Weather-based method and device for determining real-time operation route of unmanned vehicle | |
CN107610464B (en) | A kind of trajectory predictions method based on Gaussian Mixture time series models | |
Yu et al. | Prediction of bus travel time using random forests based on near neighbors | |
CN107563566B (en) | Inter-bus-station operation time interval prediction method based on support vector machine | |
WO2017020811A1 (en) | Personalized travel planning and guidance system | |
CN110889444B (en) | Driving track feature classification method based on convolutional neural network | |
US20220215749A1 (en) | Method for predicting at least one profile of the speed of a vehicle on a road network | |
CN112308292A (en) | Method for drawing fire risk grade distribution map | |
CN104834977A (en) | Traffic alarm condition level predication method based on distance metric learning | |
CN111142538B (en) | Unmanned ship operation strategy real-time decision-making method for water environment monitoring | |
CN112101132B (en) | Traffic condition prediction method based on graph embedding model and metric learning | |
CN115398062A (en) | Method for generating learned model and road surface feature determination device | |
CN113436433A (en) | Efficient urban traffic outlier detection method | |
CN111368879A (en) | Track data mining method based on deep semi-supervised neural network | |
CN115600833A (en) | Smart city restriction scheme determination method, internet of things system, device and medium | |
CN116359218A (en) | Industrial aggregation area atmospheric pollution mobile monitoring system | |
CN114898319A (en) | Vehicle type recognition method and system based on multi-sensor decision-level information fusion | |
CN117238126A (en) | Traffic accident risk assessment method under continuous flow road scene | |
CN109147322B (en) | Multi-source data self-adaptive fusion method in urban traffic big data processing | |
WO2023014311A1 (en) | Traffic density estimation system and a method thereof | |
CN108055639A (en) | A kind of density of stream of people Forecasting Methodology and system based on signaling data analysis | |
CN113965618B (en) | Abnormal track detection method based on fuzzy theory | |
CN115790635A (en) | Block chain-based unmanned transport vehicle driving route planning method and device | |
CN116189114B (en) | Method and device for identifying collision trace of vehicle | |
JP2000322682A (en) | System, device and method for predicting traffic flow |
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 |