CN112862262B - Park unmanned vehicle scheduling method, terminal equipment and storage medium - Google Patents

Park unmanned vehicle scheduling method, terminal equipment and storage medium Download PDF

Info

Publication number
CN112862262B
CN112862262B CN202110062192.9A CN202110062192A CN112862262B CN 112862262 B CN112862262 B CN 112862262B CN 202110062192 A CN202110062192 A CN 202110062192A CN 112862262 B CN112862262 B CN 112862262B
Authority
CN
China
Prior art keywords
user
park
data set
weight coefficient
judging whether
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
Application number
CN202110062192.9A
Other languages
Chinese (zh)
Other versions
CN112862262A (en
Inventor
肖苹苹
吴国贵
彭振文
郑彬彬
蒋珍妮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiamen King Long United Automotive Industry Co Ltd
Original Assignee
Xiamen King Long United Automotive Industry Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiamen King Long United Automotive Industry Co Ltd filed Critical Xiamen King Long United Automotive Industry Co Ltd
Priority to CN202110062192.9A priority Critical patent/CN112862262B/en
Publication of CN112862262A publication Critical patent/CN112862262A/en
Application granted granted Critical
Publication of CN112862262B publication Critical patent/CN112862262B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/06—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
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • 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
    • G06Q10/06316—Sequencing of tasks or work
    • 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

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to a park unmanned vehicle scheduling method, terminal equipment and a storage medium, wherein the method comprises the following steps: s1: when a user calling request is received, judging whether the user is in the park according to user position information in the user calling request, and if so, entering S2; otherwise, ending; s2: and calculating evaluation values of the user position information to different vehicles in the park through a scheduling evaluation function, and selecting vehicles responding to the user taxi calling request according to the magnitude sequence of the evaluation values. The invention does not need to appoint a station, can fully utilize the position information, the queuing information and the complexity information of the planning route to carry out strategy judgment, and realizes the dispatching of the unmanned vehicles in the park.

Description

Park unmanned vehicle scheduling method, terminal equipment and storage medium
Technical Field
The invention relates to the technical field of unmanned vehicles, in particular to a park unmanned vehicle scheduling method, terminal equipment and a storage medium.
Background
Along with the development of science and technology and the improvement of people's standard of living, people are more and more high to the demand of going on a journey, and unmanned car driving receives people's attention gradually. The unmanned technology is a current emerging technology, realizes unmanned driving by means of intelligent equipment mainly comprising an in-vehicle computer system, integrates a plurality of technologies such as a computer system structure, artificial intelligence, visual computation, automatic control and the like, and has wide prospects and high practical values in the fields of public safety, urban traffic, automobile manufacturing and the like.
The connection of public transportation often refers to short-distance, high-frequency or fixed travel modes between cities. In the urban public transport at the present stage, due to the limitation of vehicle scheduling and line network planning, a common public transport cannot go deep into residential districts, company parks and tight streets for driving. With the development of unmanned driving technology, it becomes possible to use an unmanned vehicle to carry out trip connection in a certain park. Therefore, how to schedule the unmanned vehicles in the campus becomes a problem to be solved.
Disclosure of Invention
In order to solve the problems, the invention provides a park unmanned vehicle scheduling method, terminal equipment and a storage medium.
The specific scheme is as follows:
a park unmanned vehicle scheduling method comprises the following steps:
s1: when a user taxi calling request is received, judging whether the user is in the park according to user position information in the user taxi calling request, and if so, entering S2; otherwise, ending;
s2: calculating evaluation values of the user position information to different vehicles in the park through a scheduling evaluation function, and selecting vehicles responding to the user taxi calling request according to the magnitude sequence of the evaluation values;
the scheduling evaluation function is:
T＝a 0 +a 1 *D+a 2 *L+a 3 *V+a 4 W+a 5 J+a 6 X
wherein T represents predicted arrival time, D represents spatial distance between people, L represents current number of queuing people, v represents vehicle uniform speed, W represents number of curves, J represents road condition grading index, X represents route driving distance, a 0 、a 1 、a 2 、a 3 、a 4 、a 5 And a 6 Are all weight coefficients.
Further, step S1 further includes: when a user taxi calling request is received, storing the user taxi calling request into a user taxi calling request table, and sequentially processing the user taxi calling requests according to a first-in first-out principle, wherein all the user taxi calling requests in the user taxi calling request table are arranged according to a time sequence.
Further, the user position information is longitude and latitude information of the user.
Further, the process of judging whether the user is in the campus comprises the following steps:
s101: traversing all pixel points in a park map corresponding to a park, and generating a data set (C, K) for each pixel point, wherein C represents a coordinate point corresponding to the pixel point, and K represents the radius of a circle which can cover the largest area of the park in a circle taking the coordinate point C corresponding to the pixel point as the center;
s102: arranging the data sets of all the pixel points in a descending order according to the K value; initializing a set variable k to be 1;
s103: selecting a kth data set after descending order arrangement, and adding a park position corresponding to the kth data set into a determined position of the park;
s104: selecting the (k + 1) th data set after descending order arrangement, judging whether the cross area of the (k + 1) th data set and the determined position of the garden is smaller than a preset area, if so, adding the garden position corresponding to the (k + 1) th data set into the determined position of the garden, and entering S105; otherwise, directly entering S105;
s105: judging whether k is true or not, wherein M represents the total number of pixel points, and if so, entering S107; otherwise, go to S106;
s106: making k equal to k +1, returning to S104;
s107: judging whether the position of the user is in the determined position of the park, and if so, judging that the user is in the park; otherwise, the user is determined not to be in the campus.
Further, the method for determining whether the user location is within the determined location of the campus in step S107 is as follows: calculating the distance between the user position and the coordinate points C of all data sets contained in the determined position of the park, judging whether the distance between the user position and the coordinate point C of one data set is smaller than the radius K corresponding to the data set, and if so, judging that the user position is in the determined position of the park; if not, it is determined that the user location is not within the determined location of the campus.
Furthermore, the weight coefficient in the scheduling evaluation function is determined by a mode of combining a least square method and a gradient descent method.
Further, the process of determining the weight coefficients in the scheduling evaluation function includes the following steps:
s201: obtaining a data set consisting of a plurality of groups of data obtained by a plurality of times of simulation experiments, wherein each group of data comprises a space distance D between people, a current vehicle queuing number L, a vehicle running average speed v, a curve number W, a road condition grading index J and a route running distance X;
s202: obtaining a fitting function through a minimum least square method, and setting a Loss function Loss as:
Figure BDA0002902751720000031
wherein i represents the ith group of data, and n represents that the data set contains n groups of data;
s203: optimizing the loss function, namely calculating the partial derivative value of the loss function to each weight coefficient:
Figure BDA0002902751720000041
Figure BDA0002902751720000042
Figure BDA0002902751720000043
Figure BDA0002902751720000044
Figure BDA0002902751720000045
Figure BDA0002902751720000046
Figure BDA0002902751720000047
s204: the gradient value of each weight coefficient is set as follows according to step S203:
Figure BDA0002902751720000048
Figure BDA0002902751720000049
Figure BDA00029027517200000410
Figure BDA00029027517200000411
Figure BDA00029027517200000412
Figure BDA00029027517200000413
Figure BDA0002902751720000051
wherein g _ a j Represents the weight coefficient a j J ═ 0, 1, 2, 3, 4, 5, or 6;
s205: initializing and setting each weight coefficient;
s206: calculating the gradient value of each weight coefficient and the sum of the gradient values of all the weight coefficients, and setting an updating formula of the weight coefficients after each iteration as follows:
a′ j ＝a j +learn_rate*g_a j
wherein, a' j Represents the updated weight coefficient a j The leann _ rate represents the learning rate;
s207: judging whether the sum of the gradient values of all the weight coefficients after the current iteration is smaller than the sum of the gradient values of all the weight coefficients after the last iteration, if so, entering S208; otherwise, returning to S205 to perform initialization setting on each weight coefficient again;
s208: judging whether the sum of the gradient values of all the weight coefficients is smaller than a threshold value, if so, stopping iteration, and taking the weight coefficient at the moment as the weight coefficient in the scheduling evaluation function; otherwise, adding 1 to the iteration number, returning to S206, and entering the next iteration.
The terminal equipment for dispatching the unmanned vehicles in the park comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the method of the embodiment of the invention.
A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method as described above for an embodiment of the invention.
By adopting the technical scheme, the invention can make full use of the position information, the queuing information and the complexity information of the planned route to carry out strategy judgment without specifying a station, thereby realizing the dispatching of the unmanned vehicles in the park.
Drawings
Fig. 1 is a flowchart illustrating a first embodiment of the present invention.
Detailed Description
To further illustrate the various embodiments, the invention provides the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments. Those skilled in the art will appreciate still other possible embodiments and advantages of the present invention with reference to these figures.
The invention will now be further described with reference to the drawings and the detailed description.
The first embodiment is as follows:
the embodiment of the invention provides a method for dispatching unmanned vehicles in a park, which comprises the following steps of:
s1: when a user taxi calling request is received, judging whether the user is in the park according to user position information in the user taxi calling request, and if so, entering S2; otherwise, ending.
In order to process the user's taxi-calling request in time sequence, the embodiment further comprises: when a user taxi calling request is received, storing the user taxi calling request into a user taxi calling request table, and sequentially processing the user taxi calling requests according to a first-in first-out principle, wherein all the user taxi calling requests in the user taxi calling request table are arranged according to a time sequence.
The method for judging whether the user is in the park in the embodiment comprises the following steps:
s101: traversing all pixel points in a park map corresponding to a park, and generating a data set (C, K) for each pixel point, wherein C represents a coordinate point corresponding to the pixel point, and K represents the radius of a circle which can cover the largest area of the park in a circle taking the coordinate point C corresponding to the pixel point as the center. The circle centered on C does not exceed the range of the garden, that is, the area of the included non-garden area is 0.
S102: arranging the data sets of all the pixel points in a descending order according to the K value; let k equal to 1.
S103: and selecting the kth data set after the descending order, and adding the park position corresponding to the kth data set into the determined position of the park.
S104: selecting the (k + 1) th data set after descending order arrangement, judging whether the cross area of the (k + 1) th data set and the determined position of the garden is smaller than a preset area, if so, adding the garden position corresponding to the (k + 1) th data set into the determined position of the garden, and entering S105; otherwise, the process proceeds directly to S105.
S105: judging whether k is true or not, if so, entering S107; otherwise, the process proceeds to S106.
S106: let k be k +1, return to S104.
S107: calculating whether the position of the user is in the determined position of the garden, and if so, judging that the user is in the garden; otherwise, it is determined that the user is not in the campus.
The method for judging whether the user position is in the determined position of the park comprises the following steps: calculating the distance between the user position and the coordinate points C of all data sets contained in the determined position of the park, judging whether the distance between the user position and the coordinate point C of one data set is smaller than the radius K corresponding to the data set, and if so, judging that the user position is in the determined position of the park; if not, it is determined that the user location is not within the determined location of the campus.
By the method for judging whether the user is in the park, the non-regular park can be better judged, and the judgment result is more accurate.
S2: and calculating evaluation values of the user position information to different vehicles in the park through a scheduling evaluation function, and selecting vehicles responding to the user taxi calling request according to the magnitude sequence of the evaluation values.
In this embodiment, the scheduling evaluation function is set as:
T＝a 0 +a 1 *D+a 2 *L+a 3 *V+a 4 W+a 5 J+a 6 X
wherein T represents predicted arrival time, D represents space distance between people, L represents current vehicle queuing number, v represents vehicle uniform speed, W represents number of curves, J represents road condition grading index, X represents route driving distance, W, J and X together represent planned route complexity, a 0 、a 1 、a 2 、a 3 、a 4 、a 5 And a 6 Are all weight coefficients.
In this example a 0 、a 1 、a 2 、a 3 、a 4 、a 5 And a 6 The seven weight coefficients are determined by combining a least square method and a gradient descent method, and the specific determination process comprises the following steps:
s201: obtaining a data set consisting of a plurality of groups of data obtained by a plurality of times of simulation experiments, wherein each group of data comprises a space distance D between people, a current vehicle queuing number L, a vehicle running average speed v, a curve number W, a road condition grading index J and a route running distance X;
s202: obtaining a fitting function through a minimum least square method, and setting a Loss function Loss as follows:
Figure BDA0002902751720000081
wherein i represents the ith group of data, and n represents that the data set contains n groups of data;
s203: optimizing the loss function, namely calculating the partial derivative value of the loss function to each weight coefficient:
Figure BDA0002902751720000082
Figure BDA0002902751720000083
Figure BDA0002902751720000084
Figure BDA0002902751720000085
Figure BDA0002902751720000086
Figure BDA0002902751720000087
Figure BDA0002902751720000091
s204: the gradient value of each weight coefficient is set as follows according to step S203:
Figure BDA0002902751720000092
Figure BDA0002902751720000093
Figure BDA0002902751720000094
Figure BDA0002902751720000095
Figure BDA0002902751720000096
Figure BDA0002902751720000097
Figure BDA0002902751720000098
wherein, g _ a j Represents the weight coefficient a j J ═ 0, 1, 2, 3, 4, 5, or 6;
s205: initializing and setting each weight coefficient;
s206: calculating the gradient value of each weight coefficient and the sum of the gradient values of all the weight coefficients, and setting an updating formula of the weight coefficients after each iteration as follows:
a′ j ＝a j +learn_rate*g_a j
wherein, a' j Represents the updated weight coefficient a j The leann _ rate represents the learning rate, and the cosine annealing method is adopted in the embodiment for calculation;
s207: judging whether the sum of the gradient values of all the weight coefficients after the current iteration is smaller than the sum of the gradient values of all the weight coefficients after the last iteration, if so, entering S208; otherwise, returning to S205 to perform initialization setting on each weight coefficient again;
s208: judging whether the sum of the gradient values of all the weight coefficients is smaller than a threshold value, if so, stopping iteration, and taking the weight coefficient at the moment as the weight coefficient in the scheduling evaluation function; otherwise, adding 1 to the iteration number, returning to S206, and entering the next iteration.
By adopting the scheme, the system and the method have the advantages that the site does not need to be appointed, the strategy judgment can be carried out by fully utilizing the position information, the queuing information and the planning route complexity information, and the unmanned vehicle scheduling in the park is realized.
Example two:
the invention also provides a terminal device for dispatching the unmanned vehicles in the park, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the method embodiment of the first embodiment of the invention.
Further, as an executable scheme, the terminal device for dispatching the unmanned vehicles in the park may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal equipment for dispatching the unmanned vehicles in the park can comprise, but is not limited to, a processor and a memory. It is understood by those skilled in the art that the above-mentioned constitutional structure of the terminal device for dispatching unmanned vehicles on the campus is only an example of the terminal device for dispatching unmanned vehicles on the campus, and does not constitute a limitation on the terminal device for dispatching unmanned vehicles on the campus, and may include more or less components than the above, or combine some components, or different components, for example, the terminal device for dispatching unmanned vehicles on the campus may further include an input/output device, a network access device, a bus, etc., which is not limited in this embodiment of the present invention.
Further, as an executable solution, the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, and the like. The general processor can be a microprocessor or the processor can be any conventional processor and the like, the processor is a control center of the garden unmanned vehicle dispatching terminal equipment, and various interfaces and lines are utilized to connect various parts of the whole garden unmanned vehicle dispatching terminal equipment.
The memory can be used for storing the computer program and/or the module, and the processor can realize various functions of the park unmanned vehicle dispatching terminal equipment by running or executing the computer program and/or the module stored in the memory and calling the data stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the mobile phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The invention also provides a computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the above-mentioned method of an embodiment of the invention.
The modules/units integrated with the terminal equipment for dispatching unmanned vehicles in the park can be stored in a computer readable storage medium if the modules/units are realized in the form of software functional units and sold or used as independent products. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), software distribution medium, and the like.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (7)

1. A park unmanned vehicle dispatching method is characterized by comprising the following steps:
s1: when a user taxi calling request is received, judging whether the user is in the park according to user position information in the user taxi calling request, and if so, entering S2; otherwise, ending; the judgment process of whether the user is in the park comprises the following steps:
s101: traversing all pixel points in a garden map corresponding to a garden, and generating a data set (C, K) for each pixel point, wherein C represents a coordinate point corresponding to the pixel point, and K represents the radius of a circle which can cover the largest area of the garden in a circle with the coordinate point C corresponding to the pixel point as the center;
s102: arranging the data sets of all the pixel points in a descending order according to the K value; initializing a set variable k to be 1;
s103: selecting a kth data set after descending order arrangement, and adding a park position corresponding to the kth data set into a determined position of the park;
s104: selecting the (k + 1) th data set after descending order arrangement, judging whether the cross area of the (k + 1) th data set and the determined position of the garden is smaller than a preset area, if so, adding the garden position corresponding to the (k + 1) th data set into the determined position of the garden, and entering S105; otherwise, directly entering S105;
s105: judging whether k is true or not, wherein M represents the total number of pixel points, and if so, entering S107; otherwise, go to S106;
s106: making k equal to k +1, returning to S104;
s107: judging whether the position of the user is in the determined position of the park, and if so, judging that the user is in the park; otherwise, judging that the user is not in the park;
the method for judging whether the user position is in the determined position of the park in step S107 is as follows: calculating the distance between the user position and the coordinate points C of all data sets contained in the determined position of the park, judging whether the distance between the user position and the coordinate point C of one data set is smaller than the radius K corresponding to the data set, and if so, judging that the user position is in the determined position of the park; if not, determining that the user position is not within the determined position of the park;
s2: calculating evaluation values of the user position information to different vehicles in the park through a scheduling evaluation function, and selecting vehicles responding to the user taxi calling request according to the magnitude sequence of the evaluation values;
the scheduling evaluation function is:
T＝a 0 +a 1 *D+a 2 *L+a 3 *V+a 4 W+a 5 J+a 6 X
wherein T represents predicted arrival time, D represents spatial distance between people, L represents current number of queuing people, V represents vehicle uniform speed, W represents number of curves, J represents road condition grading index, X represents route driving distance, a 0 、a 1 、a 2 、a 3 、a 4 、a 5 And a 6 Are all weight coefficients.
2. The campus unmanned vehicle scheduling method of claim 1, wherein: step S1 further includes: when a user taxi calling request is received, storing the user taxi calling request into a user taxi calling request table, and sequentially processing the user taxi calling requests according to a first-in first-out principle, wherein all the user taxi calling requests in the user taxi calling request table are arranged according to a time sequence.
3. The campus unmanned vehicle scheduling method of claim 1, wherein: the user position information is longitude and latitude information of the user.
4. The campus unmanned vehicle scheduling method of claim 1, wherein: and the weight coefficient in the scheduling evaluation function is determined by combining a least square method and a gradient descent method.
5. The campus unmanned vehicle scheduling method of claim 4, wherein: the process of determining the weight coefficients in the scheduling evaluation function comprises the following steps:
s201: obtaining a data set consisting of a plurality of groups of data obtained by multiple simulation experiments, wherein each group of data comprises a space distance D between people, the number L of current vehicle queuing people, a vehicle running average speed V, the number W of curves, a road condition grading index J and a route running distance X;
s202: obtaining a fitting function by a least square method, and setting a Loss function Loss as:
Figure FDA0003626626960000031
wherein i represents the ith group of data, and n represents that the data set contains n groups of data;
s203: optimizing the loss function, namely calculating the partial derivative value of the loss function to each weight coefficient:
Figure FDA0003626626960000032
Figure FDA0003626626960000033
Figure FDA0003626626960000034
Figure FDA0003626626960000035
Figure FDA0003626626960000036
Figure FDA0003626626960000037
Figure FDA0003626626960000038
s204: the gradient value of each weight coefficient is set as follows according to step S203:
Figure FDA0003626626960000039
Figure FDA00036266269600000310
Figure FDA00036266269600000311
Figure FDA00036266269600000312
Figure FDA0003626626960000041
Figure FDA0003626626960000042
Figure FDA0003626626960000043
wherein g _ a j Represents a weight coefficient a j J ═ 0, 1, 2, 3, 4, 5, or 6;
s205: initializing and setting each weight coefficient;
s206: calculating the gradient value of each weight coefficient and the sum of the gradient values of all the weight coefficients, and setting an updating formula of the weight coefficients after each iteration as follows:
a′ j ＝a j +learn_rate*g_a j
wherein, a' j Represents the updated weight coefficient a j The leann _ rate represents the learning rate;
s207: judging whether the sum of the gradient values of all the weight coefficients after the current iteration is smaller than the sum of the gradient values of all the weight coefficients after the last iteration, if so, entering S208; otherwise, returning to S205 to perform initialization setting on each weight coefficient again;
s208: judging whether the sum of the gradient values of all the weight coefficients is smaller than a threshold value, if so, stopping iteration, and taking the weight coefficient at the moment as the weight coefficient in the scheduling evaluation function; otherwise, adding 1 to the iteration number, returning to S206, and entering the next iteration.
6. The utility model provides a no people's car dispatch terminal equipment in garden which characterized in that: comprising a processor, a memory and a computer program stored in said memory and running on said processor, said processor implementing the steps of the method according to any one of claims 1 to 5 when executing said computer program.
7. A computer-readable storage medium storing a computer program, the computer program characterized in that: the computer program when executed by a processor implements the steps of the method as claimed in any one of claims 1 to 5.
CN202110062192.9A 2021-01-18 2021-01-18 Park unmanned vehicle scheduling method, terminal equipment and storage medium Active CN112862262B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110062192.9A CN112862262B (en) 2021-01-18 2021-01-18 Park unmanned vehicle scheduling method, terminal equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110062192.9A CN112862262B (en) 2021-01-18 2021-01-18 Park unmanned vehicle scheduling method, terminal equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112862262A CN112862262A (en) 2021-05-28
CN112862262B true CN112862262B (en) 2022-09-30

Family

ID=76006389

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110062192.9A Active CN112862262B (en) 2021-01-18 2021-01-18 Park unmanned vehicle scheduling method, terminal equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112862262B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108460966A (en) * 2017-02-21 2018-08-28 北京百度网讯科技有限公司 Method, apparatus, equipment and the computer storage media of vehicle scheduling
KR20180134636A (en) * 2017-06-09 2018-12-19 네이버 주식회사 Method and system for providing parking information
CN110458456A (en) * 2019-08-12 2019-11-15 上海同济城市规划设计研究院有限公司 The dispatching method and system of demand response formula public transit system based on artificial intelligence
CN110493724A (en) * 2019-08-22 2019-11-22 北京云中融信网络科技有限公司 Position monitoring method, device, server and computer readable storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108460966A (en) * 2017-02-21 2018-08-28 北京百度网讯科技有限公司 Method, apparatus, equipment and the computer storage media of vehicle scheduling
KR20180134636A (en) * 2017-06-09 2018-12-19 네이버 주식회사 Method and system for providing parking information
CN110458456A (en) * 2019-08-12 2019-11-15 上海同济城市规划设计研究院有限公司 The dispatching method and system of demand response formula public transit system based on artificial intelligence
CN110493724A (en) * 2019-08-22 2019-11-22 北京云中融信网络科技有限公司 Position monitoring method, device, server and computer readable storage medium

Also Published As

Publication number Publication date
CN112862262A (en) 2021-05-28

Similar Documents

Publication Publication Date Title
CN111366160B (en) Path planning method, path planning device and terminal equipment
US11449908B2 (en) Method and system for determining transport service fee
TWI638320B (en) Systems, methods and non-transitory computer-readable storage mediums for recommending an estimated time of arrival
US20220074750A1 (en) Managing a fleet of vehicles
CN111476588B (en) Order demand prediction method and device, electronic equipment and readable storage medium
Levin et al. On optimizing reservation-based intersection controls
WO2016127917A1 (en) Order pushing method and system
TW202016728A (en) Method and system for determiningwhether there is target road facility at intersection
JP2015500981A (en) Method and system for searching for multiple destinations in fleet navigation, dispatch and multiple vehicles
CN104951848A (en) Real-time car-pooling matching method
CN106504348A (en) A kind of method that Parking Fee clearing are provided, server and system
CN111523560B (en) Method, device and system for training number prediction model of arrival trucks
CN106875734A (en) A kind of method and device for pushing parking route
CN112041858A (en) System and method for providing travel advice
CN114781267A (en) Multi-source big data-based dynamic bus management method and system for stop and transfer
CN113763695A (en) Dispatching method and system for automatic driving vehicle
CN106886836A (en) Method for realizing rideshare in the car
CN112669604B (en) Urban traffic scheduling method and device
CN114036411A (en) Route planning method, device, equipment and medium
CN112862262B (en) Park unmanned vehicle scheduling method, terminal equipment and storage medium
CN107883972A (en) Running time dynamic pushing method and device
CN109447352B (en) Bus trip OD matrix reverse-thrust combination method
CN116307580A (en) Method and device for scheduling capacity, electronic equipment and storage medium
Wang et al. Dynamic parking allocation model in a multidestination multiple parking lot system
CN114724414B (en) Method and device for determining urban air traffic sharing rate, electronic equipment and medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant