CN113642796B - Dynamic sharing electric automatic driving vehicle path planning method based on historical data - Google Patents
Dynamic sharing electric automatic driving vehicle path planning method based on historical data Download PDFInfo
- Publication number
- CN113642796B CN113642796B CN202110948567.1A CN202110948567A CN113642796B CN 113642796 B CN113642796 B CN 113642796B CN 202110948567 A CN202110948567 A CN 202110948567A CN 113642796 B CN113642796 B CN 113642796B
- Authority
- CN
- China
- Prior art keywords
- planning
- vehicle
- user
- constraint
- time period
- 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 18
- 238000002922 simulated annealing Methods 0.000 claims abstract description 4
- 238000003780 insertion Methods 0.000 claims description 13
- 230000037431 insertion Effects 0.000 claims description 13
- 238000012217 deletion Methods 0.000 claims description 9
- 230000037430 deletion Effects 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012966 insertion method Methods 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000005484 gravity Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 239000000969 carrier Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Mathematics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a dynamic sharing electric automatic driving vehicle path planning method based on historical data, which comprises the steps of firstly dividing planning periods by combining the historical data to obtain mutually independent planning time periods, and decomposing problems in a time dimension, so that the solving efficiency of an algorithm can be effectively improved; secondly, modeling vehicle path planning problems in different planning time periods by combining the thought of a rolling time window and combining real-time user demand data in sequence, wherein particularly, users needing to be considered in each planning time period comprise users directly divided into the planning time period and users of which the previous planning time period is served and the latest expected arrival time is not exceeded; finally, the invention provides a large neighborhood algorithm combining local neighborhood search and simulated annealing ideas to solve the path planning problem in each planning time period to obtain a feasible path set. The algorithm of the invention has strong applicability, high expansibility and insensitivity to real-time parameters.
Description
Technical Field
The invention belongs to the field of urban public transportation, and particularly relates to a dynamic sharing electric automatic driving vehicle path planning method based on historical data.
Background
With the rapid development of automated driving technology in recent years, research and application of using automated driving vehicles as shared automobile carriers are being vigorously developed, and more companies and scholars begin to develop shared automobile services based on automated driving vehicles. Compared with the traditional shared automobile service, the automatic driving automobile can automatically complete empty automobile driving without user service, so that manpower and material resource consumption caused by empty automobile scheduling in the traditional shared automobile system is greatly reduced. And the electric automobile is used as a large carrier of the automatic driving technology, and can better adapt to various emerging automatic driving technologies compared with the traditional fuel oil automobile. Meanwhile, the electric automatic driving vehicle can effectively reduce the energy consumption and the emission of traffic pollutants, and is an important means for improving urban environment. Compared with the traditional shared automobile path planning problem, the path planning problem based on the electric automatic driving vehicle mainly has three main characteristics: charging problems of electric vehicles, idle running problems of automatic driving vehicles and shared traveling problems. Therefore, the conventional shared automobile path planning method is difficult to adapt to the shared automobile path planning problem after the electric automatic driving vehicle is introduced. Therefore, there is a need for a path planning method that can be adapted to an electric autopilot vehicle.
Disclosure of Invention
The invention aims to design a path planning method of a dynamic shared electric automatic driving vehicle based on historical data, wherein a planning period is divided into mutually independent planning time periods by combining the historical data, so that the scale of a problem is reduced, and the path planning method of the shared electric automatic driving vehicle capable of serving the travel demands of dynamic users is constructed by combining the concept of the planning time periods. By utilizing the method, the user requirements can be collected in real time, the path of the shared electric automatic driving automobile can be dynamically planned, and a foundation is created for the application of the shared electric automatic driving automobile.
In order to achieve the above, the technical scheme of the invention is as follows:
The dynamic sharing electric automatic driving vehicle path planning method based on the historical data is characterized by comprising the following steps of:
S1: dividing a planning time period according to the historical data;
s2: acquiring user travel data in a planning time period and preprocessing the data;
s3: constructing a vehicle track optimization model in a planning time period according to user information in the planning time period;
S4: and solving a path planning scheme of the shared electric automatic driving vehicle considering the electric vehicle charging plan by using a large neighbor algorithm.
In step S1, the specific steps of dividing the planning period according to the history data are as follows:
s101: collecting user history trip data of the day of m weeks continuously, and sorting the history data;
S102: according to the time published by the travel demands of the users and the expected vehicle time submitted by the users in the historical data, dividing the daily planning time period into u mutually independent planning time periods, wherein the planning time period is divided according to the fact that the maximum planning time period length and the maximum affiliated historical travel times are ensured, and the planning time period contains as many historical travel times as possible within the allowable range of the model computing capacity.
In step S2, the specific steps of obtaining the user trip data in the planning time period and performing data preprocessing are as follows:
s201: collecting travel data of a user, wherein the travel data mainly comprises departure positions, destination positions and travel demand release time of the user, the earliest estimated departure time, the latest estimated arrival time and the number of passengers;
s202: and matching the user to the nearest boarding and alighting positions of the shared electric automatic driving automobile in the walking range according to the departure position and the destination position of the user, issuing time according to the travel requirement of the user, predicting the departure time at the earliest and matching the travel request of the user to the corresponding planning time period at the latest predicted arrival time.
In step S3, the specific steps of constructing the vehicle track optimization model in the planning time period according to the user information in the planning time period are as follows:
S301: combining the user requirement corresponding to each planning time period and the user requirement which is not served by the shared electric automatic driving vehicle in the previous planning time period, and establishing a shared electric automatic driving vehicle model in the planning time period;
S302: setting an objective function as follows: Wherein M is a coefficient of the first project label function; /(I) Representing whether the vehicle k passes through the arc segment (i, j), c ij representing the running cost over the arc segment (i, j), the first project label function representing maximizing the number of users served in the planning period, and the second term representing minimizing the total running cost of the electric autopilot vehicle in the planning period;
S303: the following flow constraints are set:
Constraint (1) indicates that each user is served at most once, constraint (2) and constraint (3) respectively indicate that each vehicle finally goes to the final position from the initial position, constraint (4) is a balance constraint, and constraint (5) indicates that the get-on point and the get-off point of each user need to be accessed by the same vehicle; wherein the initial position of each vehicle represents the last position of the last planning period, and the final position is a virtual station for ensuring the consistency of the network;
a time constraint is set in which Let t ij denote the travel time of the vehicle k at point i, s i denote the service time at point i, η be the charging time, and a i and b i be the time window at point i:
The constraint (6) and the constraint (7) are time continuity constraints of a get-on and get-off position and a charging position of a user respectively, the constraint (8) limits a get-off position of the customer to be accessed after the get-on position, and the constraint (9) is a time window constraint of the user;
Setting the following electric quantity constraint, wherein h ij represents the electric quantity consumption on the arc section (i, j), and the constraint (10) and the constraint (11) represent electric quantity continuity constraint of the loading and unloading positions and charging positions of a user respectively:
setting a vehicle load constraint in which Represents the vehicle-mounted passenger capacity of the vehicle k at the point i, q i is the number of customers at the point i,/>Representing the maximum vehicle load of vehicle k, constraints (12) - (14) represent continuity constraints of the vehicle load, maximum vehicle load constraints, and guarantee that the vehicle cannot have an on-board user during charging:
In step S4, the specific steps of solving the path planning scheme of the shared electric automatic driving vehicle considering the electric vehicle charging plan by using the large neighbor algorithm are as follows:
S401: inserting as many users as possible into a path of the shared electric autopilot vehicle using a greedy insertion method;
s402: finding a new path scheme by using a large neighborhood searching algorithm comprising deletion, insertion and local neighborhood searching;
S403: and judging whether the result obtained by searching the large neighborhood in each iteration is accepted or not by using the simulated annealing idea.
Compared with the prior art, the technical scheme of the invention has the following advantages:
The invention fully utilizes the historical data, and ensures that the planning time period contains as many user demands as possible under the condition of ensuring the solving speed, thereby ensuring the quality of the path obtained by solving; in addition, a large neighborhood algorithm is used as a solving algorithm in each planning time period, so that the algorithm is high in applicability and expansibility, insensitive to real-time parameters and capable of achieving good solving quality.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow chart of a large neighborhood algorithm of the present invention.
Detailed Description
To further clarify the above objects, features and advantages of the present invention, a more detailed description of the invention will be provided with reference to the accompanying drawings.
As shown in fig. 1, the implementation process of the present invention includes the following steps:
S1: dividing a planning time period according to the historical data;
collecting user history trip data of the day of m weeks continuously, and sorting the history data;
According to the time published by the travel demands of the users and the expected vehicle time submitted by the users in the historical data, dividing the daily planning time period into u mutually independent planning time periods, wherein the dividing of the planning time period is based on the premise of guaranteeing the maximum planning time period length T max and the maximum affiliated historical travel times N max, namely T is less than or equal to T max,N≤Nmax, and the planning time period contains as many historical travel times as possible within the allowable range of the model computing capacity.
S2: acquiring user travel data in a planning time period and preprocessing the data;
Collecting travel data of a user, wherein the travel data mainly comprises departure positions, destination positions and travel demand release time of the user, the earliest estimated departure time, the latest estimated arrival time and the number of passengers;
And matching the user to the nearest boarding and alighting positions of the shared electric automatic driving automobile in the walking range according to the departure position and the destination position of the user, issuing time according to the travel requirement of the user, predicting the departure time earliest and matching the travel request of the user to the corresponding planning time period by the latest expected arrival time. Assume that the earliest predicted departure time for user i is 8:10, the most advanced expected arrival time is 8:30, the planning period includes: [8:00-8:20] and [8:20-8:40], it should be divided into planning periods [8:00-8:20] according to the start and end times of the planning periods.
S3: user information in a planning time period builds a vehicle path optimization model in the planning time period;
And establishing a shared electric automatic driving vehicle model in each planning time period by combining the user requirement corresponding to the planning time period and the user requirement which is not served by the shared electric automatic driving vehicle in the previous planning time period. The users to be considered in each planning period mainly include users directly divided into the planning period and users not served in the aforesaid period (and exceeding their most advanced expected arrival time), for example, when building a vehicle path optimization model related to the planning period [8:00-8:20], the user i is the user directly divided into the planning period in step S2. Suppose that the user i is not served by any vehicle in the planning period [8:00-8:20], while its most advanced hope arrives at time 8:30, user i still needs to be included in the next planning period [8:20-8:40 ].
Setting an objective function as follows: The first project label function represents maximizing the number of users served in the planning time period, and the second project label function represents minimizing the total running cost of the shared electric automatic driving vehicle in the planning time period;
The following flow constraints are set:
Constraint (1) indicates that each user is served at most once, constraint (2) and constraint (3) respectively indicate that each vehicle finally goes to the final position from the initial position, constraint (4) is a balance constraint, and constraint (5) indicates that the get-on point and the get-off point of each user need to be accessed by the same vehicle; wherein the initial position of each vehicle represents the last position of the last planning period, and the final position is a virtual station for ensuring the consistency of the network;
a time constraint is set in which Let t ij denote the travel time of the vehicle k at point i, s i denote the service time at point i, η be the charging time, and a i and b i be the time window at point i:
The constraint (6) and the constraint (7) are time continuity constraints of a get-on and get-off position and a charging position of a user respectively, the constraint (8) limits a get-off position of the customer to be accessed after the get-on position, and the constraint (9) is a time window constraint of the user;
Setting the following electric quantity constraint, wherein h ij represents the electric quantity consumption on the arc section (i, j), and the constraint (10) and the constraint (11) represent electric quantity continuity constraint of the loading and unloading positions and charging positions of a user respectively:
setting a vehicle load constraint in which Represents the vehicle-mounted passenger capacity of the vehicle k at the point i, q i is the number of customers at the point i,/>Representing the maximum vehicle load of vehicle k, constraints (12) - (14) represent continuity constraints of the vehicle load, maximum vehicle load constraints, and guarantee that the vehicle cannot have an on-board user during charging:
s4: solving a path planning scheme of the shared electric automatic driving vehicle considering the electric vehicle charging plan by utilizing a large neighbor algorithm;
As many users as possible are inserted into the path of the shared electric autonomous vehicle using a greedy insertion method. Specifically, from the first user, it is inserted into an optimal position of the vehicle that minimizes the total running cost of all vehicles after insertion. In particular, in the greedy insertion process, the feasibility of the vehicle load and the electric quantity is not considered, but the penalty of the vehicle load and the electric quantity constraint being violated is added in the objective function And/>
The model given in step S3 is solved using a large neighborhood search algorithm as shown in fig. 2, the specific steps are as follows:
Step 1: and deleting the users with the proportion alpha in the existing path set according to a given deletion strategy, wherein the range of alpha adopted in the example is 0-1. Specific: the applicable deletion strategy comprises randomly selecting users with the proportion alpha in the existing path set for deletion; selecting the user with the proportion alpha which can reduce the path cost most after deletion; selecting the user (k-regret deleted, in the example k selected 2,3 and 4) who can reduce the path cost by the kth position; randomly deleting all users of a vehicle service; and selecting the vehicle with the largest current cost to delete all users. And putting all the deleted users into the user set to be inserted.
Step 2: and selecting the positions of the customers to be inserted from the customer set to be inserted according to a given insertion strategy so as to minimize the running cost after the insertion. Specific insertion operations include: randomly selecting a customer from a set of customers to be inserted; the customers who have the least cost increase after the insertion are selected in this way; the customer (k-regret insert, in the example k selects 2,3 and 4) who adds to the cost k after the insert is selected in this way. In particular, similar to the greedy insertion process, the feasibility of the vehicle load and the electric quantity is not considered in the insertion process of the large neighborhood algorithm, and the penalty of violating the vehicle load and the electric quantity constraint is added to the objective function.
Wherein each delete and insert operation has a selection weight w i, in each iteration, according to the following formula:
The selection probability p i for each deletion and insertion operation is calculated according to the roulette rule, and the deletion and insertion operation is selected according to the probabilities.
Step 3: if the maximum circulation times R 1 are not reached, returning to the step 1 to continue circulation, wherein the circulation times are R 1＝r1 +1. If the maximum circulation times are reached, a local neighborhood search strategy is called to optimize the current result, and the method is specific: strategies for local neighborhood searching include: the order of two customers within the switch path, the order of two customers between the switch paths, and a plurality of customers with the same position in the service sequence between the switch paths. The number of iterations of the local neighborhood search in the example is R 2. And completing local neighborhood search to complete one integral iteration of the large neighborhood algorithm.
Step 4: judging whether the maximum searching cycle number R is reached, if the maximum searching cycle number R is not reached, updating, deleting and inserting the operation weight, returning to the step 1, setting the cycle number r=r+1, and otherwise, outputting the current best result. Specific: the specific gravity of the delete and insert operations is updated as follows:
Wherein the parameter θ represents a coefficient for updating the specific gravity according to the deletion insertion operation score, and in the example, the value of θ ranges from 0 to 1.ρ i represents the number of times each operation occurs in the iterative process, and pi i represents the score of each operation in the iterative process, specifically: when the insert operation was deleted, a new optimal solution was obtained, and when the insert operation was deleted, a solution that was not optimal but superior to the solution before the operation was obtained, a score of 9 was obtained, and when the solution after the insert operation was deleted, a solution that was inferior to the solution before the operation was obtained, but was selected based on the simulated annealing mechanism, a score of 13 was obtained.
The above is merely a preferred embodiment of the present invention, the protection scope of the present invention is not limited to the above embodiment, it should be noted that several improvements and modifications are to be considered as the protection scope of the present invention without departing from the principle of the present invention.
Claims (1)
1. The dynamic sharing electric automatic driving vehicle path planning method based on the historical data is characterized by comprising the following steps of:
S1: dividing a planning time period according to the historical data;
s2: acquiring user travel data in a planning time period and preprocessing the data;
s3: constructing a vehicle track optimization model in a planning time period according to user information in the planning time period;
s4: solving a path planning scheme of the shared electric automatic driving vehicle considering the electric vehicle charging plan by utilizing a large neighbor algorithm;
the specific steps of dividing the planning time period according to the historical data are as follows:
s101: collecting user history trip data of the day of m weeks continuously, and sorting the history data;
S102: dividing a daily planning time period into u mutually independent planning time periods according to the published time of the user travel demands in the historical data and the expected vehicle utilization time submitted by the user, wherein the planning time period is divided according to the fact that the maximum planning time period length and the maximum affiliated historical travel times are ensured, and the planning time period contains as many historical travel times as possible within the allowable range of the model computing capacity;
the specific steps of acquiring the travel data of the user in the planning time period and preprocessing the data are as follows:
s201: collecting travel data of a user, wherein the travel data mainly comprises departure positions, destination positions and travel demand release time of the user, the earliest estimated departure time, the latest estimated arrival time and the number of passengers;
S202: matching the user to the nearest boarding and alighting positions of the shared electric automatic driving automobile in the walking range according to the departure position and the destination position of the user, issuing time according to the travel requirement of the user, predicting the departure time at the earliest and matching the travel request of the user to the corresponding planning time period at the latest predicted arrival time;
The specific steps of constructing the vehicle track optimization model in the planning time period according to the user information in the planning time period are as follows:
S301: combining the user requirement corresponding to each planning time period and the user requirement which is not served by the shared electric automatic driving vehicle in the previous planning time period, and establishing a shared electric automatic driving vehicle model in the planning time period;
S302: setting an objective function as follows: Wherein M is a coefficient of the first project label function; /(I) Representing whether the vehicle k passes through the arc segment (i, j), c ij representing the running cost over the arc segment (i, j), the first project label function representing maximizing the number of users served in the planning period, and the second term representing minimizing the total running cost of the electric autopilot vehicle in the planning period;
S303: the following flow constraints are set:
Constraint (1) indicates that each user is served at most once, constraint (2) and constraint (3) respectively indicate that each vehicle finally goes to the final position from the initial position, constraint (4) is a balance constraint, and constraint (5) indicates that the get-on point and the get-off point of each user need to be accessed by the same vehicle; wherein the initial position of each vehicle represents the last position of the last planning period, and the final position is a virtual station for ensuring the consistency of the network;
a time constraint is set in which Let t ij denote the travel time of the vehicle k at point i, s i denote the service time at point i, η be the charging time, and a i and b i be the time window at point i:
The constraint (6) and the constraint (7) are time continuity constraints of a get-on and get-off position and a charging position of a user respectively, the constraint (8) limits a get-off position of the customer to be accessed after the get-on position, and the constraint (9) is a time window constraint of the user;
Setting the following electric quantity constraint, wherein h ij represents the electric quantity consumption on the arc section (i, j), and the constraint (10) and the constraint (11) represent electric quantity continuity constraint of the loading and unloading positions and charging positions of a user respectively:
setting a vehicle load constraint in which Represents the vehicle-mounted passenger capacity of the vehicle k at the point i, q i is the number of customers at the point i,/>Representing the maximum vehicle load of vehicle k, constraints (12) - (14) represent continuity constraints of the vehicle load, maximum vehicle load constraints, and guarantee that the vehicle cannot have an on-board user during charging:
The method for solving the path planning scheme of the shared electric automatic driving vehicle considering the electric vehicle charging plan by utilizing the large neighbor algorithm comprises the following specific steps:
S401: inserting as many users as possible into a path of the shared electric autopilot vehicle using a greedy insertion method;
s402: finding a new path scheme by using a large neighborhood searching algorithm comprising deletion, insertion and local neighborhood searching;
S403: and judging whether the result obtained by searching the large neighborhood in each iteration is accepted or not by using the simulated annealing idea.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110948567.1A CN113642796B (en) | 2021-08-18 | 2021-08-18 | Dynamic sharing electric automatic driving vehicle path planning method based on historical data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110948567.1A CN113642796B (en) | 2021-08-18 | 2021-08-18 | Dynamic sharing electric automatic driving vehicle path planning method based on historical data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113642796A CN113642796A (en) | 2021-11-12 |
| CN113642796B true CN113642796B (en) | 2024-06-04 |
Family
ID=78422592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110948567.1A Active CN113642796B (en) | 2021-08-18 | 2021-08-18 | Dynamic sharing electric automatic driving vehicle path planning method based on historical data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642796B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117288206B (en) * | 2023-11-23 | 2024-02-02 | 四川国蓝中天环境科技集团有限公司 | Unmanned aerial vehicle route planning method based on self-adaptive large neighborhood search |
| CN118410931B (en) * | 2024-07-04 | 2024-10-15 | 松立控股集团股份有限公司 | Method and system for recommending optimal inspection time period and path of road yard |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027755A (en) * | 2019-11-22 | 2020-04-17 | 珠海格力电器股份有限公司 | Shared trolley selecting method and reserving method based on path planning |
| KR20200064190A (en) * | 2018-11-20 | 2020-06-08 | 한국과학기술원 | Server and method for managing shared autonomous vehicles |
| CN111612358A (en) * | 2020-05-25 | 2020-09-01 | 北京交通大学 | Shared automobile vehicle scheduling and dispatcher path optimization method |
| WO2020199524A1 (en) * | 2019-04-02 | 2020-10-08 | 长安大学 | Method for matching ride-sharing travellers based on network representation learning |
| CN112577502A (en) * | 2019-09-30 | 2021-03-30 | 华为技术有限公司 | Method and device for planning driving |
| CN112729324A (en) * | 2020-11-24 | 2021-04-30 | 北京交通大学 | Electric vehicle charging guidance and path planning method based on mutual-help travel system |
| CN112882466A (en) * | 2021-01-12 | 2021-06-01 | 上海电力大学 | Fusion hierarchical planning and A*Shared electric vehicle path planning method of algorithm |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9792575B2 (en) * | 2016-03-11 | 2017-10-17 | Route4Me, Inc. | Complex dynamic route sequencing for multi-vehicle fleets using traffic and real-world constraints |
| US20190061545A1 (en) * | 2017-08-31 | 2019-02-28 | Electric Motor Werks, Inc. | Systems and methods for electric vehicle charging with automated trip planning integration |
-
2021
- 2021-08-18 CN CN202110948567.1A patent/CN113642796B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20200064190A (en) * | 2018-11-20 | 2020-06-08 | 한국과학기술원 | Server and method for managing shared autonomous vehicles |
| WO2020199524A1 (en) * | 2019-04-02 | 2020-10-08 | 长安大学 | Method for matching ride-sharing travellers based on network representation learning |
| CN112577502A (en) * | 2019-09-30 | 2021-03-30 | 华为技术有限公司 | Method and device for planning driving |
| CN111027755A (en) * | 2019-11-22 | 2020-04-17 | 珠海格力电器股份有限公司 | Shared trolley selecting method and reserving method based on path planning |
| CN111612358A (en) * | 2020-05-25 | 2020-09-01 | 北京交通大学 | Shared automobile vehicle scheduling and dispatcher path optimization method |
| CN112729324A (en) * | 2020-11-24 | 2021-04-30 | 北京交通大学 | Electric vehicle charging guidance and path planning method based on mutual-help travel system |
| CN112882466A (en) * | 2021-01-12 | 2021-06-01 | 上海电力大学 | Fusion hierarchical planning and A*Shared electric vehicle path planning method of algorithm |
Non-Patent Citations (2)
| Title |
|---|
| Modeling Heterogeneous Traffic Mixing Regular, Connected, and Connected-Autonomous Vehicles Under Connected Environment;崔少华 等;《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》;全文 * |
| 两阶段启发式算法求解带时间窗的多中心车辆路径问题;于滨;《系统工程理论与实践》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113642796A (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934391B (en) | Intelligent scheduling method for pure electric bus | |
| CN113642796B (en) | Dynamic sharing electric automatic driving vehicle path planning method based on historical data | |
| CN115547052B (en) | Dynamic demand response electric bus scheduling method for improving self-adaptive large neighborhood algorithm | |
| CN113222387B (en) | Multi-objective scheduling and collaborative optimization method for hydrogen fuel vehicle | |
| CN111915176A (en) | Scheduling method and system of pure electric bus in hybrid operation mode | |
| CN105046356B (en) | A kind of electric car course continuation mileage optimization device and method | |
| CN107274665A (en) | Bus transport capacity resource method and system for planning | |
| CN112309122A (en) | Intelligent bus grading decision-making system based on multi-system cooperation | |
| CN111127936B (en) | Dynamic vehicle scheduling and route planning method for shared bus | |
| CN115100896A (en) | Electric demand response bus dispatching method considering opportunity charging strategy | |
| CN108133329B (en) | Electric automobile travel and charging demand analysis method considering charging feedback effect | |
| CN110189182A (en) | A kind of mileage anxiety management method based on car networking | |
| CN114742340A (en) | Optimal layout solving method for intelligent network connection sharing electric vehicle charging station in large-scale road network | |
| CN116911729A (en) | Unmanned aerial vehicle and truck collaborative distribution method considering battery replacement plan | |
| CN107316100A (en) | The charging scheduling strategy of electric automobile in smart city | |
| CN112465222A (en) | Optimal charging station selection method based on charging station service level prediction | |
| CN116562538A (en) | Microcirculation public transportation scheduling optimization method and device considering rail transit connection | |
| Wan et al. | Online recommendation system for autonomous and human-driven ride-hailing taxi services | |
| CN115663867A (en) | Electric vehicle charging scheduling method based on intelligent charging network system | |
| CN116151397A (en) | Network appointment vehicle order dispatching method under mixed service mode | |
| CN113222248A (en) | Charging pile selection method for automatically driving taxi | |
| CN113313327A (en) | Agent simulation-based electric vehicle charging pile layout optimization method | |
| Van Son et al. | Prediction-based optimization for online People and Parcels share a ride taxis | |
| CN115409288B (en) | Internet of Things service management system based on regional digital economy | |
| CN115358471B (en) | Electric vehicle distribution path planning method and system based on mobile charging |
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 |