CN110009906B - Dynamic path planning method based on traffic prediction - Google Patents
Dynamic path planning method based on traffic prediction Download PDFInfo
- Publication number
- CN110009906B CN110009906B CN201910225789.3A CN201910225789A CN110009906B CN 110009906 B CN110009906 B CN 110009906B CN 201910225789 A CN201910225789 A CN 201910225789A CN 110009906 B CN110009906 B CN 110009906B
- Authority
- CN
- China
- Prior art keywords
- network model
- time
- grid
- node
- network
- 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
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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Economics (AREA)
- Chemical & Material Sciences (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
A dynamic path planning method based on traffic information comprises the following steps: network model abstraction, stacked networks and spatio-temporal scrolling algorithms. The network model abstraction is used for converting an actual road into a network graph structure of nodes and weights, the network graph structure is divided into an upper layer network model abstraction and a lower layer network model abstraction, and the traffic flow density and the path length are comprehensively considered in weight setting; the stacked network integrates the real-time traffic information and the predicted traffic information with a plurality of step lengths to obtain a final network model; the space-time rolling algorithm comprises time rolling and space rolling processes, and refreshes the traffic state according to a certain time interval to realize dynamic planning. The invention can ensure that the increment of the travel route is within a certain range under the condition of relatively congested traffic, but greatly shortens the travel time.
Description
Technical Field
The invention belongs to the field of optimal path problems, and particularly relates to a dynamic path planning algorithm comprehensively considering real-time traffic information, predicted traffic information and road length.
Background
The shortest path problem is a classic problem in graph theory, is also a research hotspot in the fields of geographic information science and the like, and has wide application in the fields of traffic planning, traffic transportation, logistics management and the like. In reality, a network entity (mainly referred to as an actual road network in the present invention) needs to be abstracted into a network graph concept in graph theory according to its characteristics, that is, a network model is established. After the network model is established, various network analysis methods in graph theory can be used for discussion and research.
The following describes the related background art of the optimal path problem, which is not included in the dynamic path planning algorithm and can be found in the related literature or books.
Road networks can be divided into two types according to the characteristics of road section impedance, namely static (static) road networks and dynamic (dynamic) road networks, wherein the dynamic road networks are also called time-varying road networks or time-dependent road networks; based on the knowledge of the impedance of the road section, the method can be divided into deterministic (deterministic) road network and stochastic (stochastic) road network. While the road segment impedance of a deterministic road network is exactly known, the road segment impedance of a random road network is uncertain and can be described by some known probability distribution. Thus, the shortest path problem or optimal path can be classified into the following 4 categories: 1) the shortest path problem of a statically determined road network, namely the impedance of a road section in the road network is fixed and invariable, for example, the famous Dijkstra algorithm, a breadth-first search algorithm represented by the Dijkstra algorithm is widely applied to the optimal path problem, but the method prepares to search all network nodes during solving, and under the condition of large number of the network nodes, the time cost of the algorithm is difficult to meet the requirement of actual operation; 2) the optimal path problem of the static random road network is that the impedance of the road sections in the road network is a random variable independent of time; 3) the shortest path problem of a time-varying road network, in which the impedance of a road segment in the road network varies with time, is a deterministic function that depends on time, and is also referred to as a time-dependent optimal path problem or a dynamic road network shortest path problem. The research in the field firstly applies the static shortest path algorithm to a time-varying network, then theoretically distinguishes an FIFO (first-in first-out) network and a Non-FIFO network, respectively carries out algorithm research, and finally applies the research content to an actual traffic network; 4) the optimal path problem of a random time-varying road network is that the impedance of road sections in the road network is a random variable or a random distribution function depending on time. The random time-varying road network is more general, is more complex compared with other network models, and is closer to an actual traffic network. Under different decision strategies, the optimal path of the random time-varying network has different definitions.
The optimal path problem has been worked on by consulting the relevant literature. However, in practical applications, most road impedance is constant, i.e. for static road networks. The increasingly congested urban traffic means that the features in an actual road network are changed randomly, and the random features are introduced into the problem of an optimal path, which is particularly necessary for improving the individual trip efficiency and the vehicle logistics distribution service level. On the other hand, the Dijkstra algorithm is taken as a classic optimal path algorithm, when a network model is established, an actual path is abstracted into one edge in the network, and certain characteristics of the actual path are taken as the weight of the edge. When the method of graph representation is adopted, no matter the adjacency matrix or the adjacency list, a large amount of memories are required to be opened up for storage, in addition, the method prepares to search all network nodes during solving, and under the condition that the number of the network nodes is large, the time cost of the algorithm is difficult to meet the requirement of actual operation.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides the dynamic rolling planning method for fusing the real-time traffic information, the predicted traffic information and the path length, which greatly shortens the travel time under the condition of relatively congested traffic while ensuring the increment of the travel path in a certain range.
The technical solution of the invention is as follows:
a dynamic path planning method based on traffic information is characterized by comprising a network model abstraction stage, a network stacking stage and a space-time rolling algorithm stage;
in the network model abstraction stage, an actual road is converted into a network graph structure of nodes and weights, the network graph structure is divided into an upper layer network model abstraction and a lower layer network model abstraction, and the traffic flow density and the path length are comprehensively considered in weight setting;
the network stacking stage integrates the real-time traffic information and the predicted traffic information with a plurality of step lengths to obtain a final network model;
the space-time rolling algorithm stage comprises time rolling and space rolling processes, and refreshes the traffic state according to a certain time interval to realize a dynamic planning algorithm.
The network model abstraction phase comprises an upper network model abstraction process and a lower network model abstraction process:
an upper network model abstraction process:
firstly, rasterizing an actual road networkDividing the grid into a plurality of grids with equal size, taking each grid as a node, wherein the ith grid is a node ViAny two adjacent nodes ViAnd VjIf there is a road communication from grid i to grid j, a connection line of grid i and grid j is generatediPoint of direction VjConnecting edge E ofijObtaining an unweighted directed graph G (V, E); obtaining a flow vector f ═ q in each gridN,qE,qS,qW]And an average velocity v;
secondly, initializing a current node s, a destination node d and a current time t of the vehicle, and calculating the traffic flow density k in each grid at the time of titThe formula is as follows:
in the formula, vitIs the average velocity in the grid, q1it,q2it,q3it,q4itRespectively representing the traffic flow flowing into adjacent grids in the north, east, south and west directions;
thirdly, obtaining a weighted directed graph G (V, E, w) through weight mappingt)，
In the formula, the t time is connected with the edge EijWeight value w ofij＝kj+li
Lower layer network model abstraction:
and fourthly, taking the intersections as nodes, connecting the intersections as connecting edges, and taking the weight as the path length to obtain a lower-layer network model G (v, e, w).
The stacking sampling stage comprises the following specific steps:
step 2.1, making m equal to 1;
step 2.2, with the current time T as a starting point, predicting the global traffic state at the time T +1, T +2, and T + n to obtain a prediction weighted directed graph G (V, E, w)T+1),…,G(V,E,wT+N) N represents a time interval;
step 2.3 weighted prediction directed graph G (V, E, w)T+1),…,G(V,E,wT+N) Stacking is carried out, taking the current position s as the center, s +m circles of node weight selection T + m moment weighted directed graph G (V, E, w)T+m) The weight of (2); s denotes a grid, and s +1 circles refer to: the grid 1 which is centered at s and closely surrounds the grid s, that is, the grid through which the red broken line drawn at the time t +1 in the right graph of fig. 4 passes; by analogy, the s +2 circles of grids refer to the other circles of grids outside the s +1 circles of grids, that is, the grids penetrated by the red broken lines drawn at the moment t +2 in the right graph of fig. 4. s + m describes a circle of meshes, the weight of each circle of meshes is resampled (i.e., the weight selection described in step 2.3), if the circle of meshes includes the destination mesh d, the sampling can be finished, and the process is described in embodiment 2-4) more accurately, that is, a new weighted directed graph after the weight is updated is obtained after the sampling is finished.
Step 2.4 sets m to m +1, and if s + m and d coincide, obtains a weighted directed graph G (V, E, w), otherwise, returns to step 2.2.
The space-time scrolling algorithm comprises a time scrolling process and a space scrolling process, and specifically comprises the following steps:
step 3.1, running Dijkstra algorithm once based on the weighted directed graph G (V, E, w) to obtain the planning result of the upper network, including all node numbers from the node s to the node d, and expressed as p < Vs,Vd＞；
Step 3.2 Path p < Vs,VdMiddle node VsAnd its next node Vs'Constructing a lower layer network model G (v, e, w) for all roads in the tree, operating Dijkstra algorithm to obtain a lower layer path p < vs,vs'＞；
Step 3.3, updating the vehicle node s ═ s', and judging whether the condition s ═ d is satisfied, if so, ending the abstraction and weight mapping work of the network graph in the step one, wherein the abstraction and the weight mapping work are obtained through the following steps:
1) the method comprises the steps of performing rasterization operation on a road network, namely dividing the road network into grids with equal sizes, and obtaining a flow vector f ═ q for each gridN,qE,qS,qW]And average speed v, taking the grids as nodes, judging whether the nodes have connected edges or not by judging whether the roads are connected between the grids, and obtaining that the nodes have no right to haveDirecting a graph;
2) the weight setting method is as follows:
wij＝kj+li
i and j respectively represent grid numbers, k is the density in the grid, l is the path length of the longest road in the grid, and q1,q2,q3,q4And respectively representing the traffic flow flowing into adjacent grids in the north, east, south and west directions, and v is the average speed in the grids.
The deviation calculation in the step seven is obtained by the following method:
taking a node s where the vehicle is located and a destination node d as diagonal lines to obtain a minimum rectangle surrounding the current node and the destination node, and calculating according to the following formula:
where n represents the number of nodes in the rectangular network, kriRepresenting the ith grid density value, k, within the real networkpiDenotes the ith grid density value of the prediction network, and sign () denotes kriAnd kpiDegree of matching of (k)minIs a value set in advance.
Compared with the prior art, the invention can select the shortest path when the whole course traffic is smooth, and can automatically avoid the congested road section when the local congestion occurs, thereby realizing the shortest overall travel time.
Drawings
FIG. 1 is a block diagram of the system of the present invention;
FIG. 2 is a schematic diagram of density calculation in step one of the present invention;
FIG. 3 is a diagram illustrating a process of weight mapping in step one of the present invention;
FIG. 4 is a schematic diagram of stacked sampling in step three and step four of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, and the scope of the present invention is not limited to the embodiments described below.
The road network in the embodiment is a ground road network of Shanghai city, and comprises 1546 intersections and 30357 road segments. The road network is divided into 60 × 60 equal-size grids, which are numbered 1,2, …,3600 from left to right and from top to bottom, and known information includes:
1) the departure grids s, the destination grids d and the departure times T, s and d of the vehicle are grid numbers;
2) longest road section length l in gridiI 1., 3600, i denotes a grid number;
3) grid velocity v it1,2, 144, where t denotes the time of day, every 10 minutes from 00:00, i.e. t denotes the time 00:00 for t-1, 00:10 for t-2, and so on, and t denotes the time 23:50 for t-144; the calculation of the grid speed is described in detail in patent 201610686958. X;
4) grid flow fit＝[q1it,q2it,q3it,q4it]Wherein q is1it,q2it,q3it,q4itRespectively representing the flow of the adjacent grids in the north, east, south and west directions into the grid i from the time t-1 to the time t.
Based on the known information, the method comprises the following specific implementation steps:
1. upper network model abstraction
The upper network model abstraction process in this embodiment includes the following steps:
1) taking grids as nodes, the i grid is the node ViAny two adjacent nodes ViAnd VjThat is, grid i and grid j must have a common connecting edge, if there is a road communication from grid i to grid j, a common connecting edge is generated from ViPoint of direction VjConnecting edge E ofijObtaining an unweighted directed graph G (V, E);
2) calculating the traffic flow density k in each grid at the time titIs of the formula
3) Setting t moment connecting edge EijWeight value w ofijtThe calculation formula is wijt＝kjt+liAnd obtaining the weighted directed graph.
2. Stack network
The forming process of the stacked network in this embodiment is shown in fig. 4, and includes the following steps:
1) knowing the current position s, destination position d and current time T of the vehicle, the upper network G (V, E, w) of the current time is obtained according to the method in 1T) This is a real-time weighted directed graph;
2) taking the current moment as a starting point, predicting T +1,T + 2.. and T + N time global traffic status, the prediction method is the method mentioned in patent 201610686958.X, and the prediction weighted directed graph G (V, E, w) is obtainedT+1),…,G(V,E,wT+N) Initializing m value as 1;
3) will direct graph G (V, E, w)T),G(V,E,wT+1),…,G(V,E,wT+N) Stacking is carried out, the weighted directed graph G (V, E, w) at the moment T + m is selected by using the node s as the center and the weighting value of the nodes (the nodes adjacent to s) of s + m circlesT+m) The weight of (2);
4) and adding 1 to the value of m, and repeating the steps 2-3) for sampling in sequence until the sampling node reaches the destination node d. And finally, obtaining a new weighted directed graph G (V, E, w).
3. Space-time rolling algorithm
The time scrolling algorithm in this embodiment is shown in fig. 1, and the implementation steps are as follows:
1) running Dijkstra algorithm once on the weighted directed graph G (V, E, w) in the step 2 to obtain the planning result of the upper network, wherein the planning result contains all node numbers from the node s to the node d, and the node numbers are expressed as p < Vs,Vd＞；
2) Selecting path p < Vs,VdMiddle node VsAnd its next node Vs'In the method, all roads in the network are constructed by taking intersections as nodes, actual roads as connecting edges and path lengths as weights, a lower-layer network model G (v, e, w) is constructed, a Dijkstra algorithm is operated, and a lower-layer path p is obtained and is less than vs,vs'＞；
3) Updating a vehicle starting node s ═ s', judging whether a condition s ═ d is met, if so, finishing planning, otherwise, performing the step 4);
4) calculating the grid density value k at the momentriI denotes path p < Vs,VdNumbering all nodes in the node;
5) calculating the deviation between the traffic information and the predicted traffic information at the moment by the formula
And
wherein k ispiRepresents the density value, k, of grid i in the graph G (V, E, w) in step 2min＝(kri+kpi)×10％；
6) Setting a threshold value to be 0.35, comparing err obtained by calculation in the step 5) with the threshold value, returning to the step 3 and the step 2) under the space-time rolling algorithm if the err is smaller than the threshold value, and returning to the step 1) in the step 2 if the err is larger than the threshold value.
Experiments show that the dynamic path planning algorithm based on the traffic information adopted by the embodiment can ensure that the travel path is within a certain range compared with the traditional static planning algorithm, and greatly shortens the travel time under the condition of relatively congested traffic.
Claims (2)
1. A dynamic path planning method based on traffic information is characterized by comprising a network model abstraction stage, a network stacking stage and a space-time rolling algorithm stage;
in the network model abstraction stage, an actual road is converted into a network graph structure of nodes and weights, the network graph structure is divided into an upper layer network model abstraction and a lower layer network model abstraction, and the traffic flow density and the path length are comprehensively considered in weight setting; the network model abstraction phase comprises an upper network model abstraction process and a lower network model abstraction process:
an upper network model abstraction process:
the method includes the steps that firstly, actual road networks are rasterized and divided into a plurality of grids with equal sizes, each grid is taken as a node, and the ith grid is taken as a node ViAny two adjacent nodes ViAnd VjIf there is a road communication from grid i to grid j, a connection line of grid i and grid j is generatediPoint of direction VjConnecting edge E ofijObtaining an unweighted directed graph G (V, E); obtaining a flow vector f ═ q in each gridN,qE,qS,qW]And an average velocity v;
secondly, initializing a current node s, a destination node d and a current time t of the vehicle, and calculating the traffic flow density k in each grid at the time of titThe formula is as follows:
in the formula, vitIs the average velocity in the grid, q1it,q2it,q3it,q4itRespectively representing the traffic flow flowing into adjacent grids in the north, east, south and west directions;
thirdly, obtaining a weighted directed graph G (V, E, w) through weight mappingt)，
In the formula, the t time is connected with the edge EijWeight value w ofij＝kj+li
Lower layer network model abstraction:
fourthly, taking intersections as nodes, connecting the intersections as connecting edges, and taking the weight as the path length to obtain a lower-layer network model G (v, e, w);
the network stacking stage integrates the real-time traffic information and the predicted traffic information with a plurality of step lengths to obtain a final network model;
the space-time rolling algorithm stage comprises time rolling and space rolling processes, and refreshes traffic states according to a certain time interval to realize a dynamic planning algorithm;
the space-time scrolling algorithm comprises a time scrolling process and a space scrolling process, and specifically comprises the following steps:
step 3.1, running Dijkstra algorithm once based on the weighted directed graph G (V, E, w) to obtain the planning result of the upper network, including all node numbers from the node s to the node d, and expressed as p < Vs,Vd＞；
Step 3.2 Path p < Vs,VdMiddle node VsAnd its next node Vs'Constructing a lower layer network model G (v, e, w) for all roads in the tree, operating Dijkstra algorithm to obtain a lower layer path p < vs,vs'＞；
Step 3.3, updating the vehicle node s ═ s', judging whether the condition s ═ d is met, if yes, finishing planning, otherwise, entering step 3.4);
step 3.4) setting the current grid density value kriI denotes path p < Vs,VdNumbering all nodes in the node;
step 3.5) calculating the deviation err of the current traffic information and the predicted traffic information, wherein the formula is as follows:
in the formula, kpiRepresents the density value, k, of grid i in the graph G (V, E, w) in step 2min＝(kri+kpi)×10％
Step 3.6) setting a threshold, if the deviation err is smaller than the threshold, returning to step 3.2, and if the deviation err is larger than the threshold, returning to step 2.1.
2. The method of claim 1, wherein the stacking sampling phase comprises:
step 2.1, making m equal to 1;
step 2.2 taking the current time T as a starting point to predict T +1,The global traffic state at the time T + n is used for obtaining a prediction weighted directed graph G (V, E, w)T+1),…,G(V,E,wT+N) N represents a time interval;
step 2.3 weighted prediction directed graph G (V, E, w)T+1),…,G(V,E,wT+N) Stacking, taking the current position s as the center, and selecting the weighted directed graph G (V, E, w) at the moment of T + m by using the node weight of s + m circlesT+m) The weight of (2);
step 2.4 sets m to m +1, and if s + m and d coincide, obtains a weighted directed graph G (V, E, w), otherwise, returns to step 2.2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910225789.3A CN110009906B (en) | 2019-03-25 | 2019-03-25 | Dynamic path planning method based on traffic prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910225789.3A CN110009906B (en) | 2019-03-25 | 2019-03-25 | Dynamic path planning method based on traffic prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110009906A CN110009906A (en) | 2019-07-12 |
| CN110009906B true CN110009906B (en) | 2021-07-27 |
Family
ID=67167935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910225789.3A Active CN110009906B (en) | 2019-03-25 | 2019-03-25 | Dynamic path planning method based on traffic prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110009906B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782178B (en) * | 2019-11-01 | 2020-11-06 | 北京航空航天大学 | Traffic network planning aid decision-making method and device |
| CN111415048B (en) * | 2020-04-10 | 2024-04-19 | 大连海事大学 | Vehicle path planning method based on reinforcement learning |
| CN111768624B (en) * | 2020-06-30 | 2022-02-15 | 北京百度网讯科技有限公司 | Traffic facility control method, device, equipment and medium |
| CN114283575B (en) * | 2020-09-27 | 2023-02-07 | 上海交通大学 | Signal lamp intersection queuing length estimation method based on video monitoring data |
| CN112629533B (en) * | 2020-11-11 | 2023-07-25 | 南京大学 | Fine path planning method based on road network rasterization road traffic prediction |
| CN112529254B (en) * | 2020-11-19 | 2022-11-25 | 歌尔股份有限公司 | Path planning method and device and electronic equipment |
| CN112687106B (en) * | 2021-03-11 | 2021-07-13 | 杭州电子科技大学 | Path optimization method based on traffic road network dynamic and static comprehensive model |
| CN115311856B (en) * | 2022-08-04 | 2023-12-26 | 广西新发展交通集团有限公司 | Judgment method for traffic control of important nodes of road network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005055974A (en) * | 2003-08-06 | 2005-03-03 | Zuken Inc | Method, device, and program for calculating current path, method, device, and program for calculating dc resistance value, and computer-readable recording medium |
| CN101739817A (en) * | 2009-11-26 | 2010-06-16 | 西北工业大学 | Shortest path planning method for dynamic origins |
| CN103994768A (en) * | 2014-05-23 | 2014-08-20 | 北京交通大学 | Method for seeking for overall situation time optimal path under dynamic time varying environment |
| CN105841709A (en) * | 2016-03-22 | 2016-08-10 | 吉林大学 | Method for planning car driving path |
| CN107944605A (en) * | 2017-11-10 | 2018-04-20 | 河海大学常州校区 | A kind of dynamic traffic paths planning method based on data prediction |
-
2019
- 2019-03-25 CN CN201910225789.3A patent/CN110009906B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005055974A (en) * | 2003-08-06 | 2005-03-03 | Zuken Inc | Method, device, and program for calculating current path, method, device, and program for calculating dc resistance value, and computer-readable recording medium |
| CN101739817A (en) * | 2009-11-26 | 2010-06-16 | 西北工业大学 | Shortest path planning method for dynamic origins |
| CN103994768A (en) * | 2014-05-23 | 2014-08-20 | 北京交通大学 | Method for seeking for overall situation time optimal path under dynamic time varying environment |
| CN105841709A (en) * | 2016-03-22 | 2016-08-10 | 吉林大学 | Method for planning car driving path |
| CN107944605A (en) * | 2017-11-10 | 2018-04-20 | 河海大学常州校区 | A kind of dynamic traffic paths planning method based on data prediction |
Non-Patent Citations (3)
| Title |
|---|
| Short Term Diverging Traffic Flow Prediction based on ImF-VOMM Method;Xiangxiang Yu, Dewei Li, Yugeng Xi;《Proceedings of the 37th Chinese Control Conference》;20180627;第4351-4356页 * |
| 基于交通流量预测的动态最优路径规划研究;刘智琦，李春贵，陈波;《广西工学院学报》;20120630;第23卷(第2期);第41-45页 * |
| 基于动态交通的最短时间路径规划方法研究;向冬梅，陈树辉;《管控一体化》;20120930;第28卷(第9期);第317-319页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110009906A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110009906B (en) | Dynamic path planning method based on traffic prediction | |
| CN109959388B (en) | Intelligent traffic refined path planning method based on grid expansion model | |
| AU2020203551A1 (en) | Dynamically determining origin and destination locations for a network system | |
| CN109724611A (en) | Paths planning method, device, electronic equipment and storage medium | |
| Alazab et al. | An optimal transportation routing approach using GIS-based dynamic traffic flows | |
| JP2002259888A (en) | Simulation control program, method and device | |
| Zhao et al. | Dynamic path planning of emergency vehicles based on travel time prediction | |
| CN106017496A (en) | Real-time navigation method based on road condition | |
| WO2023276420A1 (en) | Distributed multi-task machine learning for traffic prediction | |
| KR20230057558A (en) | Short-term traffic flow prediction method and device using deep learning | |
| CN113516277A (en) | Network connection intelligent traffic path planning method based on dynamic pricing of road network | |
| Wei et al. | A knowledge-based problem solving method in GIS application | |
| Ahmed et al. | Mobile-based Routes Network Analysis for Emergency Response Using an Enhanced Dijkstra's Algorithm and AHP. | |
| Menguc et al. | A data driven approach to forecasting traffic speed classes using extreme gradient boosting algorithm and graph theory | |
| Zavin et al. | Towards developing an intelligent system to suggest optimal path based on historic and real-time traffic data | |
| CN111008730B (en) | Crowd concentration prediction model construction method and device based on urban space structure | |
| CN106651010A (en) | Shortest path-based network division method | |
| Habibi et al. | An Intelligent Traffic Light Scheduling Algorithm by using fuzzy logic and gravitational search algorithm and considering emergency vehicles | |
| CN107679653B (en) | OD distribution method based on dominant travel distance | |
| CN110674990A (en) | Instant delivery path selection method and system with sliding window updating mechanism | |
| Yang et al. | GIS‐Based Analysis of Railway’s Origin/Destination Path‐Selecting Behavior | |
| Liu et al. | A benchmark generator for dynamic capacitated arc routing problems | |
| Xie et al. | A network condition-centric flow selection and rerouting strategy to mitigate air traffic congestion under uncertainties | |
| Pan et al. | A Discussion on the Evolution of the Pathfinding Algorithms | |
| Pang et al. | Transit route planning for megacities based on demand density of complex networks |
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 |