CN109959388A - A kind of intelligent transportation fining paths planning method based on grid extended model - Google Patents
A kind of intelligent transportation fining paths planning method based on grid extended model Download PDFInfo
- Publication number
- CN109959388A CN109959388A CN201910278787.0A CN201910278787A CN109959388A CN 109959388 A CN109959388 A CN 109959388A CN 201910278787 A CN201910278787 A CN 201910278787A CN 109959388 A CN109959388 A CN 109959388A
- Authority
- CN
- China
- Prior art keywords
- grid
- road
- time
- path
- intelligent transportation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 10
- 238000007670 refining Methods 0.000 claims abstract 2
- 239000011159 matrix material Substances 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 5
- 230000002123 temporal effect Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 239000002243 precursor Substances 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 abstract description 2
- 230000006698 induction Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009022 nonlinear effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
-
- 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)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
Intelligent transportation based on grid extended model refines paths planning method, the intelligent transportation fining paths planning method based on grid extended model is the following steps are included: step 1: based on real-time traffic information of road and historical information, using convolutional neural networks, the traffic condition of following a period of time is predicted;Step 2: according to road network structure and traffic density, in conjunction with starting point, as unit of roadway element, dynamic expansion grid;Step 3: carrying out refining minute yardstick pathfinding in grid, recommend traveling scheme inside grid to re-start prediction and planning when vehicle will be driven out to grid, until arriving at terminal.Compared to traditional path planning algorithm, present invention combination vehicle actual travel process is dynamically divided region and is carried out fine path planning using the thought of segment-and-region-based, the time that system single calculation can be efficiently reduced realizes efficient intelligent transportation induction and navigation.
Description
Technical field
The invention belongs to field of intelligent transportation technology, are related to traffic information predicting, grating map extension and optimal path
The method of planning.
Background technique
Nowadays, wisdom traffic signalling technique, processing technique are increasingly mature, and wisdom traffic is having many applications, state in recent years
Interior multiple urban construction are simultaneously equipped with " traffic brain ".In face of the dynamic and complexity of traffic information, intelligent transportation system is active
State obtains information and is used for optimal path computation, and then faces traffic above-ground demand, to alleviate traffic congestion, be provided using traffic
Source reduces traffic accident influence, reduces environmental pollution and improves production efficiency, brings a series of economic results in society.Vehicle
Navigation system be in intelligent transportation system one be in urgent need, widely used important system, it is capable of providing vehicle location, road
The critical functions such as diameter planning, Route guiding, integrated information service.
Path planning is the major issue in Vehicular navigation system.Traditional method only considers the static state from origin-to-destination
Shortest path, however traffic condition will affect practical driving experience in real time.To in practical applications, show and such as count
Calculate the problems such as validity is reduced because of the variation of traffic condition, long range path planning speed is slower.In active path planning,
On the one hand we need to make corresponding adjustment to path planning according to situations such as road upkeep, congestion;On the other hand, it is also desirable to
Calculating speed is improved, provides routing information in time.
By the retrieval discovery to existing literature, R.Rajagopalan et al. was in " IEEE Transactions in 2008
On Aerospace and Electronic Systems (IEEE Aerospace And Electronic Systems transactions) " deliver it is entitled
" the Hierarchical path computation approach for large graphs (hierarchical path of a wide range of map
Calculation method) " article in, propose a kind of hierarchical path planning algorithm.By the way that a big figure is divided into smaller son
Figure, is stored in advance the optimal path of subgraph internal boundary points, by the search of the minimal-overhead between subgraph boundary point, determines optimal road
Diameter.But this method, which needs to safeguard, largely to be precalculated, and there is excessive storage overhead in the path in subgraph.
It also found by the retrieval to existing literature, G.R.Jagadeesh et al. 2002 in " IEEE
Transactions on Intelligent Transportation Systems (IEEE intelligent transportation system journal) " on send out
Entitled " the Heuristic Techniques for Accelerating Hierarchical Routing on Road of table
Networks (for accelerating the heuristic technique of hierarchy of road network path planning) ".This article first pays close attention to main traffic artery and big
Type crossing, plans secondary road and crossing again later, and algorithm complexity can be effectively reduced in this.But in actual traffic network,
Optimal path is usually related with the departure time, and certain arterial highways in road network can get congestion in rush hour, so that this acceleration
The result of technology is invalid.
In conclusion problem of the existing technology is: (1) can not be advised in conjunction with real-time dynamic road condition information to outbound path
It draws.(2) higher cost is calculated, computational efficiency is poor.Compared with prior art, the present invention has the beneficial effect that: firstly, this is based on
The intelligent transportation fining paths planning method of grid extended model can quickly and efficiently provide dynamic navigation scheme;Secondly,
Grid extended model is one of outstanding contributions of the invention;Again, this programme can accomplish timely the congestion of road
Reaction, effectively realization traffic guidance.The present invention can provide path planning in conjunction with real-time dynamic road condition information.It reduces and calculates cost,
Improve computational efficiency.According to the development of current intelligent transport technology, path planning scheme can be more scientifically and rationally provided, is alleviated
Traffic congestion makes full use of traffic resource, promotes the development of dynamic airmanship.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of intelligent transportation based on grid extended model is fine
Change paths planning method.The present invention can provide path planning in conjunction with real-time dynamic road condition information.It reduces and calculates cost, improve and calculate
Efficiency.According to the development of current intelligent transport technology, path planning scheme can be more scientifically and rationally provided, alleviates traffic and gathers around
It blocks up, make full use of traffic resource, promote the development of dynamic airmanship.
The invention is realized in this way the intelligent transportation based on grid extended model refines paths planning method, including
Following steps:
Step 1: based on real-time traffic information of road and historical information, using convolutional neural networks, prediction future one
The traffic condition of section time;
Step 2: according to road network structure and traffic density, in conjunction with starting point, as unit of roadway element, dynamic expansion grid;
Step 3: minute yardstick pathfinding in grid is carried out, recommends to travel scheme inside grid, when vehicle will be driven out to grid,
The first step is returned, prediction and planning are re-started, until arriving at terminal.
Further, the traffic information is the number of vehicle on every road, and the traffic information at each moment can reconstruct
The traffic information matrix of squarely matrix, history is combined into a tensor in turn.
Further, the roadway element is the boundary for being divided into different enclosed regions by road, including corresponding road with
Crossing.
Further, dynamic expansion grid includes being extended along the unit of terminal direction two sides in the step 2, every time
Select the unit close apart from terminal for expanding element, using certain traffic density as extension termination condition.
Further, minute yardstick pathfinding is based on time shortest optimal path algorithm, wherein passing through every in the grid
Time used in road can obtain in conjunction with the predictive information of step 1 with road network structure.
Further, the grid extended dynamic paths planning method plans the optimal road for only needing to plan in grid every time
Diameter, it is not required that disposable planning is from the path of origin-to-destination, to require algorithm complexity lower.
Compared with prior art, the present invention has the beneficial effect that: firstly, should be based on the intelligent transportation essence of grid extended model
Refinement path planing method can quickly and efficiently provide the traveling scheme of following a period of time;Secondly, grid extension is this
One of outstanding contributions of invention;Again, the congestion of road is accomplished timely to react.The present invention can combine real-time dynamic road
Condition information provides path planning.It reduces and calculates cost, improve computational efficiency.It, can be more according to the development of current intelligent transport technology
Add and scientifically and rationally provide path planning scheme, alleviate traffic congestion, make full use of traffic resource, promotes dynamic airmanship hair
Exhibition.
Detailed description of the invention
Fig. 1 is grid extended scene figure used by the embodiment of the present invention.
Fig. 2 is that traffic information predicting algorithm of the embodiment of the present invention realizes block diagram.
Fig. 3 is that identification roadway element algorithm of the embodiment of the present invention realizes block diagram.
Fig. 4 is that minute yardstick path planning algorithm realizes block diagram in grid of the embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to of the invention
Embodiment elaborates: the present embodiment is implemented under the premise of the technical scheme of the present invention, gives detailed implementation
Mode and specific operating process.It should be appreciated that specific example described herein is only used to explain the present invention, but the present invention
Protection scope be not limited to the following embodiments.
Embodiment
The present embodiment uses the map scene of Fig. 1, and it is fine to propose a kind of intelligent transportation based on grid extended model
Change paths planning method.The elementary object of the present embodiment is that it is shortest dynamically to provide the used time for given origin-to-destination
Path.
Regard road network as an oriented plane figure G=(V, E), wherein each point in V indicates the intersection of road network.If E
Middle connection vxWith vyThe link length of two o'clock is l, is denoted as (vx,vy,l).The path starting point that we need to plan is vsPoint, terminal are
vePoint, thus vectorFor the general orientation of our traveling.
On every road, the vehicle for entering and being driven out to this road is perceived by existing technical approach, is obtained
To the number of the vehicle on every road.In t-th of time interval, in vxvyOn road and from vxDrive towards vyNumber of vehicles
It is denoted as nt(vy,vx).If road vxvyFor from vxTo vyOne-way road, then nt(vy,vx)=0.To in t time interval
In, vxvyTotal vehicle number N on roadt(vx,vy)=nt(vx,vy)+nt(vy,vx).In t-th of time interval, in all roads
On vehicle number can be reconstructed into the matrix F of M × Nt∈RM×N, referred to as traffic information matrix.The traffic information matrix of history is in turn
It is combined into a tensor { Fh| h=t, t-1 ..., t-l }, to predict { F according to this tensor firstk| k=t+1, t+2 ..., t
+s}。
In order to learn the temporal correlation of number of vehicles on road, convolutional neural networks are applied to this learning tasks
In, specific algorithm realizes that block diagram is as shown in Figure 2.In order to preferably extract input historical traffic information matrix information, no
Loss marginal information is caused, filling is originally inputted the edge of matrix, obtains input tensor a1.The network that we use removes input layer
Outside, there are five hidden layers, are followed successively by convolutional layer 1, pond layer 1, convolutional layer 2, pond layer 2, full articulamentum.Wherein, in convolutional layer
Comprising convolution nuclear parameter W, b, which connects each output with local value.Pond layer 1,2 compresses the tensor of input, mentions
Take feature.Convolutional layer 1 has 256 hidden units, and pond layer 1 has 128 hidden units, and convolutional layer 2 has 64 hidden units, pond
Changing layer 2 has 2 hidden units.It is finally full articulamentum, using the structure of common deep neural network.Convolutional neural networks are adopted
Learn temporal correlation from the historical traffic information matrix of input with the mode of supervised learning.Loss function when training CNN
For ground truth Fk(i, j) and predicted traffic information situationBetween mean square error (MSE) be
Then in conjunction with existing real data, predicted.
The accuracy of combination algorithm and time-consuming, 40 minutes traffic information datas before use, T=10 minutes future of prediction
Traffic information.Specific time span can be adjusted in conjunction with the traffic feature in area.
Using the traffic information of this region entirety, grid extension and path planning are carried out.The end of grid extension is determined first
Only condition.For a pair of of starting point vsWith terminal ve, with starting point vsCentered on, positive northeast and positive southwestward are line of demarcation 1, with just
Northwest and positive southeastern direction are line of demarcation 2, obtain four regions.In Fig. 1, terminal veThe region in east is fallen in, then delimit one just
Square region, this square is using North and South direction as a line, starting point vsThe midpoint on side thus, Directional Extension side length is a=V eastwards
The square area of × T.The region of this square is thresholding region.With the average density D in this region0As
The termination condition of grid extension.
During automobile actual travel, before reaching a certain crossing, it is only necessary to select in the clear direction at this crossing
It selects, to need to calculate the direction selection at this crossing.The selection of grid is carried out along feasible direction at this crossing.Road
Road unit is the boundary for being divided into different enclosed regions by road, including corresponding road and crossing.In the four crossway of Fig. 1 starting point
Mouthful, feasible roadway element is 1. unit B that the unit A that the road turned right and kept straight on surrounds is surrounded with the road of left-hand rotation and straight trip
1. this is two the smallest grids.
When choosing roadway element, by the way of breadth first traversal.When take determined stretch section after, ask this section
Starting point A and end point B.All K sides with end point B for an endpoint are found, fixed section and this K side point will be taken
New path is not established, judges whether starting point A is identical as another endpoint on every new addition side.Then finding one if they are the same can
Otherwise capable grid continues to traverse to the new route provided.When identifying roadway element, the situation of possible grid nesting, if certain
When Unit one includes point all in another unit, biggish grid is deleted, feasible roadway element can be obtained.
In order to consider subsequent section, two the smallest grids are extended along terminal direction.Use the city with terminal
(also referred to as manhatton distance, distance of the two o'clock in North and South direction is plus the distance on east-west direction, i.e. d for city block distance
(va,ve)=| xa-xe|+|ya-ye|) it is used as Distance evaluation function h (va).When extension, the single channel unit of selection and former grid are extremely
Rare a line is overlapped, and includes a h (va') relatively small point.Example as shown in figure 1 A 1., alternative roadway element be northwest,
Northeast and the unit of the southeast three, the Distance evaluation of these three roadway elements is respectively 4.4,3.9,3.8, selects wherein lesser list
2. member is simultaneously labeled as A.Grid average traffic current density at this time is calculated, if reaching threshold value D0, or terminal is expanded to, or reach area
Domain boundary stops calculating.Conversely, then continuing to extend.
After obtaining grid, the path planning model of minute yardstick is carried out.By the prediction technique of front, available each section
On traffic current density.It uses for reference the relational model of various traffic current densitys and car speed and combines China's condition of road surface, it can be with
(the paper Nonlinear Effects in the delivered see G.F.Newell in 1961 is calculated using Newell model
Dynamics of Car Following), road speeds are calculated with following formula
Wherein, volfFor free stream velocity, kjFor jam density, parameter calibration can be carried out according to actual cities road conditions.It is right
In in vxvyOn vehicle, calculate pass through this road time-consuming time (vx,vy)=l (vx,vy)/vol(vx,vy).To obtain path
Plan model.Node v will be reachedmWhen, based on time shortest routing update, steps are as follows:
Weight time (the v on Step1 update sidem,vm+1), save v in queue Pathm+1Posterior nodal point set PT;
Node set S={ the v of the shortest time path known to Step2m, the node set U=of unknown the shortest time path
V-S, vmInto V, the known shortest time array TM of all nodes is (if vmWith certain vertex viThere are side, TM [i]=time (vm,vi);
If viIt is not vmAdjacent node, TM [i]=∞;TM [m]=0);The precursor array P of each node on the shortest time path;
Step3 chooses the smallest node v of a TM value from Uj, it is added into S that (the selected time is exactly vmTo vj
Shortest time);
Step4 investigates each vjAdjacent node: with vkFor, if TM (k) > TM [j]+time (vj,vk), then TM
(k)=TM [j]+time (vj,vk), update P;
Step5 judgement, if vj=vn, algorithm terminates, and exports v0To vnThe shortest time path queue PathNew;If
vj∈ PL exports vsTo veThe shortest time path queue PathNew and vjTo veThe shortest time path queue Path;
Step6 returns to Step1.
Vehicle can be travelled along recommendation paths.When automobile has passed through penultimate fork, if not reaching home,
Prediction steps are then returned, continue to calculate in real time.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of intelligent transportation based on grid extended model refines paths planning method, it is characterised in that: described to be based on grid
Lattice extended model intelligent transportation fining paths planning method the following steps are included:
Step 1: based on real-time traffic information of road and historical information, using convolutional neural networks, when prediction is one section following
Between traffic condition;
Step 2: according to road network structure and traffic density, in conjunction with starting point, as unit of roadway element, dynamic expansion grid;
Step 3: carrying out refining minute yardstick pathfinding in grid, recommend to travel scheme inside grid, when vehicle will be driven out to grid
When, the first step is returned, prediction and planning are re-started, until arriving at terminal.
2. a kind of intelligent transportation based on grid extended model as described in claim 1 refines paths planning method, special
Sign is: the traffic information is the number of vehicle on every road, and the traffic information at each moment can reconstruct squarely square
The traffic information matrix of battle array, history is combined into a tensor in turn.
3. a kind of intelligent transportation based on grid extended model as described in claim 1 refines paths planning method, special
Sign is: the roadway element is the boundary for being divided into different enclosed regions by road, including corresponding road and crossing.
4. a kind of intelligent transportation based on grid extended model as described in claim 1 refines paths planning method, special
Sign is: dynamic expansion grid includes being extended along the unit of terminal direction two sides in the step 2, selects distance every time
The close unit of terminal is expanding element, using certain traffic density as extension termination condition.
5. a kind of intelligent transportation based on grid extended model as described in claim 1 refines paths planning method, special
Sign is: minute yardstick pathfinding is based on time shortest optimal path algorithm, wherein by used in every road in the grid
Time can obtain in conjunction with the predictive information of step 1 with road network structure.
6. a kind of intelligent transportation based on grid extended model as described in claim 1 refines paths planning method, special
Sign is: the grid extended dynamic paths planning method is planned every time only to be needed to plan the optimal path in grid, and should not
Ask disposable planning from the path of origin-to-destination, to require algorithm complexity lower.
7. a kind of intelligent transportation based on grid extended model as described in one of claim 1-6 refines path planning side
Method, it is characterised in that: in order to learn the temporal correlation of number of vehicles on road, convolutional neural networks are by application, filling is gone through
History traffic information is originally inputted the edge of matrix, obtains input tensor a1;Convolutional neural networks are removed outside input layer, and there are five hidden
Layer is hidden, convolutional layer, the first pond layer, convolutional layer, the second pond layer, full articulamentum are followed successively by;It wherein, include convolution in convolutional layer
Nuclear parameter W, b, the kernel connect each output with local value;The one the second pond layers compress the tensor of input, extract
Feature;Convolutional neural networks learn temporal correlation from the historical traffic information matrix of input by the way of supervised learning;
Loss function when training CNN is ground truth Fk(i, j) and predicted traffic information situationBetween mean square error
Poor (MSE) is
Then in conjunction with existing real data, predicted.
8. a kind of intelligent transportation based on grid extended model as described in claim 1 refines paths planning method, special
Sign is: using the traffic information of this region entirety, carrying out grid extension and path planning;The termination of grid extension is determined first
Condition;For a pair of of starting point vsWith terminal ve, with starting point vsCentered on, positive northeast and positive southwestward are line of demarcation 1, with due west
Northern and positive southeastern direction is line of demarcation 2, obtains four regions;As terminal veThe region in east is fallen in, then delimit a square region
Domain, this square is using North and South direction as a line, starting point vsThe midpoint on side thus, Directional Extension side length is a=V × T's eastwards
Square area;The region of this square is thresholding region;Expanded using the average density in this region as grid
The termination condition of exhibition.
9. a kind of intelligent transportation based on grid extended model as claimed in claim 8 refines paths planning method, special
Sign is: during automobile actual travel, before reaching a certain crossing, it is only necessary to select in the clear direction at this crossing
It selects, to need to calculate the direction selection at this crossing;The selection of grid is carried out along feasible direction at this crossing;Road
Road unit is the boundary for being divided into different enclosed regions by road, including corresponding road and crossing;
In the crossroad of starting point, feasible roadway element be turn right with the unit A that surrounds of road of straight trip 1. with turn left with it is straight
1., this is two the smallest grids to the unit B that capable road surrounds;When choosing roadway element, using breadth first traversal
Mode: when take determined stretch section after, ask the starting point A and end point B in this section;It finds with end point B as an endpoint
All K sides, fixed section and this K side will be taken to establish new path respectively, judge starting point A and every new addition side
Whether another endpoint is identical;A feasible grid is then found if they are the same, otherwise the new route provided is continued to traverse;It is identifying
When roadway element, the situation of possible grid nesting deletes biggish grid if a certain unit includes point all in another unit
Feasible roadway element can be obtained in lattice;
In order to consider subsequent section, two the smallest grids are extended along terminal direction.Use the city street with terminal
Offset is from (also referred to as manhatton distance, distance of the two o'clock in North and South direction is plus the distance on east-west direction, i.e. d (va,
ve)=| xa-xe|+|ya-ye|) it is used as Distance evaluation function h (va);When extension, the single channel unit of selection and former grid are at least
A line is overlapped, and includes a h (va') relatively small point;Computation grid average traffic current density if reaching threshold value, or expands
Terminal is opened up, or reaches zone boundary, stops calculating;Conversely, then continuing to extend.
10. a kind of intelligent transportation based on grid extended model as claimed in claim 8 refines paths planning method, special
Sign is: after obtaining grid, carrying out the path planning model of minute yardstick;By the prediction technique of front, road speed is calculated with following formula
Degree
Wherein, volfFor free stream velocity, kjFor jam density, parameter calibration is carried out according to actual cities road conditions;For in vxvy
On vehicle, calculate pass through this road time-consuming time (vx,vy)=l (vx,vy)/vol(vx,vy);To obtain path planning mould
Type;
Node v will be reachedmWhen, based on time shortest routing update, steps are as follows:
Weight time (the v on Step1 update sidem,vm+1), save v in queue Pathm+1Posterior nodal point set PT;
Node set S={ the v of the shortest time path known to Step2m, the node set U=V-S, v of unknown the shortest time pathm
Into V, the known shortest time array TM of all nodes is (if vmWith certain vertex viThere are side, TM [i]=time (vm,vi);If viNo
It is vmAdjacent node, TM [i]=∞;TM [m]=0);The precursor array P of each node on the shortest time path;
Step3 chooses the smallest node v of a TM value from Uj, it is added into S, which is exactly vmTo vjMost
Short time;
Step4 investigates each vjAdjacent node: with vkFor, if TM (k) > TM [j]+time (vj,vk), then TM (k)=TM
[j]+time(vj,vk), update P;
Step5 judgement, if vj=vn, algorithm terminates, and exports v0To vnThe shortest time path queue PathNew;If vj∈
PL exports vsTo veThe shortest time path queue PathNew and vjTo veThe shortest time path queue Path;
Step6 returns to Step1;
Vehicle can be travelled along recommendation paths;When automobile has passed through penultimate fork, if not reaching home, return
Prediction steps are returned, continue to calculate in real time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910278787.0A CN109959388B (en) | 2019-04-09 | 2019-04-09 | Intelligent traffic refined path planning method based on grid expansion model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910278787.0A CN109959388B (en) | 2019-04-09 | 2019-04-09 | Intelligent traffic refined path planning method based on grid expansion model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109959388A true CN109959388A (en) | 2019-07-02 |
CN109959388B CN109959388B (en) | 2023-03-14 |
Family
ID=67025877
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910278787.0A Active CN109959388B (en) | 2019-04-09 | 2019-04-09 | Intelligent traffic refined path planning method based on grid expansion model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109959388B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110364010A (en) * | 2019-08-22 | 2019-10-22 | 三星电子(中国)研发中心 | A kind of navigation methods and systems of predicting road conditions |
CN110598999A (en) * | 2019-08-21 | 2019-12-20 | 广东方纬科技有限公司 | Traffic travel analysis method, system and storage medium based on individual data |
CN111337044A (en) * | 2020-03-24 | 2020-06-26 | 北京交通发展研究院 | Urban road path planning method based on traffic weight |
CN111397625A (en) * | 2020-03-30 | 2020-07-10 | 腾讯科技(深圳)有限公司 | Vehicle navigation method and related device |
CN111623790A (en) * | 2020-05-26 | 2020-09-04 | 武汉大学深圳研究院 | Rapid path planning method for dynamic urban traffic network |
CN112504947A (en) * | 2020-12-03 | 2021-03-16 | 中国人民解放军陆军军医大学第二附属医院 | Morphological analysis and counting method for peripheral blood cells |
CN112629533A (en) * | 2020-11-11 | 2021-04-09 | 南京大学 | Refined path planning method based on road network rasterization road traffic flow prediction |
CN112669642A (en) * | 2020-12-22 | 2021-04-16 | 华东师范大学 | Dynamic path planning algorithm and system based on passing time and vehicle speed prediction |
CN112817316A (en) * | 2021-01-04 | 2021-05-18 | 浙江大学 | Multi-robot path planning method and device |
CN113029151A (en) * | 2021-03-15 | 2021-06-25 | 齐鲁工业大学 | Intelligent vehicle path planning method |
CN113283075A (en) * | 2021-05-21 | 2021-08-20 | 南京大学 | Large-scale satellite scene-oriented lightweight simulation architecture design method |
CN113516277A (en) * | 2021-04-13 | 2021-10-19 | 南京大学 | Network connection intelligent traffic path planning method based on dynamic pricing of road network |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0935183A (en) * | 1995-07-14 | 1997-02-07 | Hitachi Ltd | Dynamic route searching method and navigation device |
US20090043486A1 (en) * | 2007-07-27 | 2009-02-12 | Chaowei Yang | Near Real-time Traffic Routing |
CN105355044A (en) * | 2015-10-27 | 2016-02-24 | 山东大学 | Dynamic expression method of urban traffic road network grid lock transmission based on GIS |
CN106846805A (en) * | 2017-03-06 | 2017-06-13 | 南京多伦科技股份有限公司 | A kind of dynamic road grid traffic needing forecasting method and its system |
US20170254653A1 (en) * | 2016-03-01 | 2017-09-07 | Alibaba Group Holding Limited | System and Method of Navigation |
CN108847037A (en) * | 2018-06-27 | 2018-11-20 | 华中师范大学 | A kind of city road network paths planning method towards non-global information |
-
2019
- 2019-04-09 CN CN201910278787.0A patent/CN109959388B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0935183A (en) * | 1995-07-14 | 1997-02-07 | Hitachi Ltd | Dynamic route searching method and navigation device |
US20090043486A1 (en) * | 2007-07-27 | 2009-02-12 | Chaowei Yang | Near Real-time Traffic Routing |
CN105355044A (en) * | 2015-10-27 | 2016-02-24 | 山东大学 | Dynamic expression method of urban traffic road network grid lock transmission based on GIS |
US20170254653A1 (en) * | 2016-03-01 | 2017-09-07 | Alibaba Group Holding Limited | System and Method of Navigation |
CN106846805A (en) * | 2017-03-06 | 2017-06-13 | 南京多伦科技股份有限公司 | A kind of dynamic road grid traffic needing forecasting method and its system |
CN108847037A (en) * | 2018-06-27 | 2018-11-20 | 华中师范大学 | A kind of city road network paths planning method towards non-global information |
Non-Patent Citations (1)
Title |
---|
顾国民: ""城市综合应急指挥***的车辆路径规划研究与实现"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110598999A (en) * | 2019-08-21 | 2019-12-20 | 广东方纬科技有限公司 | Traffic travel analysis method, system and storage medium based on individual data |
CN110598999B (en) * | 2019-08-21 | 2022-05-10 | 广东方纬科技有限公司 | Traffic travel analysis method, system and storage medium based on individual data |
CN110364010A (en) * | 2019-08-22 | 2019-10-22 | 三星电子(中国)研发中心 | A kind of navigation methods and systems of predicting road conditions |
CN111337044A (en) * | 2020-03-24 | 2020-06-26 | 北京交通发展研究院 | Urban road path planning method based on traffic weight |
CN111397625A (en) * | 2020-03-30 | 2020-07-10 | 腾讯科技(深圳)有限公司 | Vehicle navigation method and related device |
CN111623790B (en) * | 2020-05-26 | 2022-04-12 | 武汉大学深圳研究院 | Rapid path planning method for dynamic urban traffic network |
CN111623790A (en) * | 2020-05-26 | 2020-09-04 | 武汉大学深圳研究院 | Rapid path planning method for dynamic urban traffic network |
CN112629533A (en) * | 2020-11-11 | 2021-04-09 | 南京大学 | Refined path planning method based on road network rasterization road traffic flow prediction |
CN112629533B (en) * | 2020-11-11 | 2023-07-25 | 南京大学 | Fine path planning method based on road network rasterization road traffic prediction |
CN112504947A (en) * | 2020-12-03 | 2021-03-16 | 中国人民解放军陆军军医大学第二附属医院 | Morphological analysis and counting method for peripheral blood cells |
CN112669642A (en) * | 2020-12-22 | 2021-04-16 | 华东师范大学 | Dynamic path planning algorithm and system based on passing time and vehicle speed prediction |
CN112817316A (en) * | 2021-01-04 | 2021-05-18 | 浙江大学 | Multi-robot path planning method and device |
CN112817316B (en) * | 2021-01-04 | 2022-03-15 | 浙江大学 | Multi-robot path planning method and device |
CN113029151A (en) * | 2021-03-15 | 2021-06-25 | 齐鲁工业大学 | Intelligent vehicle path planning method |
CN113516277A (en) * | 2021-04-13 | 2021-10-19 | 南京大学 | Network connection intelligent traffic path planning method based on dynamic pricing of road network |
CN113516277B (en) * | 2021-04-13 | 2023-10-17 | 南京大学 | Internet intelligent traffic path planning method based on road network dynamic pricing |
CN113283075A (en) * | 2021-05-21 | 2021-08-20 | 南京大学 | Large-scale satellite scene-oriented lightweight simulation architecture design method |
CN113283075B (en) * | 2021-05-21 | 2023-11-03 | 南京大学 | Lightweight simulation architecture design method for large-scale satellite scene |
Also Published As
Publication number | Publication date |
---|---|
CN109959388B (en) | 2023-03-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109959388A (en) | A kind of intelligent transportation fining paths planning method based on grid extended model | |
CN109000668B (en) | Real-time intelligent navigation method based on Internet of vehicles | |
CN107944605B (en) | Dynamic traffic path planning method based on data prediction | |
CN104157139B (en) | A kind of traffic congestion Forecasting Methodology and method for visualizing | |
KR20150128712A (en) | Lane-level vehicle navigation for vehicle routing and traffic management | |
CN109612488B (en) | Big data micro-service-based mixed travel mode path planning system and method | |
CN106017496A (en) | Real-time navigation method based on road condition | |
CN109191852B (en) | Vehicle-road-cloud cooperative traffic flow situation prediction method | |
CN112991743B (en) | Real-time traffic risk AI prediction method based on driving path and system thereof | |
Zhao et al. | Dynamic path planning of emergency vehicles based on travel time prediction | |
CN115409256B (en) | Route recommendation method for avoiding congestion area based on travel time prediction | |
CN112629533A (en) | Refined path planning method based on road network rasterization road traffic flow prediction | |
US20220414450A1 (en) | Distributed Multi-Task Machine Learning for Traffic Prediction | |
Wang et al. | Real-time urban regional route planning model for connected vehicles based on V2X communication | |
CN113516277A (en) | Network connection intelligent traffic path planning method based on dynamic pricing of road network | |
Zheng et al. | A novel approach to coordinating green wave system with adaptation evolutionary strategy | |
CN113724507A (en) | Traffic control and vehicle induction cooperation method and system based on deep reinforcement learning | |
Kanamori et al. | Evaluation of traffic management strategies with anticipatory stigmergy | |
Habibi et al. | An Intelligent Traffic Light Scheduling Algorithm by using fuzzy logic and gravitational search algorithm and considering emergency vehicles | |
Habibi et al. | Improvement of Multi-agent Routing Guidance with an Intelligent Traffic Light Scheduling and the Ability to Select Intermediate Destinations | |
Wang et al. | Real-time dynamic route optimization based on predictive control principle | |
Ye et al. | Fairlight: Fairness-aware autonomous traffic signal control with hierarchical action space | |
Yao et al. | A path planning model based on spatio-temporal state vector from vehicles trajectories | |
Liu et al. | Learning to route via theory-guided residual network | |
Wu et al. | Application of Java—Based optimization Dijkstra algorithm in parking lot berth guidance |
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 |