CN109959388B - Intelligent traffic refined path planning method based on grid expansion model - Google Patents
Intelligent traffic refined path planning method based on grid expansion model Download PDFInfo
- Publication number
- CN109959388B CN109959388B CN201910278787.0A CN201910278787A CN109959388B CN 109959388 B CN109959388 B CN 109959388B CN 201910278787 A CN201910278787 A CN 201910278787A CN 109959388 B CN109959388 B CN 109959388B
- Authority
- CN
- China
- Prior art keywords
- road
- grid
- time
- path
- path planning
- 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
- 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
The intelligent traffic refined path planning method based on the grid expansion model comprises the following steps: step 1: predicting traffic conditions in a future period of time by using a convolutional neural network on the basis of road real-time traffic information and historical information; step 2: dynamically expanding the grids by taking the road units as units according to the road network structure and the vehicle density and combining with the starting points; and step 3: and carrying out fine micro-scale road searching in the grid, recommending a driving scheme in the grid, and when the vehicle is about to drive out of the grid, carrying out prediction and planning again until a terminal is reached. Compared with the traditional path planning algorithm, the method disclosed by the invention combines the actual driving process of the vehicle, adopts the idea of segmenting and zoning, dynamically partitions the zones and carries out fine path planning, can effectively reduce the time of single calculation of the system, and realizes efficient intelligent traffic guidance and navigation.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic, and relates to a method for predicting traffic information, expanding a grid map and planning an optimal path.
Background
Nowadays, the intelligent traffic signal technology and the processing technology are mature day by day, the intelligent traffic has many applications in recent years, and a plurality of cities in China are built and equipped with traffic brains. In the face of the dynamics and complexity of traffic information, the intelligent traffic system can dynamically acquire information for optimal path calculation, and further face the ground traffic demand, so that traffic jam is relieved, traffic resources are utilized, the influence of traffic accidents is reduced, environmental pollution is reduced, the production efficiency is improved, and a series of social and economic benefits are brought. The vehicle navigation system is an important system with urgent requirements and wide application in an intelligent traffic system, and can provide important functions of vehicle positioning, path planning, path guidance, comprehensive information service and the like.
Path planning is an important issue in vehicle navigation systems. The traditional method only considers the static shortest path from the starting point to the end point, but the real-time traffic condition influences the actual driving experience. Thus, in practical applications, problems such as a decrease in computational efficiency due to a change in traffic conditions, a slow long-distance path planning speed, and the like may appear. In dynamic path planning, on one hand, the path planning needs to be adjusted correspondingly according to the conditions of road maintenance, congestion and the like; on the other hand, it is also necessary to increase the calculation speed and to provide the path information in a timely manner.
It is found through the search of the existing literature that r.rajagopalan et al proposed a Hierarchical path planning algorithm in 2008 "Hierarchical path calculation for large maps" published by IEEE Transactions on Aerospace and Electronic Systems (IEEE journal of Aerospace and Electronic Systems "). The optimal path is determined by dividing a large graph into smaller sub-graphs, pre-storing the optimal path of boundary points within the sub-graphs, and searching for minimal overhead between sub-graph boundary points. However, this approach requires the maintenance of a large number of pre-computations and excessive storage overhead for paths within the subgraph.
It was found through a search of the existing literature that Jagadeseh et al published in 2002 "IEEE Transactions on Intelligent Transportation Systems (IEEE Intelligent Transportation Systems), entitled" Heuristic technique for accessing Hierarchical Routing on Road Networks "in Jagareseh et al. The article firstly focuses on main traffic main roads and large intersections, and then plans secondary roads and intersections, so that the algorithm complexity can be effectively reduced. However, in an actual traffic network, the optimal path is usually related to departure time, and some main roads in the network may be congested at peak hours, so that the result of the acceleration technique is invalid.
In summary, the problems of the prior art are as follows: (1) And the path planning can not be given by combining the real-time dynamic road condition information. And (2) the calculation cost is high, and the calculation efficiency is poor. Firstly, the grid expansion model-based intelligent traffic refined path planning method can quickly and efficiently provide a dynamic navigation scheme; secondly, the grid expansion model is one of the outstanding contributions of the invention; thirdly, the scheme can timely react to the congestion condition of the road, and effectively realize traffic guidance. The invention can combine the real-time dynamic road condition information to give the path planning. The calculation cost is reduced, and the calculation efficiency is improved. According to the development of the current intelligent traffic technology, a path planning scheme can be more scientifically and reasonably provided, traffic jam is relieved, traffic resources are fully utilized, and the development of a dynamic navigation technology is promoted.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intelligent traffic refined path planning method based on a grid expansion model. The invention can combine the real-time dynamic road condition information to give the path planning. The calculation cost is reduced, and the calculation efficiency is improved. According to the development of the current intelligent traffic technology, a path planning scheme can be more scientifically and reasonably provided, traffic jam is relieved, traffic resources are fully utilized, and the development of a dynamic navigation technology is promoted.
The invention is realized in this way, and the intelligent traffic refined path planning method based on the grid expansion model comprises the following steps:
step 1: predicting traffic conditions in a future period of time by using a convolutional neural network on the basis of road real-time traffic information and historical information;
and 2, step: dynamically expanding the grids by taking the road units as units according to the road network structure and the vehicle density and combining with the starting points;
and step 3: and (4) carrying out micro-scale route finding in the grid, recommending a driving scheme in the grid, returning to the first step when the vehicle is about to drive out of the grid, and carrying out prediction and planning again until the destination is reached.
Further, the traffic information is the number of vehicles on each road, the traffic information at each moment can be reconstructed into a square matrix, and historical traffic information matrices are combined into a tensor.
Further, the road unit is a boundary divided into different closed areas by roads, including corresponding roads and intersections.
Further, the dynamic expansion grid in step2 includes expanding cells on both sides along the end point direction, and each time a cell close to the end point is selected as an expansion cell, and a certain vehicle density is used as an expansion termination condition.
Further, the micro-scale route finding in the grid is an optimal path algorithm based on the shortest time, wherein the time spent on passing through each road can be obtained by combining the prediction information in the step1 and the road network structure.
Furthermore, the grid expansion dynamic path planning method only needs to plan the optimal path in the grid in each planning, and does not require one-time planning of the path from the starting point to the end point, so that the algorithm complexity is lower.
Firstly, the intelligent traffic refined path planning method based on the grid expansion model can quickly and efficiently provide a driving scheme for the next period of time; secondly, grid expansion is one of the outstanding contributions of the present invention; and thirdly, timely reacting to the congestion condition of the road. The invention can combine the real-time dynamic road condition information to give the path planning. The calculation cost is reduced, and the calculation efficiency is improved. According to the development of the current intelligent traffic technology, a path planning scheme can be provided more scientifically and reasonably, traffic jam is relieved, traffic resources are fully utilized, and the development of a dynamic navigation technology is promoted.
Drawings
Fig. 1 is a diagram of a grid expansion scenario employed by an embodiment of the present invention.
Fig. 2 is a block diagram of an implementation of a traffic information prediction algorithm according to an embodiment of the present invention.
FIG. 3 is a block diagram of an implementation of an algorithm for identifying road elements according to an embodiment of the present invention.
FIG. 4 is a block diagram of an implementation of an in-grid micro-scale path planning algorithm in accordance with an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in detail below with reference to the accompanying drawings: the embodiment is implemented on the premise of the technical scheme of the invention, and gives a detailed implementation mode and a specific operation process. It should be understood that the specific examples described herein are merely illustrative of the invention and that the scope of the invention is not limited to the examples described below.
Examples
In this embodiment, a map scene shown in fig. 1 is adopted, and an intelligent traffic refined path planning method based on a grid expansion model is provided. The basic goal of this embodiment is to dynamically give the shortest path in time for a given start point to end point.
The road network is considered as a directed planar graph G = (V, E), where each point in V represents an intersection of the road network. Let E connect to v x And v y The road length at two points is l, and is marked as (v) x ,v y L). The starting point of the path that we need to plan is v s Point, end point is v e Points, thereby vectors
Is the large direction of our travel.
On each road, the vehicles entering and exiting the road are sensed through the prior art method, and the number of the vehicles on each road is obtained. In the t-th time interval, at v x v y On the road and from v x Direction of travel v y Number of vehicles n t (v y ,v x ). If the road v x v y Is from v x To v y A one-way road of (2), then n t (v y ,v x ) And =0. Thus, in t time intervals, v x v y Total number of vehicles N on road t (v x ,v y )＝n t (v x ,v y )+n t (v y ,v x ). At the t-th time interval, the number of vehicles on all roads may be reconstructed as an M N matrix F t ∈R M×N Referred to as a traffic information matrix. Historical trafficThe information matrices are then combined into a tensor { F } h L h = t, t-1, \8230;, t-l }, so that { F is first predicted from this tensor k |k＝t+1,t+2,…,t+s}。
To learn the spatiotemporal correlation of the number of vehicles on the road, a convolutional neural network is applied to this learning task, and a specific algorithm implementation block diagram is shown in fig. 2. In order to better extract the information of the input historical traffic information matrix without losing edge information, the edge of the original input matrix is filled to obtain the input tensor a 1 . The network used by us except the input layer has five hidden layers, namely a convolution layer 1, a pooling layer 1, a convolution layer 2, a pooling layer 2 and a full-connection layer. Where the convolution layer contains convolution kernel parameters W, b, which connect each output with a local value. The pooling layers 1 and 2 compress the input tensors and extract features. Convolutional layer 1 has 256 hidden units, pooled layer 1 has 128 hidden units, convolutional layer 2 has 64 hidden units, and pooled layer 2 has 2 hidden units. And finally, a full connection layer adopts a common deep neural network structure. The convolutional neural network learns the space-time correlation from the input historical traffic information matrix in a supervised learning mode. The loss function in training CNN is the ground truth F k (i, j) and predicting traffic information conditions
Mean Square Error (MSE) of
And then combining the existing actual data to predict.
Using the traffic information data of the previous 40 minutes in combination with the accuracy and time consumption of the algorithm, traffic information of T =10 minutes in the future is predicted. The specific time length can be adjusted by combining the traffic characteristics of the region.
And performing grid expansion and path planning by using the overall traffic information of the area. The termination condition for the grid expansion is first determined. For a pair of starting points v s And end point v e From the starting point v s With the central line 1 as the positive northeast and the positive southwest, and the line 2 as the positive northwest and the positive southeast, four regions are obtained. In FIG. 1, end point v e Defining a square area in the east region, the square having north and south directions as one side and a starting point v s The middle point of the side extends to the east direction to form a square area with a side length of a = V × T. This square area is the threshold determination area. With average vehicle density D in this region 0 As a termination condition for the grid expansion.
In the actual driving process of the automobile, before a certain intersection is reached, only the direction selection at the intersection needs to be determined clearly, so that the direction selection at the intersection needs to be calculated. The grid is selected along the available direction at this intersection. The road unit is a boundary divided into different closed areas by roads, and comprises corresponding roads and intersections. At the intersection at the beginning of fig. 1, the feasible road units are a unit a (1) surrounded by the road turning to the right and going straight and a unit B (1) surrounded by the road turning to the left and going straight, which are the two smallest grids.
And when the road unit is selected, a breadth-first traversal mode is adopted. When a section of road is determined, the starting point A and the ending point B of the section are obtained. And finding all the K edges taking the end point B as an end point, respectively establishing new paths for the determined road section and the K edges, and judging whether the starting point A is the same as the other end point of each newly added edge or not. If the paths are the same, a feasible grid is found, otherwise, the path is continuously traversed for the given new path. When the road units are identified, the situation of grid nesting is possible, and if a certain unit contains all points in another unit, a larger grid is deleted, so that a feasible road unit can be obtained.
In order to take into account the following route sections, the two smallest grids are expanded in the direction of the end point. Using the city block distance from the end point (also called manhattan distance, the distance of two points in the north-south direction plus the distance in the east-west direction, i.e. d (v) a ,v e )＝|x a -x e |+|y a -y e L as a distance evaluation function h (v) a ). When expanding, the selected one-way unit is superposed with at least one edge of the original grid and comprises an h (v) a ) Relatively small dots. For example, a (1) in fig. 1, the candidate road units are three road units, namely, northwest, northeast and southeast, and the distance evaluation of the three road units is 4.4, 3.9 and 3.8, respectively, and the smaller unit is selected and marked as a (2). Calculating the average traffic flow density of the grid at the moment, and if the average traffic flow density reaches a threshold value D 0 Or extend to the end point, or reach the zone boundary, and stop the calculation. Otherwise, the expansion is continued.
And after the grid is obtained, performing a micro-scale path planning model. From the foregoing prediction method, the traffic flow density on each link can be obtained. By referring to a relation model of various traffic flow densities and vehicle speeds and combining road conditions in China, the road speed can be calculated by adopting a Newell model (see the Nonlinear Effects in the Dynamics of Car pollution published in 1961 by G.F. Newell), and the road speed is calculated by the Following formula
Wherein, vol f For free flow velocity, k j In order to block the density, the parameters can be calibrated according to the actual urban road conditions. For at v x v y The time (v) of passing the road is calculated x ,v y )＝l(v x ,v y )/vol(v x ,v y ). Thereby obtaining a path planning model. Will arrive at node v m Then, the updating step based on the shortest route is as follows:
weight time (v) of Step1 update edge m ,v m+1 ) V in the save queue Path m+1 A set of later nodes PT;
step2 node set S = { v } for known shortest time path m }, set of nodes for unknown shortest time path U = V-S, V m Known shortest time array TM to all nodes in V (if V m With a certain vertex v i With edges, TM [ i]＝time(v m ,v i ) (ii) a If v is i Is not v m Adjacent section ofPoint, TM [ i]＝∞；TM[m]= 0); a predecessor array P of each node on the shortest time path;
step3 selects a node v with the minimum TM value from U j It is added to S (the selected time is v) m To v j The shortest time of);
step4 investigates each v j The neighboring node of (2): with v is k For example, if TM (k) > TM [ j >]+time(v j ,v k ) Then TM (k) = TM [ j%]+time(v j ,v k ) Updating P;
step5, if v is judged j ＝v n The algorithm ends, output v 0 To v n The shortest time path queue PathNew; if v is j E is PL, output v s To v e Shortest time path queues PathNew and v j To v e The shortest time Path queue Path;
step6 returns to Step1.
The vehicle can travel along the recommended route. And when the automobile passes through the penultimate fork, if the automobile does not reach the terminal point, returning to the predicting step and continuing to calculate in real time.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. An intelligent traffic refined path planning method based on a grid expansion model is characterized by comprising the following steps: the intelligent traffic refined path planning method based on the grid expansion model comprises the following steps:
step 1: predicting traffic conditions in a future period of time by using a convolutional neural network on the basis of road real-time traffic information and historical information;
step 2: dynamically expanding the grids by taking a road unit as a unit according to a road network structure and vehicle density and combining with a starting point;
and step 3: carrying out fine microscale road finding in the grid, recommending a driving scheme in the grid, returning to the first step when the vehicle is about to drive out of the grid, and carrying out prediction and planning again until a terminal point is reached;
the traffic information is the number of vehicles on each road, the traffic information at each moment is reconstructed into a square matrix, and historical traffic information matrices are combined into a tensor;
the road unit is a boundary divided into different closed areas by a road, and comprises a corresponding road and an intersection;
and in the step2, the dynamic expansion grid comprises units on two sides along the direction of the terminal point for expansion, the unit close to the terminal point is selected as an expansion unit every time, and a certain vehicle density is used as an expansion termination condition.
2. The intelligent traffic refined path planning method based on the grid expansion model as claimed in claim 1, characterized in that: and (3) the micro-scale route searching in the grid is an optimal path algorithm based on the shortest time, wherein the time used by each road is obtained by combining the prediction information in the step (1) and the road network structure.
3. The intelligent traffic refined path planning method based on the grid expansion model as claimed in claim 1, characterized in that: the grid expansion dynamic path planning method only needs to plan the optimal path in the grid in each planning, and does not require one-time planning of the path from the starting point to the end point, so that the algorithm complexity is lower.
4. The method for intelligent traffic fine path planning based on grid expansion model according to one of claims 1-3, characterized in that: in order to learn the time-space correlation of the number of vehicles on the road, when the convolutional neural network is applied, the edge of the original input matrix of the historical traffic information is filled to obtain an input tensor a 1 (ii) a The convolutional neural network comprises five hidden layers except an input layer, namely a convolutional layer, a first pooling layer, a convolutional layer, a second pooling layer and a full-connection layer in sequence; the convolution layer contains convolution kernel parameters W, b, and convolution kernel parameters are connected by local valuesEach output; the first pooling layer and the second pooling layer compress the input tensors and extract features; the convolutional neural network learns the time-space correlation from the input historical traffic information matrix in a supervised learning mode; the loss function in training CNN is the ground truth F k (i, j) and predicting traffic information conditions
Mean square error MSE of
And then combining the existing actual data to predict.
5. The intelligent traffic refined path planning method based on the grid expansion model as claimed in claim 1, characterized in that: carrying out grid expansion and path planning by using the overall traffic information of the area; firstly, determining termination conditions of grid expansion; for a pair of starting points v s And end point v e From the starting point v s Taking the north-east direction and the south-west direction as a boundary 1 and taking the north-west direction and the south-east direction as a boundary 2 to obtain four regions; when the end point ve is in the east area, a square area is defined, the square takes the north-south direction as one side, the starting point vs is the middle point of the side, and the square area with the side length of a = V multiplied by T is expanded in the east direction; the square area is a threshold value determination area; the average vehicle density in this region is taken as the termination condition for the grid expansion.
6. The intelligent traffic refined path planning method based on the grid expansion model as claimed in claim 5, characterized in that: in the actual driving process of the automobile, before reaching a certain intersection, only the direction selection at the intersection needs to be determined, so that the direction selection at the intersection needs to be calculated; the grid is selected along the feasible direction at the intersection; the road unit is a boundary divided into different closed areas by a road and comprises a corresponding road and an intersection;
at the crossroad of the starting point, the feasible road units are a unit A (1) formed by enclosing a right-turn road and a straight road and a unit B (1) formed by enclosing a left-turn road and a straight road, which are two minimum grids; when selecting the road unit, adopting a breadth-first traversal mode: when a section of road section is determined, a starting point A and an ending point B of the road section are obtained; finding all K edges with the end point B as an end point, respectively establishing new paths for the determined road section and the K edges, and judging whether the starting point A is the same as the other end point of each newly added edge or not; if the paths are the same, finding a feasible grid, otherwise, continuously traversing the given new path; when a road unit is identified, if grid nesting exists, deleting a larger grid if a certain unit contains all points in another unit, and obtaining a feasible road unit;
to take into account the following road sections, the two smallest grids are expanded in the direction of the end point, using the city block distance from the end point, or what is called manhattan distance, the distance of the two points in the north-south direction plus the distance in the east-west direction, i.e. d (va, ve) = | xa-xe | + | ya-ye | as the distance evaluation function h (v, ve) = | xa-xe | + | a ) (ii) a When expanding, the selected one-way unit is superposed with the original grid by at least one edge and comprises an h (v) a ) Relatively small dots; calculating the average traffic flow density of the grids, and stopping calculation if the average traffic flow density of the grids reaches a threshold value, or expands to a terminal point, or reaches a zone boundary; otherwise, the expansion is continued.
7. The intelligent traffic refined path planning method based on the grid expansion model as claimed in claim 5, characterized in that: after the grid is obtained, a path planning model of a microscale is carried out; from the foregoing prediction method, the road speed is calculated by the following formula
Wherein, vol f For free flow velocity, k j Calibrating parameters according to the actual urban road condition for the congestion density; for at v x v y The time (v) taken by the vehicle to pass through the road is calculated x ,v y )＝l(v x ,v y )/vol(v x ,v y ) (ii) a Thereby obtaining a path planning model; node v to be reached m Then, the updating steps based on the shortest route are as follows:
s1 updating the weight time (v) of the edge m ,v m+1 ) Save v in queue Path m+1 A set of later nodes PT;
s2 set of nodes with known shortest time path S = { v = m }, set of nodes for unknown shortest time path U = V-S, V m Known shortest time array TM to all nodes in V if V m With a certain vertex v i Having edges, TM [ i]＝time(v m ,v i ) (ii) a If v is i Is other than v m Of adjacent nodes, TM [ i]＝∞；TM[m]=0; a predecessor array P of each node on the shortest time path;
s3, selecting a node v with the minimum TM value from the node set U with the shortest time path j Adding it to S, the selected time being v m To v j The shortest time of (c);
s4 examining each v j The neighboring node of (2): with v k For example, if TM (k) > TM [ j >]+time(v j ,v k ) Then TM (k) = TM [ j =]+time(v j ,v k )，
Updating the P;
s5, judging if v j ＝v n The algorithm ends, output v 0 To v n The shortest time path queue PathNew; if v is j E.g. PL, output v s To v e Shortest time path queues PathNew and v j To v e The shortest time Path queue Path;
s6, returning to S1;
the vehicle can run along the recommended route; and when the automobile passes through the penultimate fork, if the automobile does not reach the terminal point, returning to the predicting step and continuing 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 CN109959388A (en) | 2019-07-02 |
| CN109959388B true 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) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111337044B (en) * | 2020-03-24 | 2022-02-18 | 北京交通发展研究院 | Urban road path planning method based on traffic weight |
| CN111397625B (en) * | 2020-03-30 | 2021-09-10 | 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 |
| 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 |
| CN112817316B (en) * | 2021-01-04 | 2022-03-15 | 浙江大学 | Multi-robot path planning method and device |
| CN113029151B (en) * | 2021-03-15 | 2023-04-14 | 齐鲁工业大学 | Intelligent vehicle path planning method |
| CN113516277B (en) * | 2021-04-13 | 2023-10-17 | 南京大学 | Internet intelligent traffic path planning method based on road network dynamic pricing |
| CN113283075B (en) * | 2021-05-21 | 2023-11-03 | 南京大学 | Lightweight simulation architecture design method for large-scale satellite scene |
Citations (4)
| 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 |
| 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 |
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8103435B2 (en) * | 2007-07-27 | 2012-01-24 | George Mason Intellectual Properties, Inc. | Near real-time traffic routing |
| CN107144286B (en) * | 2016-03-01 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Navigation method and device |
-
2019
- 2019-04-09 CN CN201910278787.0A patent/CN109959388B/en active Active
Patent Citations (4)
| 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 |
| 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 |
| 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 |
|---|
| "城市综合应急指挥***的车辆路径规划研究与实现";顾国民;《中国优秀硕士学位论文全文数据库信息科技辑》;20060515(第5期);I138-360-第50-51页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109959388A (en) | 2019-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109959388B (en) | Intelligent traffic refined path planning method based on grid expansion model | |
| Jiang et al. | Graph neural network for traffic forecasting: A survey | |
| CN102176283B (en) | Traffic network simplifying model and navigating method based on same | |
| CN112629533B (en) | Fine path planning method based on road network rasterization road traffic prediction | |
| CN107944605A (en) | A kind of dynamic traffic paths planning method based on data prediction | |
| Pattanaik et al. | Smart real-time traffic congestion estimation and clustering technique for urban vehicular roads | |
| CN108009666B (en) | Hierarchical priority optimal path calculation method based on dynamic road network | |
| CN108335483B (en) | Method and system for inferring traffic jam diffusion path | |
| 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 | |
| CN106052701A (en) | Vehicle route selection method under traffic overflow state | |
| Zheng et al. | A novel approach to coordinating green wave system with adaptation evolutionary strategy | |
| Cheng | Dynamic path optimization based on improved ant colony algorithm | |
| Jalel et al. | Continuous time markov chain traffic model for urban environments | |
| Menguc et al. | A Data Driven Approach to Forecasting Traffic Speed Classes Using Extreme Gradient Boosting Algorithm and Graph Theory | |
| Elbery et al. | A novel stochastic linear programming feedback eco-routing traffic assignment system | |
| CN114413923B (en) | Driving route recommendation method, device, storage medium and system | |
| CN113903171B (en) | Vehicle crowd sensing node optimization method based on spatial-temporal characteristics of highway network | |
| Shi et al. | An adaptive route guidance model considering the effect of traffic signals based on deep reinforcement learning | |
| Song et al. | Path planning in urban environment based on traffic condition perception and traffic light status | |
| Ye et al. | Fairlight: Fairness-aware autonomous traffic signal control with hierarchical action space | |
| Habibi et al. | Improvement of Multi-agent Routing Guidance with an Intelligent Traffic Light Scheduling and the Ability to Select Intermediate Destinations | |
| Liu et al. | Learning to route via theory-guided residual network | |
| CN114419917A (en) | Traffic jam grooming method and system based on single-direction graph | |
| Zhang et al. | Path Planning Model Based on Constrained Policy Iteration |
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 |