CN109579861A - A kind of method for path navigation and system based on intensified learning - Google Patents
A kind of method for path navigation and system based on intensified learning Download PDFInfo
- Publication number
- CN109579861A CN109579861A CN201811504732.9A CN201811504732A CN109579861A CN 109579861 A CN109579861 A CN 109579861A CN 201811504732 A CN201811504732 A CN 201811504732A CN 109579861 A CN109579861 A CN 109579861A
- Authority
- CN
- China
- Prior art keywords
- road
- congestion
- syntople
- city
- module
- 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
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
- G01C21/3453—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
-
- 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
Abstract
The invention discloses a kind of method for path navigation and system based on intensified learning, comprising: according to the map datum in city, construct the road syntople figure in city;According to track of vehicle data and road syntople figure, the congestion index of predicted city different sections of highway different periods;Based on road syntople figure, according to the road congestion probability graph in city described in congestion index construction;Guidance path is generated based on intensified learning, the state space of intensified learning includes the road congestion probability graph.Present invention randomization on the basis of numeralization by urban road congestion situation, more intuitive easy visualization;Condition of road surface and history track of vehicle data is only utilized in road congestion calculating, convenient for practice;Be different from it is general have obstacle method for searching, probability pathfinding numerical value is more accurate, it is found that the route that general pathfinding algorithm can not find;Intensified learning considers the time-consuming and unobstructed of pathfinding as heuritic approach, obtains globally optimal solution with this, increases the accuracy of pathfinding algorithm.
Description
Technical field
The invention belongs to path navigation technical fields, more particularly, to a kind of path navigation side based on intensified learning
Method and system.
Background technique
The effective driving route of Mobile Telephone Gps searching has become daily.Good travel route can not only save driver's
Time can also save energy consumption.GPS device be widely used let us can easily obtain city road it is detailed
Information such as flow motor, speed etc..These data have extremely important directive function to path navigation.
In the prior art, patent CN108847037A discloses a kind of city road network path planning towards non-global information
Method makes road network have the ability adaptively adjusted to the distribution of vehicle flowrate by intensified learning, therefore at road network state
In flow equalization state.However the A*R pathfinding algorithm in this method in evaluation function to the institute of current location to target position
Relatively rough with the estimation method therefor of time, precision is insufficient, while Space-time Complexity is very high.Tight beautiful equality people proposes that city is handed over
Access net dynamic realtime Multiple Intersections path Choice Model, in conjunction with vehicle to the real-time of the preference of front optional route and optional route
Traffic behavior, and game is carried out using adaptive learning algorithm, so that the Dynamic route-selection strategy of each driving vehicle reaches
Nash is balanced.However, this method there are application scenarios needs multiple hypotheses, (such as each vehicle is according to some fixation probability
Path selection is carried out independently of one another, and each vehicle can observe the Path selection of other vehicles), the factor mistake of consideration
More (such as road lighting, road planarization etc. are difficult to the index measured), the defect having difficulties in practice.
In conclusion the application scenarios needs that the existing method for path navigation based on intensified learning has algorithm are a variety of
Assuming that as premise, the too high problem of Space-time Complexity.
Summary of the invention
In view of the drawbacks of the prior art, it is an object of the invention to optimize prior art precondition on pathfinding algorithm
It is more, the incomplete problem of decision function.
To achieve the above object, in a first aspect, the embodiment of the invention provides a kind of path navigations based on intensified learning
Method, method includes the following steps:
S1. according to the map datum in city, the road syntople figure in the city is constructed;
S2. according to track of vehicle data and road syntople figure, gathering around for the city different sections of highway different periods is predicted
Fill in index;
S3. based on road syntople figure, according to the road congestion probability graph in city described in congestion index construction;
S4. guidance path is generated based on intensified learning, the state space of the intensified learning includes that the road congestion is general
Rate figure.
Specifically, in the road syntople figure, vertex is the public point of road, while be road, each vertex
Save the set on other vertex that it can be reached.
Specifically, step S2 the following steps are included:
S201. the track data of vehicle is mapped in road syntople figure, establishes track of vehicle data and road
Corresponding relationship;
S202. the congestion index of present road is calculated according to the road type of present road.
Specifically, the step S201 specifically includes the following steps:
(1) inflection point of track of vehicle is extracted;
(2) vertical range for calculating side in inflection point and road syntople figure acquires to be used as apart from the smallest side and works as front;
(3) inflection point is mapped to and works as the hithermost vertex in front;
(4) in chronological order, using the time difference between the distance and inflection point between the inflection point of front and back, the speed between the inflection point of track is calculated
Degree, the speed as taxi in current hour in the section.
Specifically, step S202 specifically includes the following steps:
(1) respective weights of different road types are set;
(2) using each of current road segment hour average speed and pass through number of vehicles, place road type pair
Answer weight, travel-time ratio, congestion index of the prediction present road in different periods.
Specifically, step S3 the following steps are included:
S301. congestion index is converted into current time congestion probability by Logistic function;
S302. the side that congestion probability is mapped to road syntople figure is weighted, generates each hour city road
Road congestion probability figure.
Specifically, step S4 the following steps are included:
S401. specified states space is to include urban road congestion probability figure and the three-dimensional space of time, it is specified that movement is
An adjacent edge is selected to reach next vertex, it is specified that reward function is from starting point to current vertex from vertex is currently located
The expectation of path spent time;
S402. the strategy of selection movement is that a certain vertex is chosen the smallest side of arrival point time-consuming expectation and is used as
Up to the direction of the point;
S403. after expanding to terminal, accessing its father node until returning to starting point, the route of starting point to terminal is to lead
Bit path.
To achieve the above object, second aspect, the embodiment of the invention provides a kind of path navigations based on intensified learning
System, the system include server-side and client,
The server-side includes: road syntople figure building module, congestion exponential forecasting module, road congestion probability graph
Construct module and guidance path generation module;
The road syntople figure building module constructs the road in the city for the map datum according to city
Syntople figure;
The congestion exponential forecasting module, for predicting the city according to track of vehicle data and road syntople figure
The congestion index of city's different sections of highway different periods;
The road congestion probability graph constructs module, is used for based on road syntople figure, according to congestion index structure
Build the road congestion probability graph in the city;
The guidance path generation module for generating guidance path based on intensified learning, and is sent to client progress
Path navigation, the state space of the intensified learning include the road congestion probability graph;
The client includes: navigation module, guide module and track data extraction module;
The navigation module, for obtaining navigation routine from server-side;
The track data extraction module, for obtaining the track data of vehicle;
The guide module, for indicating car owner current location and direction of advance according to navigation routine and track data.
Specifically, the track data Real-time Feedback that the track data extraction module of the client can also will acquire to
The congestion exponential forecasting module of the server-side.
To achieve the above object, the third aspect, the embodiment of the invention provides a kind of computer readable storage medium, the meters
It is stored with computer program on calculation machine readable storage medium storing program for executing, which realizes above-mentioned first aspect when being executed by processor
The method for path navigation.
In general, through the invention it is contemplated above technical scheme is compared with the prior art, have below beneficial to effect
Fruit:
1. urban road congestion situation is carried out randomization by the present invention on the basis of numeralization.Road is shown in client
When situation, whether the probability of congestion more intuitively understands compared with numerical value to people urban road, convenient for visualization.It is of the invention simultaneously
Condition of road surface and history track of vehicle data is only utilized in the calculating of road congestion situation, convenient for practice.
2. the present invention devises the pathfinding algorithm based on intensified learning.As a kind of probability pathfinding mode, it is different from general
Have obstacle pathfinding in addition to that can walk and cannot walk without other options, probability pathfinding is because numerical value is more accurate, it is found that general
The route that pathfinding algorithm can not find.Intensified learning as heuritic approach can from the point of view of totality pathfinding time-consuming and it is unobstructed
Degree obtains globally optimal solution with this, needs to estimate current location to target position rather than A* algorithm, therefore increases
The accuracy of pathfinding algorithm.
Detailed description of the invention
Fig. 1 is a kind of method for path navigation flow chart based on intensified learning provided in an embodiment of the present invention;
Fig. 2 is a kind of path guiding system structural schematic diagram based on intensified learning provided in an embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
As shown in Figure 1, a kind of method for path navigation based on intensified learning, method includes the following steps:
S1. according to the map datum in city, the road syntople figure in the city is constructed;
S2. according to track of vehicle data and road syntople figure, gathering around for the city different sections of highway different periods is predicted
Fill in index;
S3. based on road syntople figure, according to the road congestion probability graph in city described in congestion index construction;
S4. guidance path is generated based on intensified learning, the state space of the intensified learning includes that the road congestion is general
Rate figure.
Step S1. constructs the road syntople figure in the city according to the map datum in city.
The map datum that the embodiment of the present invention uses is OpenStreetMap.Map datum includes: road id, road class
Type, the Extreme points set that whether can include with two way and present road.Each endpoint has latitude and longitude information.Each endpoint energy
It is shared by a plurality of road.By endpoint, we can obtain the syntople of road, can also calculate the length of road.Construct road
The purpose of road syntople figure is to obtain road network information, so that the track data of vehicle to be mapped on true road, with this
Carry out the prediction and navigation of road traffic condition.
S101. road information is extracted from map datum.
Extract road information from OpenStreetMap, the road information include road adjacency information, road type and
Link length.Wherein, road type includes: highway, branch, level-one road, secondary road, three-level road, residential block.
S102. according to road information, road syntople figure is constructed.
According to the end-to-end syntople of road, road syntople figure is constructed.In the road syntople figure, vertex is
The public point of road, while being road, each vertex saves the set on other vertex that it can be reached.This is one oriented
Figure.
Step S2. predicts the city different sections of highway different periods according to track of vehicle data and road syntople figure
Congestion index.
Track of vehicle data are also possible to off-line data collection either acquisition in real time.The track data includes: track
Id, vehicle id, vehicle are currently located longitude, vehicle is currently located latitude, current time information.Vehicle can be taxi, private
Family's vehicle etc..
Before predicting congestion index, data cleansing can be carried out to the track data being collected into.The data cleansing is
Refer to the track data for rejecting and repeating or lacking.Due to being interrupted there are GPS signal or vehicle driving is to the situations such as intersection, GPS
Receiver at a certain moment can a large amount of same or similar redundant datas of persistent collection in the short time.These redundant datas can directly drop
The efficiency of low algorithm operation.When vehicle in building, the woods activity or GPS signal interrupt, use base station location etc.
When other localization methods, the positioning of vehicle will appear drift, generate a large amount of noise spot, cause the distortion of track.Therefore, it is necessary to
Redundant data and drift data are removed, to correct track data.
S201. the track data of vehicle is mapped in road syntople figure, establishes track of vehicle data and road
Corresponding relationship.Specifically includes the following steps:
(1) inflection point of track of vehicle is extracted.
The inflection point of track of vehicle is the characteristic point of vehicle.
(2) vertical range for calculating side in inflection point and road syntople figure acquires to be used as apart from the smallest side and works as front.
(3) inflection point is mapped to and works as the hithermost vertex in front.
After the vertex of the corresponding figure of inflection point determines, the corresponding side of taxi orbit segment is also determined that.
(4) in chronological order, using the time difference between the distance and inflection point between the inflection point of front and back, the speed between the inflection point of track is calculated
Degree, the speed as taxi in current hour in the section.
S202. the congestion index of present road is calculated according to the road type of present road.
(1) respective weights of different road types are set.
Road type | Highway, branch | Class I highway | Class II highway | Class III highway | Residential block |
Weight | 5 | 4 | 3 | 1 | 0.5 |
(2) using each of current road segment hour average speed and pass through number of vehicles, place road type pair
Weight, travel-time ratio (time that road section length covers the section divided by current vehicle) are answered, predicts present road when different
The congestion index of section.
Prediction model can be neural network model, decision tree or Logistic and return.With a road section in different periods
Congestion situation be different, for example, working day and day off, peak period on and off duty and other times section.To current city
Every road is all predicted, realizes the road congestion index that the time granularity of prediction whole city is one hour.Congestion index is used for
Reflect road environment.
Step S3. is based on road syntople figure, according to the road congestion probability in city described in congestion index construction
Figure.
After predicting road congestion index, we have obtained the traffic conditions of urban road in following a period of time, with this
Generate urban road congestion probability figure, comprising the following steps:
S301. congestion index is converted into current time congestion probability by Logistic function.
S302. the side that congestion probability is mapped to road syntople figure is weighted, generates each hour city road
Road congestion probability figure.
The urban road congestion probability figure includes the following contents: the crosspoint in vertex representation section and section, and side indicates
Section, each edge include congestion probability, link length.Urban road congestion probability figure is increased based on road syntople figure
The following contents is added: current time, congestion probability of each edge in current time.
Step S4. is based on intensified learning and generates guidance path, and the state space of the intensified learning includes that the road is gathered around
Fill in probability graph.
S401. specified states space is to include urban road congestion probability figure and the three-dimensional space of time, it is specified that movement is
An adjacent edge is selected to reach next vertex, it is specified that reward function is from starting point to current vertex from vertex is currently located
The expectation of path spent time.
S402. the strategy of selection movement is that a certain vertex is chosen the smallest side of arrival point time-consuming expectation and is used as
Up to the direction of the point.
For vertex, there are multiple directions that can reach the point.It chooses and reaches the smallest direction work of point time-consuming expectation
For the father node on the vertex.It is worth iteration by greed, is all consumption from starting point to the path of the point for any point
When shortest path.
S403. after expanding to terminal, accessing its father node until returning to starting point, the route of starting point to terminal is to lead
Bit path.
As shown in Fig. 2, a kind of path guiding system based on intensified learning, which includes server-side and client,
The server-side includes: road syntople figure building module, congestion exponential forecasting module, road congestion probability graph
Construct module and guidance path generation module;
The road syntople figure building module constructs the road in the city for the map datum according to city
Syntople figure;
The congestion exponential forecasting module, for predicting the city according to track of vehicle data and road syntople figure
The congestion index of city's different sections of highway different periods;
The road congestion probability graph constructs module, is used for based on road syntople figure, according to congestion index structure
Build the road congestion probability graph in the city;
The guidance path generation module for generating guidance path based on intensified learning, and is sent to client progress
Path navigation, the state space of the intensified learning include the road congestion probability graph.
The client includes: navigation module, guide module and track data extraction module.
The navigation module, for obtaining navigation routine from server-side;
The track data extraction module, for obtaining the track data of vehicle;
Shown guide module, for indicating car owner current location and direction of advance according to navigation routine and track data.
The server-side can also include data cleansing module, for before predicting congestion index, to track data into
The track data for repeating or lacking is rejected in row data cleansing.
The track data Real-time Feedback that the track data extraction module of the client can also will acquire gives the clothes
The congestion exponential forecasting module at business end.
The only preferable specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any to be familiar with
Within the technical scope of the present application, any changes or substitutions that can be easily thought of by those skilled in the art, should all cover
Within the scope of protection of this application.Therefore, the protection scope of the application should be subject to the protection scope in claims.
Claims (10)
1. a kind of method for path navigation based on intensified learning, which is characterized in that method includes the following steps:
S1. according to the map datum in city, the road syntople figure in the city is constructed;
S2. according to track of vehicle data and road syntople figure, predict that the congestion of the city different sections of highway different periods refers to
Number;
S3. based on road syntople figure, according to the road congestion probability graph in city described in congestion index construction;
S4. guidance path is generated based on intensified learning, the state space of the intensified learning includes the road congestion probability graph.
2. method for path navigation as described in claim 1, which is characterized in that in the road syntople figure, vertex is road
Public point, while being road, each vertex saves the set on other vertex that it can be reached.
3. method for path navigation as described in claim 1, which is characterized in that step S2 the following steps are included:
S201. the track data of vehicle is mapped in road syntople figure, it is corresponding with road establishes track of vehicle data
Relationship;
S202. the congestion index of present road is calculated according to the road type of present road.
4. method for path navigation as claimed in claim 3, which is characterized in that the step S201 specifically includes the following steps:
(1) inflection point of track of vehicle is extracted;
(2) vertical range for calculating side in inflection point and road syntople figure acquires to be used as apart from the smallest side and works as front;
(3) inflection point is mapped to and works as the hithermost vertex in front;
(4) in chronological order, using the time difference between the distance and inflection point between the inflection point of front and back, the speed between the inflection point of track is calculated,
Speed as taxi in current hour in the section.
5. method for path navigation as claimed in claim 3, which is characterized in that step S202 specifically includes the following steps:
(1) respective weights of different road types are set;
(2) using in each of current road segment hour average speed and the number of vehicles, the corresponding power of place road type that pass through
Weight, travel-time ratio, congestion index of the prediction present road in different periods.
6. method for path navigation as described in claim 1, which is characterized in that step S3 the following steps are included:
S301. congestion index is converted into current time congestion probability by Logistic function;
S302. the side that congestion probability is mapped to road syntople figure is weighted, generates each hour urban road and gathers around
Fill in probability graph.
7. method for path navigation as described in claim 1, which is characterized in that step S4 the following steps are included:
S401. specified states space is to include urban road congestion probability figure and the three-dimensional space of time, it is specified that movement is from working as
An adjacent edge is selected to reach next vertex for preceding place vertex, it is specified that reward function is the path from starting point to current vertex
The expectation of spent time;
S402. the strategy of selection movement is, for a certain vertex, choosing the smallest side of arrival point time-consuming expectation should as arrival
The direction of point;
S403. after expanding to terminal, accessing its father node until returning to starting point, the route of starting point to terminal is road of navigating
Diameter.
8. a kind of path guiding system based on intensified learning, the system include server-side and client, which is characterized in that
The server-side includes: road syntople figure building module, congestion exponential forecasting module, the building of road congestion probability graph
Module and guidance path generation module;
The road syntople figure constructs module, and for the map datum according to city, the road for constructing the city is adjacent
Relational graph;
The congestion exponential forecasting module, for predicting the city not according to track of vehicle data and road syntople figure
With the congestion index of section different periods;
The road congestion probability graph constructs module, is used for based on road syntople figure, according to congestion index construction institute
State the road congestion probability graph in city;
The guidance path generation module for generating guidance path based on intensified learning, and is sent to client and carries out path
Navigation, the state space of the intensified learning includes the road congestion probability graph;
The client includes: navigation module, guide module and track data extraction module;
The navigation module, for obtaining navigation routine from server-side;
The track data extraction module, for obtaining the track data of vehicle;
The guide module, for indicating car owner current location and direction of advance according to navigation routine and track data.
9. path guiding system as claimed in claim 8, which is characterized in that the track data extraction module of the client is also
The track data Real-time Feedback that can be will acquire gives the congestion exponential forecasting module of the server-side.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, the computer program realize method for path navigation as described in any one of claim 1 to 7 when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811504732.9A CN109579861B (en) | 2018-12-10 | 2018-12-10 | Path navigation method and system based on reinforcement learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811504732.9A CN109579861B (en) | 2018-12-10 | 2018-12-10 | Path navigation method and system based on reinforcement learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109579861A true CN109579861A (en) | 2019-04-05 |
CN109579861B CN109579861B (en) | 2020-05-19 |
Family
ID=65927980
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811504732.9A Active CN109579861B (en) | 2018-12-10 | 2018-12-10 | Path navigation method and system based on reinforcement learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109579861B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112525213A (en) * | 2021-02-10 | 2021-03-19 | 腾讯科技(深圳)有限公司 | ETA prediction method, model training method, device and storage medium |
CN113252054A (en) * | 2020-02-11 | 2021-08-13 | 株式会社日立制作所 | Navigation method and navigation system |
CN113503888A (en) * | 2021-07-09 | 2021-10-15 | 复旦大学 | Dynamic path guiding method based on traffic information physical system |
CN113516865A (en) * | 2021-03-17 | 2021-10-19 | 北京易控智驾科技有限公司 | Mine unmanned road network vehicle queuing method and device based on high-precision map |
CN113643535A (en) * | 2021-08-02 | 2021-11-12 | 宝方云科技(浙江)有限公司 | Road traffic prediction method, device, equipment and medium based on smart city |
CN116793376A (en) * | 2023-04-13 | 2023-09-22 | 北京邮电大学 | Path prediction method, device and storage medium based on shortest path and historical experience |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102929281A (en) * | 2012-11-05 | 2013-02-13 | 西南科技大学 | Robot k-nearest-neighbor (kNN) path planning method under incomplete perception environment |
CN104157139A (en) * | 2014-08-05 | 2014-11-19 | 中山大学 | Prediction method and visualization method of traffic jam |
CN104620078A (en) * | 2012-06-29 | 2015-05-13 | 通腾发展德国公司 | Generating alternative routes |
CN106530694A (en) * | 2016-11-07 | 2017-03-22 | 深圳大学 | Traffic congestion prediction method and system based on traffic congestion propagation model |
CN107747947A (en) * | 2017-10-23 | 2018-03-02 | 电子科技大学 | A kind of collaboration itinerary based on user's history GPS track recommends method |
JP2018112900A (en) * | 2017-01-11 | 2018-07-19 | Kddi株式会社 | Program, vehicle terminal, mobile terminal, estimation server, and method for estimating behaviors based on driving characteristics of users |
CN108540384A (en) * | 2018-04-13 | 2018-09-14 | 西安交通大学 | Intelligent heavy route method and device based on congestion aware in software defined network |
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 |
WO2018211140A1 (en) * | 2017-05-19 | 2018-11-22 | Deepmind Technologies Limited | Data efficient imitation of diverse behaviors |
-
2018
- 2018-12-10 CN CN201811504732.9A patent/CN109579861B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104620078A (en) * | 2012-06-29 | 2015-05-13 | 通腾发展德国公司 | Generating alternative routes |
CN102929281A (en) * | 2012-11-05 | 2013-02-13 | 西南科技大学 | Robot k-nearest-neighbor (kNN) path planning method under incomplete perception environment |
CN104157139A (en) * | 2014-08-05 | 2014-11-19 | 中山大学 | Prediction method and visualization method of traffic jam |
CN106530694A (en) * | 2016-11-07 | 2017-03-22 | 深圳大学 | Traffic congestion prediction method and system based on traffic congestion propagation model |
JP2018112900A (en) * | 2017-01-11 | 2018-07-19 | Kddi株式会社 | Program, vehicle terminal, mobile terminal, estimation server, and method for estimating behaviors based on driving characteristics of users |
WO2018211140A1 (en) * | 2017-05-19 | 2018-11-22 | Deepmind Technologies Limited | Data efficient imitation of diverse behaviors |
CN107747947A (en) * | 2017-10-23 | 2018-03-02 | 电子科技大学 | A kind of collaboration itinerary based on user's history GPS track recommends method |
CN108540384A (en) * | 2018-04-13 | 2018-09-14 | 西安交通大学 | Intelligent heavy route method and device based on congestion aware in software defined network |
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 (3)
Title |
---|
ARENTZE,THEO等: "Modeling learning and adaptation processes in activity-travel choiceA framework and numerical experiment", 《TRANSPORTATION》 * |
崔承颖: "基于累积Logistic模型的城市交通拥堵概率估计研究", 《中国优秀硕士学位论文全文数据库 社会科学Ⅰ辑》 * |
陈春林等: "基于分层式强化学习的移动机器人导航控制", 《南京航空航天大学学报》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113252054A (en) * | 2020-02-11 | 2021-08-13 | 株式会社日立制作所 | Navigation method and navigation system |
CN113252054B (en) * | 2020-02-11 | 2023-11-28 | 株式会社日立制作所 | Navigation method and navigation system |
CN112525213A (en) * | 2021-02-10 | 2021-03-19 | 腾讯科技(深圳)有限公司 | ETA prediction method, model training method, device and storage medium |
CN112525213B (en) * | 2021-02-10 | 2021-05-14 | 腾讯科技(深圳)有限公司 | ETA prediction method, model training method, device and storage medium |
CN113516865A (en) * | 2021-03-17 | 2021-10-19 | 北京易控智驾科技有限公司 | Mine unmanned road network vehicle queuing method and device based on high-precision map |
CN113516865B (en) * | 2021-03-17 | 2022-07-05 | 北京易控智驾科技有限公司 | Mine unmanned road network vehicle queuing method and device based on high-precision map |
CN113503888A (en) * | 2021-07-09 | 2021-10-15 | 复旦大学 | Dynamic path guiding method based on traffic information physical system |
CN113643535A (en) * | 2021-08-02 | 2021-11-12 | 宝方云科技(浙江)有限公司 | Road traffic prediction method, device, equipment and medium based on smart city |
CN113643535B (en) * | 2021-08-02 | 2023-02-21 | 宝方云科技(浙江)有限公司 | Road traffic prediction method, device, equipment and medium based on smart city |
CN116793376A (en) * | 2023-04-13 | 2023-09-22 | 北京邮电大学 | Path prediction method, device and storage medium based on shortest path and historical experience |
CN116793376B (en) * | 2023-04-13 | 2024-03-19 | 北京邮电大学 | Path prediction method, device and storage medium based on shortest path and historical experience |
Also Published As
Publication number | Publication date |
---|---|
CN109579861B (en) | 2020-05-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109579861A (en) | A kind of method for path navigation and system based on intensified learning | |
CN108803599B (en) | Sweeping working method based on working mode | |
US20190092171A1 (en) | Methods, Circuits, Devices, Systems & Associated Computer Executable Code for Driver Decision Support | |
CN102708698B (en) | Vehicle optimal-path navigation method based on vehicle internet | |
RU2406158C2 (en) | Methods of predicting destinations from partial trajectories employing open- and closed-world modeling methods | |
CN104121918A (en) | Real-time path planning method and system | |
CN110174117A (en) | A kind of electric car charging route planning method | |
CN103245347A (en) | Intelligent navigation method and system based on road condition prediction | |
CN106017496A (en) | Real-time navigation method based on road condition | |
CN103177561A (en) | Method and system for generating bus real-time traffic status | |
CN109740811A (en) | Passage speed prediction technique, device and storage medium | |
US20180045527A1 (en) | Systems and Methods for Predicting Vehicle Fuel Consumption | |
CN101900565A (en) | Path determining method and device | |
CN112991743B (en) | Real-time traffic risk AI prediction method based on driving path and system thereof | |
CN105043379A (en) | Scenic spot visiting path planning method and device based on space-time constraint | |
CN110118567A (en) | Trip mode recommended method and device | |
CN104680829B (en) | Bus arrival time prediction system and method based on multi-user cooperation | |
Wang et al. | An adaptive and VANETs-based Next Road Re-routing system for unexpected urban traffic congestion avoidance | |
CN110598917B (en) | Destination prediction method, system and storage medium based on path track | |
CN103679286A (en) | Path optimizing method and path optimizing device | |
CN111915078B (en) | Flexible cigarette distribution line planning method and system based on data driving | |
Xiao et al. | A collaborative reservation mechanism of multiple parking lots based on dynamic vehicle path planning | |
CN110674990B (en) | Instant distribution path selection method and system with sliding window updating mechanism | |
CN116542709A (en) | Electric vehicle charging station planning analysis method based on traffic situation awareness | |
CN108256662A (en) | The Forecasting Methodology and device of arrival time |
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 |