CN106529064A - Multi-agent based route selection simulation system in vehicle online environment - Google Patents
Multi-agent based route selection simulation system in vehicle online environment Download PDFInfo
- Publication number
- CN106529064A CN106529064A CN201611029593.XA CN201611029593A CN106529064A CN 106529064 A CN106529064 A CN 106529064A CN 201611029593 A CN201611029593 A CN 201611029593A CN 106529064 A CN106529064 A CN 106529064A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- section
- simulation
- agent
- analogue system
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention discloses a multi-agent based route selection simulation system in a vehicle online environment. The system consists of two parts: foreground and background. A foreground interface is a human-computer interaction module, and a background program is responsible for implementing a function of the simulation system. The system comprises a route network generation and initialization model, a vehicle generation and initialization model, a simulation kernel model and an information acquisition and transfer model. A simulation kernel is core rules for driving a vehicle to run in a route network and comprises two layers of rules: micro rules and macro rules. The present invention studies overall design of the multi-agent simulation system for a route selection behavior of a traveler in the vehicle online environment, two layers of action rules of the vehicle-online multi-agent and information acquisition and transfer in the simulation system and the like; and starting from each vehicle action rule, the macro state of the system is reflected, so that simulation of the complicated dynamic system is feasible and effective.
Description
Technical field
The present invention relates to Path selection simulation technical field, under more particularly to a kind of car networking environment based on multiple agent
The analogue system of Path selection.
Background technology
With the progress of computer technology since the sixties in 20th century so that traffic simulation becomes a kind of by using calculating
Machine model is reflecting complicated traffic behavior important analysis method.Traffic simulation is simulating friendship by setting up computer simulation model
Logical phenomenon change procedure over time and space and rule, particularly with grinding in some perspective, dangerous traffic environments
Study carefully, traffic simulation has irreplaceable effect.Car networking is proved to huge economic and social benefit, being capable of very great Cheng
Existing traffic problems are solved on degree.But the research with regard to car networking and application are in the primary stage, for car networking environment
The influencing mechanism of traffic system is also had little understanding, therefore by the relevant issues of traffic system under simulation study car networking environment
Seem very necessary.As traffic behavior is the collection meter phenomenon moved on road by road network user, road grid traffic flow distribution
And running status is even more and is determined by the optimizing paths of traveler.The operation conditions of the same traffic system under car networking environment
It is that optimizing paths by traveler under car networking information condition are determined, so under car networking environment, from traveler
Optimizing paths emulation set out research car networking environment it is very necessary to the influencing mechanism of traffic system, to car networking application
With important function.
Multiple agent (Multi-agent) technology is by the action between intelligent body and interacts come the traffic for simulating complexity
Phenomenon, people propose some microcosmic traffic flow models, such as vehicle following-model, lane-change model etc. with multi-agent Technology.
A kind of framework of the multi-agent Technology as Distributed Calculation, can study complicated, dynamic system.Multi-agent Technology
It is particularly suitable for simulating and the traffic behavior that macroscopic appearance is emerged in large numbers is produced by microscopic individual behavior, can be by setting up to individual behavior
Model sets out, and studies the macro-effect produced by this behavior collection meter.Because the operation of traffic system under research car networking environment
Situation needs the travel behaviour research from traveler under car networking environment, and the traffic system under car networking environment is each
Part is interweaved, interactional complex gigantic system, so using multi-agent Technology from traveler behavior research car
Under networked environment, traffic system operation conditions has more preferable credibility and effectiveness.
The content of the invention
The invention of the present invention is to provide Path selection analogue system under a kind of car networking environment based on multiple agent, to carry
For a kind of general simulation framework under a kind of car networking information condition from individual behavior traffic, improve under research car networking
The reliability and effectiveness of traffic system research, provides a kind of efficient, feasible research tool for car networking applied research.
The technical scheme is that：Based on Path selection analogue system under the car networking environment of multiple agent, by means of
The Multi-Agent simulation instrument NetLogo that increases income builds analogue system, builds and comprises the following steps：
(1) analogue system initializing set
A zero is set to the analogue system world, one, world boundary is given on the basis of this zero, such as
Arrange world wide be x directions coordinate range be [- 25,25], the scope in y directions is also [- 25,25], therefore analogue system
For 50 × 50 world being made up of 2500 discrete Patches, then according to needing the face for gathering a part of Patches
Color is set to specific color (such as Lycoperdon polymorphum Vitt) as road, and Patches in addition is set to other easily distinguishable its
Used as trackside building etc., Vehicle Agent can pass through the colour recognition road for judging Patches to his color (such as green), and give
Section Patches gives certain mark and certain free stream velocity i.e. maximal rate to divide section grade, while right
The Patches of crossing is numbered, and is used for representing emulation system with the subordinate ordered array of the numbering composition of intersection node Patches
Path and OD in system is reciprocity.
(2) generation and initialization of Vehicle Agent
Vehicle Agent (Turtles) is generated according to car rate p of coming that can be set in specific coordinate position as needed,
Algorithm is：
In if intervals [0,100], the random several k for generating are less than p 100, and then generates vehicle
Each Vehicle Agent needs to carry out Initialize installation to which after generating, as color, vehicle ID, belonging to OD, course,
Acceleration, initial velocity etc., so can need to generate the Vehicle Agent of different attribute, differently composed ratio according to research,
And these attributes and ratio can be easily adjusted by human-computer interaction interface；
(3) simulation kernel
It is regular with Macroscopic Strategy layer for the rule of ac-tion of Vehicle Agent, including microcosmic tactics layer rule：
1) tactics layer rule
Vehicle Agent essentially consists in the action of section and crossing in the online microcosmic traveling rule in analogue system Road
Rule, is with speeding on, after vehicle n is generated, to be travelled according to the initial velocity of its initializing set, being run over first on section
Traveling decision-making is made according to front truck n+1 travel conditions in journey, its algorithm is：
If vehicles n and front truck n+1 is apart from d less than setting safe distance △ x
Exist with speeding on as n carries out feed speed control according to the following formula：
else
Do not exist and with garage be, vehicle n is travelled or accelerated to the speed and travels with section free stream velocity；
Next to that in the turning behavior of crossing, 1) Vehicle Agent selects content according to strategic layer rule after generation
Described in subordinate ordered array represent path, reach crossing when according to storage road network topology structure make steering decision-making,
Its algorithm is：
If vehicles reach node i
If vehicle routes next node numbering is a
(right or straight trip) turning to the left, assignment heading=heading+90 °
If vehicle routes next node numbering is b
(keep straight on) to the right turning, assignment heading=heading-90 °
If vehicle routes next node numbering is c
Keep straight trip, assignment heading=heading
else
If vehicles reach node j
……
Each node is traveled through successively
2) strategic layer rule
Strategic layer is responsible for the Path selection of Vehicle Agent, including path computing and path allocation, and path computing rule can
It is given to be needed according to research, it is divided into two kinds according to path computing rule path allocation mode, one kind is optimal path distribution, directly
Connect the subordinate ordered array that optimal path is represented to path variable assignment, another kind is the path allocation under the pattern of discrete selection, road
Footpath r1,r2,r3,r4Select probability be respectively p1,p2,p3,p4, then path allocation algorithm be：
The random number k that 0≤interval [0,100] of if generates at random<100·p1, then selection path r1
if100·p1The random number k that≤interval [0,100] generates at random<100·(p1+p2), then selects path r2
if100·(p1+p2The random number k that)≤interval [0,100] generates at random<100·(p1+p2+p3), then selects road
Footpath r3
if 100·(p1+p2+p3The random number k that)≤interval [0,100] generates at random<100·(p1+p2+p3+p4),
Then selects path r4
(4) collection of information and transmission
The collection of information includes the collection of the information such as journey time, oil consumption, section vehicle number, section saturation, its Road
The information such as section vehicle number, section saturation are easier to obtain, most importantly journey time and fuel consumption information.
1) journey time
Clock ticks is set with analogue system, vehicle reached node i before into section a, now by the value of clock
It is assigned to Vehicle Agent variable ti, when reaching section a endpoint node j equally after vehicle rolls section a away from, then clock value is assigned
It is worth and gives Vehicle Agent variable tj, then calculate journey time t of the vehicle on a of sectiona=tj-ti, to the average of section a
The collection of journey time adopt length for 5 array TraCarry out storing journey time of the vehicle on a of section and ask its average to make
For the average travel time of section a, its algorithm is：
If vehicles n uses section a
If arrays TraLength<5
Journey time by vehicle n on section adds array TraAs first element, and calculate the average work of array
For the average travel time of section a
Else removes array TraLast element
2) oil consumption
Fuel consumption information is calculated by oil consumption model, due to it is desirable that section oil consumption situation, logical used here as one
Cross traffic flow parameter calculate oil consumption collection meter oil consumption model, here with gather real-time section saturation as input variable, mould
Type is as follows：
In formula, unit gas mileages of the FC for section,For the saturation in section, a, b, c are relevant with section grade
Coefficient.
The invention has the advantages that：
(1) present invention based on traveler Path selection analogue system under the car networking environment of multiple agent from portraying individual row
Set out for model, to embody resulting macro-effect, and while consider the row of the microcosmic point and macroscopic aspect of individuality
For.The collection meter effect of macroscopic aspect behavior determines distribution of the traffic flow in road network, and the behavior of microcosmic point is not only truer
Feature actual travel situation of the vehicle on road, and reflect the operation conditions of section operation.Realize from bottom
The research of principle with probe into macroscopic view phenomenon, with more preferable cogency and effectiveness.
(2) present invention is had based on traveler Path selection analogue system under the car networking environment of multiple agent and is opened up well
Malleability, is that traveler optimizing paths and its produced traffic system operational effect are carried under research car networking (information condition)
A reliability, efficient Unified frame are supplied, under the framework, the strategic layer that can pass through to change Vehicle Agent (is selected in path
Select) rule, but also can easily change simulation parameter by the human-computer interaction interface of analogue system to change emulation field
Scape is studying different problems.
Description of the drawings
Fig. 1 is based on traveler Path selection analogue system operational process under multiple agent car networking environment
Fig. 2 analogue systems use road network and OD situations
Fig. 3 analogue system human-computer interaction interfaces
Each Link Travel Time under Fig. 4 traditional environments
Each Link Travel Time under Fig. 5 car networking environment
Specific embodiment
Describe the present invention with embodiment below in conjunction with the accompanying drawings, it should be understood that the example is merely to illustrate this
Bright rather than restriction the scope of the present invention.
As shown in figure 1, the present invention is based on traveler Path selection emulation platform environment under the car networking environment of multiple agent
In running, information system, the three part parallel operations of operation rule and information of vehicles the flowing with data flow, car
The road network status information that intelligent body is provided according to the information system for receiving after generation is according to itself rule of ac-tion in road network
Middle operation, constantly collects itself running state data in this process and passes to information system, and information system is by receiving
The running state information of all Vehicle Agents for arriving, processes these information and obtains required road network status information and feed back to
Each Vehicle Agent.
As shown in Fig. 2 in this example, the journey time in each path of the Vehicle Agent to receive, according to discrete choosing
Select model and select path, set each OD starting points and carry out car rate as come-rate1=0.22, come-rate2=0.22, come-
Rate3=0, vehicle acceleration acceleration=0.0074, deceleration deceleration=0.030, each section freedom
In flow velocity degree such as figure in the bracket of section shown in, this example purpose is to probe into car networking environment to compare under traditional environment to traffic system
The impact of operational efficiency.
After human-computer interaction interface shown in Fig. 3 carries out simulating scenes parameter setting, pressed by the setup arranged on interface
Button carries out analogue system initialization, then proceeds by l-G simulation test by clicking on go buttons, during l-G simulation test is carried out
This button can be again tapped on and then emulates time-out by data monitoring window, 2D views and drawing Real Time Observation simulation run situation,
And the switching of car networking environment and traditional environment can be controlled by information-switch.
Experiment process is presented herein below：
1) information-switch switches cut out, selects under traditional environment, to carry out l-G simulation test, click on setup and press
Button carries out analogue system initialization, then clicks on go and starts l-G simulation test, and l-G simulation test is run the regular hour, eliminates transient state
After impact, go buttons are again tapped on after emulation natural law is reached 10 days and stop l-G simulation test, derived emulation data, obtain such as Fig. 4
Shown result.
2) information-switch switches are opened, carry out step 1) middle operation, result as shown in Figure 5 is obtained,
Contrasted with each average travel time for road sections under traditional environment shown in Fig. 4.
It is described in detail above the present invention implementation process, but the present invention be not limited to it is concrete in above-mentioned embodiment
Details, in the range of the technology design of the present invention, concrete details can be to change what is replaced, can such as only need to by changing
In simulation kernel, the rule of traveler Path selection can study different problems, have higher under this simulation universal framework
Universality, belongs within protection scope of the present invention.
Claims (6)
1. Path selection analogue system under a kind of car networking environment based on multiple agent, it is characterised in that mainly pass through three classes
Intelligent body Patches, Turtles, Observer realize the simulation to real world, and Patches intelligent bodies represent road network,
Turtles intelligent bodies represent vehicle, and Observer intelligent body representative information service systems, analogue system are mainly included such as lower module
Content：
(1) foreground human-computer interaction module
It is main that four partial functions, emulation control are adjusted by Simulation Control, emulation data display and emulation animation demonstration and simulation parameter
Mainly realize that the control for starting to stop of l-G simulation test process, emulation data display and emulation animation demonstrate main basis in part processed
Need the 2D or 3D of the animation of the real-time display and l-G simulation test running that provide data in simulation process to show, and can pass through
Simulation parameter adjustment module is adjusted to the parameter of control l-G simulation test scene before l-G simulation test or during l-G simulation test,
Adjustment relevant parameter can be needed to carry out the l-G simulation test of different scenes according to test；
(2) road network is generated and is initialized
Road network is generated and the road network system before l-G simulation test starts into l-G simulation test is responsible in initialization, and the network parameters that satisfy the need are carried out
Initialize installation, road is considered as the discrete lattice point being made up of a series of tiles (Patches), and which is in the simulated environment world
Coordinate is also discrete, but position coordinateses of the vehicle in the simulated environment world are continuous, by arranging different to Patches
Color attribute characterizing road or trackside building etc., and to the every section and the certain title of node or mark for constituting road network
Number, such as the node in road network is numbered with numeral, and with these digital subordinate ordered arrays representing path, in addition,
To in the attribute in every section by the different free stream velocity in section arranging different grades of section；
(3) vehicle is generated and is initialized
Given birth to according to car rate is necessarily carried out in the given position of road network during vehicle is generated and initialization is included in simulation process as required
Into vehicle, and the certain attribute of given vehicle, including the acceleration-deceleration of vehicle, OD, vehicle ID etc.；
(4) simulation kernel
After vehicle is generated, which can be moved in road network according to simulation kernel, that is, the tactics layer of vehicle and strategic layer rule, tool
Body is：
Tactics layer rule：The regular traveling behavior to describe microcosmic point of the vehicle on road of the tactics layer of vehicle, including
Vehicle follow gallop, turning etc., vehicle n in the process of moving by the value of constantly monitoring and the tailstock spacing of front truck n+1, and by the value
Make comparisons with the safe distance threshold value of setting, then think that vehicle n is not present with speed on will be by for, vehicle n if greater than the threshold value
Free stream velocity according to place section accelerates to the speed and travels, whereas if then thinking presence with speeding on less than the threshold value
For vehicle n is then according to the acceleration and deceleration model driving of setting；When vehicle reaches junction node, Vehicular intelligent is known from experience according to itself
The numbering of residing node serial number and the next node gone out according to its route searching is stored in foundation analogue system as input
The topological structure of road network calculates steering, and performs steering according to result of calculation；
Strategic layer rule：The strategic layer rule is mainly the path finding algorithm of Vehicle Agent, based on multiple agent
Path finding algorithm can be changed as needed under the framework of Path selection analogue system under car networking environment different to study
Problem；
(5) collection of information and transmission
Information gathering is responsible for collection of the vehicle in running to oneself state information, storage and to whole road network with transmission
The acquisition of status information, process, and these information are transmitted and shared.
2. Path selection analogue system under the car networking environment based on multiple agent according to claim 1, its feature exist
In, in Vehicle Agent tactics layer rule, carrying out vehicle using the vehicle following-model of multisection type (Multi-Regime)
Microcosmic follow gallop movement is described, and carries out certain simplification.When the tailstock spacing of vehicle n and front truck n+1 is more than minimum safe distance
Δ x, vehicle n are by the free stream velocity by place section or accelerate to the speed and travel, do not exist with speed on for, when vehicle n with
When the tailstock of front truck n+1 is smaller than distance, delta x, then Vehicle Agent n carries out feed speed control using following formula：
Wherein, l, m, a are coefficient.
3. Path selection analogue system under the vehicle net environment based on multiple agent according to right wants 1, it is characterised in that
Described information gather with transmission, in analogue system can gathering simulation system operation in real time status information, mainly include
Link Travel Time, section oil consumption, average link speed, section vehicle number, section saturation etc..
4. Path selection analogue system under the car networking environment based on multiple agent according to right wants 3, it is characterised in that
In the collection of described Vehicle Agent and Link Travel Time, a clock for being used for timing is set in analogue system, is led to
Cross the clock by Vehicle Agent n in first Patches into section a and be assigned to t1, when Vehicle Agent n leaves this
Clock value during last Patches in section is assigned to t2, by ta=t2-t1Vehicle Agent is calculated in section a
On journey time, for the average travel time in section, Observer intelligent bodies store 5 by the storehouse that length is 5 and make
With the vehicle in the section the section journey time, and with the average of this 5 journey times as the section journey time,
The journey time in section is updated by constantly updating storehouse.
5. Path selection analogue system under the car networking environment based on multiple agent according to right wants 3, it is characterised in that
In the acquisition of described section fuel consumption information, based on acquired road network status data, obtained by a kind of oil consumption model of collection meter
Obtain the real-time fuel consumption information in every section, such as following formula：
In formula, unit gas mileages of the FC for section,For the saturation in section, a, b, c are the coefficient relevant with section grade.
6. Path selection analogue system under the car networking environment based on multiple agent according to claim 1, its feature exist
In, in the content (3), vehicle is generated according to car rate p of coming of setting, obeys being uniformly distributed for [0,100] by producing one
Random number k, if k ＜ 100 p, generate a Vehicle Agent, otherwise do not generate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611029593.XA CN106529064A (en) | 2016-11-15 | 2016-11-15 | Multi-agent based route selection simulation system in vehicle online environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611029593.XA CN106529064A (en) | 2016-11-15 | 2016-11-15 | Multi-agent based route selection simulation system in vehicle online environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106529064A true CN106529064A (en) | 2017-03-22 |
Family
ID=58353192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611029593.XA Pending CN106529064A (en) | 2016-11-15 | 2016-11-15 | Multi-agent based route selection simulation system in vehicle online environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106529064A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846867A (en) * | 2017-03-29 | 2017-06-13 | 北京航空航天大学 | Signalized intersections green drives speed abductive approach and analogue system under a kind of car networking environment |
| CN107554524A (en) * | 2017-09-12 | 2018-01-09 | 北京航空航天大学 | A kind of following-speed model stability control method based on subjective dangerous criminal |
| CN108549087A (en) * | 2018-04-16 | 2018-09-18 | 北京瑞途科技有限公司 | A kind of online test method based on laser radar |
| CN108897926A (en) * | 2018-06-11 | 2018-11-27 | 青岛慧拓智能机器有限公司 | A kind of artificial car networking system and its method for building up |
| CN109670620A (en) * | 2017-10-16 | 2019-04-23 | 北京航空航天大学 | Trip information service strategy and simulation checking system under a kind of car networking environment |
| CN110189517A (en) * | 2019-05-14 | 2019-08-30 | 浙江大学 | A kind of Simulation Experimental Platform towards car networking secret protection research |
| CN111159832A (en) * | 2018-10-19 | 2020-05-15 | 百度在线网络技术（北京）有限公司 | Construction method and device of traffic information flow |
| CN111651828A (en) * | 2020-06-12 | 2020-09-11 | 招商局重庆交通科研设计院有限公司 | Traffic flow simulation method and system based on routing optimization and parallel computing architecture |
| CN112990114A (en) * | 2021-04-21 | 2021-06-18 | 四川见山科技有限责任公司 | Traffic data visualization simulation method and system based on AI identification |
| CN113033306A (en) * | 2021-02-20 | 2021-06-25 | 同济大学 | Signal source searching method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593535A (en) * | 2013-11-22 | 2014-02-19 | 南京洛普股份有限公司 | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration |
| CN104537835A (en) * | 2015-01-30 | 2015-04-22 | 北京航空航天大学 | Macroscopic view and microscopic view combined circular transportation reliability simulation method and system |
-
2016
- 2016-11-15 CN CN201611029593.XA patent/CN106529064A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593535A (en) * | 2013-11-22 | 2014-02-19 | 南京洛普股份有限公司 | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration |
| CN104537835A (en) * | 2015-01-30 | 2015-04-22 | 北京航空航天大学 | Macroscopic view and microscopic view combined circular transportation reliability simulation method and system |
Non-Patent Citations (2)
| Title |
|---|
| 张晓璇 等: "《车辆跟驰的计算机仿真***设计与实现》", 《中国汽车工程学会.2010中国汽车工程学会年会论文集》 * |
| 魏丹: "《基于多Agent仿真的城市道路交通拥挤定价政策研究》", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846867A (en) * | 2017-03-29 | 2017-06-13 | 北京航空航天大学 | Signalized intersections green drives speed abductive approach and analogue system under a kind of car networking environment |
| CN107554524A (en) * | 2017-09-12 | 2018-01-09 | 北京航空航天大学 | A kind of following-speed model stability control method based on subjective dangerous criminal |
| CN109670620A (en) * | 2017-10-16 | 2019-04-23 | 北京航空航天大学 | Trip information service strategy and simulation checking system under a kind of car networking environment |
| CN108549087B (en) * | 2018-04-16 | 2021-10-08 | 北京瑞途科技有限公司 | Online detection method based on laser radar |
| CN108549087A (en) * | 2018-04-16 | 2018-09-18 | 北京瑞途科技有限公司 | A kind of online test method based on laser radar |
| CN108897926A (en) * | 2018-06-11 | 2018-11-27 | 青岛慧拓智能机器有限公司 | A kind of artificial car networking system and its method for building up |
| CN108897926B (en) * | 2018-06-11 | 2024-02-23 | 青岛慧拓智能机器有限公司 | Artificial Internet of vehicles system and establishment method thereof |
| CN111159832A (en) * | 2018-10-19 | 2020-05-15 | 百度在线网络技术（北京）有限公司 | Construction method and device of traffic information flow |
| CN111159832B (en) * | 2018-10-19 | 2024-04-02 | 百度在线网络技术（北京）有限公司 | Traffic information stream construction method and device |
| CN110189517A (en) * | 2019-05-14 | 2019-08-30 | 浙江大学 | A kind of Simulation Experimental Platform towards car networking secret protection research |
| CN111651828A (en) * | 2020-06-12 | 2020-09-11 | 招商局重庆交通科研设计院有限公司 | Traffic flow simulation method and system based on routing optimization and parallel computing architecture |
| CN113033306A (en) * | 2021-02-20 | 2021-06-25 | 同济大学 | Signal source searching method |
| CN113033306B (en) * | 2021-02-20 | 2023-04-18 | 同济大学 | Signal source searching method |
| CN112990114A (en) * | 2021-04-21 | 2021-06-18 | 四川见山科技有限责任公司 | Traffic data visualization simulation method and system based on AI identification |
| CN112990114B (en) * | 2021-04-21 | 2021-08-10 | 四川见山科技有限责任公司 | Traffic data visualization simulation method and system based on AI identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106529064A (en) | Multi-agent based route selection simulation system in vehicle online environment | |
| CN108931927B (en) | The creation method and device of unmanned simulating scenes | |
| CN101639871B (en) | Vehicle-borne dynamic traffic information induction system analog design method facing behavior research | |
| CN110263381A (en) | A kind of automatic driving vehicle test emulation scene generating method | |
| CN106846867A (en) | Signalized intersections green drives speed abductive approach and analogue system under a kind of car networking environment | |
| CN107229973A (en) | The generation method and device of a kind of tactful network model for Vehicular automatic driving | |
| CN106846818B (en) | road network dynamic traffic flow prediction method based on Simulink simulation | |
| CN107301289B (en) | Method for realizing traffic flow cellular automaton model based on intelligent game | |
| CN101807224B (en) | Mesoscopic-microcosmic integrated traffic simulation vehicle flow loading method | |
| CN106384509A (en) | Urban road driving time distribution estimation method considering taxi operation states | |
| CN106198049A (en) | Real vehicles is at ring test system and method | |
| CN109670620A (en) | Trip information service strategy and simulation checking system under a kind of car networking environment | |
| CN103593535A (en) | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration | |
| DE102012107309A1 (en) | Method and apparatus for estimating power usage | |
| CN106373453A (en) | Intelligent immersive high-speed train virtual driving behavior evaluation method and simulation system | |
| CN106779148A (en) | A kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion | |
| CN109726804A (en) | A kind of intelligent vehicle driving behavior based on driving prediction field and BP neural network personalizes decision-making technique | |
| CN102682155A (en) | Network analysis micro-simulation system for urban road traffic | |
| CN101556625A (en) | Computer dynamic simulation method of driver dynamic response behavior about graphic path information board | |
| Aschwanden et al. | Agent based evaluation of dynamic city models: A combination of human decision processes and an emission model for transportation based on acceleration and instantaneous speed | |
| CN114328448A (en) | Expressway vehicle following behavior reconstruction method based on simulated learning algorithm | |
| CN109447327A (en) | Subway train track prediction method | |
| CN104504170A (en) | Animated simulation method and system of vehicle | |
| CN106938657A (en) | Subway conflict early warning method based on robust strategy | |
| CN110119528A (en) | A kind of random traffic flow simulation system of bridge based on intelligent body cellular automata |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |
|
| RJ01 | Rejection of invention patent application after publication |