CN108417026A - A kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal - Google Patents
A kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal Download PDFInfo
- Publication number
- CN108417026A CN108417026A CN201711249661.8A CN201711249661A CN108417026A CN 108417026 A CN108417026 A CN 108417026A CN 201711249661 A CN201711249661 A CN 201711249661A CN 108417026 A CN108417026 A CN 108417026A
- Authority
- CN
- China
- Prior art keywords
- intelligent vehicle
- vehicle
- passage capability
- road passage
- section
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal, according to the correlation theory in Statistical Physics, it is modeled by renormalization, in complicated transportation system, microcosmic discrete message is integrated in layering, simulate the road passage capability of macroscopically traffic system, sum up the formula of a reflection microcosmic vehicle number and macroscopical traffic capacity relationship, the result effectively can be directly fitted in mathematical calculation model with less noise, and then a kind of intelligent vehicle ratio acquiring method for keeping road passage capability optimal is proposed on the basis of this model, it is more efficient compared to emulation mode quick, with certain realistic meaning.
Description
Technical field
The invention belongs to traffic management technology fields, are related to a kind of intelligent vehicle ratio acquisition methods, specifically a kind of to make
The optimal intelligent vehicle ratio acquisition methods of the road traffic capacity.
Background technology
Each metropolitan most area heavy traffic in the world is suffered heavy losses caused by the situations such as crowded, blocking.And it makes
It is many at congested in traffic reason, such as the shape of road, unexpected traffic accident, the limitation etc. of road passage capability, road energy
Power is most important to the predicament for solving traffic congestion.
And in special parameter roadnet, the ratio shared by intelligent automobile how is configured, could make the road of system
The traffic capacity is optimal, is the main problem that those skilled in the art face.
Wherein, special parameter roadnet refers to that it is same that there are two types of type automobiles --- general-utility car and intelligent automobile ---
When the road traffic system that travels.General-utility car refers to the automobile for being operated by driver and being travelled；Intelligent automobile is a kind of outfit
The autonomous driving vehicle of partner systems, it can share immediate status, and can be according to environment with other intelligent automobile real-time communications
Moment decision is made with the driving information of other vehicles, adjusts driving mode.
The prior art usually calculates target variable with the mode of emulation, and huge calculating money can be consumed when data set is very big
Source, and the result of calculation approximate convergence emulated, in the random sample extracted from assuming to be distributed, accuracy is not high.
Invention content
The purpose of the present invention is to provide a kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal, from statistics
The angle of physics proposes that Renormalization Method establishes the physical model of the description system current average link traffic capacity, and then obtains
So that the intelligent vehicle ratio that system road passage capability is optimal.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal, specifically include following steps：
Step S1 models current average link traffic capacity PACR；
Step S2 determines the minimum ratio of intelligent automobile based on the model in step S1；
Step S3 obtains the maximum traffic density in arbitrary section；
Step S4 determines the corresponding intelligent vehicle ratio of road passage capability value to the section in step S3；
Step S5 calculates the intelligent vehicle ratio for keeping road passage capability optimal.
Further, it is multiple local sections by lane segmentation, to each office when being modeled to PACR in the step S1
Portion analyzes in section respectively to be integrated again；In local section, PACR is modeled using Renormalization Method, intelligent vehicle and front
Vehicle be combined as a fleet, when all vehicles are all in the fleet that common in-vehicle is taken the lead, renormalization terminates；
At this point, PACR is described by following formula：
In formula, Ψ (λ, ρ0) it is current average link traffic capacity PACR, λ is intelligent vehicle proportion；ρ0For initial vehicle
Density；dcFor intelligent vehicle between front truck at a distance from, car state is existed side by side and is made a change before capable of continuously being known due to intelligent vehicle, so
They and front truck can keep minimum safe distance ds；V () indicates the average speed of vehicle, is the function of traffic density, d
() indicates the distance of front and back two vehicles, is the function of speed.
Further, in the step S2, the current vehicle flowrate Φ in all sections is calculated to arbitrary sectioni0, i=1,
2 ..., n find out an intelligent automobile ratio lambda, all sections are made to meet：
Φi0≤Ψ(λ,ρi)max
λ=λ at this time0The as minimum ratio of intelligent automobile.
Further, in the step S3, in the minimum ratio lambda of intelligent vehicle0In the case of, equation is solved to i-th of section：
Φi0=Ψ (λ0,ρi0)
Solve the traffic density ρ for making the section reach current vehicle flowratei0, larger value is taken in two solutions, is denoted as the section
Maximum traffic density ρimax。
Further, in the step S4, to i-th of section, ρ is enabledi=ρimax, corresponding in a series of intelligent vehicle ratios
Different current average link traffic capacity ΨiIn, find out maximum current average link traffic capacity Ψimax, i.e. road energy
Force value, and record intelligent vehicle ratio lambda at this timei。
Further, in the step S5, step S3 and step S4 is repeated to all sections, each section is obtained and reaches path link
Intelligent vehicle ratio lambda when row ability valueiSequence { the λ constitutedi, i=1,2 ..., n, and the sequence converges on a limit, in
It is optimal intelligent vehicle ratio lambdabestFor：
In formula,siFor the length in i-th of section.
Beneficial effects of the present invention：The intelligent vehicle ratio acquisition methods provided by the invention for keeping road passage capability optimal,
It according to the correlation theory in Statistical Physics, is modeled by renormalization, in complicated transportation system, layering is integrated microcosmic discrete
Information simulates the road passage capability of macroscopically traffic system, sums up the microcosmic vehicle number of a reflection and macroscopical traffic capacity
The formula of relationship, the result effectively can be directly fitted in mathematical calculation model with less noise, and then in this model
On the basis of propose a kind of intelligent vehicle ratio acquiring method for keeping road passage capability optimal, it is more efficient compared to emulation mode fast
Victory has certain realistic meaning.
Description of the drawings
Present invention is further described in detail in the following with reference to the drawings and specific embodiments.
Fig. 1 is flow chart of the method for the present invention.
Fig. 2 be different intelligent vehicle ratio lambda under, the current average link traffic capacity with initial vehicle variable density curve.
Fig. 3 is the curve that the current average link traffic capacity changes with intelligent vehicle ratio lambda under different initial vehicle density.
Fig. 4 is multilane Cellular Automata result schematic diagram.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained all other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
The present invention provides a kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal, are built by renormalization
Mould, in complicated transportation system, microcosmic discrete message is integrated in layering, simulates the road energy of macroscopically traffic system
Power, sums up the formula of a microcosmic vehicle number of reflection and macroscopical traffic capacity relationship, and then finds out and make on the basis of this formula
Obtain the optimal intelligent vehicle ratio of system road passage capability.
As shown in Figure 1, specific implementation step of the present invention includes：
Step S1, the current average link traffic capacity (PACR) modeling.
Wherein, road passage capability refers under all roads, traffic and control condition, and vehicle can reasonably pass through track
Or a point of road or the maximum ratio per hour of uniform part；The current average link traffic capacity (PACR) refers to current
Under the conditions of, maximum vehicle flowrate possible per hour, unit：/ second；To which road passage capability is the extreme value of PACR curves
Therefore point by studying the relationship of PACR and intelligent vehicle ratio, and then acquires the intelligent vehicle ratio for keeping road passage capability optimal
Example.The present invention first has to model PACR, due to PACR between vehicle at a distance from, Vehicle length and Vehicle Speed have
It closes, general formulae is：
In formula, Ψ indicates that PACR, N are the vehicle fleet in target road section, vkIndicate that the speed of kth vehicle, s are that vehicle is long
Degree, d are the distance between two general-utility cars.
In conjunction with mean field theory, it is assumed that the traffic speed of a position can independently be influenced by entire road conditions, in
It can be multiple parts by lane segmentation to be, each part section is analyzed respectively to be integrated again.
In local section, the present invention uses the renormalization thought in Statistical Physics to model PACR.Renormalization it is each
Step is exactly：The vehicle of intelligent vehicle and front is combined as one " fleet ", by being transformed into " the small fleet " in local section by " small
Fleet " determines " the big fleet " of feature, to optimize the PACR functions in local section.
Our targets are to keep local PACR maximum, that is, as make car speed big as possible and spacing in this process
It is small.
First, about car speed, car state makes a change for thirty years of age before capable of continuously being known due to intelligent vehicle, and then can be with
Front truck can keep identical speed, so the average speed of final section vehicle depends on the average speed of common in-vehicle.And because
The fluctuation of mankind's driving behavior, especially unnecessary braking action, therefore the common in-vehicle with human behavioral mode is close
Degree determines the average speed of common in-vehicle.
Secondly, same because car state makes a change for thirty years of age before intelligent vehicle can continuously be known about spacing, and then can be with
Front truck can keep minimum safe distance, i.e. dc=ds；For common in-vehicle, the spacing under safe distance is minimum, and safe distance is
The function of front and back two vehicle speed, since intelligent vehicle speed is identical as front truck, so the safe distance of common in-vehicle is that common in-vehicle is flat
The function of equal speed, i.e. d (v)=d (v ((1- λ) ρ0)).,
So the core principles of renormalization strategy are：As far as possible a team is lined up with other intelligent vehicles.When all vehicles are all general
When being open to traffic in the fleet taken the lead, renormalization terminates.
Therefore, in the roadnet containing intelligent vehicle and common in-vehicle, PACR can be described by following formula：
In formula, Ψ (λ, ρ0) it is current average link traffic capacity PACR, λ is intelligent vehicle proportion；ρ0For initial vehicle
Density；dcFor intelligent vehicle between front truck at a distance from, car state is existed side by side and is made a change before capable of continuously being known due to intelligent vehicle, so
They and front truck can keep minimum safe distance ds；V () indicates the average speed of vehicle, is the function of traffic density, d
() indicates the distance of front and back two vehicles, is the function of speed.
The mode of prior art generally use Computer Simulation studies road passage capability, by comparing under identical parameters
The result of calculation of Cellular Automata result and above-mentioned model can prove the validity of model of the present invention.Experiment knot
Fruit is as follows.
Fig. 2 is current average link traffic capacity Ψ (λ, ρ0) with initial vehicle density p0Change curve, wherein intelligent vehicle
Ratio lambda value is respectively to be divided into 0.05 20 values from 0 to 0.95.Since road passage capability is defined as all roads
Under the conditions of maximum stream flow, the extreme point of each PACR curves represents the traffic capacity of target road section.As seen from Figure 2,
Intelligent vehicle ratio lambda is higher, and road passage capability is bigger, but the road passage capability under the λ of part, i.e. Ψ (λ, ρ0) hump,
Corresponding traffic density is unsatisfactory for ρ0The actual requirement of ＜ 1.
Then, by initial vehicle density p0Value be set as from 0 to 0.95, be divided into 0.05 20 values, obtain
Different initial vehicle density ps0Under, current average link traffic capacity Ψ (λ, ρ0) with the change curve of intelligent vehicle ratio lambda, such as Fig. 3
It is shown.Fig. 3 illustrates that the current average link traffic capacity and intelligent vehicle ratio are not positively related, Ψ (λ, ρ0) first increase with λ after
Reduce.
The results are shown in Figure 4 for traditional Cellular Automata under identical parameters.From left to right, from top to bottom, four sons
When figure is respectively 1 track, 2 tracks, 3 tracks and 4 track, intelligent vehicle ratio p is under nine kinds of different value conditions, current mean-trace
The road traffic capacity (Ψ) with initial vehicle density (dens i ty) change curve.
Comparison diagram 2 and Fig. 4 can be seen that the reason of the main trend and characteristic peaks and model of the present invention of simulation result
It is consistent by result of calculation, it was demonstrated that the validity of the modeling method.
Following step based on the model in step S1, will continue to obtain the intelligent vehicle ratio for keeping road passage capability optimal
Example.
Step S2 determines the minimum ratio lambda of intelligent automobile0。
The current vehicle flowrate Φ in all sections is calculated to certain a road sectioni0, i=1,2 ..., n find out an intelligent automobile
Ratio lambda makes all sections all meet：
Φi0≤Ψ(λ,ρi)max
λ=λ at this time0The as minimum ratio of intelligent automobile.Under this ratio, peak period does not have section and blocks up
Plug.
Step S3 obtains the maximum traffic density ρ in arbitrary sectionimax
In minimum intelligent vehicle ratio lambda0In the case of, equation is solved to i-th of section：
Φi0=Ψ (λ0,ρi0)
Solve the traffic density ρ for making the section reach current vehicle flowratei0, larger value is taken in two solutions, is denoted as the section
Maximum traffic density ρimax。
Step S4 determines the corresponding intelligent vehicle ratio lambda of road passage capability value to the section in step S3i。
To i-th of section, ρ is enabledi=ρimax, in a series of corresponding different road passage capability Ψ of intelligent vehicle ratio lambdasiIn,
Find out maximum current average link traffic capacity Ψimax, i.e. road passage capability value, and the intelligent vehicle ratio lambda of record at this timei。
Step S5 calculates the intelligent vehicle ratio lambda for keeping road passage capability optimalbest。
Step S3 and step S4 is repeated to all sections, obtains intelligent vehicle ratio of each section up to road passage capability value when
λiSequence { the λ constitutedi, i=1,2 ..., n, and the sequence converges on a limit.According to pertinent literature, road congestion rate
It is linearly related with link length, so the present invention weighs best intelligent vehicle ratio using link length.Then, system is optimal
Intelligent vehicle ratio lambdabestIt can be calculated by following formula：
In formula,siFor the length in i-th of section.
Claims (6)
1. a kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal, which is characterized in that specifically include following steps：
Step S1 models current average link traffic capacity PACR；
Step S2 determines the minimum ratio of intelligent automobile based on the model in step S1；
Step S3 obtains the maximum traffic density in arbitrary section；
Step S4 determines the corresponding intelligent vehicle ratio of road passage capability value to the section in step S3；
Step S5 calculates the intelligent vehicle ratio for keeping road passage capability optimal.
2. a kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal according to claim 1, feature exist
In being multiple local sections by lane segmentation when being modeled to PACR in the step S1, analyzed respectively each local section
It is integrated again；In local section, PACR is modeled using Renormalization Method, the vehicle of intelligent vehicle and front is combined as one
Fleet, when all vehicles are all in the fleet that common in-vehicle is taken the lead, renormalization terminates；
At this point, PACR is described by following formula：
In formula, Ψ (λ, ρ0) it is current average link traffic capacity PACR, λ is intelligent vehicle proportion；ρ0It is close for initial vehicle
Degree；dcFor intelligent vehicle between front truck at a distance from, car state is existed side by side and is made a change before capable of continuously being known due to intelligent vehicle, thus it
And front truck can keep minimum safe distance ds；V () indicates the average speed of vehicle, is the function of traffic density, d ()
The distance for indicating front and back two vehicles, is the function of speed.
3. a kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal according to claim 1, feature exist
In in the step S2, the current vehicle flowrate Φ in all sections is calculated to arbitrary sectionI0,I=1,2 ..., n find out one
Intelligent automobile ratio lambda makes all sections all meet：
Φi0≤ Ψ (λ, ρi)max
λ=λ at this time0The as minimum ratio of intelligent automobile.
4. a kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal according to claim 1, feature exist
In in the step S3, in the minimum ratio lambda of intelligent vehicle0In the case of, equation is solved to i-th of section：
Φi0=Ψ (λ0, ρi0)
Solve the traffic density ρ for making the section reach current vehicle flowratei0, larger value is taken in two solutions, is denoted as the section most
Big vehicle density pimax。
5. a kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal according to claim 1, feature exist
In in the step S4, to i-th of section, enabling ρi=ρimax, in a series of corresponding current mean-trace of difference of intelligent vehicle ratios
Road traffic capacity ΨiIn, find out maximum current average link traffic capacity Ψimax, i.e. road passage capability value, and record this
When intelligent vehicle ratio lambdai。
6. a kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal according to claim 1, feature exist
In in the step S5, repeating step S3 and step S4 to all sections, obtain when each section reaches road passage capability value
Intelligent vehicle ratio lambdaiSequence { the λ constitutedi, i=1,2 ..., n, and the sequence converges on a limit, then, optimal intelligence
It can vehicle ratio lambdabestFor：
In formula,siFor the length in i-th of section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711249661.8A CN108417026B (en) | 2017-12-01 | 2017-12-01 | Intelligent vehicle proportion obtaining method for optimizing road traffic capacity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711249661.8A CN108417026B (en) | 2017-12-01 | 2017-12-01 | Intelligent vehicle proportion obtaining method for optimizing road traffic capacity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108417026A true CN108417026A (en) | 2018-08-17 |
| CN108417026B CN108417026B (en) | 2020-07-07 |
Family
ID=63125345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711249661.8A Active CN108417026B (en) | 2017-12-01 | 2017-12-01 | Intelligent vehicle proportion obtaining method for optimizing road traffic capacity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108417026B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992676A (en) * | 2019-10-15 | 2020-04-10 | 同济大学 | Road traffic capacity and internet automatic driving vehicle equivalent coefficient estimation method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104821080A (en) * | 2015-03-02 | 2015-08-05 | 北京理工大学 | Intelligent vehicle traveling speed and time predication method based on macro city traffic flow |
| CN105631793A (en) * | 2015-12-18 | 2016-06-01 | 华南理工大学 | Intelligent traffic flow congestion dispersal method through vehicle group autonomous cooperative scheduling |
| US9511767B1 (en) * | 2015-07-01 | 2016-12-06 | Toyota Motor Engineering & Manufacturing North America, Inc. | Autonomous vehicle action planning using behavior prediction |
| CN106335513A (en) * | 2015-07-10 | 2017-01-18 | 沃尔沃汽车公司 | Method and system for smart use of in-car time with advanced pilot assist and autonomous drive |
| US20170113687A1 (en) * | 2015-10-27 | 2017-04-27 | International Business Machines Corporation | Controlling Spacing of Self-Driving Vehicles Based on Social Network Relationships |
| CN106896353A (en) * | 2017-03-21 | 2017-06-27 | 同济大学 | A kind of unmanned vehicle crossing detection method based on three-dimensional laser radar |
| CN106898143A (en) * | 2017-04-10 | 2017-06-27 | 合肥学院 | A kind of magnitude of traffic flow modeling method of pilotless automobile |
-
2017
- 2017-12-01 CN CN201711249661.8A patent/CN108417026B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104821080A (en) * | 2015-03-02 | 2015-08-05 | 北京理工大学 | Intelligent vehicle traveling speed and time predication method based on macro city traffic flow |
| US9511767B1 (en) * | 2015-07-01 | 2016-12-06 | Toyota Motor Engineering & Manufacturing North America, Inc. | Autonomous vehicle action planning using behavior prediction |
| CN106335513A (en) * | 2015-07-10 | 2017-01-18 | 沃尔沃汽车公司 | Method and system for smart use of in-car time with advanced pilot assist and autonomous drive |
| US20170113687A1 (en) * | 2015-10-27 | 2017-04-27 | International Business Machines Corporation | Controlling Spacing of Self-Driving Vehicles Based on Social Network Relationships |
| CN105631793A (en) * | 2015-12-18 | 2016-06-01 | 华南理工大学 | Intelligent traffic flow congestion dispersal method through vehicle group autonomous cooperative scheduling |
| CN106896353A (en) * | 2017-03-21 | 2017-06-27 | 同济大学 | A kind of unmanned vehicle crossing detection method based on three-dimensional laser radar |
| CN106898143A (en) * | 2017-04-10 | 2017-06-27 | 合肥学院 | A kind of magnitude of traffic flow modeling method of pilotless automobile |
Non-Patent Citations (5)
| Title |
|---|
| 张凤琴 等: "城市交通网元胞自动机全局流量预测方法", 《计算机应用研究》 * |
| 张瑞坤 等: "基于元胞自动机的自动驾驶汽车在交通网络中的效能分析", 《竞赛论坛》 * |
| 潘青贵: "关于无人驾驶车辆推广应用的思考", 《广汽传媒杯 广东省汽车行业第八期学术会议论文集》 * |
| 邢建民 等: "自动驾驶汽车在交通网络中的效能分析", 《数学建模及其应用》 * |
| 邱小平 等: "基于安全距离的手动_自动驾驶混合交通流研究", 《交通运输系统工程与信息》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992676A (en) * | 2019-10-15 | 2020-04-10 | 同济大学 | Road traffic capacity and internet automatic driving vehicle equivalent coefficient estimation method |
| CN110992676B (en) * | 2019-10-15 | 2021-06-04 | 同济大学 | Road traffic capacity and internet automatic driving vehicle equivalent coefficient estimation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108417026B (en) | 2020-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113781806B (en) | Mixed traffic flow passing method used in intelligent network connection environment | |
| CN108595823B (en) | Autonomous main vehicle lane changing strategy calculation method combining driving style and game theory | |
| CN109035862A (en) | A kind of more vehicles collaboration lane-change control method based on truck traffic | |
| CN109840641B (en) | Method for quickly optimizing train multi-section operation curve | |
| CN109709956A (en) | A kind of automatic driving vehicle speed control multiple-objection optimization with algorithm of speeding | |
| CN113253739B (en) | Driving behavior decision method for expressway | |
| CN103593535A (en) | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration | |
| CN106529674A (en) | Multiple-unmanned-aerial-vehicle cooperated multi-target distribution method | |
| CN103324085A (en) | Optimal control method based on supervised reinforcement learning | |
| CN110956851B (en) | Intelligent networking automobile cooperative scheduling lane changing method | |
| CN110182217A (en) | A kind of traveling task complexity quantitative estimation method towards complicated scene of overtaking other vehicles | |
| Mao et al. | A comparison of deep reinforcement learning models for isolated traffic signal control | |
| CN115457782B (en) | Automatic driving vehicle intersection conflict-free cooperation method based on deep reinforcement learning | |
| CN109544913A (en) | A kind of traffic lights dynamic timing algorithm based on depth Q e-learning | |
| CN104809890A (en) | Traffic signal timing optimization method based on principal component analysis and local search improvement orthogonality genetic algorithm | |
| CN104700634A (en) | Adjacent intersection road coordinate control method based on minimum spanning tree clustering improved genetic algorithm | |
| CN115862322A (en) | Vehicle variable speed limit control optimization method, system, medium and equipment | |
| CN103699933A (en) | Traffic signal timing optimization method based on minimum spanning tree clustering genetic algorithm | |
| CN108417026A (en) | A kind of intelligent vehicle ratio acquisition methods for keeping road passage capability optimal | |
| Li et al. | Energy-efficient autonomous vehicle control using reinforcement learning and interactive traffic simulations | |
| Wang et al. | Changing lane probability estimating model based on neural network | |
| Chen et al. | Cooperative control of connected hybrid electric vehicles and traffic signals at isolated intersections | |
| Lichtlé et al. | Fuel consumption reduction of multi-lane road networks using decentralized mixed-autonomy control | |
| CN115100866B (en) | Vehicle-road cooperative automatic driving decision-making method based on layered reinforcement learning | |
| CN110070222A (en) | A kind of evolution regulation method and system of traffic low emission |
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 |