CN106960189A - A kind of driving intention decision method based on hidden Markov model - Google Patents
A kind of driving intention decision method based on hidden Markov model Download PDFInfo
- Publication number
- CN106960189A CN106960189A CN201710167276.2A CN201710167276A CN106960189A CN 106960189 A CN106960189 A CN 106960189A CN 201710167276 A CN201710167276 A CN 201710167276A CN 106960189 A CN106960189 A CN 106960189A
- Authority
- CN
- China
- Prior art keywords
- driving
- driving intention
- model
- driver
- pedal aperture
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a kind of driving intention decision method based on hidden Markov model, different driver's driver behaviors can not only be recognized in time, judge the driving intention of current driver's, and combine road surface ahead situation, evaluation is made to driver's driving intention auxiliary just, it can also be allowed to be more suitable for present road situation, so as to reduce oil supply action unnecessary in driving procedure, actively realize reduction oil consumption and enhancing drive safety.
Description
Technical field
The present invention relates to vehicle drive auxiliary fuel-saving technique field, more particularly to it is a kind of based on hidden Markov model
Driving intention decision method.
Background technology
Since automobile came out from before more than 100 years, the essential basic vehicles and the mankind in just being lived as people
The mark of social material civilization.With the improvement of people ' s living standards, increasing automobile has come into huge numbers of families, but and this
Meanwhile, road traffic accident is also along with frequent generation, the serious disaster brought to the mankind, studies carefully and the reason for accident occurs, enters
And find and greatly the prevent accident method of generation of limit is the problem of whole society pays close attention to jointly, it is also to be related to the country and people
The important topic of interests；But traffic accident belongs to chance event, with contingency, it is difficult to predict；People is both traffic accident
Victim, is the producer of traffic accident again；Show according to the statistics of traffic accident causation, 80%~90% traffic accident
It is to be caused by the human factor of driver oneself.
With the aggravation of development and the resource scarcity of automotive engineering, the security of vehicle itself is driving while lifting
During fuel-economizing it is also extremely urgent, but different drivers has different driving habits in driving procedure, according to the study
It has been shown that, veteran driver is up to 25%, produced by different driver behavior behaviors with the driver's gap lacked experience
Oil consumption also differ greatly；In various auxiliary driving methods, mainly detected with intelligent start/stop, cruise, driver blind area,
Security and reduction oil consumption in the passive measure increase driving procedure such as doubling aid prompting；Domestic and foreign scholars propose many drive
Intension recognizing method.But mostly accommodation relative narrowness, and very high is required to the professional skill of driver；If can be driven to difference
The person's of sailing driver behavior is recognized, judges the driving intention of current driver's, and road surface ahead situation can be combined simultaneously by needing one kind badly
Make that evaluation is auxiliary just to driver's driving intention, make it to be more suitable for present road situation, so as to reducing in driving procedure
Unnecessary oil supply acts, actively realizes reduction oil consumption and strengthen the method for drive safety.
The content of the invention
In order to solve the above-mentioned technical problem, the present invention provides a kind of driving intention based on hidden Markov model and judged
Different driver's driver behaviors can not only be recognized by method in time, judge the driving intention of current driver's, and be combined
Road surface ahead situation, evaluation is made to driver's driving intention auxiliary just, moreover it is possible to be allowed to be more suitable for present road situation, so as to
Oil supply action unnecessary in driving procedure is reduced, reduction oil consumption and enhancing drive safety is actively realized.
The present invention solve its technical problem use technical scheme be：A kind of driving meaning based on hidden Markov model
Realized on figure decision method, including driving intention decision-making system of this method based on hidden Markov model, it is described based on hidden
Driving intention decision-making system containing Markov model includes server and multiple condition of road surface data terminals, the condition of road surface
Data terminal includes GPS, sillometer, accelerator pedal aperture, accelerator pedal aperture measurement meter, accelerates aperture rate of change meter,
Brake pedal aperture measurement meter；The condition of road surface data terminal also includes transportation database, condition of road surface data terminal and
Radio communication is carried out between server；This method comprises the following steps：
Driving condition is identified according to sillometer information for condition of road surface data terminal, comprises the following steps：
A, according to driver drives vehicle process, mainly have anxious acceleration on road surface, accelerate, at the uniform velocity keep, slow down, it is anxious slow down it is several
Class driving condition, above-mentioned five kinds of driving conditions are abbreviated as respectively, HD, D, N, P, HP, between the timing node of setting, and five kinds are driven
The current driving intention of driver can be reflected by sailing state.Every kind of each class driving condition has corresponding driver behavior respectively, main
It is embodied in accelerator pedal aperture, brake pedal aperture, and its on rate of change.Assuming that on track five kinds of driving intention classes
Type is respectively Sn(n=1,2,3,4,5), in continuous timing node, driving intention state can probability transfer or holding
It is constant.It is O to drive observation Value Typesm(m=1,2,3), Sn,OmWith mapping relations characterized with probable value；
B, according to continuous action in driving procedure, observed object collection is combined into O (t)={ o1(t),o2(t),o3(t) }, o1
(t),o2(t),o3(t) accelerator pedal aperture is represented respectively, accelerates aperture rate of change, brake pedal aperture；
Comprehensive Markov model is described as D=[A, μ, π, c, B], real-time status set Sn={ s1,s2,
s3......sn, then original state transfer matrix is A={ aij, aij=P (qi=Sj|qi-1=Si), initial state probabilities distribution
π={ πi},πi=P (q1=Si).The random process of driving behavior is described using the single Gauss model of three mixing herein；Wherein see
Survey probability density and use three-dimensional Gaussian probability density function, representative function is：
In above formula, Cjk-- the weight coefficient of state matrix, the mono- Gauss model numbers of M--, No(μjk,Ujk) -- sample rate
Function, o-- target observations value vector；
C, evaluation problem：Given HMM seeks the probability of an observation sequence；Decoding problem：The most possible generation one of search
The hidden state sequence of observation sequence；Problem concerning study：Given observation sequence generates a HMM；Wherein problem concerning study is i.e. to HMM moulds
Type carries out repetitive exercise several times, and the convergency value of final checking model reaches driving intention identifying purpose；
Forward direction probability is：
Backward probability is：.
, it is necessary to c in (1) formula in learning trainingjk,μjk, iterative re-evaluation, final maximum likelihood logarithm value is：
By carrying out learning training to the model to various driving datas, formula 4. middle L values convergence is finally given, that is, be can determine that
The driving intention model drawn by HMM observing and nursings；
4th, the checking of driving intention identification model and emulation
Gather the driver behavior in sampling time node：Throttle accelerator pedal aperture, accelerator open degree rate of change, brake pedal
Aperture is input in the HMM model trained as input data, obtains the HMM driving intention model groups D=in the time cycle
4. [A, μ, π, c, B], the maximum likelihood logarithm value of computation model is distinguished according to formula, and optimal result is chosen more afterwards and is adopted as the time
Driving intention in the collection cycle.
Compared with prior art, a kind of driving intention decision method based on hidden Markov model of the invention is not only
Different driver's driver behaviors can be recognized in time, judge the driving intention of current driver's, and combine road surface ahead
Situation, evaluation is made to driver's driving intention auxiliary just, moreover it is possible to be allowed to be more suitable for present road situation, so as to reduce driving
During unnecessary oil supply action, actively realize reduction oil consumption and enhancing drive safety.
Brief description of the drawings
The present invention is further described with reference to the accompanying drawings and examples.
Fig. 1 is the driving intention and observation of the present invention with the model of meshed network association mode；
Fig. 2 is that driving intention distinguishes schematic diagram；
Peration data in Fig. 3 timing nodes；
Fig. 4 HMM model identification results；
Fig. 5 is a kind of course diagram of embodiment of the present invention；
Fig. 6 is Fig. 5 driving intention recognition result；
Fig. 7 is Fig. 5 front and rear contrast of optimization；
A, b represent probability of happening in figure, and i, j (i, j=n, i ≠ j) represents driver's driving intention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, belongs to protection scope of the present invention.
A kind of driving intention decision method based on hidden Markov model, this method is based on hidden Markov model
Driving intention decision-making system on realize, the driving intention decision-making system based on hidden Markov model include server
With multiple condition of road surface data terminals, the condition of road surface data terminal is stepped on including GPS, sillometer, accelerator pedal aperture, acceleration
Plate aperture measurement meter, accelerates aperture rate of change meter, brake pedal aperture measurement meter；The condition of road surface data terminal is also wrapped
Transportation database has been included, radio communication is carried out between condition of road surface data terminal and server；This method comprises the following steps：
Driving condition is identified according to sillometer information for condition of road surface data terminal, comprises the following steps：
A, according to driver drives vehicle process, mainly have anxious acceleration on road surface, accelerate, at the uniform velocity keep, slow down, it is anxious slow down it is several
Class driving condition, above-mentioned five kinds of driving conditions are abbreviated as respectively, HD, D, N, P, HP, between the timing node of setting, and five kinds are driven
The current driving intention of driver can be reflected by sailing state.Every kind of each class driving condition has corresponding driver behavior respectively, main
It is embodied in accelerator pedal aperture, brake pedal aperture, and its on rate of change.Assuming that on track five kinds of driving intention classes
Type is respectively Sn(n=1,2,3,4,5), in continuous timing node, driving intention state can probability transfer or holding
It is constant.It is O to drive observation Value Typesm(m=1,2,3), Sn,OmWith mapping relations characterized with probable value；
B, according to continuous action in driving procedure, observed object collection is combined into O (t)={ o1(t),o2(t),o3(t) }, o1
(t),o2(t),o3(t) accelerator pedal aperture is represented respectively, accelerates aperture rate of change, brake pedal aperture；
Comprehensive Markov model is described as D=[A, μ, π, c, B], real-time status set Sn={ s1,s2,
s3......sn, then original state transfer matrix is A={ aij, aij=P (qi=Sj|qi-1=Si), initial state probabilities distribution
π={ πi},πi=P (q1=Si).The random process of driving behavior is described using the single Gauss model of three mixing herein；Wherein see
Survey probability density and use three-dimensional Gaussian probability density function, representative function is：
In above formula, Cjk-- the weight coefficient of state matrix, the mono- Gauss model numbers of M--, No(μjk,Ujk) -- sample rate
Function, o-- target observations value vector；
C, evaluation problem：Given HMM seeks the probability of an observation sequence；Decoding problem：The most possible generation one of search
The hidden state sequence of observation sequence；Problem concerning study：Given observation sequence generates a HMM；Wherein problem concerning study is i.e. to HMM moulds
Type carries out repetitive exercise several times, and the convergency value of final checking model reaches driving intention identifying purpose；
Forward direction probability is：
Backward probability is：.
, it is necessary to c in (1) formula in learning trainingjk,μjk, iterative re-evaluation, final maximum likelihood logarithm value is：
By carrying out learning training to the model to various driving datas, formula 4. middle L values convergence is finally given, that is, be can determine that
The driving intention model drawn by HMM observing and nursings；
4th, the checking of driving intention identification model and emulation
Gather the driver behavior in sampling time node：Throttle accelerator pedal aperture, accelerator open degree rate of change, brake pedal
Aperture is input in the HMM model trained as input data, obtains the HMM driving intention model groups D=in the time cycle
4. [A, μ, π, c, B], the maximum likelihood logarithm value of computation model is distinguished according to formula, and optimal result is chosen more afterwards and is adopted as the time
Driving intention in the collection cycle
As shown in Figure 2：When using the peration data in 2S time steps as input value, enter data into what is had verified that
HMM model, obtains maximum likelihood probability logarithm value.
As shown in Figure 3, Figure 4, driver be in driving procedure at the uniform velocity, it is anxious to accelerate, at the uniform velocity keep, slow down, driving at the uniform velocity
Operation is sailed, after single driver's follow-on test, HMM identification results show, the model can accurately embody driver
Driving intention combination GPS road surfaces data correction driving intention；Vehicle current position can be easily got by various GPS, when
When vehicle is in front of crossroad, bend crossing, descending section, driver's current operation intention is got in time, and prompting is driven
The person of sailing refers to optimal driving intention, it is to avoid unnecessary accelerated motion, reduces oil consumption, improves drive safety；
As a kind of preferred embodiment of the present invention, such as Fig. 5, Fig. 6, Fig. 7, when vehicle is travelled at starting point A, are being received
Take in front of the bend of station 50 meters, system identification goes out driver and accelerates or accelerate to be intended to be anxious, then points out driver to avoid accelerating, keep
At the uniform velocity or deceleration intention traveling.In front of anxious descending section, due to sight reason, driver fails to realize that front is abrupt slope road
Section, system can equally be recognized to driving intention and aid in amendment.In verification process, it is possible to find driven before relatively optimizing after optimization
The person of sailing occurs in that 3 seconds in advance in braking time, effectively avoids the appearance of unnecessary driver behavior.
From result, this method has good resolution.By known driving intention model, for continuous appearance
Special road conditions, the system can allow driver as early as possible make corresponding actions, it is to avoid skimble-skamble acceleration behavior, improve and drive
Security is sailed while reducing oil consumption.
The above, is only presently preferred embodiments of the present invention, not does any formal limitation to the present invention, it is every according to
According to the technical spirit of the present invention, any simple modification and equal change, each fall within the guarantor of the present invention to made by above example
Within the scope of shield.
Claims (1)
1. a kind of driving intention decision method based on hidden Markov model, this method is based on hidden Markov model
In driving intention decision-making system realize, the driving intention decision-making system based on hidden Markov model include server and
Multiple condition of road surface data terminals, the condition of road surface data terminal includes GPS, sillometer, accelerator pedal aperture, accelerator pedal
Aperture measurement meter, accelerates aperture rate of change meter, brake pedal aperture measurement meter；The condition of road surface data terminal also includes
There is transportation database, radio communication is carried out between condition of road surface data terminal and server；It is characterized in that：This method includes following
Step：
Driving condition is identified according to sillometer information for condition of road surface data terminal, comprises the following steps：
A, according to driver drives vehicle process, mainly have anxious acceleration on road surface, accelerate, at the uniform velocity keep, slow down, anxious several classes of slowing down are driven
State is sailed, above-mentioned five kinds of driving conditions are abbreviated as respectively, HD, D, N, P, HP, between the timing node of setting, five kinds of driving shapes
State is that can reflect the current driving intention of driver；Every kind of each class driving condition has corresponding driver behavior, main body respectively
Present accelerator pedal aperture, brake pedal aperture, and its on rate of change；Assuming that five kinds of driving intention types are divided on track
Wei not Sn(n=1,2,3,4,5), in continuous timing node, driving intention state probability can be shifted or keep constant,
It is O to drive observation Value Typesm(m=1,2,3), Sn,OmWith mapping relations characterized with probable value；
B, according to continuous action in driving procedure, observed object collection is combined into O (t)={ o1(t),o2(t),o3(t) }, o1(t),o2
(t),o3(t) accelerator pedal aperture is represented respectively, accelerates aperture rate of change, brake pedal aperture；
Comprehensive Markov model is described as D=[A, μ, π, c, B], real-time status set Sn={ s1,s2,s3......sn, then
Original state transfer matrix is A={ aij, aij=P (qi=Sj|qi-1=Si), initial state probabilities distribution π={ πi},πi=P
(q1=Si)；The random process of driving behavior is described using the single Gauss model of three mixing herein；Wherein observation probability density is used
Three-dimensional Gaussian probability density function, representative function is：
In above formula, Cjk-- the weight coefficient of state matrix, the mono- Gauss model numbers of M--, No(μjk,Ujk) -- sample rate function,
O-- target observations value vector；
C, evaluation problem：Given HMM seeks the probability of an observation sequence；Decoding problem：Search one observation of most possible generation
The hidden state sequence of sequence；Problem concerning study：Given observation sequence generates a HMM；Wherein problem concerning study is entered to HMM model
Capable repetitive exercise several times, the convergency value of final checking model, reaches driving intention identifying purpose；
Forward direction probability is：
Backward probability is：.
, it is necessary to c in (1) formula in learning trainingjk,μjk, iterative re-evaluation, final maximum likelihood logarithm value is：
By carrying out learning training to the model to various driving datas, finally giving formula, 4. middle L values restrain, that is, can determine that by
The driving intention model that HMM observing and nursings are drawn；
D, the checking of driving intention identification model and emulation
Gather the driver behavior in sampling time node：Throttle accelerator pedal aperture, accelerator open degree rate of change, brake pedal aperture
As input data, be input in the HMM model trained, obtain in the time cycle HMM driving intention model groups D=[A,
μ, π, c, B], the maximum likelihood logarithm value of computation model is 4. distinguished according to formula, optimal result is chosen more afterwards and is gathered as the time
Driving intention in cycle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710167276.2A CN106960189A (en) | 2017-03-20 | 2017-03-20 | A kind of driving intention decision method based on hidden Markov model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710167276.2A CN106960189A (en) | 2017-03-20 | 2017-03-20 | A kind of driving intention decision method based on hidden Markov model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106960189A true CN106960189A (en) | 2017-07-18 |
Family
ID=59470383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710167276.2A Pending CN106960189A (en) | 2017-03-20 | 2017-03-20 | A kind of driving intention decision method based on hidden Markov model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106960189A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944624A (en) * | 2017-11-17 | 2018-04-20 | 南京大学 | A kind of unmanned vehicle crossing Driving Decision-making method based on Hidden Markov Model |
| CN108280484A (en) * | 2018-01-30 | 2018-07-13 | 辽宁工业大学 | A kind of driver's accelerating performance online classification and discrimination method |
| CN110386144A (en) * | 2019-06-19 | 2019-10-29 | 长安大学 | The GHMM/GGAP-RBF mixed model and discrimination method that a kind of pair of driver's braking intention is recognized |
| CN110852281A (en) * | 2019-11-13 | 2020-02-28 | 吉林大学 | Driver lane change intention identification method based on Gaussian mixture hidden Markov model |
| CN111547028A (en) * | 2020-04-20 | 2020-08-18 | 江苏大学 | Brake intensity fuzzy recognition method considering brake intention |
| CN116161044A (en) * | 2023-02-28 | 2023-05-26 | 江西省交通科学研究院有限公司 | Driving behavior recognition method, system and storable medium |
-
2017
- 2017-03-20 CN CN201710167276.2A patent/CN106960189A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944624A (en) * | 2017-11-17 | 2018-04-20 | 南京大学 | A kind of unmanned vehicle crossing Driving Decision-making method based on Hidden Markov Model |
| CN108280484A (en) * | 2018-01-30 | 2018-07-13 | 辽宁工业大学 | A kind of driver's accelerating performance online classification and discrimination method |
| CN108280484B (en) * | 2018-01-30 | 2020-07-21 | 辽宁工业大学 | Driver acceleration characteristic online classification and identification method |
| CN110386144A (en) * | 2019-06-19 | 2019-10-29 | 长安大学 | The GHMM/GGAP-RBF mixed model and discrimination method that a kind of pair of driver's braking intention is recognized |
| CN110386144B (en) * | 2019-06-19 | 2020-09-08 | 长安大学 | GHMM/GGAP-RBF hybrid model for identifying driver braking intention and identification method |
| CN110852281A (en) * | 2019-11-13 | 2020-02-28 | 吉林大学 | Driver lane change intention identification method based on Gaussian mixture hidden Markov model |
| CN110852281B (en) * | 2019-11-13 | 2022-05-17 | 吉林大学 | Driver lane change intention identification method based on Gaussian mixture hidden Markov model |
| CN111547028A (en) * | 2020-04-20 | 2020-08-18 | 江苏大学 | Brake intensity fuzzy recognition method considering brake intention |
| CN111547028B (en) * | 2020-04-20 | 2021-07-20 | 江苏大学 | Brake intensity fuzzy recognition method considering brake intention |
| CN116161044A (en) * | 2023-02-28 | 2023-05-26 | 江西省交通科学研究院有限公司 | Driving behavior recognition method, system and storable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106960189A (en) | A kind of driving intention decision method based on hidden Markov model | |
| US11084494B2 (en) | Method for detecting safety of driving behavior, apparatus, device and storage medium | |
| CN107169567B (en) | Method and device for generating decision network model for automatic vehicle driving | |
| CN106203735B (en) | A kind of automobile driver driving behavior energy consumption characters measuring method | |
| CN105799512B (en) | Overspeed of vehicle based reminding method and system | |
| CN110533909B (en) | Driving behavior analysis method and system based on traffic environment | |
| CN109493566A (en) | A kind of fatigue driving prediction technique based on GPS data | |
| CN107421752A (en) | A kind of intelligent automobile test scene accelerates reconstructing method | |
| CN108491859A (en) | The recognition methods of driving behavior heterogeneity feature based on automatic coding machine | |
| Yang et al. | Arterial roadway energy/emissions estimation using modal-based trajectory reconstruction | |
| CN109272745A (en) | A kind of track of vehicle prediction technique based on deep neural network | |
| CN109118787A (en) | A kind of car speed prediction technique based on deep neural network | |
| CN107240264A (en) | A kind of non-effective driving trace recognition methods of vehicle and urban road facility planing method | |
| CN110182217A (en) | A kind of traveling task complexity quantitative estimation method towards complicated scene of overtaking other vehicles | |
| CN109900494A (en) | A kind of generation method of test case | |
| CN101327795A (en) | Vehicle running intelligent early-warning system | |
| CN113450564B (en) | Intersection passing method based on NARX neural network and C-V2X technology | |
| Salunkhe et al. | Energy optimization for CAN bus and media controls in electric vehicles using deep learning algorithms | |
| Zhai et al. | Comparative analysis of drive-cycles, speed limit violations, and emissions in two cities: Toronto and Beijing | |
| CN117037109A (en) | Traffic target detection method based on improved YOLOv5 model | |
| Yuan et al. | Study of driving cycle of city tour bus based on coupled GA-K-means and HMM algorithms: a case study in Beijing | |
| Li et al. | Modeling and verification of heavy-duty truck drivers’ car-following characteristics | |
| CN108734962A (en) | A kind of intelligent traffic information management system | |
| CN108268678A (en) | Driving behavior analysis method, apparatus and system | |
| CN117238131B (en) | Traffic flow characteristic analysis method in Internet of vehicles environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170718 |
|
| WD01 | Invention patent application deemed withdrawn after publication |