CN108995653A - A kind of driver's driving style recognition methods and system - Google Patents
A kind of driver's driving style recognition methods and system Download PDFInfo
- Publication number
- CN108995653A CN108995653A CN201810733557.4A CN201810733557A CN108995653A CN 108995653 A CN108995653 A CN 108995653A CN 201810733557 A CN201810733557 A CN 201810733557A CN 108995653 A CN108995653 A CN 108995653A
- Authority
- CN
- China
- Prior art keywords
- driver
- vehicle
- driving style
- driving
- information
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2540/00—Input parameters relating to occupants
- B60W2540/10—Accelerator pedal position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2540/00—Input parameters relating to occupants
- B60W2540/18—Steering angle
Abstract
The present invention relates to a kind of driver's driving style recognition methods and systems, belong to automobile intelligent interaction technique field, solve the problem that driver's driving style identification accuracy is low, not very practical in the prior art.A kind of driver's driving style recognition methods, the described method comprises the following steps: acquisition driver's operation information and vehicle traveling information;It is preliminary to identify driver's driving style according to the driver's operation information and vehicle traveling information of acquisition, obtain the preliminary recognition result of driver's driving style;According to the obtained preliminary recognition result of driver's driving style, change vehicle-state;The operation data and corresponding vehicle operation data of vehicle new state are adapted to according to driver, further identification obtains driver's driving style result.The present invention realizes accurately identifying for driver's driving style, has very strong practicability.
Description
Technical field
The present invention relates to automobile intelligent interaction technique field more particularly to a kind of driver's driving style recognition methods and it is
System.
Background technique
With vehicle intellectualized starting, the demand of people's experience good for automobile, so that it is desirable to automobiles to get over
More to understand oneself, and corresponding service content and auxiliary driving are customized according to the state of oneself and demand.What is accurately identified drives
The person's of sailing driving style, the auxiliary driving for providing more humane service and safer and more comfortable for driver have extremely important
Effect.
Driver's driving style recognition methods at this stage mainly passes through the driving number of passive detection and analysis driver
According to identifying driver's driving style;However due to the characterization of this method fetched data uncertainty, unstability and
The inconvenience of data is obtained, so that driver's driving style accuracy of this method identification is low, and is easy by extraneous factor
It influences, it is not very practical.
Summary of the invention
In view of above-mentioned analysis, the embodiment of the present invention is intended to provide a kind of driver's driving style recognition methods and system,
To solve the problem that driver's driving style identification accuracy is low, not very practical in the prior art.
On the one hand, the present invention provides a kind of driver's driving style recognition methods, comprising the following steps:
Acquire driver's operation information and vehicle traveling information;
It is preliminary to identify driver's driving style according to the driver's operation information and vehicle traveling information of acquisition, it is driven
The preliminary recognition result of the person's of sailing driving style;
According to the obtained preliminary recognition result of driver's driving style, change vehicle-state;
The operation data and corresponding vehicle operation data that vehicle new state is adapted to according to driver, further identify
To driver's driving style result.
Having the beneficial effect that through acquisition driver's operation information and vehicle traveling information for above-mentioned technical proposal, it is preliminary to know
Other driver's driving style changes vehicle-state, according to driver according to the obtained preliminary recognition result of driver's driving style
The operation data and corresponding vehicle status data of vehicle-state are adapted to, further identification obtains driver's driving style knot
Fruit, this recognition methods improve the accuracy of driver's driving style identification, there is very strong environmental suitability.
Further, driver's operation information is obtained by vehicle CAN bus;It is driven by the device sensor acquisition on vehicle
Sail the vehicle traveling information of vehicle.
Further, preliminary to identify that driver drives wind according to the driver's operation information and vehicle traveling information of acquisition
Lattice specifically include:
The extraction operation characteristic parameter from driver's operation information extracts travelling characteristic ginseng from the driving information
Number;
Classified in preset classifier according to the operational characteristic parameters and travelling characteristic parameter, according to described point
Classification results in class device differentiate driver's driving style corresponding with the operational characteristic parameters and travelling characteristic parameter;
Wherein, operational characteristic parameters include but is not limited to: steering wheel angle, steering wheel angular acceleration in tactile data,
Brake pedal position, accelerator pedal position, clutch pedal position and transmission gear, travelling characteristic parameter include but unlimited
In: drive the speed of the opposite surrounding vehicles of car speed, position, acceleration, yaw velocity, vehicle in vehicle traveling information
Degree, distance and acceleration.
Having the beneficial effect that for above-mentioned further scheme is realized through the above scheme, is carried out to driver's driving style preliminary
Identification.
Further, above-mentioned preset classifier is established, is specifically included:
Acquire the training operation information and vehicle traveling information of driver in preset time;
From the operation information and vehicle traveling information extract training characteristics parameter, the training characteristics parameter include with
The corresponding travelling characteristic parameter of vehicle traveling information and operational characteristic parameters corresponding with operation information;
To the mark label of different trained driving characteristics parameters, to indicate the driving style of its corresponding driver;
The training characteristics under different labels are learnt based on preset sorting algorithm, are trained, preset classification is formed
Device.
Further, according to the obtained preliminary recognition result of driver's driving style, change vehicle-state, comprising:
According to driver's operation information and vehicle traveling information, the operating habit of driver is judged;
Active probe model corresponding with driver's operating habit is matched in the active probe model pre-established;
The active probe model changes according to the preliminary recognition result of driver's driving style and current vehicle condition
Become vehicle-state.
Having the beneficial effect that for above-mentioned further scheme is realized through the above scheme, according to obtained driver's driving style
Preliminary recognition result changes vehicle-state.
Further, according to driver's operation information and vehicle traveling information, judge the operating habit of driver, it is specific to wrap
It includes:
Driver's operation information and vehicle traveling information in certain historical time section are acquired, and extracts and drives from the information
Characteristic parameter is sailed, the driving characteristics parameter includes the data set of α, yaw velocity ω, longitudinal speed υ, longitudinal acceleration a;
Calculate the corresponding entropy H (α) of above-mentioned driving characteristics parameter, H (ω), H (υ), H (a);
WithFor judgment criteria, the operating habit of driver is obtained;Its
In, when γ=1, driver's operating habit is longitudinally controlled type;When γ=2, driver's operating habit is crosswise joint type.
Further, establish above-mentioned active probe model, specifically include: the operating habit and correspondence for setting driver change
Become the mode of vehicle-state, acquires in preset time, the driver of different driving styles, the operation letter under different vehicle state
Breath and vehicle traveling information;
Driving characteristics parameter training collection is extracted from the information, establishes different vehicle state using Gaussian Kernel Density estimation
Under, the Gaussian Kernel Density of driving characteristics parameter estimates model, to establish to maximize characteristic parameter Gaussian Kernel Density difference as mesh
Target active probe model.
Further, the operation data and corresponding vehicle status data that vehicle-state is adapted to according to driver, into one
Step identification obtains driver's driving style result, comprising:
It is special that driving style is extracted from the operation data and corresponding vehicle status data that driver adapts to vehicle-state
Levy parameter;
The driving style characteristic parameter is classified in preset classifier;
Driver's driving style corresponding with the driving style characteristic parameter is identified by the classifier.
Having the beneficial effect that for above-mentioned further scheme is realized through the above scheme, further identifies driver's driving style.
Further, above-mentioned preset classifier is established, comprising:
It acquires in preset time, training information of the driver of different driving styles under different vehicle state is described
Training information includes driver's operation information and vehicle traveling information;
Driving characteristics parameter is extracted from the training information, as training set;
Label is marked to the difference training driving characteristics parameter of acquisition, to indicate the driving style of its corresponding driver;
Establish Gaussian Kernel Density estimation model of the driving characteristics parameter under different driving styles;
Model is estimated according to Bayes' theorem and the Gaussian Kernel Density, establishes driving characteristics parameter in different driving wind
Conditional probability model under lattice;
According to the conditional probability model, the driving style classifier for being up to judgment criteria with conditional probability is established.
On the other hand, the present invention provides a kind of driver's driving style identifying system, the system comprises driving styles
The preliminary identification module of information acquisition module, driving style, vehicle active probe module and driving style determination module;
Driving style information acquisition module, for acquiring driver's operation information and vehicle traveling information;
The preliminary identification module of driving style, the information for being acquired according to driving style information acquisition module, to driver
Driving style is tentatively identified, the preliminary recognition result of driver's driving style is obtained;
Vehicle active probe module, the driving style for being identified according to the preliminary identification module of driving style are tentatively known
Not as a result, changing vehicle-state;
Driving style determination module, for according to driver adapt to vehicle new state operation data and corresponding vehicle
Running data further obtains driver's driving style result.
Above-mentioned technical proposal has the beneficial effect that the identification that driver's driving style is realized by above system, improves
The accuracy and environmental suitability of driver's driving style identification.
It in the present invention, can also be combined with each other between above-mentioned each technical solution, to realize more preferred assembled schemes.This
Other feature and advantage of invention will illustrate in the following description, also, certain advantages can become from specification it is aobvious and
It is clear to, or understand through the implementation of the invention.The objectives and other advantages of the invention can by specification, claims with
And it is achieved and obtained in specifically noted content in attached drawing.
Detailed description of the invention
Attached drawing is only used for showing the purpose of specific embodiment, and is not to be construed as limiting the invention, in entire attached drawing
In, identical reference symbol indicates identical component.
Fig. 1 is 1 the method flow diagram of the embodiment of the present invention;
Fig. 2 is system schematic described in the embodiment of the present invention 2.
Specific embodiment
Specifically describing the preferred embodiment of the present invention with reference to the accompanying drawing, wherein attached drawing constitutes the application a part, and
Together with embodiments of the present invention for illustrating the principle of the present invention, it is not intended to limit the scope of the present invention.
Embodiment 1
The embodiment of the present invention provides a kind of driver's driving style recognition methods, comprising the following steps:
Step S101, driver's operation information and vehicle traveling information are acquired;
Specifically, obtaining the operation information of driver by vehicle CAN bus;It is driven by the device sensor acquisition on vehicle
The vehicle traveling information of vehicle is sailed, the device sensor may include the group of at least following one or several kinds of sensors
It closes: double-shaft acceleration sensor, velocity sensor, yaw-rate sensor etc.;
Step S102, preliminary to identify driver's driving style according to the information of acquisition, it is preliminary to obtain driver's driving style
Recognition result;
Specifically, the extraction operation characteristic parameter from driver's operation information, extracts row from the driving information
Characteristic parameter is sailed, is classified in preset classifier according to the operational characteristic parameters and travelling characteristic parameter, according to
Classification results in the classifier differentiate driver's driving style corresponding with the driving characteristics parameter;Described drives
Sailing lattice include but is not limited to: radical typeSteady type
Specifically, establish the preset classifier include: acquire preset time in driver training operation information and
Vehicle traveling information extracts training characteristics parameter, the training characteristics ginseng from the operation information and vehicle traveling information
Number is travelling characteristic parameter corresponding with vehicle traveling information and operational characteristic parameters corresponding with operation information;To difference
The mark label of training driving characteristics parameter, to indicate the driving style of its corresponding driver;Based on preset sorting algorithm
Training characteristics under different labels are learnt, are trained, preset classifier is formed;Wherein, the training characteristics parameter
Including but not limited to: speed, transverse acceleration, longitudinal acceleration, yaw velocity, steering wheel angle and accelerator pedal position;
Step S103, according to the obtained preliminary recognition result of driver's driving style, according to the active probe mould set
Type, change vehicle-state appropriate;
It specifically includes, according to the operation information and vehicle traveling information of driver, judges the operating habit of driver;Pre-
Active probe model corresponding with driver's operating habit is matched in the active probe model first established;The active probe mould
Type, according to obtained driver's driving style PRELIMINARY RESULTS change vehicle-state appropriate.
The change vehicle-state, specifically includes: changing and operates related vehicle control parameters, the vehicle with driver
Control parameter includes but is not limited to: power steering square, steer coefficient, and gas pedal aperture and engine air throttle aperture function close
System.
Described to judge the operating habit of driver according to operation information and vehicle traveling information, specifically include, acquisition is special
Driving information and driver's operation information in section of fixing time in vehicle driving, and driving characteristics ginseng is extracted from the information
Number, the driving characteristics parameter include steering wheel angle angular speed α, yaw velocity ω, longitudinal speed υ, longitudinal acceleration a
Data set;According to the corresponding entropy H (α) of the above-mentioned each driving characteristics parameter of entropy theoretical calculation, H (ω), H (υ), H (a), thus
WithFor judgment criteria, the operating habit of driver is obtained;The operation is practised
Used includes: longitudinally controlled type (γ=1), crosswise joint type (γ=2).
The process for pre-establishing active probe model specifically includes: it is longitudinally controlled for setting the operating habit of driver
Type, corresponding change vehicle-state mode are to change accelerator pedal torque output mode, and the accelerator pedal torque exports mould
Formula includes: sports type (β=1), economical (β=2), mixed type (β=3);Different driving styles in preset time are acquired to drive
Member, vehicle traveling information and operation information under different accelerator pedal torque output modes, and extract and drive from the information
Characteristic parameter is sailed, as training set, the driving characteristics parameter includes steering wheel angle angular speedYaw velocityVehicle
SpeedTransverse accelerationIt is established under different accelerator pedal torque output modes using Gaussian Kernel Density estimation, each driving characteristics
The Gaussian Kernel Density of parameter estimates modelTo establish to maximize feature
Parametric Gaussian cuclear density it is poor (X=α, ω, υ, a) actively for the longitudinally controlled type of target
Detection model.
Establish the process of crosswise joint type active probe model with above-mentioned to establish longitudinally controlled type active probe model similar.
Step S104, the operation data and corresponding vehicle status data that vehicle-state is adapted to according to driver, into one
Step identification obtains driver's driving style result;
Specifically, extracting phase from the operation data and corresponding vehicle operation data that driver adapts to vehicle new state
The driving style characteristic parameter of pass classifies to the driving style characteristic parameter in preset classifier, passes through institute
The classifier stated identifies driver's driving style corresponding to the related travelling characteristic;
Above-mentioned preset classifier establishment process specifically includes: different driving style drivers are not in acquisition preset time
With the vehicle traveling information and driver's operation information under accelerator pedal torque output mode, and extracted from the training information
Driving characteristics parameter, as training set, the driving characteristics parameter includes steering wheel angle angular speedYaw velocity
SpeedTransverse accelerationLabel is marked to the difference training driving characteristics parameter of acquisitionIt is right to indicate its
The driving style of the driver answered;Gaussian kernel of each characteristic parameter under different driving styles is established using Gaussian Kernel Density estimation
Density estimating modelIt is close according to Bayes' theorem and the Gaussian kernel
Degree estimation model, establishes conditional probability model of each characteristic parameter under different driving stylesTo establish with conditional probability maximum according to the conditional probability model
For judgment criteria (X=α, ω, υ, driving style classifier a).
Identify that driver's driving style process corresponding to the related travelling characteristic has according to the classifier
Body includes: the operation data and vehicle data for acquiring driver and adapting to new accelerator pedal torque output mode, extracts driving characteristics
Parameter is steering wheel angle angular speed αβ, yaw velocity ωβ, speed υβ, transverse acceleration aβ, it is input to the classifier
In, obtain the driving style of driver
The embodiment of the invention provides a kind of driver's driving style recognition methods, the method can be by tentatively judging
The driving style of driver, then by active probe model, according to the reaction to the movement of vehicle active probe of driver, into
One step identifies the driving style of driver;The method improves the accuracy of driver's driving style identification and environment adapts to
Property, so that the driver's driving style identified is more in line with actual conditions.
Embodiment 2
The embodiment of the present invention provides a kind of driver's driving style identifying system, and the system comprises driving style information to adopt
Collect module, the preliminary identification module of driving style, vehicle active probe module and driving style determination module;
Driving style information acquisition module, for acquiring driver's operation information and vehicle traveling information;
Specifically, the driving style information acquisition module obtains the operation information of driver by vehicle CAN bus;It is logical
The device sensor acquisition crossed on vehicle drives the vehicle traveling information of vehicle, and the device sensor may include at least following
The combination of one or several kinds of sensors: double-shaft acceleration sensor, velocity sensor, yaw-rate sensor etc.;
The preliminary identification module of driving style, the information for being acquired according to driving style information acquisition module, to driver
Driving style is tentatively identified, the preliminary recognition result of driver's driving style is obtained;
Specifically, the preliminary identification module of driving style extracts relevant behaviour from related driver's operation information
Make characteristic parameter, relevant travelling characteristic parameter extracted from the driving information, according to the operational characteristic parameters and
Travelling characteristic parameter is classified in preset classifier, is differentiated according to the classification results in the classifier and is driven with described
Sail the corresponding driver's driving style of characteristic parameter;The driving style includes but is not limited to: radical typeSurely
It is heavy
Specifically, establish the preset classifier include: acquire preset time in driver training operation information and
Vehicle traveling information extracts training characteristics parameter, the training characteristics from the vehicle traveling information and operation information
Parameter be travelling characteristic parameter corresponding with vehicle traveling information and operational characteristic parameters corresponding with operation information, it is described
Training characteristics parameter include but is not limited to: speed, transverse acceleration, longitudinal acceleration, yaw velocity, steering wheel angle and
Accelerator pedal position;To the mark label of different trained driving characteristics parameters, to indicate the driving style of its corresponding driver;
The training characteristics under different labels are learnt based on preset sorting algorithm, are trained, preset classifier is formed.
Vehicle active probe module, the driving style for being identified according to the preliminary identification module of driving style are tentatively known
Not as a result, according to the active probe model set, change vehicle-state appropriate;
Specifically, vehicle active probe module is according to the preliminary recognition result of obtained driving style, in the master pre-established
Matching active probe model corresponding with driver's operating habit in dynamic detection model;According to the operation information and vehicle of driver
Driving information judges the operating habit of driver;The active probe model tentatively identifies knot according to obtained driving style
Fruit change vehicle-state appropriate.
Described to judge the operating habit of driver according to operation information and vehicle traveling information, specifically include, acquisition is special
Driving information and driver's operation information in section of fixing time in running car, and driving characteristics parameter is extracted from the information
For the data set of steering wheel angle angular speed α, yaw velocity ω, speed υ, transverse acceleration a;According in entropy theoretical calculation
The corresponding entropy H (α) of each characteristic parameter, H (ω), H (υ), H (a) are stated, thus withFor judgment criteria, the operating habit of driver is obtained;The operating habit
It include: longitudinally controlled type (γ=1), crosswise joint type (γ=2).
The process for pre-establishing active probe model specifically includes: it is longitudinally controlled for setting the operating habit of driver
Type, the corresponding mode for changing vehicle-state are to change the output mould of accelerator pedal torque described in accelerator pedal torque output mode
Formula includes: sports type (β=1), economical (β=2), mixed type (β=3);Different driving styles in preset time are acquired to drive
Vehicle traveling information and operation information of the member under different accelerator pedal torque output modes, and extracted from the training information
Driving characteristics parameter is steering wheel angle angular speedYaw velocitySpeedTransverse accelerationTraining set;
It is established under different accelerator pedal torque output modes using Gaussian Kernel Density estimation, the Gaussian Kernel Density of each characteristic parameter estimates mould
TypeTo establish with maximize characteristic parameter Gaussian Kernel Density it is poor (X=α, ω, υ are a) the longitudinally controlled type active probe model of target.
Driving style determination module, for according to driver adapt to vehicle new state operation data and corresponding vehicle
Running data further determines out the driving style of driver;
Specifically, the driving style determination module adapts to the operation data of vehicle new state and corresponding from driver
Relevant driving style characteristic parameter is extracted in vehicle operation data, to the driving style characteristic parameter in preset classifier
In classify, driver's driving style corresponding to the related travelling characteristic is identified by the classifier;
It is above-mentioned default that classifier establishment process specifically includes: different driving style drivers in acquisition preset time,
Under different accelerator pedal torque output modes, training vehicle traveling information and driver's operation information in vehicle driving, and from
It is steering wheel angle angular speed that driving characteristics parameter is extracted in the training informationYaw velocitySpeedLaterally
AccelerationTraining set;The label for the difference training driving characteristics parameter that mark obtainsIt is corresponding to indicate its
The driving style of driver;Gaussian Kernel Density of each characteristic parameter under different driving styles is established using Gaussian Kernel Density estimation
Estimate modelEstimated according to Bayes' theorem and the Gaussian Kernel Density
Model is counted, conditional probability model of each characteristic parameter under different driving styles is establishedTo establish with conditional probability maximum according to the conditional probability model
For judgment criteria (X=α, ω, υ, driving style classifier a).
Identify that driver's driving style process corresponding to the related travelling characteristic has according to the classifier
Body includes: the operation data and vehicle data for acquiring driver and adapting to new accelerator pedal torque output mode, extracts driving characteristics
Parameter is steering wheel angle angular speed αβ, yaw velocity ωβ, speed υβ, transverse acceleration aβ, it is input to the classifier
In, obtain the driving style of driver
It will be understood by those skilled in the art that realizing all or part of the process of above-described embodiment method, meter can be passed through
Calculation machine program is completed to instruct relevant hardware, and the program can be stored in computer readable storage medium.Wherein, institute
Stating computer readable storage medium is disk, CD, read-only memory or random access memory etc..
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of driver's driving style recognition methods, which comprises the following steps:
Acquire driver's operation information and vehicle traveling information;
It is preliminary to identify driver's driving style according to the driver's operation information and vehicle traveling information of acquisition, obtain driver
The preliminary recognition result of driving style;
According to the obtained preliminary recognition result of driver's driving style, change vehicle-state;
The operation data and corresponding vehicle operation data of vehicle new state are adapted to according to driver, further identification is driven
The person's of sailing driving style result.
2. method according to claim 1, which is characterized in that obtain driver's operation information by vehicle CAN bus;Pass through
Device sensor acquisition on vehicle drives the vehicle traveling information of vehicle.
3. method according to claim 1, which is characterized in that believed according to the driver's operation information and vehicle driving of acquisition
Breath, it is preliminary to identify driver's driving style, it specifically includes:
The extraction operation characteristic parameter from driver's operation information extracts travelling characteristic parameter from the driving information;
Classified in preset classifier according to the operational characteristic parameters and travelling characteristic parameter, according to the classifier
In classification results differentiate corresponding with the operational characteristic parameters and travelling characteristic parameter driver's driving style;
Wherein, the operational characteristic parameters include but is not limited to: steering wheel angle, steering wheel angular acceleration in tactile data,
Brake pedal position, accelerator pedal position, clutch pedal position and transmission gear, the travelling characteristic parameter include but not
Be limited to: drive vehicle traveling information in car speed, position, acceleration, yaw velocity, vehicle with respect to surrounding vehicles speed
Degree, distance and acceleration.
4. method according to claim 3, which is characterized in that establish the preset classifier, specifically include:
Acquire the training operation information and vehicle traveling information of driver in preset time;
Training characteristics parameter is extracted from the operation information and vehicle traveling information, the training characteristics parameter includes and vehicle
The corresponding travelling characteristic parameter of driving information and operational characteristic parameters corresponding with operation information;
To the mark label of different training characteristics parameters, to indicate the driving style of its corresponding driver;
The training characteristics under different labels are learnt based on preset sorting algorithm, are trained, preset classifier is formed.
5. method according to claim 1, which is characterized in that according to the obtained preliminary recognition result of driver's driving style,
Change vehicle-state, comprising:
According to driver's operation information and vehicle traveling information, the operating habit of driver is judged;
Active probe model corresponding with driver's operating habit is matched in the active probe model pre-established;
The active probe model changes vehicle shape according to the preliminary recognition result of driver's driving style and current vehicle condition
State.
6. method according to claim 5, which is characterized in that according to driver's operation information and vehicle traveling information, judgement
The operating habit of driver, specifically includes:
Driver's operation information and vehicle traveling information in certain historical time section are acquired, and is extracted from the information and drives spy
Parameter is levied, the driving characteristics parameter includes steering wheel angle angular speed α, yaw velocity ω, longitudinal speed υ, longitudinal acceleration
Spend the data set of a;
Calculate the corresponding entropy H (α) of above-mentioned driving characteristics parameter, H (ω), H (υ), H (a);
WithFor judgment criteria, the operating habit of driver is obtained;Wherein, γ=
When 1, driver's operating habit is longitudinally controlled type;When γ=2, driver's operating habit is crosswise joint type.
7. method according to claim 6, which is characterized in that establish the active probe model, specifically include:
The operating habit of driver and the mode of corresponding change vehicle-state are set, is acquired in preset time, difference drives wind
The driver of lattice, operation information and vehicle traveling information under different vehicle state;
Driving characteristics parameter training collection is extracted from the information, is established under different vehicle state using Gaussian Kernel Density estimation,
The Gaussian Kernel Density of driving characteristics parameter estimates model, to establish to maximize characteristic parameter Gaussian Kernel Density difference as target
Active probe model.
8. method according to claim 1, according to the operation data of driver's adaptation vehicle new state and corresponding vehicle
Running data, further identification obtains driver's driving style result, comprising:
Driving style feature is extracted from the operation data and corresponding vehicle operation data that driver adapts to vehicle new state
Parameter;
The driving style characteristic parameter is classified in preset classifier;
Driver's driving style corresponding with the driving style characteristic parameter is identified by the classifier.
9. method according to claim 8, which is characterized in that establish the preset classifier, comprising:
It acquires in preset time, training information of the driver of different driving styles under different vehicle state, the training letter
Breath includes operation information and vehicle traveling information;
Driving characteristics parameter is extracted from the training information, as training set;
Label is marked to the difference training driving characteristics parameter of acquisition, to indicate the driving style of its corresponding driver;
Establish Gaussian Kernel Density estimation model of the driving characteristics parameter under different driving styles;
Model is estimated according to Bayes' theorem and the Gaussian Kernel Density, establishes driving characteristics characteristic parameter in different driving wind
Conditional probability model under lattice;
According to the conditional probability model, the driving style classifier for being up to judgment criteria with conditional probability is established.
10. a kind of driver's driving style identifying system, which is characterized in that the system comprises driving style information collection moulds
The preliminary identification module of block, driving style, vehicle active probe module and driving style determination module;
Driving style information acquisition module, for acquiring driver's operation information and vehicle traveling information;
The preliminary identification module of driving style, the information for being acquired according to driving style information acquisition module drive driver
Style is tentatively identified, the preliminary recognition result of driver's driving style is obtained;
Vehicle active probe module, the driving style for being identified according to the preliminary identification module of driving style tentatively identify knot
Fruit changes vehicle-state;
Driving style determination module, for adapting to the operation data and corresponding vehicle driving of vehicle new state according to driver
Data further obtain driver's driving style result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810733557.4A CN108995653B (en) | 2018-07-06 | 2018-07-06 | Method and system for identifying driving style of driver |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810733557.4A CN108995653B (en) | 2018-07-06 | 2018-07-06 | Method and system for identifying driving style of driver |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108995653A true CN108995653A (en) | 2018-12-14 |
CN108995653B CN108995653B (en) | 2020-02-14 |
Family
ID=64599067
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810733557.4A Active CN108995653B (en) | 2018-07-06 | 2018-07-06 | Method and system for identifying driving style of driver |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108995653B (en) |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109624986A (en) * | 2019-03-01 | 2019-04-16 | 吉林大学 | A kind of the study cruise control system and method for the driving style based on pattern switching |
CN109634185A (en) * | 2018-12-25 | 2019-04-16 | 福州大学 | A kind of driver style identification data collection system |
CN109808695A (en) * | 2019-02-28 | 2019-05-28 | 北京航空航天大学 | A kind of car travel mode method of adjustment and device |
CN109887124A (en) * | 2019-01-07 | 2019-06-14 | 平安科技(深圳)有限公司 | Vehicle motion data processing method and device, computer equipment and storage medium |
CN110304068A (en) * | 2019-06-24 | 2019-10-08 | 中国第一汽车股份有限公司 | Acquisition method, device, equipment and the storage medium of running car environmental information |
CN110378397A (en) * | 2019-06-27 | 2019-10-25 | 深圳大学 | A kind of driving style recognition methods and device |
CN110458214A (en) * | 2019-07-31 | 2019-11-15 | 上海远眸软件有限公司 | Driver replaces recognition methods and device |
CN110789522A (en) * | 2019-09-17 | 2020-02-14 | 福瑞泰克智能系统有限公司 | Lane keeping assist control method, device, system, vehicle and storage medium |
CN111376911A (en) * | 2018-12-29 | 2020-07-07 | 北京宝沃汽车有限公司 | Vehicle and driving style self-learning method and device thereof |
CN111661140A (en) * | 2020-01-09 | 2020-09-15 | 吉林大学 | Calculation method for power-assisted characteristic table of electric power-assisted steering system |
CN111994084A (en) * | 2020-09-21 | 2020-11-27 | 华南理工大学 | Method and system for identifying driving style of driver and storage medium |
CN112298192A (en) * | 2019-07-31 | 2021-02-02 | 比亚迪股份有限公司 | Vehicle and control strategy generation method and device thereof |
CN112319488A (en) * | 2020-10-20 | 2021-02-05 | 易显智能科技有限责任公司 | Method and system for identifying driving style of motor vehicle driver |
CN112677983A (en) * | 2021-01-07 | 2021-04-20 | 浙江大学 | System for recognizing driving style of driver |
CN112776815A (en) * | 2021-02-23 | 2021-05-11 | 东风汽车集团股份有限公司 | Driving style judgment and identification method |
CN112829758A (en) * | 2021-01-08 | 2021-05-25 | 广西宁达汽车科技有限公司 | Automobile driving style self-learning method, device, equipment and storage medium |
CN112861910A (en) * | 2021-01-07 | 2021-05-28 | 南昌大学 | Network simulation machine self-learning method and device |
CN113335286A (en) * | 2021-07-15 | 2021-09-03 | 上海洛轲智能科技有限公司 | Torque map generation method and device for vehicle, electronic device and storage medium |
CN113386779A (en) * | 2021-06-23 | 2021-09-14 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method, device and storage medium |
CN113401130A (en) * | 2021-06-25 | 2021-09-17 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method and device based on environmental information and storage medium |
CN113859247A (en) * | 2020-06-30 | 2021-12-31 | 比亚迪股份有限公司 | Vehicle user identification method and device, vehicle machine and storage medium |
CN113954855A (en) * | 2021-12-07 | 2022-01-21 | 吉林大学 | Self-adaptive matching method for automobile driving mode |
CN114228722A (en) * | 2021-12-06 | 2022-03-25 | 上海前晨汽车科技有限公司 | Driving style dividing method, device, equipment, storage medium and program product |
CN116502142A (en) * | 2023-07-03 | 2023-07-28 | 北京航空航天大学 | Driving style identification method based on input characteristic parameter selection |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103318181A (en) * | 2013-06-19 | 2013-09-25 | 电子科技大学 | Driver intention recognition method |
CN103403756A (en) * | 2011-03-03 | 2013-11-20 | 爱信精机株式会社 | State estimation device, state estimation method, and program |
CN104204475A (en) * | 2012-01-25 | 2014-12-10 | 捷豹路虎有限公司 | Motor vehicle and method of control of a motor vehicle |
US20160350986A1 (en) * | 2010-12-02 | 2016-12-01 | Zonar Systems, Inc. | Method and apparatus for implementing a vehicle inspection waiver program |
CN106394559A (en) * | 2016-11-17 | 2017-02-15 | 吉林大学 | Multi-target driving behavior evaluation analytical method based on environmental perception information |
-
2018
- 2018-07-06 CN CN201810733557.4A patent/CN108995653B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160350986A1 (en) * | 2010-12-02 | 2016-12-01 | Zonar Systems, Inc. | Method and apparatus for implementing a vehicle inspection waiver program |
CN103403756A (en) * | 2011-03-03 | 2013-11-20 | 爱信精机株式会社 | State estimation device, state estimation method, and program |
CN104204475A (en) * | 2012-01-25 | 2014-12-10 | 捷豹路虎有限公司 | Motor vehicle and method of control of a motor vehicle |
CN103318181A (en) * | 2013-06-19 | 2013-09-25 | 电子科技大学 | Driver intention recognition method |
CN106394559A (en) * | 2016-11-17 | 2017-02-15 | 吉林大学 | Multi-target driving behavior evaluation analytical method based on environmental perception information |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109634185A (en) * | 2018-12-25 | 2019-04-16 | 福州大学 | A kind of driver style identification data collection system |
CN111376911A (en) * | 2018-12-29 | 2020-07-07 | 北京宝沃汽车有限公司 | Vehicle and driving style self-learning method and device thereof |
CN109887124A (en) * | 2019-01-07 | 2019-06-14 | 平安科技(深圳)有限公司 | Vehicle motion data processing method and device, computer equipment and storage medium |
CN109887124B (en) * | 2019-01-07 | 2022-05-13 | 平安科技(深圳)有限公司 | Vehicle motion data processing method and device, computer equipment and storage medium |
CN109808695A (en) * | 2019-02-28 | 2019-05-28 | 北京航空航天大学 | A kind of car travel mode method of adjustment and device |
CN109624986A (en) * | 2019-03-01 | 2019-04-16 | 吉林大学 | A kind of the study cruise control system and method for the driving style based on pattern switching |
CN109624986B (en) * | 2019-03-01 | 2021-01-15 | 吉林大学 | Driving style learning cruise control system and method based on mode switching |
CN110304068A (en) * | 2019-06-24 | 2019-10-08 | 中国第一汽车股份有限公司 | Acquisition method, device, equipment and the storage medium of running car environmental information |
CN110378397A (en) * | 2019-06-27 | 2019-10-25 | 深圳大学 | A kind of driving style recognition methods and device |
CN110458214A (en) * | 2019-07-31 | 2019-11-15 | 上海远眸软件有限公司 | Driver replaces recognition methods and device |
CN112298192A (en) * | 2019-07-31 | 2021-02-02 | 比亚迪股份有限公司 | Vehicle and control strategy generation method and device thereof |
CN110789522A (en) * | 2019-09-17 | 2020-02-14 | 福瑞泰克智能系统有限公司 | Lane keeping assist control method, device, system, vehicle and storage medium |
CN110789522B (en) * | 2019-09-17 | 2021-03-05 | 福瑞泰克智能系统有限公司 | Lane keeping assist control method, device, system, vehicle and storage medium |
CN111661140A (en) * | 2020-01-09 | 2020-09-15 | 吉林大学 | Calculation method for power-assisted characteristic table of electric power-assisted steering system |
CN113859247A (en) * | 2020-06-30 | 2021-12-31 | 比亚迪股份有限公司 | Vehicle user identification method and device, vehicle machine and storage medium |
CN113859247B (en) * | 2020-06-30 | 2023-07-11 | 比亚迪股份有限公司 | User identification method and device for vehicle, vehicle machine and storage medium |
CN111994084A (en) * | 2020-09-21 | 2020-11-27 | 华南理工大学 | Method and system for identifying driving style of driver and storage medium |
CN112319488B (en) * | 2020-10-20 | 2022-06-03 | 易显智能科技有限责任公司 | Method and system for identifying driving style of motor vehicle driver |
CN112319488A (en) * | 2020-10-20 | 2021-02-05 | 易显智能科技有限责任公司 | Method and system for identifying driving style of motor vehicle driver |
CN112861910A (en) * | 2021-01-07 | 2021-05-28 | 南昌大学 | Network simulation machine self-learning method and device |
CN112677983A (en) * | 2021-01-07 | 2021-04-20 | 浙江大学 | System for recognizing driving style of driver |
CN112829758A (en) * | 2021-01-08 | 2021-05-25 | 广西宁达汽车科技有限公司 | Automobile driving style self-learning method, device, equipment and storage medium |
CN112776815A (en) * | 2021-02-23 | 2021-05-11 | 东风汽车集团股份有限公司 | Driving style judgment and identification method |
CN113386779A (en) * | 2021-06-23 | 2021-09-14 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method, device and storage medium |
CN113386779B (en) * | 2021-06-23 | 2022-10-18 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method, device and storage medium |
CN113401130A (en) * | 2021-06-25 | 2021-09-17 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method and device based on environmental information and storage medium |
CN113335286B (en) * | 2021-07-15 | 2022-07-26 | 上海洛轲智能科技有限公司 | Torque map generation method and device for vehicle, electronic device and storage medium |
CN113335286A (en) * | 2021-07-15 | 2021-09-03 | 上海洛轲智能科技有限公司 | Torque map generation method and device for vehicle, electronic device and storage medium |
CN114228722A (en) * | 2021-12-06 | 2022-03-25 | 上海前晨汽车科技有限公司 | Driving style dividing method, device, equipment, storage medium and program product |
CN114228722B (en) * | 2021-12-06 | 2023-10-24 | 上海前晨汽车科技有限公司 | Driving style dividing method, apparatus, device, storage medium, and program product |
CN113954855A (en) * | 2021-12-07 | 2022-01-21 | 吉林大学 | Self-adaptive matching method for automobile driving mode |
CN113954855B (en) * | 2021-12-07 | 2023-04-07 | 吉林大学 | Self-adaptive matching method for automobile driving mode |
CN116502142A (en) * | 2023-07-03 | 2023-07-28 | 北京航空航天大学 | Driving style identification method based on input characteristic parameter selection |
CN116502142B (en) * | 2023-07-03 | 2023-08-25 | 北京航空航天大学 | Driving style identification method based on input characteristic parameter selection |
Also Published As
Publication number | Publication date |
---|---|
CN108995653B (en) | 2020-02-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108995653A (en) | A kind of driver's driving style recognition methods and system | |
CN108995655A (en) | A kind of driver's driving intention recognition methods and system | |
CN108995654B (en) | Driver state identification method and system | |
US10286900B2 (en) | Intelligent driving system with an embedded driver model | |
CN109849910B (en) | Unmanned vehicle multi-target decision control method and device and computer readable storage medium | |
CN106184223A (en) | A kind of automatic Pilot control method, device and automobile | |
CN104494600B (en) | A kind of Driver intention recognition method based on SVM algorithm | |
CN109145719B (en) | Driver fatigue state identification method and system | |
CN109808706A (en) | Learning type assistant driving control method, device, system and vehicle | |
CN111332362B (en) | Intelligent steer-by-wire control method integrating individual character of driver | |
CN109436085B (en) | Driving style-based drive-by-wire steering system transmission ratio control method | |
US20050080565A1 (en) | Driver adaptive collision warning system | |
CN105000019A (en) | Method and system for detecting, tracking and estimating stationary roadside objects | |
CN110239556B (en) | Driver instant control ability sensing method | |
US20100152951A1 (en) | Adaptive vehicle control system with driving style recognition based on vehicle accelerating and decelerating | |
CN110949407B (en) | Dynamic man-machine co-driving right distribution method based on real-time risk response of driver | |
CN107521501A (en) | Driver assistance system decision-making technique, system based on game theory and other | |
JP7073880B2 (en) | Career decision device | |
CN109760678A (en) | A kind of method for limiting speed of automotive self-adaptive cruise system | |
EP3219567A1 (en) | Method, system and vehicle for analyzing a rider performance | |
US20100152950A1 (en) | Adaptive vehicle control system with driving style recognition based on vehicle stopping | |
CN110871802A (en) | Vehicle control method and device and vehicle | |
CN111717217B (en) | Driver intention identification method based on probability correction | |
KR101272570B1 (en) | Apparatus for recognition of vehicle's acceleration and deceleration information by pattern recognition and thereof method | |
GB2586490A (en) | Autonomous driving mode selection system |
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 |