CN111815947B - Method for establishing lane change time model for natural driving vehicles on expressway - Google Patents
Method for establishing lane change time model for natural driving vehicles on expressway Download PDFInfo
- Publication number
- CN111815947B CN111815947B CN202010462549.8A CN202010462549A CN111815947B CN 111815947 B CN111815947 B CN 111815947B CN 202010462549 A CN202010462549 A CN 202010462549A CN 111815947 B CN111815947 B CN 111815947B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane change
- change time
- beta
- time model
- 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.)
- Active
Links
Images
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
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides a method for establishing a lane change time model facing a natural driving vehicle on a highway, which comprises the steps of establishing a main vehicle lane change time model according to the specific conditions of a main vehicle and a vehicle in front of the main vehicle lane, substituting historical data into the main vehicle lane change time model for simulation and regression analysis, removing parameter variables with low influence degree on dependent variables, and optimizing the main vehicle lane change time model. The invention relates to a method for establishing a lane change time model for a naturally driven vehicle on a highway, which can judge the influence degree and direction of different factors on the lane change behavior of a driver on one hand; on the other hand, the lane-changing intention, the state and the result of the driver can be analyzed, estimated and judged on the basis of the factors of the driver behavior and the surrounding environment information so as to warn and reduce the bad driving lane-changing behavior.
Description
Technical Field
The invention belongs to the field of intelligent networked automobiles, and particularly relates to a method for establishing a lane change time model for natural driving vehicles on a highway.
Background
The lane change of the vehicle is a frequent phenomenon in a traffic scene, and is an important source for causing potential safety hazards and causing traffic accidents, and the lane change behavior characteristics are very complex and are influenced by different factors, including driver factors, environmental road factors, vehicle factors and the like, particularly in China, the driving environment is numerous and varied, and the random lane change behavior is prominent. A lane change model based on the actual driving condition of China is researched, so that the lane change model is very critical to preventing and managing bad lane change driving behaviors, and is also very important to developing a control decision algorithm meeting the requirements of the driving condition, driving habit and traffic standard regulation of China in an Advanced Driving Assistance System (ADAS).
Under the condition of the prior art, research and development of related technologies are to study lane changing behaviors in dangerous scenes or corner scenes such as emergency lane changing working conditions and forced lane changing at intersections, but research on lane changing duration in general scenes is blank. However, in developing the ADAS function (particularly, regarding the active lane change system and the auxiliary lane change system), the lane change duration is a relatively important influence factor to be taken into consideration. With the gradual maturity of sensor technology, data acquired by using a collection vehicle provided with advanced instruments such as a sensor, a GPS, an inertial navigation unit and an IPU are more and more accurate, and a solid foundation and an effective support are provided for the research of lane-changing behaviors.
Disclosure of Invention
In view of the above, the invention aims to provide a method for establishing a lane change time model of a vehicle for natural driving on a highway, which links lane change time with various influence factors, jointly predicts or estimates lane change time by optimal combination of a plurality of parameter variables and more effectively and practically fitted fitting efficiency, and on one hand, can judge the influence degree and direction of different factors on lane change behaviors of a driver; on the other hand, the lane-changing intention, the state and the result of the driver can be analyzed, estimated and judged on the basis of the factors of the driver behavior and the surrounding environment information so as to warn and reduce the bad driving lane-changing behavior.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a lane change time model building method for natural driving vehicles on a highway comprises the following steps:
the method comprises the following steps: step 1: establishing a main vehicle lane change time model according to the specific conditions of the main vehicle and the vehicle in front of the main vehicle lane;
step 2: the historical data is brought into a main vehicle lane change time model to be simulated and subjected to regression analysis, parameter variables with low influence degree on dependent variables are removed, and the main vehicle lane change time model is optimized;
and step 3: and when the driver has a lane change intention, transmitting data of parameters of the main vehicle and the surrounding environment in real time and calculating the lane change time by using the optimized main vehicle lane change time model, wherein the lane change time is used as a feedback quantity, and the driver is prompted according to a specific rule for setting feedback control conditions.
Further, in step 1, the main lane change time model is as follows:
DeltaTime＝α+β 1 Speed+β 2 Acceleration_x+β 3 Acceleration_y+β 4 VehicleSpeed+β 5 ObjectRelativeVelocity_x+β 6 ObjectRelativeVelocity_y+β 7 ObjectRelativeAcceleration_x+β 8 ObjectRelativeAcceleration_y+β 9 ObjectPosition_x+β 10 ObjectPosition_y+β 11 ObjectTTC1st+β 12 category _ medium wagon + beta 13 Category _ multi-axle traction truck + beta 14 Category _ large bus + beta 15 Category _ large truck + beta 16 Category _ minibus + beta 17 Category _ wagon + beta 18 Category _ special vehicle + β 19 Category _ pickup + β 20 Category car + beta 21 CPosition _ left two + beta 22 CPosition _ left three + beta 23 CPosition _ left four + beta 24 CPosition _ left five + beta 25 Turn_2+β 26 Turn_3
Wherein, the lane change time of the vehicle is represented by DeltaTime, alpha is a variable intercept term, beta is a coefficient of each parameter variable, and the explanation of each parameter variable is as follows:
further, in step 2, taking the historical data of the environment where the vehicle runs as a sample, putting the sample into the main vehicle lane change time model for regression analysis, setting confidence (default is 90%) to perform significance test on each parameter variable, removing the parameter variable with low significance by using a stepwise regression method, and finally obtaining the optimized main vehicle lane change time model as follows:
DeltaTime＝α+β 1 X 1 +β 2 X 2 +……+β i X i
wherein DeltaTime represents the lane change time of the vehicle, alpha is a constant term, X is a parameter variable which has obvious influence on a dependent variable and is subjected to screening, beta is a coefficient of each parameter variable, and an angle index i represents the number of the parameter variables after screening.
Further, in step 3, the specific rule for setting the feedback control condition is as follows:
when the DeltaTime is more than 8s, a similar prompt of 'too slow lane change time and acceleration of lane change' is made;
when the DeltaTime is less than 3.8s, making a similar prompt of 'the lane change time is too fast and collision danger exists';
when the DeltaTime is more than or equal to 3.8s and less than or equal to 8s, no warning prompt is made.
Compared with the prior art, the method for establishing the lane change time model for the natural driving vehicles on the expressway has the following advantages:
the method for establishing the lane change time model facing the natural driving vehicles on the expressway, disclosed by the invention, has the advantages that the lane change time is connected with various influence factors, the dependent variable lane change time is jointly predicted or estimated by the optimal combination of a plurality of parameter variables and the fitting efficiency which is more efficient and more practical, and on one hand, the influence degree and direction of different factors on the lane change behavior of a driver can be judged; on the other hand, the lane-changing intention, the state and the result of the driver can be analyzed, estimated and judged on the basis of the factors of the driver behavior and the surrounding environment information so as to warn and reduce the bad driving lane-changing behavior.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention.
In the drawings:
fig. 1 is a schematic flow chart of a method for establishing a lane change time model for a naturally driven vehicle on a highway according to an embodiment of the invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, a lane change time model building method for a naturally driven vehicle on a highway:
the method comprises the following steps: step 1: establishing a main vehicle lane change time model according to the specific conditions of a main vehicle and vehicles in front of the main vehicle lane;
step 2: the historical data is brought into a main vehicle lane change time model to be simulated and subjected to regression analysis, parameter variables with low influence degree on dependent variables are removed, and the main vehicle lane change time model is optimized;
and step 3: and when the driver has a lane change intention, transmitting data of parameters of the main vehicle and the surrounding environment in real time and calculating the lane change time by using the optimized main vehicle lane change time model, wherein the lane change time is used as a feedback quantity, and the driver is prompted according to a specific rule for setting feedback control conditions.
Further, in step 1, the main lane change time model is as follows:
DeltaTime＝α+β 1 Speed+β 2 Acceleration_x+β 3 Acceleration_y+β 4 VehicleSpeed+β 5 ObjectRelativeVelocity_x+β 6 ObjectRelativeVelocity_y+β 7 ObjectRelativeAcceleration_x+β 8 ObjectRelativeAcceleration_y+β 9 ObjectPosition_x+β 10 ObjectPosition_y+β 11 ObjectTTC1st+β 12 category _ medium wagon + beta 13 Category _ multi-axle traction truck + beta 14 Category _ large bus + beta 15 Category _ large truck + beta 16 Category _ minibus + beta 17 Category _ wagon + beta 18 Category _ special vehicle + β 19 Category _ pickup + β 20 Category car + beta 21 CPosition _ left two + beta 22 CPosition _ left three + beta 23 CPosition _ left four + beta 24 CPosition _ left five + beta 25 Turn_2+β 26 Turn_3
Wherein, the lane change time of the vehicle is represented by DeltaTime, alpha is a variable intercept term, beta is a coefficient of each parameter variable, and the explanation of each parameter variable is as follows:
further, in step 2, taking the historical data of the environment where the vehicle runs as a sample, putting the sample into the main vehicle lane change time model for regression analysis, setting confidence (default is 90%) to perform significance test on each parameter variable, removing the parameter variable with low significance by using a stepwise regression method, and finally obtaining the optimized main vehicle lane change time model as follows:
DeltaTime＝α+β 1 X 1 +β 2 X 2 +……+β i X i
wherein DeltaTime represents the lane change time of the vehicle, alpha is a constant term, X is a parameter variable which has obvious influence on a dependent variable and is subjected to screening, beta is a coefficient of each parameter variable, and an angle index i represents the number of the parameter variables after screening.
Further, in step 3, the specific rule for setting the feedback control condition is as follows:
when the DeltaTime is larger than 8s, making a similar prompt that the lane change time is too slow and the lane change can be accelerated;
when the DeltaTime is less than 3.8s, making a similar prompt of 'the lane change time is too fast and collision danger exists';
when the DeltaTime is more than or equal to 3.8s and less than or equal to 8s, no warning prompt is given.
In one embodiment of the invention:
taking data collected by a Beijing expressway as a sample, substituting the data into the main vehicle lane change time model in the step 1 of the method, and obtaining the following results:
main vehicle lane change time model regression result
After the screening of the stepwise regression method, parameter variables with low influence degree on dependent variables are removed, and the optimization result of the main vehicle lane change time model is as follows:
the final optimization model is:
delta time 8.225-0023Speed-1.200 Accelation _ x +1.103 Accelation _ y +0.031ObjectRelative velocity _ x +0.115ObjectRelative velocity _ y +0.011ObjectPosition _ x +0.214ObjectPosition _ y +0.0001ObjectTTC1st +1.199 Capture _ coach +0.710 Capture _ Mini-coach-1.448 Capture _ Mini-truck +1.250CPosition _ left four-0.638 Turn _2
When the driver has the intention of changing the lane, the data of the main vehicle and the parameters of the surrounding environment are transmitted in real time, the lane changing time is calculated, the lane changing time is used as the feedback quantity, and the specific rule of setting the feedback control conditions is as follows:
when the DeltaTime is more than 8s, a similar prompt of 'too slow lane change time and acceleration of lane change' is made;
when the DeltaTime is less than 3.8s, making a similar prompt of 'the lane change time is too fast and collision danger exists';
when the DeltaTime is more than or equal to 3.8s and less than or equal to 8s, no warning prompt is given.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (3)
1. A method for establishing a lane change time model for a natural driving vehicle on a highway is characterized by comprising the following steps:
the method comprises the following steps: step 1: establishing a main vehicle lane change time model according to the specific conditions of the main vehicle and the vehicle in front of the main vehicle lane;
the main lane change time model is as follows:
DeltaTime＝α+β 1 Speed+β 2 Acceleration_x+β 3 Acceleration_y+β 4 VehicleSpeed+β 5 ObjectRelativeVelocity_x+β 6 ObjectRelativeVelocity_y+β 7 ObjectRelativeAcceleration_x+β 8 ObjectRelativeAcceleration_y+β 9 ObjectPosition_x+β 10 ObjectPosition_y+β 11 ObjectTTC1st+β 12 category _ medium wagon + beta 13 Category _ multi-axle traction truck + beta 14 Category _ motorbus + beta 15 Category _ large truck + beta 16 Category _ minibus + beta 17 Category _ wagon + beta 18 Category _ special vehicle + β 19 Category _ pickup + β 20 Category car + beta 21 CPosition _ left two + beta 22 CPosition _ left three + beta 23 CPosition _ left four + beta 24 CPosition _ left five + beta 25 Turn_2+β 26 Turn_3
Wherein, the lane change time of the vehicle is represented by DeltaTime, alpha is a variable intercept term, beta is a coefficient of each parameter variable, and the explanation of each parameter variable is as follows:
the vehicle parameters are as follows: speed is the Speed of the vehicle, Acceration _ x is the longitudinal Acceleration of the vehicle, Acceration _ y is the lateral Acceleration of the vehicle, ObjectTTC1st is the shortest collision time between the vehicle and the front vehicle;
the parameters of the front vehicle are as follows: vehicle speed is front vehicle speed, objectrelative velocity _ x is longitudinal relative velocity of the vehicle and the front vehicle, objectrelative velocity _ y is transverse relative velocity of the vehicle and the front vehicle, objectrelative acceleration _ x is longitudinal relative acceleration of the vehicle and the front vehicle, objectrelative acceleration _ y is transverse relative acceleration of the vehicle and the front vehicle, ObjectPosition _ x is longitudinal relative distance of the vehicle and the front vehicle, and ObjectPosition _ y is transverse relative distance of the vehicle and the front vehicle;
the Category _ represents the type of the front vehicle, and the reference quantity is a medium bus;
the CPattitude _ is a dummy variable which represents the position of the lane where the vehicle is located, and the reference quantity is a left lane;
turn _ is a dummy variable representing the use condition of the steering lamp of the vehicle, 1 represents the use of a left steering lamp, 2 represents the use of a right steering lamp, and the reference quantity is the non-turning on of the steering lamp;
step 2: the historical data is brought into a main vehicle lane change time model for simulation and regression analysis, parameter variables with low influence degree on dependent variables are removed, and the main vehicle lane change time model is optimized;
and step 3: and when the driver has a lane change intention, transmitting data of parameters of the main vehicle and the surrounding environment in real time and calculating the lane change time by using the optimized main vehicle lane change time model, wherein the lane change time is used as a feedback quantity, and the driver is prompted according to a specific rule for setting feedback control conditions.
2. The method for establishing the lane change time model for the natural-driving vehicles on the expressway according to claim 1, wherein: in step 2, taking the historical data of the environment where the vehicle runs as a sample, putting the sample into a main vehicle lane-changing time model for regression analysis, setting a confidence coefficient which is default to 90%, performing significance inspection on each parameter variable, removing the parameter variable with low significance by using a stepwise regression method, and finally obtaining the optimized main vehicle lane-changing time model as follows:
DeltaTime＝α+β 1 X 1 +β 2 X 2 +......+β i X i
wherein DeltaTime represents the lane change time of the vehicle, alpha is a constant term, X is a parameter variable which has obvious influence on a dependent variable and is subjected to screening, beta is a coefficient of each parameter variable, and an angle index i represents the number of the parameter variables after screening.
3. The method for establishing the lane change time model for the natural-driving vehicles on the expressway according to claim 1, wherein: in step 3, the specific rule for setting the feedback control condition is as follows:
when the DeltaTime is larger than 8s, making a similar prompt that the lane change time is too slow and the lane change can be accelerated;
when the DeltaTime is less than 3.8s, making a similar prompt of 'the lane change time is too fast and collision danger exists';
when the DeltaTime is more than or equal to 3.8s and less than or equal to 8s, no warning prompt is given.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010462549.8A CN111815947B (en) | 2020-05-27 | 2020-05-27 | Method for establishing lane change time model for natural driving vehicles on expressway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010462549.8A CN111815947B (en) | 2020-05-27 | 2020-05-27 | Method for establishing lane change time model for natural driving vehicles on expressway |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111815947A CN111815947A (en) | 2020-10-23 |
| CN111815947B true CN111815947B (en) | 2022-08-09 |
Family
ID=72848102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010462549.8A Active CN111815947B (en) | 2020-05-27 | 2020-05-27 | Method for establishing lane change time model for natural driving vehicles on expressway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111815947B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009116723A (en) * | 2007-11-08 | 2009-05-28 | Denso Corp | Lane change support system |
| CN102433811B (en) * | 2011-10-15 | 2013-07-31 | 天津市市政工程设计研究院 | Method for determining minimum distance of road intersections in harbor district |
| CN104916135B (en) * | 2015-06-19 | 2017-05-10 | 南京全司达交通科技有限公司 | Method and system for acquiring cargo transport lane traffic capacity of passenger and cargo separating expressway |
| CN106710267A (en) * | 2015-11-13 | 2017-05-24 | 北京奇虎科技有限公司 | Vehicle driving data processing method and vehicle driving data processing device |
| CN106874597B (en) * | 2017-02-16 | 2019-12-13 | 北理慧动（常熟）车辆科技有限公司 | highway overtaking behavior decision method applied to automatic driving vehicle |
| CN109445428A (en) * | 2018-10-08 | 2019-03-08 | 北京海纳川汽车部件股份有限公司 | The lane change method, apparatus of automatic driving vehicle and automatic driving vehicle with it |
| CN109345832B (en) * | 2018-11-13 | 2021-06-29 | 上海应用技术大学 | Urban road overtaking prediction method based on deep recurrent neural network |
-
2020
- 2020-05-27 CN CN202010462549.8A patent/CN111815947B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111815947A (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2019205817B2 (en) | Software validation for autonomous vehicles | |
| Aria et al. | Investigation of automated vehicle effects on driver's behavior and traffic performance | |
| JP7064303B2 (en) | Autonomous system verification method | |
| CN112631246B (en) | Test evaluation information determination method, device, equipment and computer storage medium | |
| CN110155046A (en) | Automatic emergency brake hierarchical control method and system | |
| Wu et al. | Supplementary benefits from partial vehicle automation in an ecoapproach and departure application at signalized intersections | |
| DE102018131646A1 (en) | DRIVER WARNING SYSTEMS AND METHOD | |
| CN113635897B (en) | Safe driving early warning method based on risk field | |
| CN113076897A (en) | Game dynamic driving safety measurement and control method and regulation and control terminal of intelligent networked automobile | |
| CN110606070A (en) | Intelligent driving vehicle and braking method thereof, vehicle-mounted equipment and storage medium | |
| US20220229954A1 (en) | Autonomous vehicle traffic simulation and road network modeling | |
| DE102022100549A1 (en) | RANKED FAULT CONDITIONS | |
| CN113119945B (en) | Automobile advanced driver assistance system based on environment model | |
| EP3374242B1 (en) | Method and device for analysing a driving manner of a driver of a vehicle | |
| CN111815947B (en) | Method for establishing lane change time model for natural driving vehicles on expressway | |
| CN117292540A (en) | Vehicle sideslip and rollover early warning system and method in bridge crosswind environment | |
| CN110509928A (en) | A kind of auxiliary driving method, device | |
| CN116740940A (en) | Severe weather high-impact road section risk prediction and safety management method, device and equipment | |
| CN116596380A (en) | Optimization determination method, platform, equipment and medium for expressway construction organization scheme and management and control scheme | |
| CN112158206B (en) | Intelligent vehicle forced lane change merge point determination method and device | |
| CN112793566B (en) | Collision avoidance method and device | |
| US20220153283A1 (en) | Enhanced component dimensioning | |
| CN112373482A (en) | Driving habit modeling method based on driving simulator | |
| Duoba et al. | On-Track Measurement of Road Load Changes in Two Close-Following Vehicles: Methods and Results | |
| Zhang et al. | Evaluations of Driving Safety with Increasing Connected Vehicles on the Expressway: A Simulation-Driven Research |
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 |