CN113665574A - Intelligent automobile lane change duration prediction and anthropomorphic track planning method - Google Patents
Intelligent automobile lane change duration prediction and anthropomorphic track planning method Download PDFInfo
- Publication number
- CN113665574A CN113665574A CN202111237247.1A CN202111237247A CN113665574A CN 113665574 A CN113665574 A CN 113665574A CN 202111237247 A CN202111237247 A CN 202111237247A CN 113665574 A CN113665574 A CN 113665574A
- Authority
- CN
- China
- Prior art keywords
- lane change
- vehicle
- lane
- influence
- changing
- 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
- 230000008859 change Effects 0.000 title claims abstract description 333
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000001133 acceleration Effects 0.000 claims abstract description 91
- 238000013507 mapping Methods 0.000 claims abstract description 27
- 238000006073 displacement reaction Methods 0.000 claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 7
- 238000012512 characterization method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000002093 peripheral effect Effects 0.000 abstract 4
- 230000008569 process Effects 0.000 description 20
- 230000006399 behavior Effects 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 239000000284 extract Substances 0.000 description 7
- 238000011158 quantitative evaluation Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000011541 reaction mixture Substances 0.000 description 2
- 230000003442 weekly effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000002902 bimodal effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18163—Lane change; Overtaking manoeuvres
-
- 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
- B60W40/10—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 vehicle motion
- B60W40/107—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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to the technical field of intelligent automobile application, in particular to a method for predicting lane change duration and planning anthropomorphic trajectories of an intelligent automobile, which comprises the following steps: extracting a lane changing track of an excellent driver from natural driving data, and extracting lane changing duration under the influence of multiple vehicles; acquiring the peripheral movement information of the lane changing vehicle, and representing the peripheral influence as the nonlinear mapping of the peripheral kinematic parameters to the average longitudinal acceleration of the lane changing vehicle, so as to obtain a lane changing duration prediction model under the peripheral influence; when the intelligent automobile applies the lane change time length prediction model, the optimization of the lane change time length is carried out by utilizing the prediction model based on the expected lane change longitudinal displacement, the current longitudinal speed and the expected speed of the target lane after lane change in combination with the information of the week vehicles, and further the anthropomorphic lane change track planning is realized. Therefore, the control law of excellent drivers in natural driving data is fully mined, reference is provided for scientific and reasonable lane change decision of the intelligent automobile, and the method is the embodiment of the intelligent automobile anthropomorphic decision concept in the lane change decision.
Description
Technical Field
The application relates to the technical field of intelligent automobile application, in particular to a method for predicting lane change duration and planning a humanized track of an intelligent automobile.
Background
Under the mixed traffic environment of manual driving and automatic driving, the lane changing behavior of an automatic driving automobile is influenced by surrounding traffic vehicles, particularly the uncertainty of the manual driving automobile, so that the longitudinal motion rule of a lane changing track is very complex.
In the related art, it is generally assumed that the longitudinal speed of an intelligent vehicle remains unchanged in the lane change process, the lane change track obtained by planning under such an ideal working condition is considered frequently on the basis of the lateral motion law of the lane change track, however, the method lacks analysis on the longitudinal motion of the vehicle in the lane change process, and fails to fully consider the influence of surrounding vehicles on the longitudinal driving behavior of the vehicle in the lane change process, so that the expected performance of the planned track cannot necessarily meet the expected requirement, frequent acceleration and deceleration may be caused, the lane change comfort is reduced, even the lateral acceleration of the vehicle is too large due to insufficient lane change duration, the instability risks of sideslip, heeling and the like of the vehicle are induced, and the safety problems of increased collision risk with the surrounding vehicles and the like exist, and are to be solved urgently.
Disclosure of Invention
The application provides an intelligent automobile lane change time length prediction and anthropomorphic track planning method, which aims to solve the problems of insufficient lane change time length decision reasonability, poor interpretability and possible safety risks caused by the fact that the influence of surrounding vehicles on longitudinal driving behaviors in the self-automobile lane change process cannot be fully evaluated in related intelligent automobile technologies, fully excavates the driving control rule of excellent drivers in natural driving data, provides reference for scientific and reasonable lane change decisions of an intelligent automobile, and is the embodiment of an anthropomorphic decision concept of a learner, a simulator, a surmounted person and a service person of the intelligent automobile in the lane change decision.
The embodiment of the first aspect of the application provides an intelligent automobile lane change duration prediction and anthropomorphic track planning method, which comprises the following steps:
extracting a lane changing track of an excellent driver from natural driving data of a plurality of drivers, and extracting lane changing time length of the excellent driver under the influence of real multiple vehicles from the lane changing track of the excellent driver;
acquiring the vehicle-turnover motion information of a lane-changing vehicle, establishing a vehicle lane-changing longitudinal kinematic model under the influence of multiple vehicles according to the vehicle-turnover motion information, and representing the influence of the vehicles as the nonlinear mapping of the vehicle-turnover kinematic parameters to the average longitudinal acceleration of the lane-changing vehicle, so as to obtain a trained lane-changing duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification;
under the condition that an intelligent automobile in a network multi-automobile environment uses the lane change duration prediction model to make a decision, when a lane change instruction is given, the lane change duration of the intelligent automobile is optimized by using the lane change duration prediction model based on the expected lane change longitudinal displacement, the longitudinal speed of the intelligent automobile and the expected speed of a target lane after lane change in combination with the week information of the intelligent automobile, and the lane change duration of the intelligent automobile is subjected to anthropomorphic track planning according to the lane change duration of the intelligent automobile obtained through optimization, so that the lane change intention of the intelligent automobile is accurately implemented.
In some examples, the extracting of the lane change trajectory of the excellent driver from the natural driving data of several drivers and the extracting of the excellent driver lane change duration under the influence of real multiple vehicles from the excellent driver lane change trajectory include:
calculating an orientation angle of a lane change trajectory of the excellent driver;
determining a peak point from the natural driving data based on the orientation angle, and searching from the peak point to two sides to obtain a time point meeting a preset condition;
matching the initial interval of the corresponding lane changing track by the time point;
and calculating the peak-peak time difference of the lateral acceleration of the track changing track according to the initial interval, and calculating corresponding time points when the lateral acceleration obtains the maximum value and the minimum value based on the time difference to obtain the excellent track changing time of the driver under the influence of real multiple vehicles.
In some examples, the obtaining a trained lane change duration prediction model under the influence of multiple vehicles and identifying obtained model parameters includes:
performing acceleration correction on the average longitudinal acceleration of the lane changing vehicle to obtain the corrected average longitudinal acceleration, and representing the influence of the week vehicle as nonlinear mapping of the kinetic parameters of the week vehicle on the average longitudinal acceleration of the lane changing vehicle;
and according to the longitudinal vehicle lane change kinematics model under the influence of the multiple vehicles and the influence characterization of the vehicles in the week, obtaining a lane change duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification by nonlinear mapping of the vehicle lane change kinematics parameters to the average longitudinal acceleration of the lane change vehicle.
In some examples, the lane change duration prediction model is:
wherein the content of the first and second substances,
in order to prolong the lane change time of the self vehicle,
a longitudinal displacement for anticipating lane change of the bicycle,
Is the average longitudinal acceleration of the own vehicle,
and the expected speed of the vehicle in the target lane after the vehicle is changed.
In some examples, the expected lane-change longitudinal displacement is determined as a function of longitudinal position, longitudinal velocity, and longitudinal acceleration state.
The embodiment of the second aspect of the present application provides an intelligent automobile lane change duration prediction and anthropomorphic trajectory planning device, including:
the extraction module is used for extracting a lane changing track of an excellent driver from natural driving data of a plurality of drivers and extracting the lane changing time length of the excellent driver under the influence of real multiple vehicles from the lane changing track of the excellent driver;
the generation module is used for acquiring the vehicle-turnover motion information of the lane-changing vehicle, establishing a vehicle lane-changing longitudinal kinematic model under the influence of multiple vehicles according to the vehicle-turnover motion information, representing the influence of the vehicles as the nonlinear mapping of the vehicle-turnover kinematic parameters to the average longitudinal acceleration of the lane-changing vehicle, and further acquiring a trained lane-changing duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification; and
and the lane change track planning module is used for optimizing the lane change time length of the intelligent automobile by using the lane change time length prediction model according to the lane change time length prediction model and the acquired lane change time length of the intelligent automobile according to the optimization when a lane change instruction is issued under the condition that the intelligent automobile applies the lane change time length prediction model to make a decision, and the lane change time length prediction model is combined with the week automobile information of the intelligent automobile, so that the accurate implementation of the lane change intention of the intelligent automobile is realized.
In some examples, the extraction module is specifically configured to:
calculating an orientation angle of a lane change trajectory of the excellent driver;
determining a peak point from the natural driving data based on the orientation angle, and searching from the peak point to two sides to obtain a time point meeting a preset condition;
matching the initial interval of the corresponding lane changing track by the time point;
and calculating the peak-peak time difference of the lateral acceleration of the track changing track according to the initial interval, and calculating corresponding time points when the lateral acceleration obtains the maximum value and the minimum value based on the time difference to obtain the excellent track changing time of the driver under the influence of real multiple vehicles.
In some examples, the generation module is specifically configured to:
performing acceleration correction on the average longitudinal acceleration of the lane changing vehicle to obtain the corrected average longitudinal acceleration, and representing the influence of the week vehicle as nonlinear mapping of the kinetic parameters of the week vehicle on the average longitudinal acceleration of the lane changing vehicle;
and according to the longitudinal vehicle lane change kinematics model under the influence of the multiple vehicles and the influence characterization of the vehicles in the week, obtaining a lane change duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification by nonlinear mapping of the vehicle lane change kinematics parameters to the average longitudinal acceleration of the lane change vehicle.
In some examples, the lane change duration prediction model is:
wherein the content of the first and second substances,
in order to prolong the lane change time of the self vehicle,
a longitudinal displacement for anticipating lane change of the bicycle,
Is the average longitudinal acceleration of the own vehicle,
and the expected speed of the vehicle in the target lane after the vehicle is changed.
In some examples, the expected lane-change longitudinal displacement is determined as a function of longitudinal position, longitudinal velocity, and longitudinal acceleration state.
An embodiment of a third aspect of the present application provides an intelligent vehicle track change decision device, including: the intelligent automobile lane change duration prediction and anthropomorphic track planning method in the embodiment of the first aspect serves the lane change intention recognition module and the lane change track planning module.
The embodiment of the fourth aspect of the present application provides a lane change trajectory tracking module, where a computer program is stored on the tracking module, and the computer program is executed by a processor, so as to implement the method for predicting the lane change duration and planning the anthropomorphic trajectory of the intelligent vehicle described in the embodiment of the first aspect.
The embodiment of the invention can extract the lane change track of the excellent driver from natural driving data of a large number of drivers, extract the lane change time length of the excellent driver under the influence of real multiple vehicles from the lane change track of the excellent driver, then obtain the vehicle-to-vehicle motion information of the lane-changed vehicle, establish a vehicle lane change longitudinal kinematic model under the influence of the multiple vehicles according to the vehicle-to-vehicle motion information, represent the influence of the vehicle-to-vehicle motion as the nonlinear mapping of the vehicle-to-vehicle motion parameters to the average longitudinal acceleration of the lane-changed vehicle, and further obtain the lane change time length prediction model under the influence of the multiple vehicles, so that after the lane change time length prediction model is applied to the intelligent vehicle under the network-connected multiple-vehicle environment, the intelligent vehicle can combine the vehicle-to-vehicle information of the intelligent vehicle according to the expected lane change longitudinal displacement, the longitudinal speed of the intelligent vehicle, the expected vehicle speed of a target lane after lane change and the like, and optimizing the lane change time of the intelligent automobile by using the lane change time prediction model, and further performing anthropomorphic track planning according to the lane change time of the intelligent automobile obtained through optimization so as to realize accurate implementation of the lane change intention of the intelligent automobile. Therefore, the method and the device solve the problems of insufficient decision reasonability of lane change duration, poor interpretability and possible safety risks caused by insufficient quantitative evaluation of the influence of surrounding vehicles on longitudinal driving behaviors in the lane change process of the vehicle in related intelligent vehicle technologies.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flowchart of a method for predicting lane change duration and planning a personalized trajectory of an intelligent vehicle according to an embodiment of the present application;
fig. 2 is a schematic diagram illustrating a variation rule of a left lane-changing trajectory, a lateral speed and a lateral acceleration extracted from the natural driving trajectory set HighD according to an embodiment of the present application;
fig. 3 is a change rule of the lane change trajectory, the lateral speed and the lateral acceleration extracted from the natural driving trajectory set HighD according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a nonlinear mapping relationship of a weekly vehicle to an average equivalent longitudinal acceleration during a lane change of the self vehicle according to an embodiment of the present application;
FIG. 5 is an illustrative diagram of a cycle movement parameter identification in a networked environment in accordance with one embodiment of the present application;
FIG. 6 is an exemplary graph of a statistical analysis of longitudinal driving behavior of a measured natural driving data set HighD lane change trajectory according to one embodiment of the present application;
FIG. 7 is a schematic diagram of a histogram and a scatter plot of a comparison of lane change durations for a current vehicle obtained by prediction and corresponding lane change trajectories according to one embodiment of the present application;
FIG. 8 is a flowchart of a method for predicting lane change duration and personifying trajectory planning for an intelligent vehicle according to an embodiment of the present application;
fig. 9 is a block diagram illustrating an intelligent device for predicting lane change time and planning a personalized trajectory according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The intelligent automobile lane change duration prediction and anthropomorphic track planning method in the embodiment of the application is described below with reference to the accompanying drawings.
Before introducing the intelligent automobile lane change duration prediction and anthropomorphic track planning method in the embodiment of the application, a lane change track extraction method in the related technology is simply introduced.
There are two main approaches in the related art: (1) collecting lane change data by adopting a driving simulator for analysis; (2) and directly extracting a lane changing track from natural driving data for analysis.
Specifically, the driving simulator data can be directly combined with a driver questionnaire survey, different driving lane change data of the same driver in different scenes are collected, and clustering analysis of the driver style is facilitated, but the driving simulator has the defects that the sample size is limited, the driving simulator is different from the actual driving environment and the like, so that the conventional lane change research is more and more focused on directly extracting and mining the law of lane change behavior from high-precision natural driving track data.
However, it still faces a great challenge to accurately extract the lane change trajectory from the natural driving data, and the existing technical solution of extracting the lane change trajectory from the natural driving data usually gives a threshold, and considers that the lane change starts when the distance from the vehicle to the center of the lane line is greater than the threshold, and considers that the lane change ends when the distance from the vehicle to the center of the target lane line is less than the threshold, or extracts the lane change trajectory according to the change process of the lateral speed from zero value to peak value to zero value.
Based on the above problems, the present application provides a method for predicting lane change duration and planning anthropomorphic trajectories for an intelligent vehicle, in which a lane change trajectory of an excellent driver is extracted from natural driving data of a large number of drivers, the lane change duration of the excellent driver under the influence of real multiple vehicles is extracted from the lane change trajectory of the excellent driver, then the surrounding vehicle motion information of a lane change vehicle is obtained, a vehicle lane change longitudinal kinematics model under the influence of multiple vehicles is established according to the surrounding vehicle motion information, the influence of the surrounding vehicle is represented as a nonlinear mapping of the surrounding vehicle kinematics parameters to the average longitudinal acceleration of the lane change vehicle, and a lane change duration prediction model under the influence of multiple vehicles can be obtained, so that when the lane change duration prediction model is applied to the intelligent vehicle under the internet-connected multiple vehicle environment, the intelligent vehicle can predict the lane change longitudinal displacement according to an expected lane change duration, The method comprises the steps that the longitudinal speed of the intelligent automobile, the expected speed of a target lane after lane changing and the like are combined with the week information of the intelligent automobile, the lane changing duration of the intelligent automobile is optimized by using a lane changing duration prediction model, and furthermore, anthropomorphic track planning can be carried out according to the lane changing duration of the intelligent automobile obtained through optimization, so that the lane changing intention of the intelligent automobile is accurately implemented. Therefore, the method and the device solve the problems of insufficient decision reasonability of lane change duration, poor interpretability and possible safety risks caused by insufficient quantitative evaluation of the influence of surrounding vehicles on longitudinal driving behaviors in the lane change process of the vehicle in related intelligent vehicle technologies.
Specifically, fig. 1 is a schematic flow chart of a method for predicting lane change duration and planning a personalized track of an intelligent vehicle according to an embodiment of the present application.
As shown in fig. 1, the intelligent automobile lane change duration prediction and anthropomorphic track planning method comprises the following steps:
in step S101, a lane change trajectory of an excellent driver is extracted from natural driving data of several drivers, and an excellent driver lane change duration under the influence of real multiple vehicles is extracted from the lane change trajectory of the excellent driver. Namely: the lane changing track of the excellent driver is extracted from the natural driving data of the mass drivers, and then the lane changing duration of the excellent driver under the influence of real multiple vehicles corresponding to the lane changing track of the excellent driver is extracted.
In a specific example, extracting a lane change trajectory of an excellent driver from natural driving data of several drivers, and extracting an excellent driver lane change duration under the influence of real multiple vehicles from the excellent driver lane change trajectory includes: calculating an orientation angle of a lane change trajectory of the excellent driver; determining a peak point from the natural driving data based on the orientation angle, and searching from the peak point to two sides to obtain a time point meeting a preset condition; matching the initial interval of the corresponding lane changing track by the time point; and calculating the peak-peak time difference of the lateral acceleration of the track changing track according to the initial interval, and calculating corresponding time points when the lateral acceleration obtains the maximum value and the minimum value based on the time difference to obtain the excellent track changing time of the driver under the influence of real multiple vehicles.
Specifically, when extracting a lane change trajectory of a vehicle from a large amount of natural driving data of a driver, the embodiment of the present application may first calculate an orientation angle of the lane change trajectory
The peak point may be an orientation angle
Points greater than a preset orientation angle threshold, assuming an orientation angle threshold of 2, then the orientation angle in the natural driving data
All the points of (A) are peak pointsSearching from the peak point to both sides to obtain a time point satisfying a preset condition, wherein the preset condition may be
So that the initial interval of the corresponding lane change track can be matched by the time point
。
Therefore, the initial section of the extracted lane change track has a redundant time section due to the lateral displacement and the speed fluctuation of the vehicle, so that the lane change track can be accurately extracted by adopting the lateral acceleration peak-peak value.
Further, the peak-peak time difference of the lateral acceleration of the track-changing track
The formula (2) is shown in formula (1):
wherein the content of the first and second substances,
the sign is calculated for the absolute value of the value,
the corresponding time point when the lateral acceleration takes the maximum value,
the corresponding time point when the lateral acceleration takes the minimum value,
the track-changing time corresponding to the track-changing track is provided.
Thus, it can be seen thatLength of track change time corresponding to track change track
Is twice the peak-to-peak time difference of lateral acceleration
So that the starting point of the lane change time
And end of track change time
Respectively shown in formula (2) and formula (3):
wherein the content of the first and second substances,
in order to take the sign of the minimum value,
the sign of the maximum value is taken.
For example, as shown in fig. 2 and 3, (a) to (c) in fig. 2 are respectively the change laws of the lane change trajectory to the left, the lateral speed and the lateral acceleration extracted from the natural driving trajectory set HighD; fig. 3 (a) to (c) show the change laws of the lane change trajectory, the lateral speed, and the lateral acceleration extracted from the natural driving trajectory set HighD, respectively. In FIGS. 2 and 3, the lane change start point and the lane change end point correspond to those of equations (2) and (3)
And
the time point corresponding to the lateral acceleration peak-peak value is the time point
And
. As can be seen from fig. 2 and 3, the lane change trajectory extraction method can accurately and completely extract the lane change trajectory from the natural driving data set, and lays a reliable data foundation for the next lane change duration prediction modeling.
In step S102, the turnaround motion information of the turnaround vehicle is obtained, a longitudinal vehicle turnaround motion model under the influence of multiple vehicles is established according to the turnaround motion information, and the influence of the turnaround vehicle is represented as a nonlinear mapping of the turnaround motion parameter to the average longitudinal acceleration of the turnaround vehicle, so as to obtain a trained lane change duration prediction model under the influence of multiple vehicles and model parameters obtained by identification. In a specific application, the unmanned aerial vehicle can be used for obtaining motion information of vehicles around the lane changing vehicle, for example, data in a germany natural driving data set HighD is obtained; the motion information of vehicles around the lane-changing vehicle can also be obtained by the roadside camera, for example, the data in the american natural driving data set NGSIM is acquired.
In one specific example, obtaining a trained lane change duration prediction model under the influence of multiple vehicles and identifying obtained model parameters includes: performing acceleration correction on the average longitudinal acceleration of the lane changing vehicle to obtain the corrected average longitudinal acceleration, and representing the influence of the week vehicle as nonlinear mapping of the kinetic parameters of the week vehicle on the average longitudinal acceleration of the lane changing vehicle; and according to the longitudinal vehicle lane change kinematics model under the influence of the multiple vehicles and the influence characterization of the vehicles in the week, obtaining a lane change duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification by nonlinear mapping of the vehicle lane change kinematics parameters to the average longitudinal acceleration of the lane change vehicle.
It will be appreciated that the ideal would beThe lane change is performed by the driver in order to pursue a higher driving speed, so that the driver tends to keep a constant speed or accelerate the lane change in the lane change process without considering the influence of the surrounding vehicle, so as to quickly realize lane change and improvement of driving efficiency, while in a complex driving environment, the lane change action of the driver has to consider the influence of the surrounding vehicle, and the influence of the surrounding vehicle on the longitudinal driving action of the lane change of the self vehicle needs to be generated through the stress reaction of the driver of the self vehicle. Therefore, the embodiment of the present application can equate the influence of other vehicles within a preset range of the vehicle periphery to the average longitudinal acceleration of the own vehicle
Influence of, equivalence coefficient
The non-linear mapping relationship between (i.e., the influence value) and the other vehicle state within the preset range of the vehicle periphery can be expressed by equation (4):
one possible solution for the non-linear mapping of equation (4) is the regression model solution of equations (5) and (6). In the formulae (5) and (6),
、
and
all the coefficients are regression coefficients, and can be calibrated according to the actual lane change trajectory (i.e. the lane change trajectory extracted in step S101):
further, when the average longitudinal acceleration of the own vehicle is subjected to acceleration correction according to the influence of the cycle, the average longitudinal acceleration
Can be obtained by averaging the longitudinal acceleration as shown in FIG. 4
The expression quantified can be made using the mathematical formula shown in equation (7):
in the formula (7), the reaction mixture is,
is an equivalent coefficient relating to other vehicle motion states within a preset range of the vehicle periphery,
under ideal conditions, only the expected longitudinal acceleration of the lane change efficiency gain is considered,
can be defined as shown in formula (8):
in the formula (8), the reaction mixture is,
the lane change by the driver is to pursue higher driving efficiency, which is the expected driving speed of the target lane, under the assumption of an ideal driver, and therefore,
the vehicle can quickly realize the increase of the longitudinal driving speed in the lane changing process, the driver has to consider the interaction with the week vehicle in the lane changing process, the final actual longitudinal acceleration is the result of the game with the week vehicle in the interactive game process with the week vehicle, and the influence of the week vehicle is mainly reflected in the influence value shown in the formula (7)
In (1).
Therefore, a trained lane change duration prediction model under the influence of multiple vehicles can be obtained according to a vehicle lane change longitudinal kinematics model shown in the formula (9) and the like.
Optionally, in some embodiments, the lane change duration prediction model may be obtained by solving a quadratic equation shown in equation (9) and removing a negative number solution:
wherein the content of the first and second substances,
in order to prolong the lane change time of the self vehicle,
a longitudinal displacement for anticipating lane change of the bicycle,
Is the average longitudinal acceleration of the own vehicle,
and the expected speed of the vehicle in the target lane after the vehicle is changed.
The formula (10) is as follows
Under the mathematical limit condition of (1), the lane change duration without considering the longitudinal acceleration can be obtained
. It is obvious that
When formula (10) is
The limit problem of mathematics is solved by utilizing the Luobada rule to simultaneously obtain the numerator-denominator pair
As shown in equation (11):
as can be seen from equation (11), the length of the lane change time
In the calculation formula (10), the average longitudinal acceleration of the vehicle
The solution at zero-go equals the expected lane-change distance
Expected speed of target lane after lane change
The ratio of (a) to (b) meets the uniform kinematics rule, which shows that the conventional longitudinal uniform lane change duration model is a special case of the lane change duration prediction model provided by the application.
It should be noted that the nonlinear mapping model of the influence of the weekly vehicle on the average longitudinal acceleration of the self vehicle can be obtained not only by the above regression modeling method, but also by other means in other examples, such as: the method is obtained by non-parametric modeling methods such as a neural network model, a support vector machine model, a random forest model and a deep learning model.
In step S103, under the condition that the intelligent vehicle in the internet multi-vehicle environment uses the lane change duration prediction model to make a decision, when a lane change instruction is issued, based on the expected lane change longitudinal displacement, the longitudinal speed of the intelligent vehicle and the expected speed of the target lane after lane change, in combination with the vehicle-circulation information of the intelligent vehicle, the lane change duration prediction model is used to optimize the lane change duration of the intelligent vehicle, and a humanized trajectory plan is performed according to the lane change duration of the intelligent vehicle obtained by optimization, so as to implement the accurate implementation of the lane change intention of the intelligent vehicle.
That is, after the lane change duration prediction model is obtained through steps S101 and S102, the lane change duration prediction model may be applied to the smart vehicle for automatic and intelligent lane change control.
It should be understood that, in a networked multi-Vehicle environment, the smart Vehicle may obtain the motion information of the surrounding Vehicle through a Vehicle-mounted sensing system and V2X (Vehicle to X, information exchange between vehicles and the outside), where X may be vehicles, roads and clouds, and the smart Vehicle may obtain the motion information of the surrounding Vehicle through sensors (such as laser radar, millimeter wave radar, camera, GPS, inertial navigation, etc.) of the sensing system and V2X communication equipment, so as to evaluate risks generated by the motion of the surrounding Vehicle, and thus provide accurate environment information for a lane change decision of the Vehicle.
Therefore, when a lane change instruction is issued by a lane change intention module and a lane change decision module of the intelligent automobile, based on the expected lane change longitudinal displacement, the average longitudinal acceleration of the automobile and the expected speed of a target lane after lane change, the lane change duration of the intelligent automobile is optimized by using the lane change duration prediction model in combination with the week automobile information acquired by the intelligent automobile sensing system and the V2X equipment, and the anthropomorphic track planning is performed according to the lane change duration of the intelligent automobile obtained through optimization, so that the lane change intention of the intelligent automobile is accurately implemented.
Wherein the expected lane-change longitudinal displacement is determined as a function of longitudinal position, longitudinal velocity, and longitudinal acceleration state.
Specifically, as shown in fig. 5, in the lane change process, the surrounding vehicles that can be considered by the embodiment of the present application are the front and rear vehicles from the current lane and the front and rear vehicles from the target lane, respectively, in fig. 5, vehicle No. 1 is the front vehicle of the current lane, vehicle No. 2 is the rear vehicle of the current lane, vehicle No. 3 is the rear vehicle of the target lane, vehicle No. 4 is the front vehicle of the target lane,
as a function of the longitudinal position, longitudinal velocity and longitudinal acceleration status of each vehicle.
Therefore, the problems of insufficient decision reasonability of lane change duration, poor interpretability and possible safety risks caused by insufficient quantitative evaluation of the influence of surrounding vehicles on longitudinal driving behaviors in the lane change process of the vehicle in the related intelligent vehicle technology are solved, the driving control rule of an excellent driver in natural driving data is fully mined, a reference is provided for scientific and reasonable lane change decisions of the intelligent vehicle, and the method is the embodiment of the anthropomorphic decision concept of a learner, a simulator, a surrogator and a serviceman of the intelligent vehicle in the lane change decisions.
In order to enable those skilled in the art to further understand the method for predicting the lane change time and planning the anthropomorphic track of the intelligent vehicle according to the embodiment of the present application, a natural driving data set HighD is taken as an example for detailed description.
Specifically, there are 5600 lane change tracks in the HighD data set, data of multiple lane changes are removed, lane change tracks in which the week vehicle meets the environment shown in fig. 5 in the lane change process are extracted, and 1000 lane change tracks are randomly selected as study objects.
As shown in FIG. 6, FIGS. 6 (a) to 6 (c) are the longitudinal displacements of the lane change tracks, respectively
Longitudinal initial velocity
And average equivalent longitudinal acceleration
Statistical distribution of the measured results. As can be seen in FIG. 6, the longitudinal displacement
Obey normal distribution, the longitudinal displacement distribution in the channel changing process is
Within the interval (c). Initial longitudinal velocity
Is in bimodal distribution and is concentrated in
In the high-speed travel interval. By averaging longitudinal acceleration of the vehicle
The distribution characteristics of the acceleration sensor are known, the lane changing process may generate a scene with negative average acceleration under the influence of the surrounding vehicles, and under most scenes, a driver wants to maintain the working condition that the average longitudinal acceleration is zero, so that more attention is paid to the transverse driving behavior of successfully completing the lane changing.
Further, as shown in fig. 7, fig. 7 (a) and fig. 7 (b) are a histogram and a scatter diagram respectively illustrating a comparison between a lane change time length of the current vehicle predicted and obtained according to the present application and a lane change time length corresponding to an initially measured lane change track, and it can be known from a statistical histogram that the lane change time length follows a log-normal distribution, and a probability density curve of the predicted lane change time length established by using the log-normal distribution has a high consistency with the statistical histogram of the lane change time length obtained by the actual measurement, which indicates that the accuracy of the lane change time length of the current vehicle predicted by the present application is high. As can be seen from the comparison of the lane change time corresponding to the lane change track and the predicted scatter diagram of the lane change time of the current vehicle, the predicted lane change time is uniformly dispersed on both sides of the true value, which indicates that the modeling effect is better.
In summary, as shown in fig. 8, the present application first extracts a complete lane change trajectory from natural driving data, and calculates a lane change duration; secondly, acquiring kinematic parameters of vehicles around the self-vehicle by utilizing a network connection technology, and providing data for quantitative evaluation under the influence of the self-vehicle; and finally, modeling lane change duration, wherein on the premise of giving a lane change longitudinal distance and a longitudinal speed, a predicted value of the lane change duration (the lane change duration of the current vehicle obtained by using a lane change duration prediction model) can be directly solved by a kinematic model by combining a longitudinal acceleration under the influence of a surrounding vehicle.
According to the method for predicting the lane change time length of the intelligent automobile and planning the anthropomorphic track, which is provided by the embodiment of the application, the lane change track of an excellent driver can be extracted from natural driving data of a large number of drivers, the lane change time length of the excellent driver under the influence of real multiple vehicles can be extracted from the lane change track of the excellent driver, then the surrounding vehicle motion information of a lane change vehicle is obtained, a vehicle lane change longitudinal kinematics model under the influence of the multiple vehicles is established according to the surrounding vehicle motion information, the influence of the surrounding vehicle is represented as the nonlinear mapping of the surrounding vehicle kinematics parameters to the average longitudinal acceleration of the lane change vehicle, and further the lane change time length prediction model under the influence of the multiple vehicles can be obtained, so that after the lane change time length prediction model is applied to the intelligent automobile under the environment of the internet multiple vehicles, the intelligent automobile can predict the lane change longitudinal displacement, the longitudinal speed of the intelligent automobile, the expected lane change target lane speed and the like according to the intelligent automobile, and optimizing the lane change time of the intelligent automobile by using the lane change time prediction model in combination with the week information of the intelligent automobile, and further performing anthropomorphic track planning according to the lane change time of the intelligent automobile obtained through optimization so as to realize accurate implementation of the lane change intention of the intelligent automobile. Therefore, the method and the device solve the problems of insufficient decision reasonability of lane change duration, poor interpretability and possible safety risks caused by insufficient quantitative evaluation of the influence of surrounding vehicles on longitudinal driving behaviors in the lane change process of the vehicle in related intelligent vehicle technologies.
The intelligent automobile lane change duration prediction and anthropomorphic track planning device provided by the embodiment of the application is described with reference to the attached drawings.
Fig. 9 is a block diagram of the intelligent automobile lane change duration prediction and anthropomorphic trajectory planning device according to the embodiment of the application.
As shown in fig. 9, the intelligent vehicle lane change duration prediction and anthropomorphic trajectory planning device 10 includes: an extraction module 100, a generation module 200 and a lane change trajectory planning module 300.
The extraction module 100 is configured to extract a lane change trajectory of an excellent driver from natural driving data of a plurality of drivers, and extract lane change duration of the excellent driver under the influence of real multiple vehicles from the lane change trajectory of the excellent driver;
the generation module 200 is configured to obtain the vehicle-turnover motion information of the lane-changing vehicle, establish a vehicle lane-changing longitudinal kinematics model under the influence of multiple vehicles according to the vehicle-turnover motion information, and characterize the influence of the vehicles as nonlinear mapping of the vehicle-turnover kinematics parameters to the average longitudinal acceleration of the lane-changing vehicle, so as to obtain a trained lane-changing duration prediction model under the influence of multiple vehicles and model parameters obtained through identification; and
the lane change trajectory planning module 300 is configured to, when a lane change instruction is issued under the condition that the intelligent vehicle uses the lane change duration prediction model to make a decision, optimize the lane change duration of the intelligent vehicle by using the lane change duration prediction model in combination with the vehicle circulation information of the intelligent vehicle based on an expected lane change longitudinal displacement, the longitudinal speed of the intelligent vehicle and the expected speed of a target lane after lane change, and perform anthropomorphic trajectory planning according to the lane change duration of the intelligent vehicle obtained through optimization, so as to implement accurate implementation of the lane change intention of the intelligent vehicle.
Optionally, the extraction module 100 is specifically configured to:
calculating an orientation angle of a lane change trajectory of the excellent driver;
determining a peak point from the natural driving data based on the orientation angle, and searching from the peak point to two sides to obtain a time point meeting a preset condition;
matching the initial interval of the corresponding lane changing track by the time point;
and calculating the peak-peak time difference of the lateral acceleration of the track changing track according to the initial interval, and calculating corresponding time points when the lateral acceleration obtains the maximum value and the minimum value based on the time difference to obtain the excellent track changing time of the driver under the influence of real multiple vehicles.
Optionally, the generating module 200 is specifically configured to:
performing acceleration correction on the average longitudinal acceleration of the lane changing vehicle to obtain the corrected average longitudinal acceleration, and representing the influence of the week vehicle as nonlinear mapping of the kinetic parameters of the week vehicle on the average longitudinal acceleration of the lane changing vehicle;
and according to the longitudinal vehicle lane change kinematics model under the influence of the multiple vehicles and the influence characterization of the vehicles in the week, obtaining a lane change duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification by nonlinear mapping of the vehicle lane change kinematics parameters to the average longitudinal acceleration of the lane change vehicle.
Optionally, the lane change duration prediction model is:
wherein the content of the first and second substances,
in order to prolong the lane change time of the self vehicle,
a longitudinal displacement for anticipating lane change of the bicycle,
Is the average longitudinal acceleration of the own vehicle,
and the expected speed of the vehicle in the target lane after the vehicle is changed.
Optionally, the expected lane-change longitudinal displacement is determined as a function of longitudinal position, longitudinal velocity, and longitudinal acceleration state.
It should be noted that the explanation of the embodiment of the method for predicting lane change time length of an intelligent vehicle and planning a personalized trajectory is also applicable to the device for predicting lane change time length of an intelligent vehicle and planning a personalized trajectory in this embodiment, and is not repeated here.
According to the intelligent automobile lane change duration prediction and anthropomorphic trajectory planning device provided by the embodiment of the application, the lane change trajectory of an excellent driver can be extracted from a large amount of natural driving data of the driver, the lane change duration of the excellent driver under the influence of real multiple vehicles can be extracted from the lane change trajectory of the excellent driver, then the surrounding vehicle motion information of a lane change vehicle is obtained, a vehicle lane change longitudinal kinematics model under the influence of the multiple vehicles is established according to the surrounding vehicle motion information, the influence of the surrounding vehicle is represented as the nonlinear mapping of the surrounding vehicle kinematics parameters to the average longitudinal acceleration of the lane change vehicle, and further the lane change duration prediction model under the influence of the multiple vehicles can be obtained, so that after the lane change duration prediction model is applied to the intelligent automobile under the internet multiple vehicle environment, the intelligent automobile can predict the lane change longitudinal displacement, the longitudinal speed of the intelligent automobile, the expected lane speed of a target lane after lane change and the like according to the expected lane change duration prediction model, and optimizing the lane change time of the intelligent automobile by using the lane change time prediction model in combination with the week information of the intelligent automobile, and further performing anthropomorphic track planning according to the lane change time of the intelligent automobile obtained through optimization so as to realize accurate implementation of the lane change intention of the intelligent automobile. Therefore, the method and the device solve the problems of insufficient decision reasonability of lane change duration, poor interpretability and possible safety risks caused by insufficient quantitative evaluation of the influence of surrounding vehicles on longitudinal driving behaviors in the lane change process of the vehicle in related intelligent vehicle technologies.
In addition, this application embodiment provides an intelligent automobile track change decision-making equipment, includes: the intelligent automobile lane change duration prediction and anthropomorphic track planning method comprises a lane change intention recognition module and a lane change track planning module, wherein the intelligent automobile lane change duration prediction and anthropomorphic track planning method serves the lane change intention recognition module and the lane change track planning module.
In addition, a track-changing track tracking module is provided in an embodiment of a fourth aspect of the present application, and a computer program is stored on the track-changing track tracking module, where the computer program is executed by a processor, so as to implement the method for predicting a track-changing time of an intelligent vehicle and planning a humanized track.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" 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" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of implementing the embodiments of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. An intelligent automobile lane change duration prediction and anthropomorphic track planning method is characterized by comprising the following steps:
extracting a lane changing track of an excellent driver from natural driving data of a plurality of drivers, and extracting lane changing time length of the excellent driver under the influence of real multiple vehicles from the lane changing track of the excellent driver;
acquiring the vehicle-turnover motion information of a lane-changing vehicle, establishing a vehicle lane-changing longitudinal kinematic model under the influence of multiple vehicles according to the vehicle-turnover motion information, and representing the influence of the vehicles as the nonlinear mapping of the vehicle-turnover kinematic parameters to the average longitudinal acceleration of the lane-changing vehicle, so as to obtain a trained lane-changing duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification;
under the condition that an intelligent automobile in a network multi-automobile environment uses the lane change duration prediction model to make a decision, when a lane change instruction is given, the lane change duration of the intelligent automobile is optimized by using the lane change duration prediction model based on the expected lane change longitudinal displacement, the longitudinal speed of the intelligent automobile and the expected speed of a target lane after lane change in combination with the week information of the intelligent automobile, and the lane change duration of the intelligent automobile is subjected to anthropomorphic track planning according to the lane change duration of the intelligent automobile obtained through optimization, so that the lane change intention of the intelligent automobile is accurately implemented.
2. The method according to claim 1, wherein the extracting of the lane change trajectory of the excellent driver from the natural driving data of several drivers and the extracting of the excellent driver lane change duration under the influence of real multi-vehicle from the excellent driver lane change trajectory comprises:
calculating an orientation angle of a lane change trajectory of the excellent driver;
determining a peak point from the natural driving data based on the orientation angle, and searching from the peak point to two sides to obtain a time point meeting a preset condition;
matching the initial interval of the corresponding lane changing track by the time point;
and calculating the peak-peak time difference of the lateral acceleration of the track changing track according to the initial interval, and calculating corresponding time points when the lateral acceleration obtains the maximum value and the minimum value based on the time difference to obtain the excellent track changing time of the driver under the influence of real multiple vehicles.
3. The method of claim 1, wherein the obtaining a trained lane change duration prediction model under the influence of multiple vehicles and identifying obtained model parameters comprises:
performing acceleration correction on the average longitudinal acceleration of the lane changing vehicle to obtain the corrected average longitudinal acceleration, and representing the influence of the week vehicle as nonlinear mapping of the kinetic parameters of the week vehicle on the average longitudinal acceleration of the lane changing vehicle;
and according to the longitudinal vehicle lane change kinematics model under the influence of the multiple vehicles and the influence characterization of the vehicles in the week, obtaining a lane change duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification by nonlinear mapping of the vehicle lane change kinematics parameters to the average longitudinal acceleration of the lane change vehicle.
4. The method of claim 3, wherein the lane change duration prediction model is:
wherein the content of the first and second substances,
in order to prolong the lane change time of the self vehicle,
a longitudinal displacement for anticipating lane change of the bicycle,
Is the average longitudinal acceleration of the own vehicle,
and the expected speed of the vehicle in the target lane after the vehicle is changed.
5. The method of claim 1, wherein the expected lane-change longitudinal displacement is determined as a function of longitudinal position, longitudinal velocity, and longitudinal acceleration state.
6. The utility model provides an intelligent automobile lane change duration prediction and anthropomorphic track planning device which characterized in that includes:
the extraction module is used for extracting a lane changing track of an excellent driver from natural driving data of a plurality of drivers and extracting the lane changing time length of the excellent driver under the influence of real multiple vehicles from the lane changing track of the excellent driver;
the generation module is used for acquiring the vehicle-turnover motion information of the lane-changing vehicle, establishing a vehicle lane-changing longitudinal kinematic model under the influence of multiple vehicles according to the vehicle-turnover motion information, representing the influence of the vehicles as the nonlinear mapping of the vehicle-turnover kinematic parameters to the average longitudinal acceleration of the lane-changing vehicle, and further acquiring a trained lane-changing duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification; and
and the lane change track planning module is used for optimizing the lane change time length of the intelligent automobile by using the lane change time length prediction model according to the lane change time length prediction model and the acquired lane change time length of the intelligent automobile according to the optimization when a lane change instruction is issued under the condition that the intelligent automobile applies the lane change time length prediction model to make a decision, and the lane change time length prediction model is combined with the week automobile information of the intelligent automobile, so that the accurate implementation of the lane change intention of the intelligent automobile is realized.
7. The apparatus according to claim 6, wherein the extraction module is specifically configured to:
calculating an orientation angle of a lane change trajectory of the excellent driver;
determining a peak point from the natural driving data based on the orientation angle, and searching from the peak point to two sides to obtain a time point meeting a preset condition;
matching the initial interval of the corresponding lane changing track by the time point;
and calculating the peak-peak time difference of the lateral acceleration of the track changing track according to the initial interval, and calculating corresponding time points when the lateral acceleration obtains the maximum value and the minimum value based on the time difference to obtain the excellent track changing time of the driver under the influence of real multiple vehicles.
8. The apparatus of claim 6, wherein the generating module is specifically configured to:
performing acceleration correction on the average longitudinal acceleration of the lane changing vehicle to obtain the corrected average longitudinal acceleration, and representing the influence of the week vehicle as nonlinear mapping of the kinetic parameters of the week vehicle on the average longitudinal acceleration of the lane changing vehicle;
and according to the longitudinal vehicle lane change kinematics model under the influence of the multiple vehicles and the influence characterization of the vehicles in the week, obtaining a lane change duration prediction model under the influence of the multiple vehicles and model parameters obtained by identification by nonlinear mapping of the vehicle lane change kinematics parameters to the average longitudinal acceleration of the lane change vehicle.
9. An intelligent automobile track change decision-making device is characterized by comprising: the lane change intention identification module and the lane change track planning module, wherein the intelligent automobile lane change duration prediction and anthropomorphic track planning method as claimed in any one of claims 1-5 serves the lane change intention identification module and the lane change track planning module.
10. A lane change trajectory tracking module, on which a computer program is stored, wherein the program is executed by a processor to implement the intelligent vehicle lane change duration prediction and anthropomorphic trajectory planning method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111237247.1A CN113665574B (en) | 2021-10-22 | 2021-10-22 | Intelligent automobile lane change duration prediction and anthropomorphic track planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111237247.1A CN113665574B (en) | 2021-10-22 | 2021-10-22 | Intelligent automobile lane change duration prediction and anthropomorphic track planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113665574A true CN113665574A (en) | 2021-11-19 |
| CN113665574B CN113665574B (en) | 2022-01-11 |
Family
ID=78550986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111237247.1A Active CN113665574B (en) | 2021-10-22 | 2021-10-22 | Intelligent automobile lane change duration prediction and anthropomorphic track planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113665574B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114056332A (en) * | 2022-01-14 | 2022-02-18 | 清华大学 | Intelligent automobile following decision and control method based on cognitive risk balance |
| CN114169371A (en) * | 2021-12-09 | 2022-03-11 | 合肥工业大学智能制造技术研究院 | Driving style classification method considering risk potential field distribution under vehicle lane change working condition |
| CN114475608A (en) * | 2022-04-13 | 2022-05-13 | 清华大学 | Method and device for changing lanes for automatic driving vehicle, vehicle and storage medium |
| CN114475607A (en) * | 2022-04-13 | 2022-05-13 | 清华大学 | Method and device for changing lane for automatic driving vehicle, vehicle and storage medium |
| CN114633750A (en) * | 2022-03-29 | 2022-06-17 | 山东交通学院 | Unsupervised technology-based lane change process extraction and lane change characteristic analysis method |
| CN115050183A (en) * | 2022-06-09 | 2022-09-13 | 上海人工智能创新中心 | Method for generating simulated traffic flow |
| CN115830886A (en) * | 2023-02-09 | 2023-03-21 | 西南交通大学 | Intelligent network vehicle collaborative lane change time sequence calculation method, device, equipment and medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103754221A (en) * | 2014-01-24 | 2014-04-30 | 清华大学 | Vehicle adaptive cruise control system |
| JP2018030479A (en) * | 2016-08-25 | 2018-03-01 | スズキ株式会社 | Travel control device of vehicle |
| CN109739218A (en) * | 2018-12-24 | 2019-05-10 | 江苏大学 | It is a kind of that outstanding driver's lane-change method for establishing model is imitated based on GRU network |
| CN110576864A (en) * | 2019-08-15 | 2019-12-17 | 中国第一汽车股份有限公司 | driving mode control method and device, vehicle and storage medium |
| CN110936958A (en) * | 2019-11-26 | 2020-03-31 | 交通运输部公路科学研究所 | Automatic driving track changing track optimization model, track changing track optimization method and system |
| CN111009153A (en) * | 2019-12-04 | 2020-04-14 | 珠海深圳清华大学研究院创新中心 | Training method, device and equipment of trajectory prediction model |
| CN111260956A (en) * | 2020-01-15 | 2020-06-09 | 清华大学 | Automatic vehicle lane change planning and control method based on model predictive control |
| CN112053589A (en) * | 2020-08-18 | 2020-12-08 | 北京航空航天大学 | Target vehicle lane changing behavior adaptive identification model construction method |
| JP2020200039A (en) * | 2016-08-25 | 2020-12-17 | スズキ株式会社 | Travel control device of vehicle |
-
2021
- 2021-10-22 CN CN202111237247.1A patent/CN113665574B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103754221A (en) * | 2014-01-24 | 2014-04-30 | 清华大学 | Vehicle adaptive cruise control system |
| JP2018030479A (en) * | 2016-08-25 | 2018-03-01 | スズキ株式会社 | Travel control device of vehicle |
| JP2020200039A (en) * | 2016-08-25 | 2020-12-17 | スズキ株式会社 | Travel control device of vehicle |
| CN109739218A (en) * | 2018-12-24 | 2019-05-10 | 江苏大学 | It is a kind of that outstanding driver's lane-change method for establishing model is imitated based on GRU network |
| CN110576864A (en) * | 2019-08-15 | 2019-12-17 | 中国第一汽车股份有限公司 | driving mode control method and device, vehicle and storage medium |
| CN110936958A (en) * | 2019-11-26 | 2020-03-31 | 交通运输部公路科学研究所 | Automatic driving track changing track optimization model, track changing track optimization method and system |
| CN111009153A (en) * | 2019-12-04 | 2020-04-14 | 珠海深圳清华大学研究院创新中心 | Training method, device and equipment of trajectory prediction model |
| CN111260956A (en) * | 2020-01-15 | 2020-06-09 | 清华大学 | Automatic vehicle lane change planning and control method based on model predictive control |
| CN112053589A (en) * | 2020-08-18 | 2020-12-08 | 北京航空航天大学 | Target vehicle lane changing behavior adaptive identification model construction method |
Non-Patent Citations (3)
| Title |
|---|
| YUE YUAN 等: "An Empirical Study on the Lane-Change Duration of Naturalistic Driving Based on Multiple Linear Regression Model", 《2020 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND INFORMATION SYSTEMS (ICAIIS)》 * |
| 李林波 等: "基于时依等比例风险回归模型的换道时长影响因素", 《同济大学学报（自然科学版）》 * |
| 王世明等: "面向高速公路的车辆换道安全预警模型", 《华南理工大学学报(自然科学版)》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114169371A (en) * | 2021-12-09 | 2022-03-11 | 合肥工业大学智能制造技术研究院 | Driving style classification method considering risk potential field distribution under vehicle lane change working condition |
| CN114169371B (en) * | 2021-12-09 | 2024-05-14 | 合肥工业大学智能制造技术研究院 | Driving style classification method considering risk potential field distribution under vehicle lane change working condition |
| CN114056332A (en) * | 2022-01-14 | 2022-02-18 | 清华大学 | Intelligent automobile following decision and control method based on cognitive risk balance |
| CN114056332B (en) * | 2022-01-14 | 2022-04-12 | 清华大学 | Intelligent automobile following decision and control method based on cognitive risk balance |
| CN114633750A (en) * | 2022-03-29 | 2022-06-17 | 山东交通学院 | Unsupervised technology-based lane change process extraction and lane change characteristic analysis method |
| CN114475608A (en) * | 2022-04-13 | 2022-05-13 | 清华大学 | Method and device for changing lanes for automatic driving vehicle, vehicle and storage medium |
| CN114475607A (en) * | 2022-04-13 | 2022-05-13 | 清华大学 | Method and device for changing lane for automatic driving vehicle, vehicle and storage medium |
| CN115050183A (en) * | 2022-06-09 | 2022-09-13 | 上海人工智能创新中心 | Method for generating simulated traffic flow |
| CN115830886A (en) * | 2023-02-09 | 2023-03-21 | 西南交通大学 | Intelligent network vehicle collaborative lane change time sequence calculation method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113665574B (en) | 2022-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113665574B (en) | Intelligent automobile lane change duration prediction and anthropomorphic track planning method | |
| Zhu et al. | Modeling car-following behavior on urban expressways in Shanghai: A naturalistic driving study | |
| US9053433B2 (en) | Assisting vehicle guidance over terrain | |
| DE102016113903A1 (en) | Vehicle route determination | |
| CN110562258A (en) | Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium | |
| CN113946943B (en) | Human-vehicle-road micro traffic system modeling and risk identification method and device | |
| US20210397198A1 (en) | Enhanced vehicle operation | |
| Dong et al. | Smooth behavioral estimation for ramp merging control in autonomous driving | |
| KR20230069940A (en) | Methods and systems for testing driver assistance systems | |
| EP2405383A1 (en) | Assisting with guiding a vehicle over terrain | |
| CN113942526A (en) | Acceptable risk based automatic driving overtaking track planning method | |
| CN115923833A (en) | Personifying decision control method and device for vehicle, vehicle and storage medium | |
| CN110986994B (en) | Automatic lane change intention marking method based on high-noise vehicle track data | |
| CN114730494A (en) | Method for estimating the coverage of a space of a traffic scene | |
| Wheeler et al. | A probabilistic framework for microscopic traffic propagation | |
| Ramezani-Khansari et al. | [Retracted] Estimating Lane Change Duration for Overtaking in Nonlane‐Based Driving Behavior by Local Linear Model Trees (LOLIMOT) | |
| CN113771884B (en) | Intelligent automobile anthropomorphic track planning method based on lateral quantitative balance index | |
| Akca et al. | eTS fuzzy driver model for simultaneous longitudinal and lateral vehicle control | |
| CN116262507A (en) | Human data driven interpretable artificial intelligence system and method | |
| Salzmann et al. | Online Path Generation from Sensor Data for Highly Automated Driving Functions | |
| Mechernene et al. | Lane change decision algorithm based on risk prediction and fuzzy logic method | |
| Pavelko et al. | Modification and Experimental Validation of a Logistic Regression Vehicle-Pedestrian Model | |
| US20240043022A1 (en) | Method, system, and computer program product for objective assessment of the performance of an adas/ads system | |
| US20230195977A1 (en) | Method and system for classifying scenarios of a virtual test, and training method | |
| Mitrovich | Database-Mediated Network Friction Utilization Analysis to Improve Road Safety |
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 |