CN115092138A - Vehicle expressway lane change track planning method based on natural driver characteristics - Google Patents

Vehicle expressway lane change track planning method based on natural driver characteristics Download PDF

Info

Publication number
CN115092138A
CN115092138A CN202210557257.1A CN202210557257A CN115092138A CN 115092138 A CN115092138 A CN 115092138A CN 202210557257 A CN202210557257 A CN 202210557257A CN 115092138 A CN115092138 A CN 115092138A
Authority
CN
China
Prior art keywords
track
vehicle
longitudinal
time
lane change
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210557257.1A
Other languages
Chinese (zh)
Inventor
赵治国
梁凯冲
颜丹姝
李园
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tongji University
Original Assignee
Tongji University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tongji University filed Critical Tongji University
Priority to CN202210557257.1A priority Critical patent/CN115092138A/en
Publication of CN115092138A publication Critical patent/CN115092138A/en
Pending legal-status Critical Current

Links

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, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • 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
    • 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
    • B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • 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
    • 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
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/10—Historical data

Abstract

The invention relates to a vehicle expressway lane change track planning method based on natural driver characteristics, which comprises the following steps: obtaining historical driving track information of a vehicle highway based on natural drivers; extracting track segment information of vehicle track change; classifying the vehicle track change track segments; performing statistical analysis on the elapsed time of each type of track change track segment to obtain expected track change time; scaling the track changing track segments in each class on a time scale; carrying out statistical analysis on different horizontal and longitudinal positions at the same time by using two-dimensional Gaussian function maximum likelihood estimation to obtain expected horizontal and longitudinal positions, thereby obtaining a teaching lane change track under the longitudinal vehicle speed classification; learning a lane change teaching track to obtain a track primitive library; and generating a lane changing track based on the characteristics of the natural driver by using the optimal track primitive. Compared with the prior art, the method has the advantages of high calculation efficiency, strong generalization capability, good driving and riding comfort and the like.

Description

Vehicle expressway lane change track planning method based on natural driver characteristics
Technical Field
The invention relates to the technical field of automatic driving vehicle track planning, in particular to a vehicle expressway lane change track planning method based on natural driver characteristics.
Background
The trajectory planning technology is used for adapting to an automatic driving decision and a motion control technology, and the trajectory planning result directly concerns the driving safety and the comfort, is one of key technologies for realizing automatic driving of a vehicle, and is a hotspot and difficulty of automatic driving research. The conventional track planning method can be roughly divided into an artificial potential field method, a graph search method, a random sampling method, a parameter curve method, a numerical optimization method and the like.
Chinese patent CN112414419A discloses a method for planning lane change path of vehicle and related device, the method uses meta-cavel spiral line to plan the lane change path according to the lane change start point and lane change end point information; chinese patent CN110244713A discloses an intelligent vehicle lane change track planning system and method based on an artificial potential field method, which draws a model of an obstacle repulsion field in the artificial potential field method into consideration of the constraints of maximum lateral safe acceleration and road curvature to plan a lane change path. However, the above trajectory planning method mostly considers the aspects of environmental constraints, vehicle dynamics constraints, etc., and rarely considers the characteristics of natural drivers; with the continuous improvement of the automatic driving level, the trajectory planning technology only considering efficiency and safety cannot meet the requirements of drivers and passengers.
The expressway lane change scene is one of the most common driving scenes, and if the characteristics of natural drivers cannot be fully considered in the automatic driving vehicle lane change trajectory planning, the comfort level of drivers and passengers is certainly influenced, the receptivity of the automatic driving system is reduced, and the psychological panic feeling is increased. Therefore, it is urgent to research how to extract useful information from historical driving track information of a natural driver-based vehicle highway and plan a highway lane change track according with the characteristics of the natural driver.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a method for planning the lane change track of the vehicle highway based on the characteristics of natural drivers, which has high calculation efficiency, strong generalization capability and good driving comfort.
The purpose of the invention can be realized by the following technical scheme:
a vehicle expressway lane change track planning method based on natural driver characteristics comprises the following steps:
step 1: obtaining historical driving track information of a vehicle highway based on natural drivers;
and 2, step: segmenting the historical driving track of the vehicle based on the vehicle course angle information, and extracting track segment information of the vehicle lane change;
and step 3: classifying the vehicle track change track segments according to the acquired longitudinal speed of the vehicle track change track segment at the starting moment;
and 4, step 4: performing statistical analysis on the elapsed time of each type of track changing track segment in the step 3 by using one-dimensional Gaussian function maximum likelihood estimation to obtain the expected track changing time in the statistical sense;
and 5: scaling the track changing track segments in each class on a time scale according to the corresponding expected track changing time obtained in the step 4;
and 6: carrying out statistical analysis on different horizontal and longitudinal positions at the same time by using two-dimensional Gaussian function maximum likelihood estimation to obtain expected horizontal and longitudinal positions in statistical significance, thereby obtaining a teaching lane change track under the longitudinal vehicle speed classification;
and 7: learning the lane change teaching track obtained in the step 6 by using an improved track primitive algorithm to obtain a track primitive library;
and 8: and matching the optimal track elements according to the longitudinal running speed of the vehicle, and generating a lane changing track based on the characteristics of the natural driver by using the optimal track elements according to the target position.
Preferably, the historical travel track information in step 1 includes a vehicle lateral position, a longitudinal position, a speed, an acceleration, and a time stamp.
Preferably, the step 2 specifically comprises:
step 2-1: calculating a vehicle course angle according to the vehicle position parameter;
step 2-2: traversing the course angle from the lane changing point in the forward direction to obtain a lane changing end point, and then traversing the course angle in the reverse direction to obtain a lane changing starting point;
the lane changing points are specifically as follows: the intersection point of the vehicle track and the lane line;
step 2-3: and extracting the track segment information of the vehicle track change according to the starting point and the end point of the track change.
More preferably, the method for calculating the vehicle heading angle specifically comprises the following steps:
Figure BDA0003652657790000031
wherein, theta (t) The course angle at the time t; x is the number of (t) Is the longitudinal position of the vehicle at time t; y is (t) Is the lateral position of the vehicle at time t.
Preferably, the step 3 specifically comprises:
dividing the track change track segment according to the longitudinal speed of the starting moment of the track change track segment of the vehicle, wherein the speed division intervals are as follows: and dividing 14 classes by taking 5km/h as a dividing step length from 60km/h to 130 km/h.
Preferably, the one-dimensional gaussian function maximum likelihood estimation in step 4 specifically includes:
Figure BDA0003652657790000032
wherein T is the elapsed time of the track change track segment; mu.s T Expecting a track-changing time for the track-changing track segment;
Figure BDA0003652657790000033
the variance over time for the zapping track segment.
Preferably, the step 5 specifically comprises:
step 5-1: acquiring and zooming a lane change track longitudinal speed curve;
the method comprises the following specific steps:
Figure BDA0003652657790000034
wherein the content of the first and second substances,
Figure BDA0003652657790000035
is the scaled longitudinal vehicle speed; v. of x Is the pre-zoom longitudinal vehicle speed;
step 5-2: carrying out N times of equal interval sampling on the scaled longitudinal vehicle speed based on the time dimension by utilizing one-dimensional linear interpolation to obtain a longitudinal vehicle speed sequence under the expected time, and obtaining an expected longitudinal position sequence by combining the expected lane changing time;
the number of times N is specifically:
Figure BDA0003652657790000036
wherein Δ t is a sampling interval;
the longitudinal vehicle speed sequence at the expected time is specifically as follows:
Figure BDA0003652657790000037
the desired longitudinal position sequence is in particular:
Figure BDA0003652657790000038
step 5-3: based on the expected longitudinal position sequence obtained in the step 5-2, combining the lane change track, and obtaining an expected transverse position by utilizing one-dimensional linear interpolation to finish the scaling of the lane change track on a time scale;
the desired sequence of transverse positions is specifically:
Figure BDA0003652657790000041
preferably, the two-dimensional gaussian function maximum likelihood estimation in step 6 is specifically
Figure BDA0003652657790000042
Wherein σ x Is the longitudinal position standard deviation; sigma y Is the lateral position standard deviation; rho is a correlation coefficient between x and y; mu.s x Is a desired longitudinal position; mu.s y Is the desired lateral position.
Preferably, the trajectory primitive algorithm modified in step 7 is:
Figure BDA0003652657790000043
wherein τ is a time scaling factor; alpha is alpha z And beta z Is a system parameter; g is the target position; y is 0 Is the system starting position; f is a forcing function; y, y,
Figure BDA00036526577900000411
And
Figure BDA00036526577900000410
respectively system displacement, velocity and acceleration; x is a system independent variable;
the forcing function f is specifically:
Figure BDA0003652657790000044
wherein Ψ (x) is a gaussian basis function; omega is the weight of the basis function; m is the number of basis functions;
x is a function of time t, and specifically:
Figure BDA0003652657790000045
wherein alpha is x Is greater than 0 and is a system constant;
the step 7 specifically comprises the following steps:
step 7-1: calculating a target forcing function based on the teaching track;
the method specifically comprises the following steps:
Figure BDA0003652657790000046
wherein, y demo 、
Figure BDA0003652657790000047
And
Figure BDA0003652657790000048
respectively demonstrating displacement, speed and acceleration of the track;
step 7-2: constructing a loss function, and solving a weight value corresponding to the basis function by using a local weighted regression algorithm;
the loss function is specifically:
Figure BDA0003652657790000049
the method for solving the weight values corresponding to the basis functions by the local weighted regression algorithm specifically comprises the following steps:
Figure BDA0003652657790000051
Figure BDA0003652657790000052
Figure BDA0003652657790000053
Figure BDA0003652657790000054
preferably, the step 8 specifically comprises:
step 8-1: based on the longitudinal speed of the teaching track at the starting moment, selecting the teaching track closest to the longitudinal running speed of the vehicle according to the minimum distance principle, and further matching an optimal track element;
step 8-2: calculating and generating a lane changing track based on the characteristics of a driver by using the optimal track primitive according to the target lane changing position;
the method specifically comprises the following steps: calculating by using a track primitive algorithm to obtain displacement, speed and acceleration information of the lane changing track;
the track primitive algorithm specifically comprises:
Figure BDA0003652657790000055
compared with the prior art, the invention has the following beneficial effects:
firstly, the calculation efficiency is high, and the generalization capability is strong: according to the method for planning the lane change track of the vehicle expressway, after the track primitive library is obtained, the optimal track primitive is matched according to the longitudinal running speed of the vehicle, only iterative operation is needed when the lane change track is generated, and the problems of numerical solution and optimization are not involved, so that the calculation efficiency is high; and a plurality of lane changing tracks which accord with the characteristics of natural drivers can be quickly formed according to the difference of the target lane changing positions.
Secondly, the characteristics of natural drivers in the lane changing process are fully considered, and the riding comfort is high: the track primitive library obtained by the method for planning the vehicle expressway lane change track is obtained based on the driving data of the natural driver, so that the generalized lane change track is more consistent with the characteristics of the natural driver, and the acceptance of drivers and passengers is high.
Drawings
FIG. 1 is a schematic flow chart of a method for planning a lane change track of a vehicle highway according to the present invention;
FIG. 2 is a schematic diagram of probability distribution of transverse and longitudinal positions of a lane change track in a vehicle speed range of 85km/h to 90km/h in the embodiment of the invention;
FIG. 3 is a schematic diagram of a lane change teaching track of a vehicle speed range of 85km/h to 90km/h in the embodiment of the invention;
FIG. 4 is a schematic diagram of a track change track generalized in the transverse and longitudinal directions according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.
A method for planning a vehicle expressway lane change track based on natural driver characteristics is shown in a flow chart of fig. 1 and comprises the following steps:
step 1: obtaining historical driving track information of a vehicle highway based on natural drivers;
the natural driver-based vehicle highway historical driving track information comprises vehicle transverse and longitudinal positions, speed, acceleration and time stamps;
step 2: segmenting the historical driving track of the vehicle based on the vehicle course angle information, and extracting track segment information of the vehicle lane change;
and step 3: classifying the vehicle track change track segment according to the acquired longitudinal speed of the vehicle track change track segment at the starting moment;
and 4, step 4: performing statistical analysis on the elapsed time of each type of track changing track segment in the step 3 by using one-dimensional Gaussian function maximum likelihood estimation to obtain the expected track changing time in the statistical sense;
the one-dimensional Gaussian function maximum likelihood estimation specifically comprises the following steps:
Figure BDA0003652657790000061
wherein T is the elapsed time of the track-changing track segment, mu T Track changing track sheet for the classThe segment expects a time to change lanes,
Figure BDA0003652657790000062
the variance over time for the zapping track segment.
And 5: scaling the track changing track segments in each class on a time scale according to the corresponding expected track changing time obtained in the step 4;
step 6: carrying out statistical analysis on different horizontal and longitudinal positions at the same time by using two-dimensional Gaussian function maximum likelihood estimation to obtain expected horizontal and longitudinal positions in statistical significance, thereby obtaining a teaching lane change track under the longitudinal vehicle speed classification, as shown in FIGS. 2 and 3;
the two-dimensional Gaussian function maximum likelihood estimation specifically comprises
Figure BDA0003652657790000071
Wherein σ x As standard deviation of longitudinal position, σ y ρ is the correlation coefficient between x and y, μ, for the lateral position standard deviation x To a desired longitudinal position, mu y Is the desired lateral position.
And 7: learning the lane change teaching track obtained in the step 6 by using an improved track primitive algorithm to obtain a track primitive library;
and step 8: and matching the optimal track primitive according to the longitudinal running speed of the vehicle, and generating a lane changing track based on the characteristics of the driver by using the optimal track primitive according to the target position, as shown in FIG. 4.
The step 2 specifically comprises the following steps:
step 2-1: calculating a vehicle course angle according to the vehicle position parameter;
step 2-2: traversing the course angle from the lane changing point in the forward direction to obtain a lane changing end point; reversely traversing the course angle to obtain a lane change starting point, wherein the lane change point is defined as an intersection point of a vehicle track and a lane line;
step 2-3: and extracting the track segment information of the vehicle track change according to the track change starting point and the track change end point.
The vehicle course angle calculation method specifically comprises the following steps:
Figure BDA0003652657790000072
wherein, theta (t) Course angle at time t, x (t) Is the longitudinal position of the vehicle at time t, y (t) Is the lateral position of the vehicle at time t.
The step 3 specifically comprises the following steps: dividing the track change track segments according to the longitudinal speed of the starting time of the track change track segments of the vehicle, wherein the speed division interval is divided into 14 classes from 60km/h to 130km/h by taking 5km/h as a division step length.
The step 5 specifically comprises the following steps:
step 5-1: the method comprises the following steps of obtaining a lane change track longitudinal speed curve for zooming, wherein the specific formula is as follows:
Figure BDA0003652657790000073
wherein the content of the first and second substances,
Figure BDA0003652657790000081
for scaled longitudinal vehicle speed, v x To zoom in on the front longitudinal vehicle speed.
Step 5-2: carrying out N times of equal interval sampling on the scaled longitudinal vehicle speed based on the time dimension by utilizing one-dimensional linear interpolation to obtain a longitudinal vehicle speed sequence under the expected time, and obtaining an expected longitudinal position sequence by combining the expected lane changing time;
n is specifically as follows:
Figure BDA0003652657790000082
wherein Δ t is a sampling interval;
the longitudinal vehicle speed sequence at the expected time is specifically as follows:
Figure BDA0003652657790000083
the desired longitudinal position sequence is in particular:
Figure BDA0003652657790000084
step 5-3: based on the expected longitudinal position sequence obtained in the step 5-2, combining the lane change track, and obtaining an expected transverse position by utilizing one-dimensional linear interpolation to finish the scaling of the lane change track on a time scale;
the desired sequence of lateral positions is specifically:
Figure BDA0003652657790000085
the step 7 specifically comprises the following steps:
the improved track primitive algorithm can avoid the failure of the algorithm when the target position is close to the initial position, and specifically comprises the following steps:
Figure BDA0003652657790000086
wherein τ is a time scaling factor; alpha is alpha z And beta z Is a system parameter; g is the target position; y is 0 Is the system starting position; f is a forcing function; y, y,
Figure BDA0003652657790000087
And
Figure BDA0003652657790000088
respectively, system displacement, velocity and acceleration; x is a system independent variable;
the forcing function f is specifically:
Figure BDA0003652657790000089
wherein Ψ (x) is a Gaussian basis function; omega is the weight of the basis function; m is the number of basis functions;
x is a function of time t, and specifically:
Figure BDA00036526577900000810
wherein alpha is x > 0, is a system constant;
the step 7 specifically comprises:
step 7-1: calculating a target forcing function based on the teaching track;
the method comprises the following specific steps:
Figure BDA0003652657790000091
wherein, y demo 、
Figure BDA0003652657790000092
And
Figure BDA0003652657790000093
respectively demonstrating displacement, speed and acceleration of the track;
step 7-2: constructing a loss function, and solving a weight value corresponding to the basis function by using a local weighted regression algorithm;
the loss function is specifically:
Figure BDA0003652657790000094
the method for solving the weight values corresponding to the basis functions by the local weighted regression algorithm specifically comprises the following steps:
Figure BDA0003652657790000095
Figure BDA0003652657790000096
Figure BDA0003652657790000097
Figure BDA0003652657790000098
the step 8 specifically comprises:
step 8-1: based on the longitudinal speed of the teaching track at the starting moment, selecting the teaching track closest to the longitudinal running speed of the vehicle according to the minimum distance principle, and further matching the optimal track element;
step 8-2: calculating and generating a lane changing track based on the characteristics of the driver by using the optimal track primitive according to the target lane changing position;
the calculation and generation of the track changing track based on the characteristics of the driver specifically comprises the following steps: calculating by using a track primitive algorithm to obtain displacement, speed and acceleration information of the lane changing track;
the trajectory primitive algorithm specifically comprises:
Figure BDA0003652657790000099
while the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A vehicle expressway lane change track planning method based on natural driver characteristics is characterized by comprising the following steps:
step 1: obtaining historical driving track information of a vehicle highway based on natural drivers;
step 2: segmenting the historical driving track of the vehicle based on the vehicle course angle information, and extracting track segment information of the vehicle lane change;
and step 3: classifying the vehicle track change track segments according to the acquired longitudinal speed of the vehicle track change track segment at the starting moment;
and 4, step 4: performing statistical analysis on the elapsed time of each type of track changing track segment in the step 3 by using one-dimensional Gaussian function maximum likelihood estimation to obtain the expected track changing time in the statistical sense;
and 5: scaling the track changing track segments in each class on a time scale according to the corresponding expected track changing time obtained in the step 4;
step 6: carrying out statistical analysis on different horizontal and longitudinal positions at the same time by using two-dimensional Gaussian function maximum likelihood estimation to obtain expected horizontal and longitudinal positions in statistical significance, thereby obtaining a teaching lane change track under the longitudinal vehicle speed classification;
and 7: learning the lane change teaching track obtained in the step 6 by using an improved track primitive algorithm to obtain a track primitive library;
and 8: and matching the optimal track elements according to the longitudinal running speed of the vehicle, and generating a lane changing track based on the characteristics of the natural driver by using the optimal track elements according to the target position.
2. The method for vehicle expressway lane change trajectory planning based on natural driver characteristics as claimed in claim 1, wherein the historical driving trajectory information in step 1 comprises vehicle lateral position, longitudinal position, speed, acceleration and time stamp.
3. The method for planning the lane change track of the vehicle expressway according to claim 1, wherein the step 2 specifically comprises:
step 2-1: calculating a vehicle course angle according to the vehicle position parameter;
step 2-2: traversing the course angle from the lane changing point in the forward direction to obtain a lane changing end point, and then traversing the course angle in the reverse direction to obtain a lane changing starting point;
the lane changing points are specifically as follows: the intersection point of the vehicle track and the lane line;
step 2-3: and extracting the track segment information of the vehicle track change according to the starting point and the end point of the track change.
4. The method as claimed in claim 3, wherein the calculation method of the vehicle heading angle specifically comprises:
Figure FDA0003652657780000021
wherein, theta (t) The course angle at the time t; x is the number of (t) Is the longitudinal position of the vehicle at time t; y is (t) Is the vehicle lateral position at time t.
5. The method for planning the lane change track of the vehicle expressway according to claim 1, wherein the step 3 specifically comprises:
dividing the track change track segment according to the longitudinal speed of the starting moment of the track change track segment of the vehicle, wherein the speed division interval specifically comprises the following steps: and dividing 14 classes by taking 5km/h as a dividing step length from 60km/h to 130 km/h.
6. The method for planning the vehicle expressway lane change trajectory based on the natural driver characteristics as claimed in claim 1, wherein the one-dimensional Gaussian function maximum likelihood estimation in the step 4 is specifically as follows:
Figure FDA0003652657780000022
wherein T is the elapsed time of the track change track segment; mu.s T Expecting a track-changing time for the track-changing track segment;
Figure FDA0003652657780000023
the variance over time for the zapping track segment.
7. The method for planning the lane change track of the expressway of vehicles according to claim 1, wherein the step 5 specifically comprises:
step 5-1: acquiring and scaling a lane change track longitudinal speed curve;
the method comprises the following specific steps:
Figure FDA0003652657780000024
wherein the content of the first and second substances,
Figure FDA0003652657780000025
is the scaled longitudinal vehicle speed; v. of x Is the pre-zoom longitudinal vehicle speed;
step 5-2: carrying out N times of equal interval sampling on the scaled longitudinal vehicle speed based on the time dimension by utilizing one-dimensional linear interpolation to obtain a longitudinal vehicle speed sequence under the expected time, and obtaining an expected longitudinal position sequence by combining the expected lane changing time;
the number N is specifically:
Figure FDA0003652657780000026
wherein Δ t is a sampling interval;
the longitudinal vehicle speed sequence at the expected time is specifically as follows:
Figure FDA0003652657780000031
the desired longitudinal position sequence is in particular:
Figure FDA0003652657780000032
step 5-3: based on the expected longitudinal position sequence obtained in the step 5-2, combining the lane change track, and obtaining an expected transverse position by utilizing one-dimensional linear interpolation to finish the scaling of the lane change track on a time scale;
the desired sequence of lateral positions is specifically:
Figure FDA0003652657780000033
8. the method as claimed in claim 1, wherein the two-dimensional gaussian function maximum likelihood estimation in step 6 is specifically based on the natural driver characteristics
Figure FDA0003652657780000034
Wherein σ x Is the longitudinal position standard deviation; sigma y Is the lateral position standard deviation; rho is a correlation coefficient between x and y; mu.s x Is a desired longitudinal position; mu.s y Is the desired lateral position.
9. The method for planning the vehicle expressway lane change track based on the natural driver characteristics as claimed in claim 1, wherein the track primitive algorithm improved in the step 7 is as follows:
Figure FDA0003652657780000035
wherein τ is a time scaling factor; alpha is alpha z And beta z Is a system parameter; g is the target position; y is 0 Is the system starting position; f is a forcing function; y, y,
Figure FDA0003652657780000036
And
Figure FDA0003652657780000037
respectively system displacement, velocity and acceleration; x is a system independent variable;
the forcing function f is specifically:
Figure FDA0003652657780000038
wherein Ψ (x) is a Gaussian basis function; omega is a basis function weight; m is the number of basis functions;
x is a function of time t, specifically:
Figure FDA0003652657780000039
wherein alpha is x > 0, is a system constant;
the step 7 specifically comprises the following steps:
step 7-1: calculating a target forcing function based on the teaching track;
the method specifically comprises the following steps:
Figure FDA0003652657780000041
wherein, y demo 、
Figure FDA0003652657780000042
And
Figure FDA0003652657780000043
respectively demonstrating displacement, speed and acceleration of the track;
step 7-2: constructing a loss function, and solving a weight value corresponding to the basis function by using a local weighted regression algorithm;
the loss function is specifically:
Figure FDA0003652657780000044
the method for solving the weight values corresponding to the basis functions by the local weighted regression algorithm specifically comprises the following steps:
Figure FDA0003652657780000045
Figure FDA0003652657780000046
Figure FDA0003652657780000047
Figure FDA0003652657780000048
10. the method for planning the lane change track of the expressway of vehicles according to claim 1, wherein the step 8 is specifically as follows:
step 8-1: based on the longitudinal speed of the teaching track at the starting moment, selecting the teaching track closest to the longitudinal running speed of the vehicle according to the minimum distance principle, and further matching the optimal track element;
step 8-2: calculating and generating a lane changing track based on the characteristics of the driver by using the optimal track primitive according to the target lane changing position;
the method specifically comprises the following steps: calculating by using a track primitive algorithm to obtain displacement, speed and acceleration information of the lane changing track;
the trajectory primitive algorithm specifically comprises:
Figure FDA0003652657780000049
CN202210557257.1A 2022-05-19 2022-05-19 Vehicle expressway lane change track planning method based on natural driver characteristics Pending CN115092138A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210557257.1A CN115092138A (en) 2022-05-19 2022-05-19 Vehicle expressway lane change track planning method based on natural driver characteristics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210557257.1A CN115092138A (en) 2022-05-19 2022-05-19 Vehicle expressway lane change track planning method based on natural driver characteristics

Publications (1)

Publication Number Publication Date
CN115092138A true CN115092138A (en) 2022-09-23

Family

ID=83288234

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210557257.1A Pending CN115092138A (en) 2022-05-19 2022-05-19 Vehicle expressway lane change track planning method based on natural driver characteristics

Country Status (1)

Country Link
CN (1) CN115092138A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117584991A (en) * 2024-01-17 2024-02-23 上海伯镭智能科技有限公司 Mining area unmanned vehicle outside personnel safety protection method and system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117584991A (en) * 2024-01-17 2024-02-23 上海伯镭智能科技有限公司 Mining area unmanned vehicle outside personnel safety protection method and system
CN117584991B (en) * 2024-01-17 2024-03-22 上海伯镭智能科技有限公司 Mining area unmanned vehicle outside personnel safety protection method and system

Similar Documents

Publication Publication Date Title
CN113291308B (en) Vehicle self-learning lane-changing decision-making system and method considering driving behavior characteristics
CN110928297B (en) Intelligent bus route planning method based on multi-objective dynamic particle swarm optimization
CN113401143B (en) Individualized self-adaptive trajectory prediction method based on driving style and intention
CN107229973A (en) The generation method and device of a kind of tactful network model for Vehicular automatic driving
CN111930110A (en) Intent track prediction method for generating confrontation network by combining society
CN112793576B (en) Lane change decision method and system based on rule and machine learning fusion
CN102568200A (en) Method for judging vehicle driving states in real time
CN112614373B (en) BiLSTM-based weekly vehicle lane change intention prediction method
CN111368879A (en) Track data mining method based on deep semi-supervised neural network
CN115092138A (en) Vehicle expressway lane change track planning method based on natural driver characteristics
CN115523934A (en) Vehicle track prediction method and system based on deep learning
Gao et al. Discretionary cut-in driving behavior risk assessment based on naturalistic driving data
CN114368387A (en) Attention mechanism-based driver intention identification and vehicle track prediction method
Mineta et al. Development of a lane mark recognition system for a lane keeping assist system
CN112559968B (en) Driving style representation learning method based on multi-situation data
Bando et al. Generating contextual description from driving behavioral data
CN113306558B (en) Lane changing decision method and system based on lane changing interaction intention
CN114564849A (en) Data-driven vehicle economy simulation test scene generation method
CN115440041A (en) Method for predicting driving behavior of key vehicle under road side view angle
CN115062202A (en) Method, device, equipment and storage medium for predicting driving behavior intention and track
CN114612867A (en) BiLSTM-CRF model-based vehicle lane change intention prediction method
CN113252057A (en) Method and system for identifying driving tendency based on high altitude navigation data
Wang et al. Driver modeling based on vehicular sensing data
CN112785863B (en) Merging decision classification early warning method based on K-Means and entropy weighting
Fan et al. Anomalous state recognition of lane-changing behavior using a hybrid autoencoder architecture

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