CN114523978A - Method and device for generating rear road model - Google Patents

Method and device for generating rear road model Download PDF

Info

Publication number
CN114523978A
CN114523978A CN202011209559.7A CN202011209559A CN114523978A CN 114523978 A CN114523978 A CN 114523978A CN 202011209559 A CN202011209559 A CN 202011209559A CN 114523978 A CN114523978 A CN 114523978A
Authority
CN
China
Prior art keywords
curvature
road model
rear road
period
lane
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
Application number
CN202011209559.7A
Other languages
Chinese (zh)
Other versions
CN114523978B (en
Inventor
柏满飞
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.)
SAIC Motor Corp Ltd
Shanghai Automotive Industry Corp Group
Original Assignee
SAIC Motor Corp Ltd
Shanghai Automotive Industry Corp Group
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 SAIC Motor Corp Ltd, Shanghai Automotive Industry Corp Group filed Critical SAIC Motor Corp Ltd
Priority to CN202011209559.7A priority Critical patent/CN114523978B/en
Publication of CN114523978A publication Critical patent/CN114523978A/en
Application granted granted Critical
Publication of CN114523978B publication Critical patent/CN114523978B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • B60W40/02—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 ambient conditions
    • B60W40/06—Road conditions
    • 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
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • 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
    • B60W40/02—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 ambient conditions
    • B60W40/06—Road conditions
    • B60W40/072—Curvature of the road

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

The invention provides a method and a device for generating a rear road model, wherein the method comprises the following steps: calculating historical tracks of the previous N periods of the vehicle according to the motion information of the vehicle, wherein the period is the collection period of the motion information; calculating the curvature of the lane center line in the front N periods, the course angle of the current position of the lane center line and the transverse intercept by using the lane line information of the forward camera; a rear road model is generated based on the historical track of the vehicle in the previous N cycles, the curvature of the lane in the previous N cycles, and the course angle and the transverse intercept at the current position of the lane center line. According to the invention, the rear road model is generated by means of the forward cameras required to be equipped by the self-adaptive cruise control system and the lane keeping auxiliary system, so that a judgment basis is provided for the automatic lane changing auxiliary driving system to screen rear effective target vehicles, and the mass production cost of the automatic lane changing auxiliary driving system is reduced.

Description

Method and device for generating rear road model
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a method and a device for generating a rear road model.
Background
Nowadays, the intelligent driving technology is gradually mature, and more automobile manufacturers want to integrate an Adaptive Cruise Control (ACC), a Lane Keeping Assist (LKA), and an automatic Lane changing Assist (ALC) system to form a driving Assist system with stronger functions. However, the greater functionality means that more environmental information needs to be acquired.
For the automatic lane-changing auxiliary driving system, not only target vehicles which run slowly in front of a target lane and have collision risks need to be screened, but also target vehicles which approach quickly behind the target lane and have collision risks need to be screened, and lane changing is prohibited when collision risks exist behind the target lane. The prerequisite for screening rear valid target vehicles is that the rear road model is known. Due to the wide application and popularization of the adaptive cruise control system, the research on the road model is basically directed to the front, and the research on the rear road model is little and needs to be deeply researched.
Therefore, how to generate the rear road model is an urgent problem to be solved at the present stage.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for generating a rear road model to solve the above problems. The technical scheme is as follows:
a method of rear road model generation, the method comprising:
calculating historical tracks of previous N periods of the vehicle according to the motion information of the vehicle, wherein the period is the acquisition period of the motion information;
calculating the curvature of the lane center line in the front N periods, and the course angle and the transverse intercept of the current position of the lane center line by using the lane line information of the forward camera;
and generating a rear road model based on the historical track of the vehicle in the previous N periods, the curvature of the lane center line in the previous N periods, and the course angle and the transverse intercept of the lane center line at the current position.
Preferably, the calculating the historical track of the vehicle in the previous N periods according to the motion information of the vehicle includes:
collecting the yaw angular velocity and the longitudinal vehicle speed of the vehicle in the front N periods;
calculating the course angles of the front N periods of the vehicle relative to the current coordinate system by using the yaw rates of the front N periods of the vehicle;
and calculating the abscissa and the ordinate of the vehicle in the front N periods relative to the current coordinate system according to the longitudinal speed and the heading angle of the vehicle in the front N periods.
Preferably, the calculating the curvature of the lane center line N cycles ahead by using the lane line information of the forward camera, and the heading angle and the lateral intercept at the current position of the lane center line includes:
for each period in the first N periods, acquiring the curvature, the course angle, the transverse intercept and the confidence coefficient of a lane line in the period through the forward camera, wherein the lane line comprises a left lane line and a right lane line;
judging whether the left lane line exists in the period according to the confidence coefficient of the left lane line, and judging whether the right lane line exists in the period according to the confidence coefficient of the right lane line;
if the left lane line and the right lane line exist in the period, calculating the curvature of the lane center line in the period according to the curvature of the left lane line in the period and the curvature of the right lane line in the period;
calculating the course angle of the lane central line in the period according to the course angle of the left lane line in the period and the course angle of the right lane line in the period;
calculating the transverse intercept of the lane center line in the period according to the transverse intercept of the left lane line in the period and the transverse intercept of the right lane line in the period;
if one lane line exists in the left lane line and the right lane line in the period, taking the curvature of the existing lane line as the curvature of the lane center line in the period;
if the left lane line and the right lane line do not exist in the period, discarding the period;
and respectively taking the course angle and the transverse intercept in the current period as the course angle and the transverse intercept at the current position of the lane center line.
Preferably, the generating a rear road model based on the historical track N cycles before the vehicle, the curvature N cycles before the lane center line, and the heading angle and the lateral intercept at the current position of the lane center line includes:
judging whether the rear road model is divided into two sections according to the longitudinal track of the historical tracks of the previous N periods of the vehicle;
if the rear road model is not divided into two sections, inputting the longitudinal track of the historical track of the previous N periods of the vehicle and the curvature of the previous N periods of the vehicle into a clothoid curvature model by taking as input, and calculating the curvature and the curvature change rate of the rear road model by applying a least square method;
and generating a rear road model based on the curvature and the curvature change rate of the rear road model and the course angle and the transverse intercept of the lane center line at the current position.
Preferably, the generating a rear road model based on the curvature and the curvature change rate of the rear road model and the heading angle and the lateral intercept at the current position of the lane center line further includes:
if the rear road model is divided into two sections, respectively intercepting a first longitudinal track of a first section of rear road model and a second longitudinal track of a second section of rear road model from longitudinal tracks of historical tracks of the vehicle in the previous N periods;
respectively cutting a first curvature of the first section of rear road model and a second curvature of the second section of rear road model from the curvatures of the vehicle in the front N periods;
inputting the first longitudinal track and the first curvature into a clothoid curvature model, and calculating the curvature and the curvature change rate of the first section rear road model by applying a least square method;
generating a first section of rear road model based on the curvature and the curvature change rate of the first section of rear road model and the course angle and the transverse intercept of the lane center line at the current position, and calculating the abscissa, the course angle and the curvature of the starting point of the second section of rear road model;
inputting the second longitudinal track and the second curvature into the clothoid curvature model, and calculating the curvature change rate of the second section rear road model by applying the least square method;
and generating a second section of rear road model based on the curvature change rate of the second section of rear road model and the abscissa, the course angle and the curvature of the starting point of the second section of rear road model.
A rear road model generation apparatus, the apparatus comprising:
the first calculation module is used for calculating the historical tracks of the previous N periods of the vehicle according to the motion information of the vehicle, wherein the period is the acquisition period of the motion information;
the second calculation module is used for calculating the curvature of the lane center line in the front N periods, and the course angle and the transverse intercept of the current position of the lane center line by using the lane line information of the forward camera;
and the model generation module is used for generating a rear road model based on the historical track of the vehicle in the previous N periods, the curvature of the lane center line in the previous N periods, and the course angle and the transverse intercept of the current position of the lane center line.
Preferably, the first calculating module is specifically configured to:
collecting the yaw angular velocity and the longitudinal vehicle speed of the vehicle in the front N periods; calculating the course angles of the front N periods of the vehicle relative to the current coordinate system by using the yaw rates of the front N periods of the vehicle; and calculating the abscissa and the ordinate of the vehicle in the front N periods relative to the current coordinate system according to the longitudinal speed and the heading angle of the vehicle in the front N periods.
Preferably, the second calculating module is specifically configured to:
for each period in the first N periods, acquiring the curvature, the course angle, the transverse intercept and the confidence coefficient of a lane line in the period through the forward camera, wherein the lane line comprises a left lane line and a right lane line; judging whether the left lane line exists in the period according to the confidence coefficient of the left lane line, and judging whether the right lane line exists in the period according to the confidence coefficient of the right lane line; if the left lane line and the right lane line exist in the period, calculating the curvature of the lane center line in the period according to the curvature of the left lane line in the period and the curvature of the right lane line in the period; calculating the course angle of the lane central line in the period according to the course angle of the left lane line in the period and the course angle of the right lane line in the period; according to the transverse intercept of the left lane line in the period and the transverse intercept of the right lane line in the period, calculating the transverse intercept of the lane center line in the period; if one lane line exists in the left lane line and the right lane line in the period, taking the curvature of the existing lane line as the curvature of the lane center line in the period; if the left lane line and the right lane line do not exist in the period, discarding the period; and respectively taking the course angle and the transverse intercept in the current period as the course angle and the transverse intercept at the current position of the lane center line.
Preferably, the model generation module is specifically configured to:
judging whether the rear road model is divided into two sections according to the longitudinal track of the historical tracks of the previous N periods of the vehicle; if the rear road model is not divided into two sections, inputting the longitudinal track of the historical track of the previous N periods of the vehicle and the curvature of the previous N periods of the vehicle into a clothoid curvature model by taking as input, and calculating the curvature and the curvature change rate of the rear road model by applying a least square method; and generating a rear road model based on the curvature and the curvature change rate of the rear road model and the course angle and the transverse intercept of the lane center line at the current position.
Preferably, the model generation module is further configured to:
if the rear road model is divided into two sections, respectively intercepting a first longitudinal track of a first section of rear road model and a second longitudinal track of a second section of rear road model from longitudinal tracks of historical tracks of the vehicle in the previous N periods; respectively cutting a first curvature of the first section of rear road model and a second curvature of the second section of rear road model from the curvatures of the vehicle in the front N periods; inputting the first longitudinal track and the first curvature into a clothoid curvature model, and calculating the curvature and the curvature change rate of the first section rear road model by applying a least square method; generating a first section of rear road model based on the curvature and the curvature change rate of the first section of rear road model and the course angle and the transverse intercept of the lane center line at the current position, and calculating the abscissa, the course angle and the curvature of the starting point of the second section of rear road model; inputting the second longitudinal track and the second curvature into the clothoid curvature model, and calculating the curvature change rate of the second section rear road model by applying the least square method; and generating a second section of rear road model based on the curvature change rate of the second section of rear road model and the abscissa, the course angle and the curvature of the starting point of the second section of rear road model.
According to the method and the device for generating the rear road model, the rear road model is generated by means of the forward cameras required to be equipped by the adaptive cruise control system and the lane keeping auxiliary system, judgment basis is provided for the automatic lane changing auxiliary driving system to screen rear effective target vehicles, and the mass production cost of the automatic lane changing auxiliary driving system is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic diagram of a vehicle mounted with four corner radars, a forward facing camera, and a forward facing radar in position;
FIG. 2 is a flowchart of a method for generating a rear road model according to an embodiment of the present invention;
FIG. 3 is a partial method flowchart of a method for generating a rear road model according to an embodiment of the present invention;
FIG. 4 is a diagram of a position relationship between a previous time and a current time of a vehicle coordinate system;
FIG. 5 is a schematic illustration of a left lane line heading angle;
FIG. 6 is a flowchart of another portion of a method for generating a rear road model according to an embodiment of the present invention;
FIG. 7 is a flowchart of a portion of a method for generating a rear road model according to an embodiment of the present invention;
FIG. 8 is a flowchart of a portion of a method for generating a rear road model according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a rear road model generation device 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 only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiment of the invention belongs to the technical field of intelligent driving, and particularly relates to a rear road model generation method in an automatic lane change auxiliary driving system.
With the rapid development of the automobile industry, people pay more and more attention to how to improve driving safety, which is also an important problem to be solved in the technical field of intelligent driving. The intelligent driving auxiliary system takes a driver as a main body, and can remarkably reduce traffic accidents caused by misjudgment or improper decision of the driver by means of the perception and decision-making capability of the intelligent sensor to the environment. As a classic representative of the intelligent driving assistance system, an Adaptive Cruise Control (ACC), an Automatic Emergency Braking (AEB), and a Lane Keeping Assistance (LKA) can improve driving performance, reduce driving pressure, and alleviate driving fatigue, which is recognized by drivers.
For an adaptive cruise control system, a front effective target vehicle needs to be screened quickly and accurately, and active braking can be performed to avoid collision or reduce harm caused by collision when collision is dangerous. To accurately screen a front effective target vehicle, a front road model, that is, an equation of a center line of a lane where the vehicle is located in a vehicle coordinate system, needs to be obtained, the lane where the target vehicle is located according to a transverse distance between the target vehicle and the center line of the vehicle, and finally the effective target vehicle located in the vehicle lane is selected according to a longitudinal distance between the target vehicle and the vehicle. Currently, in the research on the estimation algorithm of the front road model, there are different algorithms based on different sensors: identifying the road sign line based on the camera to obtain a road model in front of the vehicle; based on the information of the millimeter wave radar and the camera, the information is fused and estimated to a front road model through a Kalman filtering algorithm; extracting characteristics to estimate a road model in front of the vehicle based on signals returned by the laser radar; the GPS and high precision map information are combined to estimate the road model ahead.
Nowadays, the intelligent driving technology is gradually mature, and more automobile manufacturers want to integrate an adaptive cruise control system, a Lane keeping assist system, and an automatic Lane Change assist driving system (ALC) to form a driving assist system with a stronger function. However, the greater functionality means that more environmental information needs to be acquired.
For the automatic lane-changing auxiliary driving system, not only target vehicles which run slowly in front of a target lane and have collision risks need to be screened, but also target vehicles which approach quickly behind the target lane and have collision risks need to be screened, and lane changing is prohibited when collision risks exist behind the target lane. The prerequisite for screening rear valid target vehicles is that the rear road model is known. Due to the wide application and popularization of the adaptive cruise control system, the research on the road model is basically directed to the front, and the research on the rear road model is little and needs to be deeply researched.
Generally, automobile manufacturers are equipped with a forward camera and a millimeter wave radar in order to meet the environmental perception requirements of an adaptive cruise control system and a lane keeping assist system. The automatic lane-changing assistant driving system needs to additionally sense a target vehicle in front of the side and a target vehicle behind the side, so that two (four in total) millimeter wave angle radars in front and behind are also needed to be equipped to detect the surrounding target vehicles, as shown in fig. 1. In order to screen the rear valid target vehicles, a rear road model also needs to be generated. In order to save cost as much as possible, the invention uses the forward camera to accurately generate the rear road model.
The road model is a cubic equation of the lane center line in the host vehicle coordinate system, and the x-axis of the host vehicle coordinate system is the longitudinal axis direction of the host vehicle.
The embodiment of the invention provides a method for generating a rear road model, and the method has the flow chart shown in figure 2 and comprises the following steps:
and S10, calculating the historical track of the previous N periods of the vehicle according to the motion information of the vehicle, wherein the period is the acquisition period of the motion information.
In the embodiment of the invention, the acquired motion information comprises the yaw angular speed, the longitudinal speed and the data acquisition period of the vehicle, and the data is preprocessed to obtain a data set:
S1＝{ω,v,T}
where ω represents the yaw rate of the host vehicle, v represents the longitudinal vehicle speed of the host vehicle, and T represents the data acquisition period, i.e., the software operating period. Since the software operating frequency of the present embodiment is 50HZ, the period is 0.02 s.
In a specific implementation process, in step S10, "calculating the historical track of the vehicle in the previous N cycles according to the motion information of the vehicle" may adopt the following steps, and a flowchart of the method is shown in fig. 3:
and S101, acquiring the yaw rate and the longitudinal speed of the vehicle in the front N periods.
In this embodiment, the yaw rate and the longitudinal speed of the vehicle are stored for N cycles, and the historical motion information of the host vehicle is obtained:
Figure RE-RE-GDA0002909124450000081
Figure RE-RE-GDA0002909124450000082
wherein, ω isi、viThe yaw rate and the longitudinal vehicle speed are respectively represented for i (i ═ 1,2,3, … N) cycles ahead of the vehicle. Since the detection distance of the rear angle radar equipped in the automatic lane change assistant driving system in the embodiment is 80m, the rear road model only needs to estimate 80m, the minimum speed of the automatic lane change function is 60km/h, and the vehicle runs 80m at 60km/h, and needs 4.8s, namely 240 cycles, so that N is 240.
And S102, calculating the heading angles of the front N periods of the vehicle relative to the current coordinate system by using the yaw rates of the front N periods of the vehicle.
In the embodiment, the heading angles of the vehicle relative to the current coordinate system in the previous N periods are calculated by using the historical yaw rate of the vehicle:
Figure RE-RE-GDA0002909124450000083
wherein the content of the first and second substances,
Figure RE-RE-GDA0002909124450000091
respectively represents heading angles of i (i is 1,2,3, … N) periods in front of the vehicle relative to the current coordinate system,
Figure RE-RE-GDA0002909124450000092
is shown in fig. 4.
Further, in the present invention,
Figure RE-RE-GDA0002909124450000093
can be calculated using the following formula:
Figure RE-RE-GDA0002909124450000094
the initial value is
Figure RE-RE-GDA0002909124450000095
Indicating the heading angle of the vehicle at the current time relative to the vehicle's current time coordinate system, and therefore the initial value is 0.
S103, calculating the abscissa and the ordinate of the vehicle in the front N periods relative to the current coordinate system according to the longitudinal vehicle speed and the course angle of the vehicle in the front N periods.
In the present embodiment, the abscissa and ordinate of the vehicle in the front N cycles with respect to the current coordinate system are as follows:
Figure RE-RE-GDA0002909124450000096
Figure RE-RE-GDA0002909124450000097
wherein, Xi、YiThe coordinates of the front i (i ═ 1,2,3, … N) cycles of the vehicle are respectively shown on the ordinate and the abscissa of the current coordinate system.
Further, Xi、YiCan be calculated using the following formula:
Figure RE-RE-GDA0002909124450000098
and S20, calculating the curvature of the lane center line in the front N periods, the heading angle and the transverse intercept at the current position of the lane center line by using the lane line information of the forward camera.
In the embodiment of the invention, the lane line information acquired by the forward camera comprises the curvature change rate, the curvature, the course angle, the transverse intercept and the confidence coefficient of the left lane line and the right lane line of the lane, and the data is preprocessed to obtain a data set:
S2＝{C1L,C0L,αL,dyL,PL,C1R,C0R,αR,dyR,PR}
wherein, C1L、C1RRespectively representing the curvature change rate of the left lane line and the right lane line of the lane; c0L、C0RRespectively representing the curvatures of the left lane line and the right lane line of the lane at the position where the vehicle coordinate system X is equal to 0; alpha is alphaL、αRRespectively representing the course angles of the left and right lane lines of the lane, namely the included angles between the tangent lines of the left and right lane lines at the position where X is equal to 0 and the X axis of the vehicle coordinate system, as shown in fig. 5; dyL、dyRRespectively representing the transverse intercept of the left lane line and the right lane line of the lane, namely the intercept of the left lane line and the right lane line on the Y axis of a vehicle coordinate system; pL、PRAnd respectively distinguishing the confidence degrees of the left lane line and the right lane line of the lane.
It should be noted that the heading angle in this embodiment is a heading angle of the lane line relative to the vehicle coordinate system, and the heading angle in step S102 is an included angle between the X-axis of the coordinate system at the historical time and the X-axis of the coordinate system at the current time.
It should be further noted that, in this embodiment, the confidence of the lane line indicates the confidence of the lane line detected by the forward camera, and the higher the confidence is, the higher the possibility of the lane line is, and conversely, the lower the confidence is, the lower the possibility of the lane line is.
In the specific implementation process, in step S20, "calculating the curvature of the lane center line in the front N cycles, and the heading angle and the lateral intercept at the current position of the lane center line by using the lane line information of the forward camera" may adopt the following steps, and the flowchart of the method is shown in fig. 6:
s201, aiming at each period in the first N periods, the curvature, the course angle, the transverse intercept and the confidence coefficient of a lane line in the period are collected through a forward camera, and the lane line comprises a left lane line and a right lane line.
S202, judging whether the left lane line exists in the period according to the confidence coefficient of the left lane line, and judging whether the right lane line exists in the period according to the confidence coefficient of the right lane line.
In this embodiment, the existence of the lane line means that the confidence of the lane line acquired from the forward camera satisfies the following condition:
PL≥PThreshold
PR≥PThreshold
wherein, PThresholdTo determine the probability threshold of whether a lane line exists, a value is empirically selected, which in this embodiment is 0.85.
The output result is 2, which indicates that both the left lane line and the right lane line exist, and the step S203 is switched to; the output result is 1, which indicates that one of the left lane line and the right lane line exists, and the step S206 is switched to; the output result is 0, indicating that neither of the left and right lane lines is present, and the process proceeds to step S207.
S203, if the left lane line and the right lane line exist in the period, calculating the curvature of the lane center line in the period according to the curvature of the left lane line in the period and the curvature of the right lane line in the period.
In the present embodiment, the curvature of the lane center line in the period is calculated using the following formula:
Figure RE-RE-GDA0002909124450000101
wherein, C0CRepresenting the curvature of the lane centerline within the cycle.
S204, calculating the course angle of the lane central line in the period according to the course angle of the left lane line in the period and the course angle of the right lane line in the period.
In this embodiment, the heading angle of the lane centerline in the cycle is calculated using the following formula:
Figure RE-RE-GDA0002909124450000111
wherein alpha isCIndicating the heading angle of the lane centerline within the cycle.
And S205, calculating the transverse intercept of the lane center line in the period according to the transverse intercept of the left lane line in the period and the transverse intercept of the right lane line in the period.
In the present embodiment, the lateral intercept of the lane center line in the cycle is calculated using the following formula:
Figure RE-RE-GDA0002909124450000112
wherein d isyCRepresenting the lateral intercept of the lane centerline within the cycle.
And S206, if one lane line exists in the period of the left lane line and the right lane line, taking the curvature of the existing lane line as the curvature of the lane center line in the period.
In this embodiment, if there is only one lane line, the curvature of a virtual lane center line needs to be calculated, because the automatic lane change assistant driving system can be activated only when there are two lane lines, where the curvature parameter is calculated to store the curvature, so as to meet the requirement of subsequently generating a rear road model.
The curvature of the lane center line within this period takes the curvature of the existing lane line:
C0C＝C0L OR C0C＝C0R
and S207, if the left lane line and the right lane line do not exist in the period, discarding the period.
In this embodiment, if the left and right lane lines do not exist, the curvature of the lane center line in the period does not take a value, and the period is discarded when the curvature is stored.
According to the steps S201 to S207, the curvature of the lane center line is stored for N periods to obtain the curvature of the N periods:
Figure RE-RE-GDA0002909124450000113
wherein, C0CiRepresents the curvature of the center line of the first i (i ═ 1,2,3, … N) periodic lanes.
And S208, taking the heading angle and the transverse intercept in the current period as the heading angle and the transverse intercept at the current position of the lane center line respectively.
In the embodiment of the present invention, the current period refers to a period in which the current time is located after the discarding period or a period closest to the current time.
S30, a rear road model is generated based on the historical track of the vehicle N cycles before, the curvature of the lane center line N cycles before, and the heading angle and the lateral intercept at the current position of the lane center line.
In the embodiment of the invention, the historical tracks and curvatures of N periods are used as input and input into a clothoid curvature model, and the curvature and curvature change rate of a rear road model are calculated by using a least square method; further, a rear road model is generated based on the curvature and the rate of change of curvature of the rear road model, and the heading angle and the lateral intercept at the current position of the lane centerline.
In a specific implementation process, in step S30, "generating a rear road model based on the historical track N cycles before the vehicle, the curvature N cycles before the lane center line, and the heading angle and the lateral intercept at the current position of the lane center line" may adopt the following steps, and a flowchart of the method is shown in fig. 7:
s301, judging whether the rear road model is divided into two sections according to the longitudinal track of the historical track of the vehicle in the front N periods.
In this embodiment, the rule whether the rear road model needs to be divided into two segments is as follows:
Figure RE-RE-GDA0002909124450000121
wherein, XThresholdA threshold value representing whether the rear road model requires two segmentation. Since the cubic equation is used to describe the highway, the error is 60m at the maximum within an acceptable range, so XThresholdAnd taking-60.
If XNIf the condition of segmentation is met, the output result is 0, and the step S302 is switched to; if XNIf the two-stage condition is satisfied, the output result of the model is 1, and step S304 is performed.
S302, if the rear road model is not divided into two sections, inputting the longitudinal track of the historical track of the previous N periods of the vehicle and the curvature of the previous N periods of the vehicle into a clothoid curvature model by taking as input, and calculating the curvature and the curvature change rate of the rear road model by applying a least square method.
In the present embodiment, the result obtained in step S103
Figure RE-RE-GDA0002909124450000122
And obtained in step S207
Figure RE-RE-GDA0002909124450000123
As input, the following clothoid curvature model is entered:
K(x)＝a+bx
where a denotes a curvature at x ═ 0, b denotes a curvature change rate, and k (x) denotes a curvature corresponding to x.
In particular, the curvature C of the rear road model0And rate of change of curvature C1The following least square fitting formula is adopted for calculation:
Figure RE-RE-GDA0002909124450000124
Figure RE-RE-GDA0002909124450000125
s303, generating a rear road model based on the curvature and the curvature change rate of the rear road model, and the course angle and the transverse intercept of the lane center line at the current position.
In the present embodiment, the rear road model is as follows:
Figure RE-RE-GDA0002909124450000131
on the basis, the step S30 "generating the rear road model based on the curvature and the curvature change rate of the rear road model, and the heading angle and the lateral intercept at the current position of the lane center line" further includes the following steps, and the method flowchart is shown in fig. 8:
s304, if the rear road model is divided into two sections, respectively intercepting a first longitudinal track of the first section of rear road model and a second longitudinal track of the second section of rear road model from the longitudinal tracks of the historical tracks of the vehicle in the front N periods.
S305, respectively cutting a first curvature of the first section of the rear road model and a second curvature of the second section of the rear road model from the curvatures of the vehicle in the front N periods.
In the present embodiment, the result obtained in step S103
Figure RE-RE-GDA0002909124450000132
And obtained in step S207
Figure RE-RE-GDA0002909124450000133
Cutting a part of the frontObtaining input in elements
Figure RE-RE-GDA0002909124450000134
And
Figure RE-RE-GDA0002909124450000135
the following were used:
Figure RE-RE-GDA0002909124450000136
Figure RE-RE-GDA0002909124450000137
wherein the index m is a vector
Figure RE-RE-GDA0002909124450000138
All of them are greater than XThresholdThe largest index among the elements of (1).
Further, the one obtained in step S103
Figure RE-RE-GDA0002909124450000139
And obtained in step S207
Figure RE-RE-GDA00029091244500001310
Intercepting a part of the latter elements to obtain input
Figure RE-RE-GDA00029091244500001311
And
Figure RE-RE-GDA00029091244500001312
the following were used:
Figure RE-RE-GDA00029091244500001313
Figure RE-RE-GDA00029091244500001314
wherein the intercepted number q is a vector
Figure RE-RE-GDA00029091244500001315
All of them are greater than 2XThresholdThe largest index among the elements of (1).
S306, inputting the first longitudinal track and the first curvature into a clothoid curvature model, and calculating the curvature and the curvature change rate of the first section of rear road model by using a least square method.
In the present embodiment, the result obtained in step S304
Figure RE-RE-GDA00029091244500001316
And step S305 of obtaining
Figure RE-RE-GDA00029091244500001317
Is input into the following clothoid curvature model:
K(x)＝a+bx
where a denotes a curvature at x ═ 0, b denotes a curvature change rate, and k (x) denotes a curvature corresponding to x.
Specifically, the curvature C of the first-segment rear road model01 and rate of curvature change C1The _1is calculated by using the following least square fitting formula:
Figure RE-RE-GDA00029091244500001318
Figure RE-RE-GDA0002909124450000141
s307, generating a first section of rear road model based on the curvature and the curvature change rate of the first section of rear road model and the course angle and the transverse intercept of the lane center line at the current position, and calculating the abscissa, the course angle and the curvature of the starting point of the second section of rear road model.
In the present embodiment, the first-stage rear road model is as follows:
Figure RE-RE-GDA0002909124450000142
calculating the abscissa y of the starting point of the second section rear road model by adopting the following formulaC2, course angle αC2 and curvature C0_2：
Figure RE-RE-GDA0002909124450000143
Figure RE-RE-GDA0002909124450000144
C0_2＝C0_1+C1_1·Xm
And S308, inputting the second longitudinal track and the second curvature into a clothoid curvature model by taking the second longitudinal track and the second curvature as input, and calculating the curvature change rate of the second section of rear road model by applying a least square method.
In the present embodiment, the result obtained in step S304
Figure RE-RE-GDA0002909124450000145
And step S305 of obtaining
Figure RE-RE-GDA0002909124450000146
Is input into the following clothoid curvature model:
K(x)＝a+bx
where a denotes a curvature at x ═ 0, b denotes a curvature change rate, and k (x) denotes a curvature corresponding to x.
Specifically, the curvature change rate C of the second-stage rear road model1The _2is calculated by using the following least square fitting formula:
Figure RE-RE-GDA0002909124450000147
s309, generating a second section rear road model based on the curvature change rate of the second section rear road model and the abscissa, the course angle and the curvature of the starting point of the second section rear road model.
In the present embodiment, the second-stage rear road model is as follows:
Figure RE-RE-GDA0002909124450000148
according to the method for generating the rear road model, the rear road model is generated by means of the forward cameras required to be equipped by the adaptive cruise control system and the lane keeping auxiliary system, judgment basis is provided for the automatic lane changing auxiliary driving system to screen rear effective target vehicles, and the mass production cost of the automatic lane changing auxiliary driving system is reduced.
Based on the method for generating a rear road model provided in the foregoing embodiment, an embodiment of the present invention correspondingly provides an apparatus for executing the method for generating a rear road model, where a schematic structural diagram of the apparatus is shown in fig. 9:
the first calculation module 10 is configured to calculate historical tracks of N previous periods of the vehicle according to the motion information of the vehicle, where the period is an acquisition period of the motion information;
the second calculation module 20 is used for calculating the curvature of the lane center line in the front N periods, and the course angle and the transverse intercept at the current position of the lane center line by using the lane line information of the forward camera;
and the model generation module 30 is used for generating a rear road model based on the historical track of the vehicle in the previous N periods, the curvature of the lane center line in the previous N periods, and the heading angle and the transverse intercept of the current position of the lane center line.
Optionally, the first calculating module 10 is specifically configured to:
collecting the yaw angular velocity and the longitudinal vehicle speed of the vehicle in the front N periods; calculating course angles of the front N periods of the vehicle relative to a current coordinate system by using the yaw rates of the front N periods of the vehicle; and calculating the abscissa and the ordinate of the vehicle in the front N periods relative to the current coordinate system according to the longitudinal speed and the heading angle of the vehicle in the front N periods.
Optionally, the second calculating module 20 is specifically configured to:
for each period in the first N periods, acquiring the curvature, the course angle, the transverse intercept and the confidence coefficient of a lane line in the period through a forward camera, wherein the lane line comprises a left lane line and a right lane line; judging whether the left lane line exists in the period according to the confidence coefficient of the left lane line, and judging whether the right lane line exists in the period according to the confidence coefficient of the right lane line; if the left lane line and the right lane line exist in the period, calculating the curvature of the lane central line in the period according to the curvature of the left lane line in the period and the curvature of the right lane line in the period; calculating the course angle of the lane central line in the period according to the course angle of the left lane line in the period and the course angle of the right lane line in the period; calculating the transverse intercept of the lane central line in the period according to the transverse intercept of the left lane line in the period and the transverse intercept of the right lane line in the period; if one lane line exists in the left lane line and the right lane line in the period, taking the curvature of the existing lane line as the curvature of the lane center line in the period; if the left lane line and the right lane line do not exist in the period, discarding the period; and respectively taking the course angle and the transverse intercept in the current period as the course angle and the transverse intercept at the current position of the lane center line.
Optionally, the model generating module 30 is specifically configured to:
judging whether the rear road model is divided into two sections or not according to the longitudinal track of the historical track of the vehicle in the previous N periods; if the rear road model is not divided into two sections, inputting the longitudinal track of the historical track of the previous N periods of the vehicle and the curvature of the previous N periods of the vehicle into a clothoid curvature model by taking as input, and calculating the curvature and the curvature change rate of the rear road model by applying a least square method; a rear road model is generated based on the curvature and the rate of change of curvature of the rear road model, and the heading angle and the lateral intercept at the current position of the lane centerline.
Optionally, the model generation module 30 is further configured to:
if the rear road model is divided into two sections, respectively intercepting a first longitudinal track of a first section of rear road model and a second longitudinal track of a second section of rear road model from longitudinal tracks of historical tracks of N periods in front of the vehicle; respectively intercepting a first curvature of a first section of rear road model and a second curvature of a second section of rear road model from the curvatures of the vehicle in the front N periods; inputting the first longitudinal track and the first curvature into a clothoid curvature model, and calculating the curvature and the curvature change rate of the first section of rear road model by using a least square method; generating a first section of rear road model based on the curvature and the curvature change rate of the first section of rear road model and the course angle and the transverse intercept of the lane center line at the current position, and calculating the abscissa, the course angle and the curvature of the starting point of a second section of rear road model; inputting the second longitudinal track and the second curvature into a clothoid curvature model, and calculating the curvature change rate of a second section of rear road model by using a least square method; and generating a second section of rear road model based on the curvature change rate of the second section of rear road model and the abscissa, the course angle and the curvature of the starting point of the second section of rear road model.
The rear road model generation device provided by the embodiment of the invention generates the rear road model by means of the forward cameras required to be equipped by the adaptive cruise control system and the lane keeping auxiliary system, provides judgment basis for screening rear effective target vehicles by the automatic lane changing auxiliary driving system, and reduces the mass production cost of the automatic lane changing auxiliary driving system.
The method and the device for generating the rear road model provided by the invention are described in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include or include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims (10)

1. A method of generating a rear road model, the method comprising:
calculating historical tracks of previous N periods of the vehicle according to the motion information of the vehicle, wherein the period is the acquisition period of the motion information;
calculating the curvature of the lane center line in the front N periods, and the course angle and the transverse intercept of the current position of the lane center line by using the lane line information of the forward camera;
and generating a rear road model based on the historical track of the vehicle in the previous N periods, the curvature of the lane center line in the previous N periods, and the course angle and the transverse intercept of the lane center line at the current position.
2. The method of claim 1, wherein the calculating the historical trajectory of the vehicle for the previous N cycles based on the motion information of the vehicle comprises:
collecting the yaw angular velocity and the longitudinal vehicle speed of the vehicle in the front N periods;
calculating the course angles of the front N periods of the vehicle relative to the current coordinate system by using the yaw rates of the front N periods of the vehicle;
and calculating the abscissa and the ordinate of the vehicle in the front N periods relative to the current coordinate system according to the longitudinal speed and the course angle of the vehicle in the front N periods.
3. The method of claim 1, wherein the calculating the curvature of the lane center line N cycles ahead, and the heading angle and the lateral intercept at the current position of the lane center line using the lane line information of the forward facing camera comprises:
for each period in the first N periods, acquiring the curvature, the course angle, the transverse intercept and the confidence coefficient of a lane line in the period through the forward camera, wherein the lane line comprises a left lane line and a right lane line;
judging whether the left lane line exists in the period according to the confidence coefficient of the left lane line, and judging whether the right lane line exists in the period according to the confidence coefficient of the right lane line;
if the left lane line and the right lane line exist in the period, calculating the curvature of the lane center line in the period according to the curvature of the left lane line in the period and the curvature of the right lane line in the period;
calculating the course angle of the lane central line in the period according to the course angle of the left lane line in the period and the course angle of the right lane line in the period;
calculating the transverse intercept of the lane center line in the period according to the transverse intercept of the left lane line in the period and the transverse intercept of the right lane line in the period;
if one lane line exists in the left lane line and the right lane line in the period, taking the curvature of the existing lane line as the curvature of the lane center line in the period;
if the left lane line and the right lane line do not exist in the period, discarding the period;
and respectively taking the course angle and the transverse intercept in the current period as the course angle and the transverse intercept at the current position of the lane center line.
4. The method of claim 1, wherein generating a rear road model based on the historical trajectory N cycles before the vehicle, the curvature N cycles before the lane centerline, and the heading angle and lateral intercept at the current location of the lane centerline comprises:
judging whether the rear road model is divided into two sections according to the longitudinal track of the historical tracks of the previous N periods of the vehicle;
if the rear road model is not divided into two sections, inputting the longitudinal track of the historical track of the previous N periods of the vehicle and the curvature of the previous N periods of the vehicle into a clothoid curvature model by taking as input, and calculating the curvature and the curvature change rate of the rear road model by applying a least square method;
and generating a rear road model based on the curvature and the curvature change rate of the rear road model and the course angle and the transverse intercept of the lane center line at the current position.
5. The method of claim 4, wherein generating a rear road model based on the curvature and the rate of change of curvature of the rear road model and the heading angle and the lateral intercept at the current location of the lane centerline further comprises:
if the rear road model is divided into two sections, respectively intercepting a first longitudinal track of a first section of rear road model and a second longitudinal track of a second section of rear road model from longitudinal tracks of historical tracks of the vehicle in the previous N periods;
respectively cutting a first curvature of the first section of rear road model and a second curvature of the second section of rear road model from the curvatures of the vehicle in the front N periods;
inputting the first longitudinal track and the first curvature into a clothoid curvature model, and calculating the curvature and the curvature change rate of the first section rear road model by applying a least square method;
generating a first section of rear road model based on the curvature and the curvature change rate of the first section of rear road model and the course angle and the transverse intercept of the lane center line at the current position, and calculating the abscissa, the course angle and the curvature of the starting point of the second section of rear road model;
inputting the second longitudinal track and the second curvature into the clothoid curvature model, and calculating the curvature change rate of the second section rear road model by applying the least square method;
and generating a second section of rear road model based on the curvature change rate of the second section of rear road model and the abscissa, the course angle and the curvature of the starting point of the second section of rear road model.
6. A rear road model generation apparatus, characterized in that the apparatus comprises:
the first calculation module is used for calculating the historical tracks of the previous N periods of the vehicle according to the motion information of the vehicle, wherein the period is the acquisition period of the motion information;
the second calculation module is used for calculating the curvature of the lane center line in the front N periods, and the course angle and the transverse intercept of the current position of the lane center line by using the lane line information of the forward camera;
and the model generation module is used for generating a rear road model based on the historical track of the vehicle in the previous N periods, the curvature of the lane central line in the previous N periods, and the course angle and the transverse intercept of the current position of the lane central line.
7. The apparatus of claim 6, wherein the first computing module is specifically configured to:
collecting the yaw angular velocity and the longitudinal vehicle speed of the vehicle in the front N periods; calculating the course angles of the front N periods of the vehicle relative to the current coordinate system by using the yaw rates of the front N periods of the vehicle; and calculating the abscissa and the ordinate of the vehicle in the front N periods relative to the current coordinate system according to the longitudinal speed and the heading angle of the vehicle in the front N periods.
8. The apparatus of claim 6, wherein the second computing module is specifically configured to:
for each period in the first N periods, acquiring the curvature, the course angle, the transverse intercept and the confidence coefficient of a lane line in the period through the forward camera, wherein the lane line comprises a left lane line and a right lane line; judging whether the left lane line exists in the period according to the confidence coefficient of the left lane line, and judging whether the right lane line exists in the period according to the confidence coefficient of the right lane line; if the left lane line and the right lane line exist in the period, calculating the curvature of the lane center line in the period according to the curvature of the left lane line in the period and the curvature of the right lane line in the period; calculating the course angle of the lane central line in the period according to the course angle of the left lane line in the period and the course angle of the right lane line in the period; calculating the transverse intercept of the lane center line in the period according to the transverse intercept of the left lane line in the period and the transverse intercept of the right lane line in the period; if one lane line exists in the left lane line and the right lane line in the period, taking the curvature of the existing lane line as the curvature of the lane center line in the period; if the left lane line and the right lane line do not exist in the period, discarding the period; and respectively taking the course angle and the transverse intercept in the current period as the course angle and the transverse intercept at the current position of the lane center line.
9. The apparatus of claim 6, wherein the model generation module is specifically configured to:
judging whether the rear road model is divided into two sections according to the longitudinal track of the historical tracks of the previous N periods of the vehicle; if the rear road model is not divided into two sections, inputting the longitudinal track of the historical track of the previous N periods of the vehicle and the curvature of the previous N periods of the vehicle into a clothoid curvature model by taking as input, and calculating the curvature and the curvature change rate of the rear road model by applying a least square method; and generating a rear road model based on the curvature and the curvature change rate of the rear road model and the course angle and the transverse intercept of the lane center line at the current position.
10. The apparatus of claim 9, wherein the model generation module is further configured to:
if the rear road model is divided into two sections, respectively intercepting a first longitudinal track of a first section of rear road model and a second longitudinal track of a second section of rear road model from longitudinal tracks of historical tracks of the vehicle in the previous N periods; respectively cutting a first curvature of the first section of rear road model and a second curvature of the second section of rear road model from the curvatures of the vehicle in the front N periods; inputting the first longitudinal track and the first curvature into a clothoid curvature model, and calculating the curvature and the curvature change rate of the first section rear road model by applying a least square method; generating a first section of rear road model based on the curvature and the curvature change rate of the first section of rear road model and the course angle and the transverse intercept of the lane center line at the current position, and calculating the abscissa, the course angle and the curvature of the starting point of the second section of rear road model; inputting the second longitudinal track and the second curvature into the clothoid curvature model, and calculating the curvature change rate of the second section rear road model by applying the least square method; and generating a second section of rear road model based on the curvature change rate of the second section of rear road model and the abscissa, the course angle and the curvature of the starting point of the second section of rear road model.
CN202011209559.7A 2020-11-03 2020-11-03 Rear road model generation method and device Active CN114523978B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011209559.7A CN114523978B (en) 2020-11-03 2020-11-03 Rear road model generation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011209559.7A CN114523978B (en) 2020-11-03 2020-11-03 Rear road model generation method and device

Publications (2)

Publication Number Publication Date
CN114523978A true CN114523978A (en) 2022-05-24
CN114523978B CN114523978B (en) 2024-01-16

Family

ID=81619117

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011209559.7A Active CN114523978B (en) 2020-11-03 2020-11-03 Rear road model generation method and device

Country Status (1)

Country Link
CN (1) CN114523978B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116977968A (en) * 2023-08-10 2023-10-31 广州瀚臣电子科技有限公司 Vehicle-mounted camera-based roadway identification system, method and storage medium

Citations (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011107190A1 (en) * 2010-07-20 2012-01-26 Gm Global Technology Operations Llc (N.D.Ges.D. Staates Delaware) Method for determining position of vehicle of traffic lane, involves supplying data of forward directed camera module to board of vehicle and supplying data of backward directed camera module to board of vehicle
WO2013075072A2 (en) * 2011-11-18 2013-05-23 Tomtom North America Inc. A method and apparatus for creating cost data for use in generating a route across an electronic map
CN103924538A (en) * 2014-04-29 2014-07-16 武汉理工大学 Exhaust gas dust collector of self-energized sweeping machine based on self-circulation of waste water
KR20150034400A (en) * 2013-09-26 2015-04-03 현대모비스 주식회사 Apparatus and method for controlling lane keeping
US20160075280A1 (en) * 2014-09-12 2016-03-17 Hyundai Motor Company System for estimating lane and method thereof
CN106114511A (en) * 2016-07-21 2016-11-16 辽宁工业大学 A kind of automobile cruise system core target identification method
WO2017105319A1 (en) * 2015-12-17 2017-06-22 Scania Cv Ab Method and system for facilitating following a leader vehicle along a road
US20170261989A1 (en) * 2016-03-14 2017-09-14 Honda Motor Co., Ltd. Vehicle control system, vehicle control method, and vehicle control program
CN208360053U (en) * 2018-05-21 2019-01-11 上海博泰悦臻网络技术服务有限公司 The vehicle bottom perspective Road System and automobile for looking around device based on 360
CN109724618A (en) * 2017-10-27 2019-05-07 现代自动车株式会社 The device and its system and method for determining the cartographic information of traveling state of vehicle are provided
KR20190054352A (en) * 2017-11-13 2019-05-22 현대오트론 주식회사 Apparatus for tracking vehicle and operating method thereof
CN110194169A (en) * 2019-05-31 2019-09-03 惠州华阳通用智慧车载系统开发有限公司 A kind of vehicle lane change householder method
CN110308470A (en) * 2018-03-27 2019-10-08 上海汽车集团股份有限公司 Vehicle positioning method and vehicle positioning system
CN110738366A (en) * 2019-10-11 2020-01-31 中国科学院软件研究所 outdoor blind area behavior prediction method
EP3608635A1 (en) * 2018-08-10 2020-02-12 Aptiv Technologies Limited Positioning system
CN110803161A (en) * 2018-08-02 2020-02-18 上海汽车集团股份有限公司 Lane keeping method and lane keeping assist system
CN110853377A (en) * 2019-11-15 2020-02-28 东南大学 Road vehicle lane change model calibration and decision-making method and device based on headway
CN110962847A (en) * 2019-11-26 2020-04-07 清华大学苏州汽车研究院（吴江） Lane centering auxiliary self-adaptive cruise trajectory planning method and system
CN110979305A (en) * 2019-03-18 2020-04-10 长城汽车股份有限公司 Vehicle abnormal lane change control method, device and system
US20200117921A1 (en) * 2018-10-10 2020-04-16 Denso Corporation Apparatus and method for recognizing road shapes
JP2020060936A (en) * 2018-10-10 2020-04-16 株式会社Ｓｏｋｅｎ Road shape recognition device
US20200180612A1 (en) * 2018-12-10 2020-06-11 Mobileye Vision Technologies Ltd. Navigation in vehicle crossing scenarios
CN111400823A (en) * 2020-03-27 2020-07-10 清华大学 Functional safety concept analysis method for intelligent vehicle VS-L KA system
CN111717204A (en) * 2019-03-18 2020-09-29 长城汽车股份有限公司 Lateral control method and system for automatic driving vehicle
CN111717189A (en) * 2019-03-18 2020-09-29 长城汽车股份有限公司 Lane keeping control method, device and system

Patent Citations (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011107190A1 (en) * 2010-07-20 2012-01-26 Gm Global Technology Operations Llc (N.D.Ges.D. Staates Delaware) Method for determining position of vehicle of traffic lane, involves supplying data of forward directed camera module to board of vehicle and supplying data of backward directed camera module to board of vehicle
US20120062747A1 (en) * 2010-07-20 2012-03-15 Gm Global Technology Operations, Inc. Lane fusion system using forward-view and rear-view cameras
WO2013075072A2 (en) * 2011-11-18 2013-05-23 Tomtom North America Inc. A method and apparatus for creating cost data for use in generating a route across an electronic map
KR20150034400A (en) * 2013-09-26 2015-04-03 현대모비스 주식회사 Apparatus and method for controlling lane keeping
CN103924538A (en) * 2014-04-29 2014-07-16 武汉理工大学 Exhaust gas dust collector of self-energized sweeping machine based on self-circulation of waste water
US20160075280A1 (en) * 2014-09-12 2016-03-17 Hyundai Motor Company System for estimating lane and method thereof
WO2017105319A1 (en) * 2015-12-17 2017-06-22 Scania Cv Ab Method and system for facilitating following a leader vehicle along a road
US20170261989A1 (en) * 2016-03-14 2017-09-14 Honda Motor Co., Ltd. Vehicle control system, vehicle control method, and vehicle control program
CN106114511A (en) * 2016-07-21 2016-11-16 辽宁工业大学 A kind of automobile cruise system core target identification method
CN109724618A (en) * 2017-10-27 2019-05-07 现代自动车株式会社 The device and its system and method for determining the cartographic information of traveling state of vehicle are provided
KR20190054352A (en) * 2017-11-13 2019-05-22 현대오트론 주식회사 Apparatus for tracking vehicle and operating method thereof
CN110308470A (en) * 2018-03-27 2019-10-08 上海汽车集团股份有限公司 Vehicle positioning method and vehicle positioning system
CN208360053U (en) * 2018-05-21 2019-01-11 上海博泰悦臻网络技术服务有限公司 The vehicle bottom perspective Road System and automobile for looking around device based on 360
CN110803161A (en) * 2018-08-02 2020-02-18 上海汽车集团股份有限公司 Lane keeping method and lane keeping assist system
CN110865374A (en) * 2018-08-10 2020-03-06 德尔福技术有限公司 Positioning system
EP3608635A1 (en) * 2018-08-10 2020-02-12 Aptiv Technologies Limited Positioning system
US20200117921A1 (en) * 2018-10-10 2020-04-16 Denso Corporation Apparatus and method for recognizing road shapes
JP2020060936A (en) * 2018-10-10 2020-04-16 株式会社Ｓｏｋｅｎ Road shape recognition device
US20200180612A1 (en) * 2018-12-10 2020-06-11 Mobileye Vision Technologies Ltd. Navigation in vehicle crossing scenarios
CN110979305A (en) * 2019-03-18 2020-04-10 长城汽车股份有限公司 Vehicle abnormal lane change control method, device and system
WO2020187257A1 (en) * 2019-03-18 2020-09-24 长城汽车股份有限公司 Vehicle abnormal lane change control method, device and system
CN111717204A (en) * 2019-03-18 2020-09-29 长城汽车股份有限公司 Lateral control method and system for automatic driving vehicle
CN111717189A (en) * 2019-03-18 2020-09-29 长城汽车股份有限公司 Lane keeping control method, device and system
CN110194169A (en) * 2019-05-31 2019-09-03 惠州华阳通用智慧车载系统开发有限公司 A kind of vehicle lane change householder method
CN110738366A (en) * 2019-10-11 2020-01-31 中国科学院软件研究所 outdoor blind area behavior prediction method
CN110853377A (en) * 2019-11-15 2020-02-28 东南大学 Road vehicle lane change model calibration and decision-making method and device based on headway
CN110962847A (en) * 2019-11-26 2020-04-07 清华大学苏州汽车研究院（吴江） Lane centering auxiliary self-adaptive cruise trajectory planning method and system
CN111400823A (en) * 2020-03-27 2020-07-10 清华大学 Functional safety concept analysis method for intelligent vehicle VS-L KA system

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
张凯;刘军;后士浩;晏晓娟;: "基于Simulink的换道防碰撞预警建模与仿真分析", 重庆理工大学学报(自然科学), no. 02 *
李看;雷斌;李慧云;: "自动驾驶在拥堵路段的道路几何信息估计", 集成技术, no. 05 *
陈学文;张进国;刘伟川;朱甲林;李刚;: "汽车巡航系统前方关键目标识别研究", 机械科学与技术, no. 09 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116977968A (en) * 2023-08-10 2023-10-31 广州瀚臣电子科技有限公司 Vehicle-mounted camera-based roadway identification system, method and storage medium

Also Published As

Publication number Publication date
CN114523978B (en) 2024-01-16

Similar Documents

Publication Publication Date Title
CN111775940B (en) Automatic channel changing method, device, equipment and storage medium
CN107848533B (en) Vehicle control device, vehicle control method, and medium storing vehicle control program
US20220187834A1 (en) Generating trajectories for autonomous vehicles
EP3699051A1 (en) Vehicle control device
CN110775034B (en) Control method of automatic brake auxiliary system, terminal equipment and storage medium
US11242040B2 (en) Emergency braking for autonomous vehicles
US20190009784A1 (en) Vehicle control apparatus, vehicle control method, and vehicle control program
EP3663152A1 (en) Vehicle control device
CN111361564A (en) Lane change system considering benefit maximization and comprehensive decision method
JP2003536096A (en) Tracking map generator
JP2019160031A (en) Vehicle control device, vehicle control method, and program
CN114126940A (en) Electronic control device
CN113954827B (en) Intersection vehicle collision probability calculation method and system considering positioning error and communication time delay
CN111325187A (en) Lane position identification method and device
CN114523978B (en) Rear road model generation method and device
US20240051531A1 (en) Vehicle control device, vehicle control method, and storage medium
CN117416375A (en) Vehicle avoidance method, device, equipment and storage medium
CN110834626B (en) Driving obstacle early warning method and device, vehicle and storage medium
CN114829219A (en) Method for providing a positive decision signal for a vehicle
CN211995540U (en) Lane change system considering benefit maximization
JP2019185113A (en) Vehicle control device, vehicle control method, and program
CN113942505A (en) Vehicle self-adaptive cruise algorithm
CN114655208A (en) Method and device for determining obstacle vehicle behind vehicle
CN117272690B (en) Method, equipment and medium for extracting dangerous cut-in scene of automatic driving vehicle
KR100559393B1 (en) Tracking a preceding vehicle for adaptive cruise control using a block matching method

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