CN112965489A - Intelligent vehicle high-speed lane change planning method based on collision detection - Google Patents

Intelligent vehicle high-speed lane change planning method based on collision detection Download PDF

Info

Publication number
CN112965489A
CN112965489A CN202110164523.XA CN202110164523A CN112965489A CN 112965489 A CN112965489 A CN 112965489A CN 202110164523 A CN202110164523 A CN 202110164523A CN 112965489 A CN112965489 A CN 112965489A
Authority
CN
China
Prior art keywords
lane change
track
collision detection
speed
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
CN202110164523.XA
Other languages
Chinese (zh)
Other versions
CN112965489B (en
Inventor
蒋朝阳
盛树轩
荆崇波
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.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
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 Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN202110164523.XA priority Critical patent/CN112965489B/en
Publication of CN112965489A publication Critical patent/CN112965489A/en
Application granted granted Critical
Publication of CN112965489B publication Critical patent/CN112965489B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses an intelligent vehicle high-speed lane change planning method based on collision detection, which comprises the following steps: sampling the state space of a target lane to obtain the terminal state of a lane change end point, and fitting a lane change track between the lane change start point and the lane change end point by utilizing a quintic polynomial to form a lane change candidate track set; evaluating candidate track changing tracks in the track changing track set by using a cost evaluation function, and selecting the track with the lowest evaluation score as the best track changing track; acquiring historical motion state information of a target vehicle in a target lane, and then mapping the historical motion state information to a Frenet coordinate system from a Cartesian coordinate system to predict the track of the target vehicle; performing collision detection between the planned lane change track and the predicted track of the target vehicle, and controlling the lane change behavior of the vehicle according to the result of the collision detection; the invention ensures that the vehicle can change the lane according to the optimal lane changing track and ensures the safety of high-speed lane changing to the maximum extent by a collision detection mode.

Description

Intelligent vehicle high-speed lane change planning method based on collision detection
Technical Field
The invention belongs to the technical field of intelligent traffic, and particularly relates to an intelligent vehicle high-speed lane change planning method based on collision detection.
Background
The intelligent automobile technology is considered to have great potential in improving road safety and improving traffic operation efficiency, and has been widely paid attention and researched in recent years. For an intelligent vehicle, safety is the most important cornerstone, and at present, most of the evaluation methods for lane change safety are realized by a time-space quantitative model, such as a Time To Collision (TTC) model. Chinese patent document CN111016898A (application number: 201911113734.X) discloses a lane change planning method for an intelligent vehicle, which determines the lane change time and the maximum lateral acceleration according to the movement state of a main vehicle and the information of an obstacle, and brings the lane change time and the maximum lateral acceleration into a lane change safety model to judge whether the vehicle is safe or not. The lane change safety assessment method performs an idealized assumption on the motion state of other vehicles in the lane change process, if the lane change safety assessment method assumes that the vehicles follow a uniform motion model, uncertainty of driving intentions and trajectories of the vehicles is not considered comprehensively, and therefore a certain collision risk exists, especially under a high-speed working condition.
Therefore, how to provide an intelligent vehicle high-speed lane change planning method with high safety is a problem that needs to be solved urgently by technical personnel in the field.
Disclosure of Invention
In view of this, the invention provides an intelligent vehicle high-speed lane change planning method based on collision detection, which ensures the lane change safety through a collision detection mode.
In order to achieve the purpose, the invention adopts the following technical scheme:
an intelligent vehicle high-speed lane change planning method based on collision detection comprises the following steps:
s1: sampling the state space of a target lane to obtain the terminal state of a lane change end point, and fitting a lane change track between the lane change start point and the lane change end point by utilizing a quintic polynomial to form a lane change candidate track set; evaluating candidate track changing tracks in the track changing track set by using a cost evaluation function, and selecting the track with the lowest evaluation score as the track changing track;
s2: acquiring historical motion state information of a target vehicle in a target lane by using a vehicle-mounted sensor, wherein the historical motion state information comprises position, speed, acceleration and course, mapping the historical motion state information to a Frenet coordinate system from a Cartesian coordinate system, predicting the track of the target vehicle, and finally mapping the predicted track coordinate back to the Cartesian coordinate system;
s3: and performing collision detection between the planned lane change track and the predicted track of the target vehicle, controlling lane change behavior according to the result of the collision detection, performing lane change according to the planned optimal track if the collision detection is passed, and not performing the lane change if the collision detection is not passed. .
Preferably, the lane change candidate trajectory set is:
Sset＝Ψ(T,S0,Sf)
wherein T represents the track-changing time, S0Indicating the initial state of the main lane change, SfIndicating the terminal state, Ψ (t, S)0,Sf) Indicating a slave initial state S0To terminal state SfThe lane change trajectory.
Preferably, the track-changing track is obtained by fitting two points, namely a starting point and an end point, by using a fifth-order polynomial:
Figure BDA0002937223550000021
wherein x represents a longitudinal position coordinate, y represents a lateral position coordinate, cx0、cx1、cx2、cx3、cx4、cx5And cy0、cy1、cy2、cy3、cy4、cy5The coefficient is to be calculated;
initial point longitudinal state
Figure BDA0002937223550000022
And end point longitudinal state
Figure BDA0002937223550000023
Taking the longitudinal trajectory as a boundary condition may result in:
Figure BDA0002937223550000031
Figure BDA0002937223550000032
the lane change time is T such that the following holds:
tf＝t0+T
solving to obtain polynomial coefficients:
Figure BDA0002937223550000033
Figure BDA0002937223550000034
transverse state of initial point
Figure BDA0002937223550000035
And end point lateral state
Figure BDA0002937223550000036
Taking the transverse trajectory as a boundary condition yields:
Figure BDA0002937223550000037
Figure BDA0002937223550000038
the lane change time is T such that the following holds:
tf＝t0+T
solving to obtain polynomial coefficients:
Figure BDA0002937223550000041
Figure BDA0002937223550000042
and selecting different lane change end point terminal states and lane change time to obtain a set of lane change tracks.
Preferably, the longitudinal and lateral terminal states of the lane change end point are determined according to the current motion state of the vehicle. Wherein the longitudinal terminal state satisfies:
Figure BDA0002937223550000043
in the formula, TcIs the collision avoidance time.
The transverse terminal state satisfies:
Figure BDA0002937223550000044
where L is the lane width, Δ is the unit lateral sampling distance, and k is the number of samples, the greater the initial speed the greater the number of samples k, depending on the lane change initial speed.
Preferably, the cost evaluation function is:
Ctotal＝kxCx+kyCy
in the formula, kx、kyIs a weight coefficient, Cx、CyRespectively representing a transverse cost function and a longitudinal cost function, wherein the expressions are respectively as follows:
Figure BDA0002937223550000045
in the formula, ki、kvIs a weight coefficient, vdesIs the desired speed during the lane change;
Figure BDA0002937223550000051
in the formula, kj、klIs the weight coefficient, ldesIs the desired lateral displacement during the lane change.
Preferably, in step S2, the vehicle-mounted sensor is used to obtain the historical motion state information of the target vehicle in the target lane, including position, speed, acceleration, and heading, and then the historical motion information is mapped from the cartesian coordinate system to the Frenet coordinate system, where the mapping formula is:
Figure BDA0002937223550000052
in the formula (I), the compound is shown in the specification,
Figure BDA0002937223550000053
is the time derivative of the longitudinal coordinate in the Frenet coordinate system, vxIs the speed in a Cartesian coordinate system, and theta is the heading angle theta in the Cartesian coordinate systemxAnd matching point heading θrIs equal to θx-θr，κrIs the curvature of the reference point;
Figure BDA0002937223550000054
in the formula, axIs the acceleration in a cartesian coordinate system, l' is the derivative of l with respect to the longitudinal coordinate s, l ═ 1- κrl)tan(θ)；
Figure BDA0002937223550000055
Where l' is the second derivative of l with respect to the longitudinal coordinate s, κxIs the curvature of a location point in a cartesian coordinate system.
Preferably, every interval
Figure BDA0002937223550000056
Recording the historical motion state information after once mapping, packing historical data recorded in a time domain n into a vector with n as a time domain value, inputting the vector into a track prediction module, wherein the track prediction module is based on a coding and decoding structure of a multilayer neural network, coding the historical motion information of a target vehicle by using a coder, outputting the predicted track of the target vehicle under a Frenet coordinate system by using a decoder, and mapping the trackThe mapping formula of the Hui Cartesian coordinate system is as follows:
x＝r(s)+nrl
where x is a position vector in Cartesian coordinate system, x is (x, y), r(s) is a reference point position vector in Frenet coordinate system, and n isrIs the reference normal vector at the reference point and l is the offset along the normal direction.
Preferably, the predicted trajectory of the target vehicle is finally obtained as follows:
Figure BDA0002937223550000061
in the formula (I), the compound is shown in the specification,
Figure BDA0002937223550000062
is at t at the beginning of a lane change0The predicted position coordinates of the vehicle at the time are in cartesian coordinates, and mp is the length of the predicted time domain.
Preferably, the track changing planning module plans a track changing track, samples the track changing track at a time interval p to obtain discrete track changing track points, and the expression is as follows:
Figure BDA0002937223550000063
the target vehicle track prediction module predicts the future motion track of a target vehicle, and judges whether collision occurs in the lane changing process by simulating the future motion of the vehicle, wherein the judgment formula of collision detection is as follows:
Figure BDA0002937223550000064
in the formula, robj、regoThe expansion radius of a target vehicle and the expansion radius of a main vehicle are respectively, xi is a safety coefficient, the safety coefficient is related to the speed of the main vehicle and the time of collision detection, the higher the speed is, the higher the safety coefficient is, the higher the sampling time is, the higher the uncertainty of track prediction is, and the higher the safety coefficient is; the expression of the safety factor is as follows:
Figure BDA0002937223550000065
where v is the velocity of the host vehicle in km/h and i is the time of collision detection in s.
The invention has the beneficial effects that:
the method adopts a sampling fitting method to generate a candidate track changing track set, determines the optimal track changing track through a cost function evaluation method, and has better adaptability compared with a deterministic track changing track model; the motion uncertainty of surrounding vehicles in the high-speed lane changing process is considered, and the safety of the high-speed lane changing is ensured in a collision detection mode; the safety of high-speed lane changing is ensured to the maximum extent while the vehicle changes the lane with the optimal track.
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 flow chart of the process of the present invention;
fig. 2 is a schematic diagram of the collision detection 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.
Referring to fig. 1, the invention provides a collision detection-based intelligent vehicle high-speed lane change planning method, which includes:
step 1, generating a lane change track:
sampling the state space of the target lane to obtain the terminal state of the lane change end point, and fitting the lane change track between the lane change start point and the lane change end point by utilizing a quintic polynomial to form a lane change candidate track set:
Sset＝Ψ(T,S0,Sf)
wherein T represents the track-changing time, S0Indicating the initial state of the main lane change, SfIndicating the terminal state, Ψ (t, S)0,Sf) Indicating a slave initial state S0To terminal state SfThe lane change trajectory.
The track-changing track is obtained by fitting two points of a starting point and an end point by utilizing a fifth-order polynomial:
Figure BDA0002937223550000081
wherein x represents a longitudinal position coordinate, y represents a lateral position coordinate, cx0、cx1、cx2、cx3、cx4、cx5And cy0、cy1、cy2、cy3、cy4、cy5The coefficients are to be found.
Initial point longitudinal state
Figure BDA0002937223550000082
And end point longitudinal state
Figure BDA0002937223550000083
Taking the longitudinal trajectory as a boundary condition may result in:
Figure BDA0002937223550000084
Figure BDA0002937223550000085
the lane change time is T such that the following holds:
tf＝t0+T
the polynomial coefficients can be solved as:
Figure BDA0002937223550000086
Figure BDA0002937223550000087
transverse state of initial point
Figure BDA0002937223550000088
And end point lateral state
Figure BDA0002937223550000089
Bringing in the transverse trajectory as a boundary condition can result in:
Figure BDA00029372235500000810
Figure BDA0002937223550000091
the lane change time is T such that the following holds:
tf＝t0+T
the polynomial coefficients can be solved as:
Figure BDA0002937223550000092
Figure BDA0002937223550000093
and selecting different lane change ending point terminal states and lane change time to obtain a set of lane change tracks, and determining the sampling point according to the motion state of the main vehicle.
And determining the longitudinal and transverse terminal states of the lane change end point according to the current motion state of the vehicle. Wherein the longitudinal terminal state satisfies:
Figure BDA0002937223550000094
in the formula, TcIs the collision avoidance time.
The transverse terminal state satisfies:
Figure BDA0002937223550000095
where L is the lane width, Δ is the unit lateral sampling distance, and k is the number of samples, the greater the initial speed the greater the number of samples k, depending on the lane change initial speed.
Evaluating candidate track changing tracks in the track changing track set by using a cost evaluation function, selecting the track with the lowest evaluation score as the track changing track, wherein the cost evaluation function is as follows:
Ctotal＝kxCx+kyCy
in the formula, kx、kyIs a weight coefficient, Cx、CyRespectively representing a transverse cost function and a longitudinal cost function, wherein the expressions are respectively as follows:
Figure BDA0002937223550000101
in the formula, ki、kvIs a weight coefficient, vdesIs the desired speed during the lane change.
Figure BDA0002937223550000102
In the formula, kj、klIs the weight coefficient, ldesIs the desired lateral displacement during the lane change.
Step 2, target vehicle track prediction:
acquiring historical motion state information of a target vehicle in a target lane by using a vehicle-mounted sensor, wherein the historical motion state information comprises position, speed, acceleration and course, and then mapping the historical motion information to a Frenet coordinate system from a Cartesian coordinate system, wherein the mapping formula is as follows:
Figure BDA0002937223550000103
in the formula (I), the compound is shown in the specification,
Figure BDA0002937223550000104
is the time derivative of the longitudinal coordinate in the Frenet coordinate system, vxIs the speed in a Cartesian coordinate system, and theta is the heading angle theta in the Cartesian coordinate systemxAnd matching point heading θrIs equal to θx-θr，κrIs the curvature of the reference point.
Figure BDA0002937223550000105
In the formula, axIs the acceleration in a cartesian coordinate system, l' is the derivative of l with respect to the longitudinal coordinate s, l ═ 1- κrl)tan(θ)。
Figure BDA0002937223550000106
Where l' is the second derivative of l with respect to the longitudinal coordinate s, κxIs the curvature of a location point in a cartesian coordinate system.
At intervals of time
Figure BDA0002937223550000111
Recording the historical motion state information after once mapping, taking n as a time domain value, and dividing the time domainn, packing historical data recorded in the n into a vector and inputting the vector to a track prediction module, wherein the track prediction module is an encoding and decoding structure based on a multilayer neural network, encoding historical motion information of a target vehicle by using an encoder, outputting a predicted track of the target vehicle under a Frenet coordinate system by using a decoder, and mapping the track back to a Cartesian coordinate system, and the mapping formula is as follows:
x＝r(s)+nrl
where x is a position vector in Cartesian coordinate system, x is (x, y), r(s) is a reference point position vector in Frenet coordinate system, and n isrIs the reference normal vector at the reference point and l is the offset along the normal direction.
The predicted track of the target vehicle is finally obtained as follows:
Figure BDA0002937223550000112
in the formula (I), the compound is shown in the specification,
Figure BDA0002937223550000113
is at t at the beginning of a lane change0The predicted position coordinates of the vehicle at the time are in cartesian coordinates, and mp is the length of the predicted time domain.
Step 3, lane change decision based on collision detection:
the track changing planning module plans a track changing track, samples the track changing track at a time interval p to obtain discrete track changing track points, and the expression is as follows:
Figure BDA0002937223550000114
the target vehicle track prediction module predicts the future motion track of the target vehicle, and judges whether collision occurs in the lane changing process by simulating the future motion of the vehicle, and referring to fig. 2, the judgment formula of the collision detection is as follows:
Figure BDA0002937223550000115
in the formula, robj、regoThe expansion radius of the target vehicle and the expansion radius of the main vehicle are respectively, xi is a safety coefficient, the safety coefficient is related to the speed of the main vehicle and the time of collision detection, the higher the speed is, the higher the safety coefficient is, the higher the sampling time is, the higher the uncertainty of the track prediction is, and the higher the safety coefficient is. The expression of the safety factor is as follows:
Figure BDA0002937223550000121
where v is the velocity of the host vehicle in km/h and i is the time of collision detection in s. And performing collision detection on the planned trajectory of the main vehicle and the predicted trajectory of the target vehicle within the lane changing time T, and if the collision detection is passed, changing the lane according to the planned lane changing trajectory. And if the collision detection is not passed, restarting to plan the track changing track, and waiting for the passage of the collision detection to change the track. In FIG. 2, robj、regoExpansion radius, t, of the target vehicle and the main vehicle, respectively0,…t0+npIs the time of collision detection, whether the collision detection formula is satisfied is judged by detecting the positional relationship between the target vehicle and the host vehicle at each time, and the target vehicle and the host vehicle will be at t in fig. 20+4pA collision occurs at a moment.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are 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.
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.

Claims (9)

1. An intelligent vehicle high-speed lane change planning method based on collision detection is characterized by comprising the following steps:
s1: sampling the state space of a target lane to obtain the terminal state of a lane change end point, and fitting a lane change track between the lane change start point and the lane change end point by utilizing a quintic polynomial to form a lane change candidate track set; evaluating candidate track changing tracks in the track changing track set by using a cost evaluation function, and selecting the track with the lowest evaluation score as the track changing track;
s2: acquiring historical motion state information of a target vehicle in a target lane by using a vehicle-mounted sensor, wherein the historical motion state information comprises position, speed, acceleration and course, mapping the historical motion state information to a Frenet coordinate system from a Cartesian coordinate system, predicting the track of the target vehicle, and finally mapping the predicted track coordinate back to the Cartesian coordinate system;
s3: and performing collision detection between the planned lane change track and the predicted track of the target vehicle, controlling lane change behavior according to the result of the collision detection, performing lane change according to the planned optimal track if the collision detection is passed, and not performing the lane change if the collision detection is not passed.
2. The intelligent vehicle high-speed lane change planning method based on collision detection according to claim 1, wherein the lane change candidate trajectory set is:
Sset＝Ψ(T,S0,Sf)
wherein T represents the track-changing time, S0Indicating the initial state of the main lane change, SfIndicating the terminal state, Ψ (t, S)0,Sf) Indicating a slave initial state S0To terminal state SfThe lane change trajectory.
3. The intelligent vehicle high-speed lane change planning method based on collision detection as claimed in claim 2, wherein the lane change track is obtained by fitting two points of a starting point and an end point by using a quintic polynomial:
Figure FDA0002937223540000011
wherein x represents a longitudinal position coordinate, y represents a lateral position coordinate, cx0、cx1、cx2、cx3、cx4、cx5And cy0、cy1、cy2、cy3、cy4、cy5The coefficient is to be calculated;
initial point longitudinal state
Figure FDA0002937223540000021
And end point longitudinal state
Figure FDA0002937223540000022
Taking the longitudinal trajectory as a boundary condition may result in:
Figure FDA0002937223540000023
Figure FDA0002937223540000024
the lane change time is T such that the following holds:
tf＝t0+T
solving to obtain polynomial coefficients:
Figure FDA0002937223540000025
Figure FDA0002937223540000026
transverse state of initial point
Figure FDA0002937223540000027
And end point lateral state
Figure FDA0002937223540000028
Taking the transverse trajectory as a boundary condition yields:
Figure FDA0002937223540000029
Figure FDA00029372235400000210
the lane change time is T such that the following holds:
tf＝t0+T
solving to obtain polynomial coefficients:
Figure FDA0002937223540000031
Figure FDA0002937223540000032
and selecting different lane change end point terminal states and lane change time to obtain a set of lane change tracks.
4. The intelligent vehicle high-speed lane change planning method based on collision detection as claimed in claim 3, wherein the longitudinal and transverse terminal states of the lane change end point are determined according to the current motion state of the vehicle; wherein the longitudinal terminal state satisfies:
Figure FDA0002937223540000033
in the formula, TcIs the collision avoidance time;
the transverse terminal state satisfies:
Figure FDA0002937223540000034
where L is the lane width, Δ is the unit lateral sampling distance, and k is the number of samples, the greater the initial speed the greater the number of samples k, depending on the lane change initial speed.
5. The intelligent vehicle high-speed lane change planning method based on collision detection as claimed in claim 3, wherein the cost evaluation function is:
Ctotal＝kxCx+kyCy
in the formula, kx、kyIs a weight coefficient, Cx、CyRespectively representing a transverse cost function and a longitudinal cost function, wherein the expressions are respectively as follows:
Figure FDA0002937223540000041
in the formula, ki、kvIs a weight coefficient, vdesIs the desired speed during the lane change;
Figure FDA0002937223540000042
in the formula, kj、klIs the weight coefficient, ldesIs the desired lateral displacement during the lane change.
6. The intelligent vehicle high-speed lane change planning method based on collision detection as claimed in claim 1, wherein in step S2, historical motion state information of the target vehicle in the target lane, including position, speed, acceleration, and heading, is obtained by using the vehicle-mounted sensor, and then the historical motion information is mapped from a cartesian coordinate system to a Frenet coordinate system, wherein the mapping formula is as follows:
Figure FDA0002937223540000043
in the formula (I), the compound is shown in the specification,
Figure FDA0002937223540000044
is the time derivative of the longitudinal coordinate in the Frenet coordinate system, vxIs the speed in a Cartesian coordinate system, and theta is the heading angle theta in the Cartesian coordinate systemxAnd matching point heading θrIs equal to θx-θr，κrIs the curvature of the reference point;
Figure FDA0002937223540000045
in the formula, axIs the acceleration in a cartesian coordinate system, l' is the derivative of l with respect to the longitudinal coordinate s, l ═ 1- κrl)tan(θ)；
Figure FDA0002937223540000046
Where l' is the second derivative of l with respect to the longitudinal coordinate s, κxIs the curvature of a location point in a cartesian coordinate system.
7. The intelligent vehicle high-speed lane change planning method based on collision detection as claimed in claim 6, wherein the time interval is every
Figure FDA0002937223540000047
Recording the historical motion state information after one mapping, taking n as a time domain value,the method comprises the following steps of packaging historical data recorded in a time domain n into a vector, inputting the vector to a track prediction module, wherein the track prediction module is an encoding and decoding structure based on a multilayer neural network, encoding historical motion information of a target vehicle by using an encoder, outputting a predicted track of the target vehicle under a Frenet coordinate system by using a decoder, and mapping the track back to a Cartesian coordinate system, wherein the mapping formula is as follows:
x＝r(s)+nrl
where x is a position vector in Cartesian coordinate system, x is (x, y), r(s) is a reference point position vector in Frenet coordinate system, and n isrIs the reference normal vector at the reference point and l is the offset along the normal direction.
8. The intelligent vehicle high-speed lane change planning method based on collision detection according to claim 7, wherein the final obtained predicted trajectory of the target vehicle is:
Figure FDA0002937223540000051
in the formula (I), the compound is shown in the specification,
Figure FDA0002937223540000052
is at t at the beginning of a lane change0The predicted position coordinates of the vehicle at the time are in cartesian coordinates, and mp is the length of the predicted time domain.
9. The intelligent vehicle high-speed lane change planning method based on collision detection according to claim 8, characterized in that the lane change planning module plans a lane change track, samples the lane change track at time intervals p to obtain discrete lane change track points, and the expression is as follows:
Figure FDA0002937223540000053
the target vehicle track prediction module predicts the future motion track of a target vehicle, and judges whether collision occurs in the lane changing process by simulating the future motion of the vehicle, wherein the judgment formula of collision detection is as follows:
Figure FDA0002937223540000054
in the formula, robj、regoThe expansion radius of a target vehicle and the expansion radius of a main vehicle are respectively, xi is a safety coefficient, the safety coefficient is related to the speed of the main vehicle and the time of collision detection, the higher the speed is, the higher the safety coefficient is, the higher the sampling time is, the higher the uncertainty of track prediction is, and the higher the safety coefficient is; the expression of the safety factor is as follows:
Figure FDA0002937223540000061
where v is the velocity of the host vehicle in km/h and i is the time of collision detection in s.
CN202110164523.XA 2021-02-05 2021-02-05 Intelligent vehicle high-speed lane change planning method based on collision detection Active CN112965489B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110164523.XA CN112965489B (en) 2021-02-05 2021-02-05 Intelligent vehicle high-speed lane change planning method based on collision detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110164523.XA CN112965489B (en) 2021-02-05 2021-02-05 Intelligent vehicle high-speed lane change planning method based on collision detection

Publications (2)

Publication Number Publication Date
CN112965489A true CN112965489A (en) 2021-06-15
CN112965489B CN112965489B (en) 2022-04-08

Family

ID=76274808

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110164523.XA Active CN112965489B (en) 2021-02-05 2021-02-05 Intelligent vehicle high-speed lane change planning method based on collision detection

Country Status (1)

Country Link
CN (1) CN112965489B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113386795A (en) * 2021-07-05 2021-09-14 西安电子科技大学芜湖研究院 Intelligent decision-making and local track planning method for automatic driving vehicle and decision-making system thereof
CN113581181A (en) * 2021-08-04 2021-11-02 武汉理工大学 Intelligent vehicle overtaking track planning method
CN113886764A (en) * 2021-10-28 2022-01-04 哈尔滨工业大学 Intelligent vehicle multi-scene track planning method based on Frenet coordinate system
CN113961002A (en) * 2021-09-09 2022-01-21 浙江零跑科技股份有限公司 Active lane change planning method based on structured road sampling
CN114194215A (en) * 2021-12-30 2022-03-18 江苏大学 Intelligent vehicle obstacle avoidance and track changing planning method and system
CN115195743A (en) * 2022-09-16 2022-10-18 毫末智行科技有限公司 Automatic lane changing method, device, equipment and medium for vehicle based on unmanned driving
CN117284297A (en) * 2023-11-27 2023-12-26 福思(杭州)智能科技有限公司 Vehicle control method and device and domain controller
CN117698730A (en) * 2024-01-08 2024-03-15 昆明理工大学 Optimal lane change track planning method for anti-collision dynamic intelligent network-connected vehicle

Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107146412A (en) * 2017-06-07 2017-09-08 江苏大学 A kind of vehicle on highway anticollision early warning generalized variable construction method based on car networking
DE102018107340A1 (en) * 2017-03-31 2018-10-04 Ford Global Technologies, Llc STEERING CONTROL
CN109283843A (en) * 2018-10-12 2019-01-29 江苏大学 A kind of lane-change method for planning track merged based on multinomial with particle swarm algorithm
CN109501799A (en) * 2018-10-29 2019-03-22 江苏大学 A kind of dynamic path planning method under the conditions of car networking
CN109855639A (en) * 2019-01-15 2019-06-07 天津大学 Unmanned method for planning track based on forecasting-obstacle and MPC algorithm
CN110085056A (en) * 2019-04-24 2019-08-02 华南理工大学 Vehicle lane-changing instantaneous risk recognition methods under a kind of highway bus or train route cooperative surroundings
CN110329263A (en) * 2019-07-05 2019-10-15 西南交通大学 The adaptive lane-change method for planning track of automatic driving vehicle
CN110362096A (en) * 2019-08-13 2019-10-22 东北大学 A kind of automatic driving vehicle dynamic trajectory planing method based on local optimality
CN110466516A (en) * 2019-07-11 2019-11-19 北京交通大学 A kind of curved road automatic vehicle lane-change method for planning track based on Non-Linear Programming
CN110555476A (en) * 2019-08-29 2019-12-10 华南理工大学 intelligent vehicle track change track prediction method suitable for man-machine hybrid driving environment
CN110568760A (en) * 2019-10-08 2019-12-13 吉林大学 Parameterized learning decision control system and method suitable for lane changing and lane keeping
CN110597245A (en) * 2019-08-12 2019-12-20 北京交通大学 Automatic driving track-changing planning method based on quadratic planning and neural network
CN110705388A (en) * 2019-09-16 2020-01-17 清华大学 Target vehicle lane change identification method for auxiliary driving based on prediction feedback
CN110877612A (en) * 2019-11-26 2020-03-13 江苏大学 Vehicle emergency lane change danger assessment method based on vehicle kinematics and genetic algorithm
CN111260956A (en) * 2020-01-15 2020-06-09 清华大学 Automatic vehicle lane change planning and control method based on model predictive control
CN111338335A (en) * 2019-12-31 2020-06-26 清华大学 Vehicle local track planning method under structured road scene
CN111681452A (en) * 2020-01-19 2020-09-18 重庆大学 Unmanned vehicle dynamic lane change track planning method based on Frenet coordinate system
CN111845774A (en) * 2020-07-20 2020-10-30 上海大学 Automatic driving automobile dynamic trajectory planning and tracking method based on transverse and longitudinal coordination
CN111873990A (en) * 2020-07-15 2020-11-03 哈尔滨理工大学 Lane changing collision avoidance device and method suitable for high-speed emergency working condition
CN112258893A (en) * 2020-09-01 2021-01-22 华南理工大学 Intelligent vehicle lane change collision probability assessment method based on track prediction
CN112258841A (en) * 2020-10-26 2021-01-22 大连大学 Intelligent vehicle risk assessment method based on vehicle track prediction

Patent Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102018107340A1 (en) * 2017-03-31 2018-10-04 Ford Global Technologies, Llc STEERING CONTROL
CN107146412A (en) * 2017-06-07 2017-09-08 江苏大学 A kind of vehicle on highway anticollision early warning generalized variable construction method based on car networking
CN109283843A (en) * 2018-10-12 2019-01-29 江苏大学 A kind of lane-change method for planning track merged based on multinomial with particle swarm algorithm
CN109501799A (en) * 2018-10-29 2019-03-22 江苏大学 A kind of dynamic path planning method under the conditions of car networking
CN109855639A (en) * 2019-01-15 2019-06-07 天津大学 Unmanned method for planning track based on forecasting-obstacle and MPC algorithm
CN110085056A (en) * 2019-04-24 2019-08-02 华南理工大学 Vehicle lane-changing instantaneous risk recognition methods under a kind of highway bus or train route cooperative surroundings
CN110329263A (en) * 2019-07-05 2019-10-15 西南交通大学 The adaptive lane-change method for planning track of automatic driving vehicle
CN110466516A (en) * 2019-07-11 2019-11-19 北京交通大学 A kind of curved road automatic vehicle lane-change method for planning track based on Non-Linear Programming
CN110597245A (en) * 2019-08-12 2019-12-20 北京交通大学 Automatic driving track-changing planning method based on quadratic planning and neural network
CN110362096A (en) * 2019-08-13 2019-10-22 东北大学 A kind of automatic driving vehicle dynamic trajectory planing method based on local optimality
CN110555476A (en) * 2019-08-29 2019-12-10 华南理工大学 intelligent vehicle track change track prediction method suitable for man-machine hybrid driving environment
CN110705388A (en) * 2019-09-16 2020-01-17 清华大学 Target vehicle lane change identification method for auxiliary driving based on prediction feedback
CN110568760A (en) * 2019-10-08 2019-12-13 吉林大学 Parameterized learning decision control system and method suitable for lane changing and lane keeping
CN110877612A (en) * 2019-11-26 2020-03-13 江苏大学 Vehicle emergency lane change danger assessment method based on vehicle kinematics and genetic algorithm
CN111338335A (en) * 2019-12-31 2020-06-26 清华大学 Vehicle local track planning method under structured road scene
CN111260956A (en) * 2020-01-15 2020-06-09 清华大学 Automatic vehicle lane change planning and control method based on model predictive control
CN111681452A (en) * 2020-01-19 2020-09-18 重庆大学 Unmanned vehicle dynamic lane change track planning method based on Frenet coordinate system
CN111873990A (en) * 2020-07-15 2020-11-03 哈尔滨理工大学 Lane changing collision avoidance device and method suitable for high-speed emergency working condition
CN111845774A (en) * 2020-07-20 2020-10-30 上海大学 Automatic driving automobile dynamic trajectory planning and tracking method based on transverse and longitudinal coordination
CN112258893A (en) * 2020-09-01 2021-01-22 华南理工大学 Intelligent vehicle lane change collision probability assessment method based on track prediction
CN112258841A (en) * 2020-10-26 2021-01-22 大连大学 Intelligent vehicle risk assessment method based on vehicle track prediction

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113386795B (en) * 2021-07-05 2022-07-01 西安电子科技大学芜湖研究院 Intelligent decision-making and local track planning method for automatic driving vehicle and decision-making system thereof
CN113386795A (en) * 2021-07-05 2021-09-14 西安电子科技大学芜湖研究院 Intelligent decision-making and local track planning method for automatic driving vehicle and decision-making system thereof
CN113581181A (en) * 2021-08-04 2021-11-02 武汉理工大学 Intelligent vehicle overtaking track planning method
CN113961002A (en) * 2021-09-09 2022-01-21 浙江零跑科技股份有限公司 Active lane change planning method based on structured road sampling
CN113961002B (en) * 2021-09-09 2023-10-03 浙江零跑科技股份有限公司 Active lane change planning method based on structured road sampling
CN113886764B (en) * 2021-10-28 2024-05-03 哈尔滨工业大学 Intelligent vehicle multi-scene track planning method based on Frenet coordinate system
CN113886764A (en) * 2021-10-28 2022-01-04 哈尔滨工业大学 Intelligent vehicle multi-scene track planning method based on Frenet coordinate system
CN114194215A (en) * 2021-12-30 2022-03-18 江苏大学 Intelligent vehicle obstacle avoidance and track changing planning method and system
CN114194215B (en) * 2021-12-30 2024-05-10 江苏大学 Intelligent vehicle obstacle avoidance lane change track planning method and system
CN115195743A (en) * 2022-09-16 2022-10-18 毫末智行科技有限公司 Automatic lane changing method, device, equipment and medium for vehicle based on unmanned driving
CN117284297B (en) * 2023-11-27 2024-02-27 福思(杭州)智能科技有限公司 Vehicle control method and device and domain controller
CN117284297A (en) * 2023-11-27 2023-12-26 福思(杭州)智能科技有限公司 Vehicle control method and device and domain controller
CN117698730A (en) * 2024-01-08 2024-03-15 昆明理工大学 Optimal lane change track planning method for anti-collision dynamic intelligent network-connected vehicle
CN117698730B (en) * 2024-01-08 2024-05-31 昆明理工大学 Optimal lane change track planning method for anti-collision dynamic intelligent network-connected vehicle

Also Published As

Publication number Publication date
CN112965489B (en) 2022-04-08

Similar Documents

Publication Publication Date Title
CN112965489B (en) Intelligent vehicle high-speed lane change planning method based on collision detection
CN110329263B (en) Self-adaptive track changing planning method for automatic driving vehicle
US11049398B2 (en) Surrounding environment recognizing apparatus
JP6232004B2 (en) Method for performing risk-based traffic scene analysis by advanced driver assistance system, and vehicle equipped with the system for performing the analysis
CN108062600B (en) Vehicle collision early warning method and device based on rectangular modeling
CN101395648B (en) Vehicle path determining method and vehicle course determining device
JP5407764B2 (en) Driving assistance device
JP4254844B2 (en) Travel control plan evaluation device
JP5082433B2 (en) Method, apparatus, and program for determining surrounding object risk
JP4946739B2 (en) Mobile body course acquisition method and mobile body course acquisition apparatus
CN111338335A (en) Vehicle local track planning method under structured road scene
Tang et al. Modeling drivers' dynamic decision-making behavior during the phase transition period: An analytical approach based on hidden markov model theory
CN112349141B (en) Front collision control method, front collision early warning device and automobile
JP2008123217A (en) Obstacle course predicting method, device and program
JP2006327545A (en) Device and method for calculating traveling pattern of traveling object
WO2022053026A1 (en) Automatic driving meeting scene processing method and apparatus, vehicle, and storage medium
CN112258893B (en) Intelligent vehicle lane change collision probability assessment method based on track prediction
CN114543827A (en) Path planning method and device
CN113655469A (en) Method and system for predicting and sensing object in blind area based on intelligent driving
Aoki et al. Multicruise: eco-lane selection strategy with eco-cruise control for connected and automated vehicles
Weisswange et al. Intelligent traffic flow assist: Optimized highway driving using conditional behavior prediction
CN115662131A (en) Multi-lane cooperative lane changing method for road accident section in networking environment
CN114132311A (en) Method and module for screening dangerous targets for automatic emergency braking of vehicle
CN117707163A (en) Emergency obstacle avoidance method and system for unmanned vehicle
JP2022086680A (en) Behavior prediction device

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