CN117698730A - Optimal lane change track planning method for anti-collision dynamic intelligent network-connected vehicle - Google Patents
Optimal lane change track planning method for anti-collision dynamic intelligent network-connected vehicle Download PDFInfo
- Publication number
- CN117698730A CN117698730A CN202410025717.5A CN202410025717A CN117698730A CN 117698730 A CN117698730 A CN 117698730A CN 202410025717 A CN202410025717 A CN 202410025717A CN 117698730 A CN117698730 A CN 117698730A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- intelligent network
- connected vehicle
- lane change
- 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
Links
- 230000008859 change Effects 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 10
- 230000001133 acceleration Effects 0.000 claims description 37
- 230000014509 gene expression Effects 0.000 claims description 27
- 230000036461 convulsion Effects 0.000 claims description 10
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 abstract description 4
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of automatic driving of vehicles, and discloses an anti-collision dynamic intelligent network-connected vehicle optimal lane change track planning method. According to the method, the optimal lane change track planning and the real-time collision detection are combined, the optimal lane change track of each time step is calculated, the collision detection is carried out on the potential collision risk in each time step, the real-time collision avoidance in the lane change process can be realized, and the safety and the comfort of lane change behaviors are improved.
Description
Technical Field
The invention relates to the technical field of automatic driving of vehicles, in particular to an optimal lane change track planning method of an anti-collision dynamic intelligent network-connected vehicle.
Background
With the continuous development of global economy and the acceleration of urban process, road traffic jam has become a ubiquitous problem, and road switching is one of the most common driving behaviors of intelligent network vehicles, so that the traffic and safety of roads are greatly affected. The safe, quick and stable lane change behavior can improve the traffic efficiency and reduce the occurrence of traffic accidents. The reasonable lane change track is a precondition that the intelligent network-connected vehicle safely completes the lane change task, and meanwhile, the performance of the intelligent network-connected vehicle also determines the safety, the high efficiency and the comfort of the lane change process.
The automatic lane changing is composed of a decision module, a track planning module and an execution module, wherein the decision module acquires information around the intelligent network-connected vehicle by using a sensor and V2V communication to carry out lane changing decision judgment, the track planning module plans a lane changing track which has no collision and meets the vehicle dynamics constraint aiming at the lane changing decision, and the execution module carries out lane changing according to the lane changing track.
The prior method has the defects that: the lane change is regarded as a static process, acceleration and deceleration of surrounding vehicles in the lane change process are not considered, the problem of real-time collision is not considered, rear-end collision of the vehicles is easy to cause, and a real driving scene cannot be represented.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides an optimal lane change track planning method for an anti-collision dynamic intelligent network-connected vehicle, which has the advantages of comfortable and safe lane change and the like and solves the technical problems.
(II) technical scheme
In order to achieve the above purpose, the present invention provides the following technical solutions: an optimal lane change track planning method of an anti-collision dynamic intelligent network-connected vehicle comprises the following steps:
s1, establishing a lane change track planning equation of an intelligent network-connected vehicle M based on a quintuple polynomial;
s2, constructing an intelligent network vehicle M channel changing comfort function, a channel changing efficiency function and a total cost function;
s3, constructing vehicle dynamics constraint and traffic rule constraint of lane change of the intelligent network-connected vehicle M;
s4, matching the function established in the step S2 with the track planning equation established in the step S1, solving the nonlinear programming problem by adopting a sequence quadratic method under the constraint of the step S3, and calculating an optimal track change track;
s5, the intelligent network-connected vehicle M executes collision detection, and whether the next time step has collision risk is judged; if the next time step does not have collision risk, executing step S6; if the next time step has collision risk, executing step S7;
s6, the intelligent network-connected vehicle M performs lane change according to the optimal lane change track in a fixed time step and judges whether the lane change is completed, if the lane change is completed, the intelligent network-connected vehicle M completes lane change; if the lane change is not completed, the intelligent network vehicle M takes the position of the intelligent network vehicle M as a starting point, and executes the steps S1-S4 to re-plan the optimal lane change track;
s7, the intelligent network-connected vehicle M starts from the current position, steps S1-S4 are executed, the optimal lane change track of the intelligent network-connected vehicle M returning to the original lane is calculated, and the intelligent network-connected vehicle M returns to the original lane according to the optimal lane change track of the intelligent network-connected vehicle M returning to the original lane.
As a preferable technical scheme of the invention, the track equation establishing process of the step S1 specifically comprises the following steps:
s1.1, decoupling channel changing motion into two orthogonal directions: a longitudinal direction (X direction) and a transverse direction (Y direction) are utilized to construct a track planning equation in each direction of the intelligent network vehicle M by utilizing a fifth-order polynomial;
s1.2, establishing an intelligent network connection vehicle M at the initial time t of channel change i And a final time t f Displacement, velocity and acceleration equations of (2);
s1.3, initializing related variables;
and S1.4, calculating the track planning equation coefficient in the step S1.
As a preferred embodiment of the present invention, the trajectory planning equation expression in the step S1.1 is:
wherein x (t) and y (t) respectively represent the longitudinal position and the transverse position of the vehicle at the moment t, a i (i=1, 2,3,4, 5) and b i (i=1, 2,3,4, 5) represents the coefficient to be determined, and the expression of the displacement, velocity and acceleration equations in step S1.2 is as follows:
wherein x (t) i )、Respectively representing the initial time t of lane change of the vehicle in the x direction i Position, velocity, acceleration, x (t) f )、/>Respectively representing the final time t of lane change of the vehicle in the x direction f Position, velocity, acceleration, y (t) i )、Respectively representing the initial time t of lane change of the vehicle in the y direction i Position, velocity, acceleration, y (t) f )、Respectively representing the final time t of lane change of the vehicle in the y direction f Position, velocity, acceleration of (c).
As a preferred embodiment of the present invention, the initialization expression of the step S1.3 is as follows:
wherein x is f Is the final position of the vehicle in the x-direction, W lane For the width of the lane, v M 、v C Representing the speed of the current vehicle and the speed of the vehicle in front of the target lane of the vehicle respectively, the step S1.4 is to a i (i=1, 2,3,4, 5) and b i (i=1, 2,3,4, 5).
As a preferred embodiment of the present invention, the lane change comfort function J in step S2 comfort The expression of (2) is as follows:
wherein w is 1 And w 2 As the weight coefficient, j x (t) is the acceleration in the x direction at the time t, j y (t) is the jerk in the y direction at time t, j x,max 、j y,max Maximum jerk, t in x-direction and y-direction respectively i 、t f Respectively representing the initial time and the final time of lane change of the vehicle, a x,max 、a y,max The maximum acceleration in the x direction and the y direction are respectively indicated,representing the integration of the internal function, the lane change efficiency function J in step S2 efficiency The expression of (2) is as follows:
J efficiency ＝w 3 (x f -x i )+w 4 (t f -t i )
wherein w is 3 And w 4 As the weight coefficient, x i 、x f Respectively representing the x-direction position of the initial channel switching time and the x-direction position of the final channel switching time of the intelligent network vehicle M, wherein the total Cost function Cost (x f ，x i ) The expression of (2) is as follows:
Cost(x f ，x i )＝J efficiency +J comfort
as a preferred technical solution of the present invention, the specific expressions of the vehicle dynamics constraint and the traffic rule constraint in the step S3 are as follows:
wherein v is x,max 、v y,max Maximum speeds in the x-direction and the y-direction, a x,max 、a y,max Maximum acceleration in x direction, maximum acceleration in y direction, maximum acceleration in j direction x,max 、j y,max Maximum jerk in x-direction, y-direction, s.t. represents constraint,representing the minimization of the internal function.
As a preferred technical solution of the present invention, the collision detection in step S5 specifically includes the following steps:
s5.1, modeling an intelligent network vehicle M by adopting a dynamic rectangle; the center of the rectangular model serves as the deflection center of the intelligent networked vehicle M,the deflection center coordinates are (X) M (t),Y M (t)) and the coordinates of the rectangular vertices of the intelligent networked vehicle M before deflection are expressed as (X) o (t),Y o (t)), o=1, 2,3,4, and the coordinates of the rectangular vertices after deflection are expressed as (X) o '(t),Y o 't'), o=1, 2,3,4, wherein the point corresponding to o=1 represents the right front vertex of the rectangular model of the intelligent network connected vehicle M, the point corresponding to o=2 represents the left front Fang Dingdian of the rectangular model of the intelligent network connected vehicle M, the point corresponding to o=3 represents the left rear vertex of the rectangular model of the intelligent network connected vehicle M, and the point corresponding to o=4 represents the right rear vertex of the rectangular model of the intelligent network connected vehicle M;
s5.2, calculating coordinates of each point;
s5.3, setting and defining frame fixed points of an intelligent network-connected vehicle M rectangular model;
s5.4, calculating safety constraint between the intelligent network-connected vehicle M and the front vehicle A of the original lane of the intelligent network-connected vehicle M;
s5.5, calculating safety constraint between the intelligent network-connected vehicle M and the front vehicle C of the target lane of the intelligent network-connected vehicle M;
s5.6, calculating the safety constraint between the intelligent network-connected vehicle M and the vehicle B behind the target lane of the intelligent network-connected vehicle M.
As a preferred technical solution of the present invention, the calculation formula of step S5.2 is as follows:
wherein R represents the distance between the deflection center and each rectangular vertex, L is the intelligent network vehicle length, W is the intelligent network vehicle width, and θ (t) representsThe off angle of the intelligent network vehicle, a is a rectangular model (X 1 (t),Y 1 (t)) and the horizontal direction, cos (x) represents a cosine function, sin (x) represents a sine function, and the parameters of the rectangular model in step S5.3 are set as follows:
the left side frame of the rectangular model of the intelligent network-connected vehicle M after deflection is L2, the right side frame is L5, the front side frame is L4, the rear side frame of the rectangular model of the intelligent network-connected vehicle M original lane front vehicle A is L1, the left side frame of the rectangular model of the intelligent network-connected vehicle M target lane front vehicle C is L3, the front side frame of the rectangular model of the intelligent network-connected vehicle M target lane rear vehicle B is L6, the left front vertex of the rectangular model of the intelligent network-connected vehicle M after deflection is assumed to be point 1, the right front vertex is point 3, the right rear vertex is point 6, the right rear vertex of the rectangular model of the intelligent network-connected vehicle M original lane front vehicle A is point 2, the left rear vertex of the rectangular model of the intelligent network-connected vehicle M target lane front vehicle C after deflection is point 4, and the left front vertex of the rectangular model of the intelligent network-connected vehicle M target lane rear vehicle B after deflection is point 5.
As a preferred technical solution of the present invention, the safety constraint expression between the intelligent network-connected vehicle M and the original lane front vehicle a of the intelligent network-connected vehicle M in the step S5.4 is as follows:
wherein X is M (t)、Y M (t) is the center coordinate, X, of the intelligent network vehicle M A (t)、Y A (t) is the center coordinate of the front vehicle A of the original lane of the intelligent network-connected vehicle M, tan alpha represents the tangent function of the deflection angle alpha, L A Representing the length, d, of the front vehicle A of the original lane of the intelligent network-connected vehicle M M,safe1 (t) is the minimum safety distance between the intelligent network vehicle M and the front vehicle A of the original lane of the intelligent network vehicle M, and the step S5.5 is that the intelligent network vehicle M and the intelligent network vehicle M are in front of the target laneThe safety constraint expression between vehicles C is as follows:
wherein X is C (t)、Y C (t) is the central coordinate of the front vehicle C of the target lane of the intelligent network-connected vehicle M, d M,safe2 (t) represents the minimum safe distance between the intelligent network-connected vehicle M and the vehicle C in front of the target lane of the intelligent network-connected vehicle M,representation pairAnd (3) performing tangent operation, wherein the safety constraint expression between the intelligent network-connected vehicle M and the intelligent network-connected vehicle M target lane rear vehicle B in the step S5.6 is as follows:
wherein X is B (t)、Y B (t) center coordinates, d of the rear vehicle B of the target lane of the intelligent network-connected vehicle M M,safe3 And (t) is the minimum safety distance between the intelligent network-connected vehicle M and the vehicle B behind the target lane of the intelligent network-connected vehicle M.
As a preferred solution of the present invention, in the case that the collision detection in step S5 does not meet the safety constraint, the intelligent network vehicle M will immediately stop lane change and begin planning the optimal lane change track to return to the original lane.
Compared with the prior art, the invention provides an optimal lane change track planning method for an anti-collision dynamic intelligent network-connected vehicle, which has the following beneficial effects:
1. according to the method, the optimal lane change track planning and the real-time collision detection are combined, the optimal lane change track of each time step is calculated, the collision detection is carried out on the potential collision risk in each time step, and if the potential collision exists, the optimal track returned to the original lane is calculated and returned to the original lane; the real-time collision avoidance in the lane changing process can be realized, and the safety and the comfort of lane changing behavior can be improved.
2. The track change track is established by using the quintic polynomial curve, the curve has fourth-order smoothness, and the position, the speed, the acceleration and the jerk of the intelligent network-connected vehicle are continuous in the whole track change process, so that the track change track has good comfortableness.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 is a schematic diagram of dynamic deflection of a rectangular vehicle model of the present invention;
FIG. 3 is a schematic diagram of an analysis scenario for collision avoidance detection according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-3, an optimal lane change track planning method for an anti-collision dynamic intelligent network-connected vehicle includes the following steps:
s1, establishing a lane change track planning equation of the intelligent network vehicle M based on a quintic polynomial, wherein the lane change motion is decoupled into two orthogonal directions: longitudinal (X-direction) and transverse (Y-direction) track planning equations for each direction of intelligent networked vehicle M using a fifth order polynomial
Wherein x (t) and y (t) respectively represent the longitudinal position and the transverse position of the vehicle at the moment t, a i (i=1, 2,3,4, 5) and b i (i=1, 2,3,4, 5) represents the coefficient to be determined, after which the intelligent network vehicle M is established at the initial time t of lane change i And a final time t f Displacement, velocity and acceleration equations:
wherein x (t) i )、Respectively representing the initial time t of lane change of the vehicle in the x direction i Position, velocity, acceleration, x (y) f )、/>Respectively representing the final time t of lane change of the vehicle in the x direction f Position, velocity, acceleration, y (t) i )、Respectively representing the initial time t of lane change of the vehicle in the y direction i Position, velocity, acceleration, y (t) f )、Respectively representing the final time t of lane change of the vehicle in the y direction f The initial position and the final position of the intelligent network vehicle M in the y direction have zero speed and acceleration, and the initial position and the final position of the intelligent network vehicle M in the x direction have zero acceleration, and can be deduced to beThe following equation:
wherein x is f Is the final position of the vehicle in the x-direction, W lane For the width of the lane, v M 、v C Respectively representing the speeds of the current vehicle M and the front vehicle C of the target lane of the vehicle M;
finally substituting the displacement, speed and acceleration equation into the track planning equation, and then substituting the coefficient, a i (i=1, 2,3,4, 5) and b i (i=1, 2,3,4, 5) can be represented by x f And t f The following is indicated:
s2, constructing an intelligent network vehicle M channel change comfort function, a channel change efficiency function and a total cost function, and a channel change comfort function J comfort The expression of (2) is as follows:
wherein w is 1 And w 2 As the weight coefficient, j x (t) is the acceleration in the x direction at the time t, j y (t) is the jerk in the y direction at time t, j x,max 、j y,max Maximum jerk, t in x-direction and y-direction respectively i 、t f Respectively representing the initial time and the final time of lane change of the vehicle, a x,max 、a y,max Respectively indicate the x direction and the y directionIs used for the acceleration of the vehicle,representing the integration of the internal function, the lane change efficiency function J in step S2 efficiency The expression of (2) is as follows:
J efficiency ＝w 3 (x f -x i )+w 4 (t f -t i )
wherein w is 3 And w 4 As the weight coefficient, x i 、x f Respectively representing the x-direction position of the initial channel switching time and the x-direction position of the final channel switching time of the intelligent network vehicle M, wherein the total Cost function Cost (x f ，x i ) The expression of (2) is as follows:
Cost(x f ，x i )＝J efficiency +J comfort
s3, constructing vehicle dynamics constraint and traffic rule constraint of lane change of the intelligent network-connected vehicle M, wherein the specific expression is as follows:
wherein v is x,max 、v y,max Maximum speeds in the x-direction and the y-direction, a x,max 、a y,max Maximum acceleration in x direction, maximum acceleration in y direction, maximum acceleration in j direction x,max 、j y,max Maximum jerk in x-direction, y-direction, s.t. represents constraint,representing taking a minimum value for the internal function;
s4, matching the function established in the step S2 with the track planning equation established in the step S1, solving the nonlinear programming problem by adopting a sequence quadratic method under the constraint of the step S3, and calculating an optimal track change track;
s5, the intelligent network-connected vehicle M executes collision detection, and whether the next time step has collision risk is judged; if the next time step does not have collision risk, executing step S6; if the next time step has collision risk, executing step S7;
s5.1, modeling an intelligent network vehicle M by adopting a dynamic rectangle; the center of the rectangular model is used as the deflection center of the intelligent network vehicle M, and the deflection center coordinates are (X M (t),Y M (t)) and the coordinates of the rectangular vertices of the intelligent networked vehicle M before deflection are expressed as (X) o (t),Y o (t)), o=1, 2,3,4, and the coordinates of the rectangular vertices after deflection are expressed as (X) o '(t),Y o 't'), o=1, 2,3,4, wherein the point corresponding to o=1 represents the right front vertex of the rectangular model of the intelligent network connected vehicle M, the point corresponding to o=2 represents the left front Fang Dingdian of the rectangular model of the intelligent network connected vehicle M, the point corresponding to o=3 represents the left rear vertex of the rectangular model of the intelligent network connected vehicle M, and the point corresponding to o=4 represents the right rear vertex of the rectangular model of the intelligent network connected vehicle M;
s5.2, calculating the coordinates of each point, wherein the calculation formula is as follows:
wherein R represents the distance between the deflection center and each rectangular vertex, L is the intelligent network vehicle length, W is the intelligent network vehicle width, θ (t) represents the deflection angle of the intelligent network vehicle, a is the rectangular model (X 1 (t),Y 1 (t) an angle with the horizontal direction, cos (x) representing a cosine function and sin (x) representing a sine function;
s5.3, setting and defining the frame fixed points of an intelligent network-connected vehicle M rectangular model, wherein the left side frame of the deflected intelligent network-connected vehicle M rectangular model is L2, the right side frame is L5, the front side frame is L4, the rear side frame of an intelligent network-connected vehicle M original lane front vehicle A rectangular model is L1, the left side frame of an intelligent network-connected vehicle M target lane front vehicle C rectangular model is L3, the front side frame of the intelligent network-connected vehicle M target lane rear vehicle B rectangular model is L6, the left front side vertex of the deflected intelligent network-connected vehicle M rectangular model is assumed to be point 1, the right front side vertex is point 3, the right rear side vertex is point 6, the right rear side vertex of the deflected intelligent network-connected vehicle M original lane front vehicle A rectangular model is point 2, the left rear vertex of the deflected intelligent network-connected vehicle M target lane front vehicle C rectangular model is point 4, and the left front side vertex of the deflected intelligent network-connected vehicle M target lane rear vehicle B rectangular model is point 5;
s5.4, calculating safety constraint between the intelligent network-connected vehicle M and the front vehicle A of the original lane of the intelligent network-connected vehicle M, wherein the expression is as follows:
wherein X is M (t)、Y M (t) is the center coordinate, X, of the intelligent network vehicle M A (t)、Y A (t) is the center coordinate of the front vehicle A of the original lane of the intelligent network-connected vehicle M, tan alpha represents the tangent function of the deflection angle alpha, L A Representing the length, d, of the front vehicle A of the original lane of the intelligent network-connected vehicle M M,safe1 (t) is the minimum safe distance between the intelligent network-connected vehicle M and the front vehicle A of the original lane of the intelligent network-connected vehicle M;
s5.5, calculating safety constraint between the intelligent network-connected vehicle M and the intelligent network-connected vehicle M target lane front vehicle C, wherein the expression is as follows:
wherein X is C (t)、Y C (t) is the central coordinate of the front vehicle C of the target lane of the intelligent network-connected vehicle M, d M,safe2 (t) represents the minimum safe distance between the intelligent network-connected vehicle M and the vehicle C in front of the target lane of the intelligent network-connected vehicle M,representation pairPerforming tangent operation;
s5.6, calculating safety constraint between the intelligent network-connected vehicle M and the intelligent network-connected vehicle M target lane rear vehicle B, wherein the expression is as follows:
wherein X is B (t)、Y B (t) center coordinates, d of the rear vehicle B of the target lane of the intelligent network-connected vehicle M M,safe3 And (t) is the minimum safety distance between the intelligent network-connected vehicle M and the vehicle N behind the target lane of the intelligent network-connected vehicle M.
S6, the intelligent network-connected vehicle M performs lane change according to the optimal lane change track in a fixed time step and judges whether the lane change is completed, if the lane change is completed, the intelligent network-connected vehicle M completes lane change; if the lane change is not completed, the intelligent network vehicle M takes the position of the intelligent network vehicle M as a starting point, and executes the steps S1-S4 to re-plan the optimal lane change track;
s7, the intelligent network-connected vehicle M starts from the current position, steps S1-S4 are executed, the optimal lane change track of the intelligent network-connected vehicle M returning to the original lane is calculated, and the intelligent network-connected vehicle M returns to the original lane according to the optimal lane change track of the intelligent network-connected vehicle M returning to the original lane.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. An optimal lane change track planning method of an anti-collision dynamic intelligent network-connected vehicle is characterized by comprising the following steps of: the method comprises the following steps:
s1, establishing a lane change track planning equation of an intelligent network-connected vehicle M based on a quintuple polynomial;
s2, constructing an intelligent network vehicle M channel changing comfort function, a channel changing efficiency function and a total cost function;
s3, constructing vehicle dynamics constraint and traffic rule constraint of lane change of the intelligent network-connected vehicle M;
s4, matching the function established in the step S2 with the track planning equation established in the step S1, solving the nonlinear programming problem by adopting a sequence quadratic method under the constraint of the step S3, and calculating an optimal track change track;
s5, the intelligent network-connected vehicle M executes collision detection, and whether the next time step has collision risk is judged; if the next time step does not have collision risk, executing step S6; if the next time step has collision risk, executing step S7;
s6, the intelligent network vehicle M carries out lane change according to the optimal lane change track by a fixed time step and judges whether the lane change is completed, if the lane change is completed, the intelligent network vehicle M carries out the steps S1-S4 by taking the position of the intelligent network vehicle M as a starting point, and if the lane change is not completed, the optimal lane change track is planned again;
s7, the intelligent network-connected vehicle M starts from the current position, steps S1-S4 are executed, the optimal lane change track of the intelligent network-connected vehicle M returning to the original lane is calculated, and the intelligent network-connected vehicle M returns to the original lane according to the optimal lane change track of the intelligent network-connected vehicle M returning to the original lane.
2. The method for planning the optimal lane change track of the anti-collision dynamic intelligent network-connected vehicle according to claim 1, which is characterized in that: the track equation establishing process in the step S1 specifically comprises the following steps:
s1.1, decoupling channel changing motion into two orthogonal directions: a longitudinal direction (X direction) and a transverse direction (Y direction) are utilized to construct a track planning equation in each direction of the intelligent network vehicle M by utilizing a fifth-order polynomial;
s1.2, establishing an intelligent network connection vehicle M at the initial time t of channel change i And a final time t f Displacement, velocity and acceleration equations of (2);
s1.3, initializing related variables;
and S1.4, calculating the track planning equation coefficient in the step S1.
3. The method for planning the optimal lane change track of the anti-collision dynamic intelligent network-connected vehicle according to claim 2, which is characterized in that: the trajectory planning equation expression in step S1.1 is as follows:
wherein x (t) and y (t) respectively represent the longitudinal position and the transverse position of the vehicle at the moment t, a i (i=1, 2,3,4, 5) and b i (i=1, 2,3,4, 5) represents the coefficient to be determined, and the expression of the displacement, velocity and acceleration equations in step S1.2 is as follows:
wherein x (t) i )、Respectively representing the initial time t of lane change of the vehicle in the x direction i Position, velocity, acceleration, x (t) f )、/>Respectively representing the final time t of lane change of the vehicle in the x direction f Position, velocity, acceleration, y (t) i )、Respectively representing the initial time t of lane change of the vehicle in the y direction i Position, velocity, acceleration, y (t) f )、Respectively representing the final time t of lane change of the vehicle in the y direction f Position, velocity, acceleration of (c).
4. The method for planning the optimal lane change track of the anti-collision dynamic intelligent network-connected vehicle according to claim 3, wherein the method comprises the following steps of: the initialization expression of step S1.3 is as follows:
wherein x is f Is the final position of the vehicle in the x-direction, W lane For the width of the lane, v M 、v C Representing the speed of the current vehicle and the speed of the vehicle in front of the target lane of the vehicle respectively, the step S1.4 is to a i (i=1, 2,3,4, 5) and b i (i=1, 2,3,4, 5).
5. The method for planning the optimal lane change track of the anti-collision dynamic intelligent network-connected vehicle according to claim 1, which is characterized in that: channel changing comfort in the step S2Moderating function J comfort The expression of (2) is as follows:
wherein w is 1 And w 2 As the weight coefficient, j x (t) is the acceleration in the x direction at the time t, j y (t) is the jerk in the y direction at time t, j x,max 、j y,max Maximum jerk, t in x-direction and y-direction respectively i 、t f Respectively representing the initial time and the final time of lane change of the vehicle, a x,max 、a y,max The maximum acceleration in the x direction and the y direction are respectively indicated,representing the integration of the internal function, the lane change efficiency function J in step S2 efficiency The expression of (2) is as follows:
J efficiency ＝w 3 (x f -x i )+w 4 (t f -t i )
wherein w is 3 And w 4 As the weight coefficient, x i 、x f Respectively representing the x-direction position of the initial channel switching time and the x-direction position of the final channel switching time of the intelligent network vehicle M, wherein the total Cost function Cost (x f ，x i ) The expression of (2) is as follows:
Cost(x f ，x i )＝j efficiency +J comfort 。
6. the method for planning the optimal lane change track of the anti-collision dynamic intelligent network-connected vehicle according to claim 5, which is characterized in that: the specific expressions of the vehicle dynamics constraint and the traffic rule constraint in the step S3 are as follows:
wherein v is x,max 、v y,max Maximum speeds in the x-direction and the y-direction, a x,max 、a y,max Maximum acceleration in x direction, maximum acceleration in y direction, maximum acceleration in j direction x,max 、j y,max Maximum jerk in x-direction, y-direction, s.t. represents constraint,representing the minimization of the internal function.
7. The method for planning the optimal lane change track of the anti-collision dynamic intelligent network-connected vehicle according to claim 1, which is characterized in that: the collision detection process in step S5 is specifically as follows:
s5.1, modeling an intelligent network vehicle M by adopting a dynamic rectangle; the center of the rectangular model is used as the deflection center of the intelligent network vehicle M, and the deflection center coordinates are (X M (t),Y M (t)) and the coordinates of the rectangular vertices of the intelligent networked vehicle M before deflection are expressed as (X) o (t),Y o (t)), o=1, 2,3,4, and the coordinates of the rectangular vertices after deflection are expressed as (X) o '(t),Y o 't'), o=1, 2,3,4, wherein the point corresponding to o=1 represents the right front vertex of the rectangular model of the intelligent network connected vehicle M, the point corresponding to o=2 represents the left front Fang Dingdian of the rectangular model of the intelligent network connected vehicle M, the point corresponding to o=3 represents the left rear vertex of the rectangular model of the intelligent network connected vehicle M, and the point corresponding to o=4 represents the right rear vertex of the rectangular model of the intelligent network connected vehicle M;
s5.2, calculating coordinates of each point;
s5.3, setting and defining frame fixed points of an intelligent network-connected vehicle M rectangular model;
s5.4, calculating safety constraint between the intelligent network-connected vehicle M and the front vehicle A of the original lane of the intelligent network-connected vehicle M;
s5.5, calculating safety constraint between the intelligent network-connected vehicle M and the front vehicle C of the target lane of the intelligent network-connected vehicle M;
s5.6, calculating the safety constraint between the intelligent network-connected vehicle M and the vehicle B behind the target lane of the intelligent network-connected vehicle M.
8. The method for planning the optimal lane change track of the anti-collision dynamic intelligent network-connected vehicle according to claim 7, wherein the method comprises the following steps of: the calculation formula of the step S5.2 is as follows:
wherein R represents the distance between the deflection center and each rectangular vertex, L is the intelligent network vehicle length, W is the intelligent network vehicle width, θ (t) represents the deflection angle of the intelligent network vehicle, a is the rectangular model (X 1 (t),Y 1 (t)) and the horizontal direction, cos (x) represents a cosine function, sin (x) represents a sine function, and the parameters of the rectangular model in step S5.3 are set as follows:
the left side frame of the rectangular model of the intelligent network-connected vehicle M after deflection is L2, the right side frame is L5, the front side frame is L4, the rear side frame of the rectangular model of the intelligent network-connected vehicle M original lane front vehicle A is L1, the left side frame of the rectangular model of the intelligent network-connected vehicle M target lane front vehicle C is L3, the front side frame of the rectangular model of the intelligent network-connected vehicle M target lane rear vehicle B is L6, the left front vertex of the rectangular model of the intelligent network-connected vehicle M after deflection is assumed to be point 1, the right front vertex is point 3, the right rear vertex is point 6, the right rear vertex of the rectangular model of the intelligent network-connected vehicle M original lane front vehicle A is point 2, the left rear vertex of the rectangular model of the intelligent network-connected vehicle M target lane front vehicle C after deflection is point 4, and the left front vertex of the rectangular model of the intelligent network-connected vehicle M target lane rear vehicle B after deflection is point 5.
9. The method for planning the optimal lane change track of the anti-collision dynamic intelligent network-connected vehicle according to claim 8, which is characterized in that: the safety constraint expression between the intelligent network-connected vehicle M and the intelligent network-connected vehicle M original lane front vehicle a in the step S5.4 is as follows:
wherein X is M (t)、Y M (t) is the center coordinate, X, of the intelligent network vehicle M A (t)、Y A (t) is the center coordinate of the front vehicle A of the original lane of the intelligent network-connected vehicle M, tan alpha a represents the tangent function of the deflection angle alpha, L A Representing the length, d, of the front vehicle A of the original lane of the intelligent network-connected vehicle M M,safe1 (t) is the minimum safety distance between the intelligent network-connected vehicle M and the intelligent network-connected vehicle original lane front vehicle A, and the safety constraint expression between the intelligent network-connected vehicle M and the intelligent network-connected vehicle M target lane front vehicle C in the step S5.5 is as follows:
wherein X is C (t)、Y C (t) is the central coordinate of the front vehicle C of the target lane of the intelligent network-connected vehicle M, d M,safe2 (t) represents the minimum safe distance between the intelligent network-connected vehicle M and the vehicle C in front of the target lane of the intelligent network-connected vehicle M,representation pairAnd (3) performing tangent operation, wherein the safety constraint expression between the intelligent network-connected vehicle M and the intelligent network-connected vehicle M target lane rear vehicle B in the step S5.6 is as follows:
wherein X is B (t)、Y B (t) center coordinates, d of the rear vehicle B of the target lane of the intelligent network-connected vehicle M M,safe3 (t) is the minimum safe distance between the intelligent network vehicle M and the vehicle B behind the target lane of the intelligent network vehicle M, tan [ theta (t) ]]The tangent operation of θ (t) is shown.
10. The method for planning the optimal lane change track of the anti-collision dynamic intelligent network-connected vehicle according to claim 9, wherein the method comprises the following steps of: in the case that the collision detection in step S5 does not meet the safety constraint, the intelligent network-connected vehicle M immediately stops lane change and starts planning the optimal lane change track to return to the original lane.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410025717.5A CN117698730B (en) | 2024-01-08 | 2024-01-08 | Optimal lane change track planning method for anti-collision dynamic intelligent network-connected vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410025717.5A CN117698730B (en) | 2024-01-08 | 2024-01-08 | Optimal lane change track planning method for anti-collision dynamic intelligent network-connected vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117698730A true CN117698730A (en) | 2024-03-15 |
| CN117698730B CN117698730B (en) | 2024-05-31 |
Family
ID=90144491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410025717.5A Active CN117698730B (en) | 2024-01-08 | 2024-01-08 | Optimal lane change track planning method for anti-collision dynamic intelligent network-connected vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117698730B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150073663A1 (en) * | 2013-09-12 | 2015-03-12 | Volvo Car Corporation | Manoeuver generation for automated driving |
| CN106926844A (en) * | 2017-03-27 | 2017-07-07 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track based on real time environment information |
| CN107315411A (en) * | 2017-07-04 | 2017-11-03 | 合肥工业大学 | A kind of lane-change method for planning track based on automatic driving vehicle under collaborative truck |
| 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 |
| 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 |
| CN112965489A (en) * | 2021-02-05 | 2021-06-15 | 北京理工大学 | Intelligent vehicle high-speed lane change planning method based on collision detection |
| WO2022148282A1 (en) * | 2021-01-07 | 2022-07-14 | 腾讯科技（深圳）有限公司 | Method and apparatus for planning trajectory of vehicle, storage medium, and device |
| CN115140093A (en) * | 2022-07-18 | 2022-10-04 | 东南大学 | Real-time trajectory planning method |
-
2024
- 2024-01-08 CN CN202410025717.5A patent/CN117698730B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150073663A1 (en) * | 2013-09-12 | 2015-03-12 | Volvo Car Corporation | Manoeuver generation for automated driving |
| CN106926844A (en) * | 2017-03-27 | 2017-07-07 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track based on real time environment information |
| CN107315411A (en) * | 2017-07-04 | 2017-11-03 | 合肥工业大学 | A kind of lane-change method for planning track based on automatic driving vehicle under collaborative truck |
| 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 |
| 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 |
| WO2022148282A1 (en) * | 2021-01-07 | 2022-07-14 | 腾讯科技（深圳）有限公司 | Method and apparatus for planning trajectory of vehicle, storage medium, and device |
| CN112965489A (en) * | 2021-02-05 | 2021-06-15 | 北京理工大学 | Intelligent vehicle high-speed lane change planning method based on collision detection |
| CN115140093A (en) * | 2022-07-18 | 2022-10-04 | 东南大学 | Real-time trajectory planning method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117698730B (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ersal et al. | Connected and automated road vehicles: state of the art and future challenges | |
| EP4141736A1 (en) | Lane tracking method and apparatus | |
| CN111653113B (en) | Method, device, terminal and storage medium for determining local path of vehicle | |
| WO2017022447A1 (en) | Vehicle control device, vehicle control method and vehicle control program | |
| CN108088456A (en) | A kind of automatic driving vehicle local paths planning method with time consistency | |
| CN108919795A (en) | A kind of autonomous driving vehicle lane-change decision-making technique and device | |
| US20230286536A1 (en) | Systems and methods for evaluating domain-specific navigation system capabilities | |
| EP4030403A1 (en) | Method and device for predicting exit for vehicle | |
| CN108446463B (en) | Microcosmic traffic flow collaborative simulation platform, simulation method and safety evaluation method | |
| CN113689735B (en) | Vehicle lane change collision early warning method and device | |
| Jayawardana et al. | Learning eco-driving strategies at signalized intersections | |
| CN112046484A (en) | Q learning-based vehicle lane-changing overtaking path planning method | |
| WO2023231569A1 (en) | Bayesian-game-based vehicle-road cooperative decision-making algorithm for lane changing behavior of autonomous vehicle | |
| CN114945959B (en) | Driving track determining method, device, computer equipment and storage medium | |
| US20240174221A1 (en) | Vehicle decision-making planning method and apparatus, device and medium | |
| CN113848914A (en) | Collision coefficient artificial potential field method local path planning method in dynamic environment | |
| Zhang et al. | Structured road-oriented motion planning and tracking framework for active collision avoidance of autonomous vehicles | |
| Lattarulo et al. | Real-time trajectory planning method based on n-order curve optimization | |
| Malayjerdi et al. | Practical path planning techniques in overtaking for autonomous shuttles | |
| 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 | |
| Guo et al. | Self-defensive coordinated maneuvering of an intelligent vehicle platoon in mixed traffic | |
| CN117698730B (en) | Optimal lane change track planning method for anti-collision dynamic intelligent network-connected vehicle | |
| Sukthankar et al. | Tactical-level simulation for intelligent transportation systems | |
| CN113815645B (en) | Automatic driving behavior decision system and motion planning method suitable for annular intersection |
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 |