CN114771526A - Longitudinal vehicle speed control method and system for automatically changing lanes - Google Patents
Longitudinal vehicle speed control method and system for automatically changing lanes Download PDFInfo
- Publication number
- CN114771526A CN114771526A CN202210395665.1A CN202210395665A CN114771526A CN 114771526 A CN114771526 A CN 114771526A CN 202210395665 A CN202210395665 A CN 202210395665A CN 114771526 A CN114771526 A CN 114771526A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- longitudinal
- planning
- lane changing
- speed
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 230000001133 acceleration Effects 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18163—Lane change; Overtaking manoeuvres
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/53—Road markings, e.g. lane marker or crosswalk
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/402—Type
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4041—Position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/802—Longitudinal distance
-
- 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
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a longitudinal vehicle speed control method and a longitudinal vehicle speed control system for automatic lane changing, which comprise S1, acquiring the surrounding environment information of a vehicle; s2, judging whether to start automatic lane changing, if so, executing the next step; s3, judging whether the automatic lane changing safety condition is met or not according to the surrounding environment information, if so, starting lane changing, otherwise, executing the next step; s4, longitudinally planning the target space with the automatic lane changing according to the surrounding environment information to obtain a plurality of feasible longitudinal planning schemes; s5, deciding an optimal scheme from a plurality of feasible longitudinal planning schemes; s6, generating a longitudinal control instruction according to the optimal scheme, and checking whether the book meets the automatic lane changing safety condition after the longitudinal control instruction is executed; and S7, executing the longitudinal control command and starting lane changing. The method accurately models the longitudinal planning problem of automatic lane changing, solves an accurate solution by utilizing nonlinear optimization, and greatly improves the precision and the success rate of planning through the real-time verification of constraint.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to a longitudinal vehicle speed control method and system for automatic lane changing.
Background
With the development of artificial intelligence technology, multi-sensor fusion technology and control decision technology, the demand for automatically driving automobiles is more and more strong. The automatic driving automobile can be classified into no grades from L1 to L5 according to the use scene, technical capability and the like of the automatic driving automobile. Where L2 is advanced driving assistance, L3 level is conditional autopilot, L4 level is full autopilot of a defined area, and L5 is full autopilot.
The industry is currently focusing on mass production of automated driving technologies at the level L2-L3, which is primarily directed to limited automated driving capabilities in urban expressway and highway scenarios. The system comprises main functions of lane centering driving, vehicle self-adaptive cruising, automatic lane changing and the like.
For point-to-point automatic driving tasks of structured roads such as expressways, besides basic lane centering and vehicle adaptive cruising, an automatic driving system is required to have the capabilities of automatic on-off ramp, automatic switching interactive driving, automatic overtaking and lane changing and the like. The automatic overtaking lane changing function refers to that when a navigation path is started: (1) the vehicle can automatically execute an overtaking lane changing instruction when the speed of the vehicle on the adjacent lane is high so as to improve the overall traffic efficiency; (2) and automatically changing the lane to the lane which can enter and exit the ramp or the interchange so as to finish the driving of the next stage.
In a scene that an automatic lane change needs to be executed, a situation that a target lane and a vehicle in the lane of the vehicle occupy a lane change space of the vehicle may exist, and at this time, a system needs to automatically perform longitudinal decision planning and adjust the vehicle speed so as to smoothly and safely complete a lane change action.
The chinese patent CN202110604908.3 discloses an automatic driving longitudinal planning method, system and vehicle for creating a lane change condition, which describes a method for creating a safe lane change condition by active acceleration and deceleration, and the method traverses all possible acceleration and deceleration schemes to find a feasible scheme to meet the safe lane change condition. However, the solution precision is also rough by the traversal method, and meanwhile, a feasible solution is difficult to obtain along with the complication of the constraint problem.
Disclosure of Invention
In order to solve the problems, the invention provides a longitudinal vehicle speed control method and a longitudinal vehicle speed control system for automatic lane changing, which are used for accurately modeling the longitudinal planning problem of the automatic lane changing, solving an accurate solution by utilizing nonlinear optimization, and greatly improving the planning accuracy and success rate through the real-time verification of constraint.
In order to solve the technical problem, the technical scheme adopted by the invention is as follows: a longitudinal vehicle speed control method for automatic lane changing comprises the following steps,
s1, acquiring the surrounding environment information of the vehicle;
s2, judging whether to start automatic lane changing, if so, executing the next step;
s3, judging whether the automatic lane changing safety condition is met or not according to the surrounding environment information, if so, starting lane changing, otherwise, executing the next step;
s4, longitudinally planning the target space with the automatic lane changing according to the surrounding environment information to obtain a plurality of feasible longitudinal planning schemes;
s5, deciding an optimal scheme from a plurality of feasible longitudinal planning schemes;
s6, generating a longitudinal control instruction according to the optimal scheme, and checking whether the book meets the automatic lane changing safety condition after the longitudinal control instruction is executed;
and S7, executing the longitudinal control command and starting lane changing.
As optimization, the surrounding environment information comprises surrounding vehicle target information and lane line information which are acquired by a vehicle-mounted sensor in real time, and a corresponding relation is established between the vehicle target information and the lane line information; the vehicle target information comprises the position, speed and type of the surrounding vehicle; the lane line information includes a lane line coefficient, a length, and a type.
As optimization, the automatic lane changing safety condition includes that the relative longitudinal distance between the vehicle and the target vehicle is greater than a preset distance, and the relative vehicle speed is less than a preset vehicle speed.
As an optimization, step S4 includes,
s401, searching all target spaces capable of changing channels according to surrounding environment information;
s402, determining a front vehicle and a rear vehicle for each target space;
s403, establishing a nonlinear optimization model by taking the vehicle as acceleration, deceleration and uniform motion and taking the front vehicle and the rear vehicle as uniform motion;
and S404, solving the model, and obtaining the optimal solution corresponding to each target space as a feasible longitudinal planning scheme.
As an optimization, step S403 includes,
s4031, setting longitudinal vehicle speed adjustment duration and planning acceleration and deceleration a of the vehicle1The time length includes an acceleration/deceleration time length t1And a uniform speed duration t2;
S4032, setting safety constraint conditions,
t1,t2≥0 (1)
amin≤a1≤amax (2)
Tmin≤t1+t2≤Tmax (3)
in the formula, w1/w2/w3Three weighting factors related to the driving style, a, for a performance indicatorhThe current acceleration and deceleration of the vehicle is obtained,is (t)1+t2) The longitudinal distance from the vehicle to the front vehicle, VfrontThe speed of the front vehicle is the speed of the front vehicle,is (t)1+t2) Longitudinal distance, V, from the vehicle to the vehicle after the momentrearIn order to obtain the speed of the rear vehicle,is (t)1+t2) At the moment, the longitudinal distance, V, from the vehicle to the vehicle in front of the lanehostfrontThe speed of the vehicle in front of the lane of the vehicle,is (t)1+t2) At the moment of time, the vehicle speed, TdisFor safety time-distance calibration, TvelCalibrating the safe relative vehicle speed;
s4033, setting and a1,t1,t2Associated Performance index f (a)1,t1,t2) Introducing a weight coefficient related to the driving style, and calculating f (a) on the premise of meeting the safety constraint condition1,t1,t2) Minimum a1,t1,t2The value of (a) is set to (b),
min f(a1,t1,t2)=(t1+t2)w1+(t1a1)2w2+(ah-a1)2w3 (10)
the calculation model is that the model is,
as an optimization, in step S404, the model is solved according to a sequential quadratic programming algorithm, and a corresponding to each target space is calculated1,t1,t2And outputs the optimum value f (a) when the flag bit and the performance index are minimum1,t1,t2)。
As an optimization, in step S5, a plurality of optimal values f (a)1,t1,t2) And selecting the smallest longitudinal planning scheme as the optimal scheme.
As an optimization, step S6, including,
s601, starting to calculate the accumulated time t from the moment of obtaining the optimal scheme and using the expected acceleration and deceleration atAs the vertical control instruction:
s602, verifying whether the longitudinal control instruction meets a safety constraint condition after the execution is finished;
s603, if yes, continuously outputting a longitudinal control command atOtherwise, returning to S4 for replanning;
s604, judging t is larger than or equal to t1+t2If, ifIf yes, the longitudinal speed regulation is finished, the step S2 is returned to judge whether the current time meets the automatic lane changing safety condition, and if not, the step S601 is returned to generate a longitudinal control instruction of the next period; if not, continuously outputting a longitudinal control instruction at。
Based on the method, the invention also provides a longitudinal vehicle speed control system capable of automatically changing lanes, which comprises,
the environment perception system is used for acquiring surrounding environment information of the vehicle;
the upper-layer action decision system is used for making a decision on automatic lane changing, outputting an automatic lane changing instruction and scheduling tasks of each stage of the automatic lane changing;
the longitudinal planning system is used for planning a plurality of feasible longitudinal planning schemes by combining the surrounding environment information;
the longitudinal decision system is used for deciding an optimal longitudinal planning scheme from a plurality of feasible longitudinal planning schemes;
and the longitudinal control system is used for issuing the optimal longitudinal planning scheme to the actuator for control execution and verifying the automatic lane changing safety condition by combining with the surrounding environment information.
Compared with the prior art, the invention has the following advantages:
the invention utilizes sensors such as angle radar, cameras and the like which are produced in mass to obtain environmental information, and carries out longitudinal decision planning of automatic lane change, and the hardware scheme is reliable and mature and has controllable cost. The calculation method based on the nonlinear optimization algorithm is mature, is easy to transplant to an embedded controller environment for operation, and meets the performance requirement of vehicle-mounted calculation. The longitudinal decision result is close to the intention of a driver, and the user experience is good. The longitudinal decision-making style can be calibrated through the weight parameters, and the driver styles of conservation, commonness, aggressiveness and the like can be better reflected.
Drawings
FIG. 1 is a block diagram of the overall architecture of the present invention;
FIG. 2 is an overall design of the present invention;
FIG. 3 is a basic timing diagram of the present invention.
Detailed Description
The invention will be further explained with reference to the drawings and the embodiments.
The embodiment is as follows: referring to fig. 1, the following steps are exemplified by way of left lane change unless otherwise specified.
A longitudinal vehicle speed control method for automatic lane changing comprises the following steps,
and S1, acquiring the surrounding environment information of the vehicle.
Specifically, information (including position, speed, type) of a target such as a surrounding vehicle and information (including lane line coefficient, length, type) of a surrounding lane line is acquired, and the vehicle target is associated with each lane. As shown in fig. 2, the vehicle is HV, the target directly in front of the vehicle is target No. 1, the target No. 3 on the front left, the target No. 4 on the front right, the target No. 7 on the lateral left, the target No. 8 on the right lateral side, the target No. 9 on the rear left, the target No. 10 on the rear right, and the target No. 11 on the rear right.
And S2, judging whether to start automatic lane changing, if so, executing the next step.
Specifically, if the upper-layer action decision system outputs a command that the vehicle needs to actively switch lanes to the left, it needs to be determined whether the states of the target number 1, the target number 3, the target number 7 and the target number 9 meet the safety condition for switching lanes of the vehicle. Here, the target No. 3 is taken as the leading vehicle and the host vehicle is taken as the trailing vehicle for example (similarly, when the target No. 9 and the host vehicle are determined, the host vehicle is the leading vehicle and the target No. 9 is the trailing vehicle).
S3, judging whether the automatic lane changing safety condition is met or not according to the surrounding environment information, if so, starting lane changing, otherwise, executing the next step;
specifically, the automatic lane change safety condition includes,
1. the relative longitudinal distance between the front vehicle and the rear vehicle needs to be more than or equal to a certain value:
Slong≥Vrear*Tdis (16)
above SlongIs the absolute longitudinal distance, V, from the rear vehicle to the front vehiclerearFor rear vehicle speed, TdisFor safety time-distance calibration, the quantity is generally obtained according to the speed of the vehicle0.2~0.5;
2. The relative speed of the front vehicle and the rear vehicle needs to be less than or equal to a certain value:
above SlongIs the absolute longitudinal distance, V, from the rear vehicle to the front vehiclefrontFor the front vehicle speed, VrearFor rear vehicle speed, TvelIn order to safely calibrate the relative vehicle speed, 5-6 vehicle speeds are generally selected;
if the lane change safety condition is met, the lane change is directly executed, otherwise, the next step is executed.
And S4, performing longitudinal planning on the target space of the automatic lane changing according to the surrounding environment information to obtain a plurality of feasible longitudinal planning schemes. The step S4 includes the steps of,
s401, searching all target spaces capable of changing channels according to surrounding environment information;
s402, determining a front vehicle and a rear vehicle for each target space; for a lane change to the left, all obstacles of the lane on the left side are traversed, and all lane change spaces are found. For example, if 3,7,9 targets exist, the lane change space of the vehicle has the following: (1) changing the lane to the rear of the No. 9 target; (2) changing the channel to be between the targets No. 7 and No. 9; (3) changing the track to be between the targets No. 3 and No. 7; (4) and changing the lane to the front of the No. 3 target. Thus, 4 lane-changing spaces can be obtained, and for each lane-changing space, there is one relative to the front vehicle and the rear vehicle. For example, in lane change space 2, the front vehicle is target No. 7, and the rear vehicle is target No. 9. If there is no front vehicle or rear vehicle (lane change space 1 or 4), it is assumed that both the distance and the speed are absolutely safe front and rear vehicle target attributes (for example, the front/rear vehicle speed is equivalent to the vehicle, and the front/rear vehicle is more than 1000 meters away from the vehicle).
And S403, establishing a nonlinear optimization model by taking the vehicle as acceleration, deceleration and uniform motion and taking the front vehicle and the rear vehicle as uniform motion. As shown in fig. 3, taking lane change space (2) as an example, the problem is modeled by defining the front vehicle as a target No. 7, the rear vehicle as a target No. 9, and the front vehicle of the lane of the vehicle as a target No. 1: active lane changingThe longest time for the vehicle to adjust the speed of the vehicle in the lane does not exceed a certain time Tmax(ii) a The vehicle speed adjustment is divided into two stages at most: acceleration and deceleration and uniform speed stage, and acceleration and deceleration t is carried out first1After the time, t is constant2,t1,t2More than or equal to 0, acceleration and deceleration a in the acceleration and deceleration action stagemin≤a1≤amaxAcceleration a in constant velocity stage20; the longest and shortest time T of the vehicle in the vehicle path for adjusting the speed during the active lane changemax/Tmin,Tmin≤(t1+t2)≤Tmax(ii) a Predicting a passing t1+t2After the acceleration, deceleration and uniform speed stages, the automatic lane changing safety condition needs to be met; and processing the target vehicle according to the uniform motion model. The following non-linear optimal programming can be obtained:
s4031, setting longitudinal speed adjustment duration and planning acceleration and deceleration a of the vehicle1The time length includes an acceleration/deceleration time length t1And a uniform time duration t2;
S4032, setting safety constraint conditions,
s4032, setting safety constraint conditions,
t1,t2≥0 (1)
amin≤a1≤amax (2)
Tmin≤t1+t2≤Tmax (3)
in the formula, w1/w2/w3Three weighting factors related to the driving style, a, for a performance indicatorhThe current acceleration and deceleration speed of the vehicle is set,is (t)1+t2) At the moment, the longitudinal distance, V, from the vehicle to the preceding vehiclefrontThe speed of the front vehicle is the speed of the front vehicle,is (t)1+t2) Longitudinal distance, V, from the vehicle to the vehicle after the momentrearIn order to obtain the speed of the rear vehicle,is (t)1+t2) The longitudinal distance, V, from the vehicle to the vehicle in front of the vehicle lane at that momenthostfrontThe speed of the vehicle in front of the lane of the vehicle,is (t)1+t2) At the moment of time the vehicle speed, TdisFor safety time-distance calibration, TvelCalibrating the safe relative speed;
s4033, setting and a1,t1,t2Associated Performance index f (a)1,t1,t2) Introducing a weight coefficient related to the driving style, and calculating f (a) on the premise of meeting the safety constraint condition1,t1,t2) Minimum a1,t1,t2The value of (a) is set to (b),
min f(a1,t1,t2)=(t1+t2)w1+(t1a1)2w2+(ah-a1)2w3 (10)
the vehicle is a uniform acceleration and uniform motion calculation model, and the target vehicle is a uniform motion calculation model:
and S404, solving the model to obtain the optimal solution corresponding to each target space as a feasible longitudinal planning scheme. The performance index of formula (1) includes three indices: (1) the total time is shortest; (2) the absolute value of the speed change of the vehicle is minimum; (3) the absolute value of the difference between the planned acceleration and deceleration and the current acceleration and deceleration of the vehicle is minimum. Whether the style is aggressive or comfortable can be decided by adjusting the weights. Equations (5), (7) and (9) represent the relative distance safety condition in the automatic lane change safety condition, and equations (6), (8) and (10) represent the relative vehicle speed safety condition in the automatic lane change safety condition.
The problem is a non-linear optimization problem that can be solved using a corresponding mathematical algorithm, such as a sequential quadratic programming algorithm (SQP).
For each lane change space, the corresponding a is calculated1,t1,t2If a feasible optimal solution meeting the constraint exists, outputting a flag bit and an optimal value f (a)1,t1,t2). And if no feasible solution exists, outputting the corresponding flag bit.
S5, deciding an optimal scheme from a plurality of feasible longitudinal planning schemes; from several optimal values f (a)1,t1,t2) And selecting the smallest longitudinal planning scheme as the optimal scheme.
S6, generating a longitudinal control instruction according to the optimal scheme, and checking whether the book meets the automatic lane changing safety condition after the longitudinal control instruction is executed; s601, starting to calculate the accumulated time t from the moment of obtaining the optimal scheme and using the expected acceleration and deceleration atAs the vertical control instruction:
s602, due to the existence of control errors and the change of the surrounding target state, whether the currently output instruction still meets the safety constraint condition after the execution is finished needs to be checked in each period of control output, and the calculation model is as follows:
s in the above formulafront,Vfront,Srear,Vrear,Shostfront,VhostfrontAll target states corresponding to the current time t are obtained. t'1,t′2Is t1,t2According to the time after t correction:
s603, if yes, continuously outputting the longitudinal control command atOtherwise, returning to S4 for replanning;
s604, judging t is larger than or equal to t1+t2If yes, the longitudinal speed regulation is finished, the step S2 is returned to judge whether the current time meets the automatic lane changing safety condition, if not, the step S601 is returned to generate the longitudinal control instruction of the next period; if not, continuously outputting a longitudinal control instruction at. Specifically, because the existence of the control error and the change of the surrounding target state may already satisfy the safe lane change condition before the speed regulation is completed longitudinally, the judgment condition of step a2 is referred to judge whether the current time already satisfies the automatic lane change safe condition, if yes, the lane change is directly executed, and if not, the step S601 is returned to perform the longitudinal control instruction generation of the next period.
And S7, executing the longitudinal control command and starting lane changing.
Based on the method, the invention also provides a longitudinal vehicle speed control system capable of automatically changing lanes, which comprises,
the environment perception system is used for acquiring surrounding environment information of the vehicle; information on a target such as a surrounding vehicle, lane line information, navigation route information, and the like is acquired by using various sensors mounted on the vehicle.
The upper-layer action decision system is used for deciding the automatic lane changing, outputting an automatic lane changing instruction and scheduling tasks of each stage of the automatic lane changing;
the longitudinal planning system is used for planning a plurality of feasible longitudinal planning schemes by combining the surrounding environment information; and acquiring target information, and respectively corresponding the targets to the driving lane of the vehicle and the adjacent lane according to the lane line information. And according to the target information, constructing a nonlinear optimization problem, constructing a performance index by using factors such as acceleration and deceleration, acceleration and deceleration change, execution time and the like, and calculating a plurality of feasible longitudinal planning schemes with optimal performance indexes under the condition of meeting safety constraints.
The longitudinal decision system is used for deciding an optimal longitudinal planning scheme from a plurality of feasible longitudinal planning schemes;
and the longitudinal control system is used for issuing the optimal longitudinal planning scheme to the actuator for control execution and verifying the automatic lane changing safety condition by combining with the surrounding environment information.
The invention utilizes sensors such as a mass-produced angle radar and a camera to obtain environmental information, and performs longitudinal decision planning of automatic lane change, and the hardware scheme is reliable and mature and has controllable cost. The calculation method based on the nonlinear optimization algorithm is mature, is easy to transplant to an embedded controller environment for operation, and meets the performance requirement of vehicle-mounted calculation. The longitudinal decision result is close to the intention of a driver, and the user experience is good. The longitudinal decision-making style can be calibrated through the weight parameters, and the driver styles of conservation, commonness, aggressiveness and the like can be better reflected.
It should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting the technical solutions, and those skilled in the art should understand that the technical solutions of the present invention can be modified or substituted with equivalent solutions without departing from the spirit and scope of the technical solutions, and all should be covered in the claims of the present invention.
Claims (9)
1. A longitudinal vehicle speed control method for automatic lane changing is characterized by comprising the following steps,
s1, acquiring the surrounding environment information of the vehicle;
s2, judging whether the automatic lane changing is started or not, if so, executing the next step;
s3, judging whether the automatic lane changing safety condition is met or not according to the surrounding environment information, if so, starting lane changing, otherwise, executing the next step;
s4, performing longitudinal planning on the target space of the automatic lane changing according to the surrounding environment information to obtain a plurality of feasible longitudinal planning schemes;
s5, deciding an optimal scheme from a plurality of feasible longitudinal planning schemes;
s6, generating a longitudinal control instruction according to the optimal scheme, and checking whether the book meets the automatic lane changing safety condition after the longitudinal control instruction is executed;
and S7, executing the longitudinal control command and starting lane changing.
2. The longitudinal vehicle speed control method for automatically changing lanes according to claim 1, wherein the ambient environment information includes ambient vehicle target information and lane line information which are acquired in real time by a vehicle-mounted sensor, and a corresponding relationship is established between the vehicle target information and the lane line information; the vehicle target information comprises the position, speed and type of the surrounding vehicle; the lane line information includes a lane line coefficient, a length, and a type.
3. The longitudinal vehicle speed control method for automatically changing lanes as claimed in claim 1 or 2, wherein the safety conditions for automatically changing lanes include that the relative longitudinal distance between the vehicle and the target vehicle is greater than a preset distance, and the relative vehicle speed is less than a preset vehicle speed.
4. The longitudinal vehicle speed control method of an automatic lane change according to claim 3, wherein step S4 comprises,
s401, searching all target spaces capable of changing channels according to surrounding environment information;
s402, determining a front vehicle and a rear vehicle for each target space;
s403, establishing a nonlinear optimization model by taking the vehicle as acceleration, deceleration and uniform motion and taking the front vehicle and the rear vehicle as uniform motion;
and S404, solving the model, and obtaining the optimal solution corresponding to each target space as a feasible longitudinal planning scheme.
5. The automatic lane change longitudinal vehicle speed control method according to claim 4, wherein step S403 comprises,
s4031, setting longitudinal vehicle speed adjustment duration and planning acceleration and deceleration a of the vehicle1The time length includes an acceleration/deceleration time length t1And a uniform speed duration t2;
S4032, setting safety constraint conditions,
t1,t2≥0 (1)
amin≤a1≤amax (2)
Tmin≤t1+t2≤Tmax (3)
in the formula, w1/w2/w3Three weight coefficients related to the driving style, a, for a performance indexhThe current acceleration and deceleration speed of the vehicle is set,is (t)1+t2) The longitudinal distance from the vehicle to the front vehicle, VfrontThe speed of the front vehicle is the speed of the front vehicle,is (t)1+t2) Longitudinal distance, V, from the vehicle to the rear at that momentrearThe speed of the vehicle is the speed of the rear vehicle,is (t)1+t2) At the moment, the longitudinal distance, V, from the vehicle to the vehicle in front of the lanehostfrontThe speed of the vehicle in front of the lane of the vehicle,is (t)1+t2) At the moment of time, the vehicle speed, TdisFor safety time-distance calibration, TvelCalibrating the safe relative vehicle speed;
s4033, setting and a1,t1,t2Associated Performance index f (a)1,t1,t2) Introducing a weight coefficient related to the driving style, and calculating f (a) on the premise of meeting the safety constraint condition1,t1,t2) Minimum a1,t1,t2The value of (a) is,
min f(a1,t1,t2)=(t1+t2)w1+(t1a1)2w2+(ah-a1)2w3 (10)
the calculation model is that the model is,
6. the method as claimed in claim 4, wherein in step S404, the model is solved according to a sequential quadratic programming algorithm, and a corresponding to each target space is calculated1,t1,t2And outputs the optimum value f (a) when the flag bit and the performance index are minimum1,t1,t2)。
7. The longitudinal vehicle speed control method of automatic lane changing according to claim 6, wherein in step S5, the optimal values f (a) are selected1,t1,t2) And selecting the minimum longitudinal planning scheme as the optimal scheme.
8. The automatic lane change longitudinal vehicle speed control method according to any one of claims 5 to 7, wherein step S6 comprises,
s601, starting to calculate the accumulated time t from the moment of obtaining the optimal scheme and using the expected acceleration and deceleration atAs the vertical control instruction:
s602, verifying whether the longitudinal control instruction meets a safety constraint condition after the execution is finished;
s603, if yes, continuously outputting the longitudinal control command atOtherwise, returning to S4 againNew planning;
s604, judging t is larger than or equal to t1+t2If yes, the longitudinal speed regulation is finished, the step S2 is returned to judge whether the current time meets the automatic lane changing safety condition, if not, the step S601 is returned to generate the longitudinal control instruction of the next period; if not, continuously outputting the longitudinal control instruction at。
9. A longitudinal vehicle speed control system capable of automatically changing lanes is characterized by comprising,
the environment sensing system is used for acquiring surrounding environment information of the vehicle;
the upper-layer action decision system is used for making a decision on automatic lane changing, outputting an automatic lane changing instruction and scheduling tasks of each stage of the automatic lane changing;
the longitudinal planning system is used for planning a plurality of feasible longitudinal planning schemes by combining the surrounding environment information;
the longitudinal decision system is used for deciding an optimal longitudinal planning scheme from a plurality of feasible longitudinal planning schemes;
and the longitudinal control system is used for issuing the optimal longitudinal planning scheme to the actuator for control execution and verifying the automatic lane changing safety condition by combining with the surrounding environment information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210395665.1A CN114771526B (en) | 2022-04-14 | 2022-04-14 | Longitudinal vehicle speed control method and system for automatic lane changing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210395665.1A CN114771526B (en) | 2022-04-14 | 2022-04-14 | Longitudinal vehicle speed control method and system for automatic lane changing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114771526A true CN114771526A (en) | 2022-07-22 |
CN114771526B CN114771526B (en) | 2024-06-14 |
Family
ID=82429746
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210395665.1A Active CN114771526B (en) | 2022-04-14 | 2022-04-14 | Longitudinal vehicle speed control method and system for automatic lane changing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114771526B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101575298B1 (en) * | 2014-06-26 | 2015-12-21 | 한양대학교 산학협력단 | Vehicle control system and method for the same |
CN106740457A (en) * | 2016-12-07 | 2017-05-31 | 镇江市高等专科学校 | Vehicle lane-changing decision-making technique based on BP neural network model |
CN111016902A (en) * | 2019-12-30 | 2020-04-17 | 重庆长安汽车股份有限公司 | Vehicle speed auxiliary control method and system during lane changing of vehicle and vehicle |
WO2021238303A1 (en) * | 2020-05-29 | 2021-12-02 | 华为技术有限公司 | Motion planning method and apparatus |
CN113799800A (en) * | 2021-10-08 | 2021-12-17 | 河南科技大学 | Automatic lane changing and overtaking track planning method for unmanned vehicle |
-
2022
- 2022-04-14 CN CN202210395665.1A patent/CN114771526B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101575298B1 (en) * | 2014-06-26 | 2015-12-21 | 한양대학교 산학협력단 | Vehicle control system and method for the same |
CN106740457A (en) * | 2016-12-07 | 2017-05-31 | 镇江市高等专科学校 | Vehicle lane-changing decision-making technique based on BP neural network model |
CN111016902A (en) * | 2019-12-30 | 2020-04-17 | 重庆长安汽车股份有限公司 | Vehicle speed auxiliary control method and system during lane changing of vehicle and vehicle |
WO2021238303A1 (en) * | 2020-05-29 | 2021-12-02 | 华为技术有限公司 | Motion planning method and apparatus |
CN113799800A (en) * | 2021-10-08 | 2021-12-17 | 河南科技大学 | Automatic lane changing and overtaking track planning method for unmanned vehicle |
Non-Patent Citations (1)
Title |
---|
张嘉明等: ""一种多线形车道线检测算法"", 《合肥工业大学学报(自然科学版)》, vol. 43, no. 4, 30 April 2020 (2020-04-30), pages 536 - 542 * |
Also Published As
Publication number | Publication date |
---|---|
CN114771526B (en) | 2024-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11561542B2 (en) | Safety and comfort constraints for navigation | |
CN111681452B (en) | Unmanned vehicle dynamic lane change track planning method based on Frenet coordinate system | |
CN110304074B (en) | Hybrid driving method based on layered state machine | |
JP3714258B2 (en) | Recommended operation amount generator for vehicles | |
CN105292116B (en) | The lane changing path planning algorithm of automatic driving vehicle | |
JP4952268B2 (en) | Travel control plan generator | |
US11499834B2 (en) | Aligning road information for navigation | |
CN110834644A (en) | Vehicle control method and device, vehicle to be controlled and storage medium | |
CN110568841A (en) | Automatic driving decision method and system | |
JP2023502797A (en) | Adaptive control for autonomous or semi-autonomous vehicles | |
CN115257745A (en) | Automatic driving lane change decision control method based on rule fusion reinforcement learning | |
CN112406905B (en) | Data processing method and device based on vehicle, computer and storage medium | |
CN113665593B (en) | Longitudinal control method and system for intelligent driving of vehicle and storage medium | |
CN115257746A (en) | Uncertainty-considered decision control method for lane change of automatic driving automobile | |
CN114506340A (en) | Intelligent driving vehicle lane-changing transverse path planning method and system and vehicle | |
CN115140096A (en) | Spline curve and polynomial curve-based automatic driving track planning method | |
CN115494849A (en) | Navigation control method and system for automatic driving vehicle | |
CN114802306A (en) | Intelligent vehicle integrated decision-making system based on man-machine co-driving concept | |
CN114442630A (en) | Intelligent vehicle planning control method based on reinforcement learning and model prediction | |
CN114771526B (en) | Longitudinal vehicle speed control method and system for automatic lane changing | |
CN114543831B (en) | Route planning method, device and equipment based on driving style and storage medium | |
CN116225026A (en) | Automatic driving vehicle operation method, electronic device, and computer-readable medium | |
CN114475607B (en) | Method and device for changing lanes for automatic driving vehicle, vehicle and storage medium | |
JP2023531927A (en) | Driving decision-making method, driving decision-making device, and chip | |
Yang et al. | Deep Reinforcement Learning Lane-Changing Decision Algorithm for Intelligent Vehicles Combining LSTM Trajectory Prediction |
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 |