CN117198082A - Double-layer optimization-based vehicle ramp afflux decision method and system - Google Patents
Double-layer optimization-based vehicle ramp afflux decision method and system Download PDFInfo
- Publication number
- CN117198082A CN117198082A CN202311460469.9A CN202311460469A CN117198082A CN 117198082 A CN117198082 A CN 117198082A CN 202311460469 A CN202311460469 A CN 202311460469A CN 117198082 A CN117198082 A CN 117198082A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- ramp
- gap
- layer optimization
- optimization
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000008676 import Effects 0.000 claims abstract description 36
- 239000010410 layer Substances 0.000 claims description 57
- 230000008859 change Effects 0.000 claims description 50
- 230000001133 acceleration Effects 0.000 claims description 16
- 239000002355 dual-layer Substances 0.000 claims description 8
- 230000008685 targeting Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 28
- 238000010168 coupling process Methods 0.000 abstract description 6
- 238000005859 coupling reaction Methods 0.000 abstract description 6
- 230000008878 coupling Effects 0.000 abstract description 4
- 230000009471 action Effects 0.000 description 3
- 230000036461 convulsion Effects 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 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
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention provides a vehicle ramp afflux decision method and system based on double-layer optimization, and belongs to the technical field of traffic control systems. The method comprises the following steps: according to the acquired motion state data, a current import gap and a next import gap on a main line lane are obtained, and respective front and rear vehicles of the two import gaps are determined; according to the motion state data of vehicles in front of and behind the two afflux gaps, performing uniform speed prediction on the related vehicles, and performing lower layer optimization to obtain optimal longitudinal maneuvering parameters of the vehicles with the two afflux gaps, wherein the longitudinal direction is the direction of a main line lane; performing upper-layer optimization on the optimal maneuver parameters of the two import gaps to obtain the optimal import gap, and performing import control according to the ramp vehicle longitudinal maneuver parameters corresponding to the optimal import gap; the invention solves the problem of dynamic coupling between longitudinal speed adjustment and entry gap selection of the intelligent vehicle in the ramp entry process, and ensures the entry safety.
Description
Technical Field
The invention relates to the technical field of traffic control systems, in particular to a vehicle ramp afflux decision method and system based on double-layer optimization.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The intelligent driving technology refers to that the vehicle can autonomously sense the surrounding environment, position the vehicle, make decisions and plans and execute corresponding tracking control operation under the condition of no or little intervention, so that safe, efficient and comfortable driving is realized. The ramp afflux process of the vehicle refers to a process of entering the main line of the expressway from the ramp. It needs to coordinate with the main line vehicle in a limited time and space to find out the proper position and speed to finish the merging action. Decision planning is carried out for the ramp afflux process of the intelligent vehicle, and the intelligent vehicle has important significance and value for improving the running safety, the traffic efficiency and the riding comfort of the intelligent vehicle in complex traffic scenes.
In the course of the merging of ramp vehicles, they need to make longitudinal speed adjustments on the accelerating lane and change the lane into the target gap on the main lane. The two processes are mutually-interactive and dynamically-coupled: different entry gaps may result in different speed adjustments for the own vehicle, and speed variations for the own vehicle may also affect the usability of the entry gap. The conventional ramp control method can effectively regulate traffic demand and supply, but cannot microscopically consider complex driving behavior of the vehicle. The rule-based import decision method has low computational complexity and is easy to implement and deploy; however, they cannot adapt to dynamically complex traffic environments and the optimality of decisions is limited. The machine learning-based approach has the potential to adapt to highly dynamic complex traffic environments, but requires significant amounts of effective training data and training resources; in addition, the decision making process of the model is not transparent enough for human beings, the interpretation is poor, the application of the model on intelligent vehicles still needs to break through a plurality of safety problems and trust and ethics problems, and the current research does not well solve the problem of dynamic coupling between longitudinal speed adjustment and afflux gap selection.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a vehicle ramp converging decision method and a system based on double-layer optimization, which solve the problem of dynamic coupling between longitudinal (namely along the direction of a main line lane) speed adjustment and converging gap selection of an intelligent vehicle in the ramp converging process and ensure converging safety.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, the invention provides a vehicle ramp afflux decision method based on double-layer optimization.
A vehicle ramp afflux decision method based on double-layer optimization comprises the following steps:
acquiring motion state data of a ramp vehicle to be converged and objects in a surrounding environment, acquiring a current convergence gap and a next convergence gap on a main line lane according to the acquired motion state data, and determining respective front and rear vehicles of the two convergence gaps;
according to the motion state data of vehicles in front of and behind the two afflux gaps, performing uniform speed prediction on the related vehicles, and performing lower layer optimization to obtain optimal longitudinal maneuvering parameters of the vehicles with the two afflux gaps, wherein the longitudinal direction is the direction of a main line lane;
and executing upper-layer optimization on the optimal maneuver parameters of the two import gaps to obtain the optimal import gap, and performing import control according to the ramp vehicle longitudinal maneuver parameters corresponding to the optimal import gap.
As a further limitation of the first aspect of the present invention, in the lower-layer optimization currently incorporated into the gap, the objective is to minimize the difference between the product of the first positive weight coefficient and the planning time and the planning speed; the next merge gap is in the lower optimization, targeting the minimum planning time.
As a further limitation of the first aspect of the present invention, in the upper-layer optimization, a product of the second positive weight coefficient and the planning time is used as a first variable, and a product of the third positive weight coefficient and a headway of the ramp vehicle before the next convergence gap is used as a second variable;
and taking the product of the fourth positive weight coefficient and the headway of the vehicle after the ramp vehicle and the next converging gap as a third variable, and taking the minimum result of subtracting the second variable from the first variable as an optimization target to obtain the target converging gap.
As a further limitation of the first aspect of the invention, the selection of the second positive weighting factor is made based on the remaining time for which the ramp vehicle is traveling to the end of the acceleration lane at the current vehicle speed.
As a further limitation of the first aspect of the invention, if the selected longitudinal shift maneuver time is less than the set time threshold, initiating a lane change; or if the distance between the ramp vehicle and the tail end of the acceleration lane is smaller than a set threshold value, the lane change is started.
As a further limitation of the first aspect of the present invention, the lane change maneuver parameters of the ramp vehicle are obtained with the objective of minimizing the difference between the product of the fifth positive weight coefficient and the lane change time and the planned speed, and the lane change control of the ramp vehicle is performed according to the lane change maneuver parameters.
In a second aspect, the invention provides a vehicle ramp afflux decision system based on double-layer optimization.
A dual-layer optimization-based vehicle ramp afflux decision system, comprising:
an ingress clearance determination module configured to: acquiring motion state data of a ramp vehicle to be converged and objects in a surrounding environment, acquiring a current convergence gap and a next convergence gap on a main line lane according to the acquired motion state data, and determining respective front and rear vehicles of the two convergence gaps;
a lower layer optimization module configured to: according to the motion state data of vehicles in front of and behind the two afflux gaps, performing uniform speed prediction on the related vehicles, and performing lower layer optimization to obtain optimal longitudinal maneuvering parameters of the vehicles with the two afflux gaps, wherein the longitudinal direction is the direction of a main line lane;
an upper layer optimization module configured to: and executing upper-layer optimization on the optimal maneuver parameters of the two import gaps to obtain the optimal import gap, and performing import control according to the ramp vehicle longitudinal maneuver parameters corresponding to the optimal import gap.
As a further limitation of the second aspect of the present invention, in the lower optimization module, in the lower optimization of the current import gap, the minimum difference between the product of the first positive weight coefficient and the planning time and the planning speed is taken as a target; the next merge gap is in the lower optimization, targeting the minimum planning time.
As a further limitation of the second aspect of the present invention, in the upper optimization module, a product of the second positive weight coefficient and the planning time is used as a first variable, and a product of the third positive weight coefficient and a headway of the ramp vehicle before the next convergence gap is used as a second variable;
and taking the product of the fourth positive weight coefficient and the headway of the vehicle after the ramp vehicle and the next converging gap as a third variable, and taking the minimum result of subtracting the second variable from the first variable as an optimization target to obtain the target converging gap.
As a further limitation of the second aspect of the invention, if the selected longitudinal shift maneuver time is less than the set time threshold, initiating a lane change; or if the distance between the ramp vehicle and the tail end of the accelerating lane is smaller than a set threshold value, starting to execute lane change;
and obtaining the lane change maneuver parameters of the ramp vehicle by taking the product of the fifth positive value weight coefficient and the lane change time and the minimization of the difference value of the planning speed as targets, and carrying out lane change control of the ramp vehicle according to the lane change maneuver parameters.
In a third aspect, the present invention provides a computer readable storage medium having stored thereon a program which when executed by a processor implements the steps in a dual layer optimization based vehicle ramp merge decision method according to the first aspect of the present invention.
In a fourth aspect, the present invention provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor, where the processor implements the steps in the dual-layer optimization-based vehicle ramp merge decision method according to the first aspect of the present invention when the program is executed.
In a fifth aspect, the present invention provides a vehicle, where the vehicle ramp merge decision method based on double-layer optimization according to the first aspect of the present invention is used for merge control; alternatively, a computer readable storage medium comprising the third aspect of the present invention; or comprises the electronic device according to the fourth aspect of the invention.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention solves the problem of dynamic coupling between the longitudinal speed adjustment of the intelligent vehicle and the remittance gap selection, can make corresponding reasonable remittance actions under the condition of different movement intentions (overrun or yield) of the vehicle after the main line gap, and ensures the remittance safety.
2. In the situation that the bus has an overrun intention after the main line gap, the bus can focus on safety to be converged, in the situation that the bus has a yielding intention after the main line gap, the bus can focus on efficiency to be converged, and the bus ramp can be converged on the premise of conforming to the interaction habit of a human driver, so that the convergence safety is further improved.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a flow chart of a vehicle ramp entry decision method based on double-layer optimization provided in embodiment 1 of the present invention;
fig. 2 is a schematic diagram of a vehicle ramp afflux decision system based on double-layer optimization provided in embodiment 2 of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1:
as shown in fig. 1, embodiment 1 of the present invention provides a vehicle ramp afflux decision method based on double-layer optimization, which includes the following steps:
acquiring the kinematic information states (position, course, speed and acceleration) of the intelligent vehicle and objects in the surrounding environment;
according to the acquired kinematic information state, a current afflux gap and a next afflux gap on a main line lane are obtained, and respective front and rear vehicles of the two afflux gaps are determined;
according to the kinematic information states of vehicles in front of and behind the two entry gaps, and the related vehicles are predicted at a uniform speed, a lower-layer optimization problem is established, and the optimal maneuvering parameters (time, position and speed) of the two entry gaps are obtained, namely, when and at what speed the intelligent vehicle reaches to what position;
the output of the lower optimizing module is used as the input of the upper optimizing module, an upper optimizing problem is established, and the optimal maneuvering parameters (time, position and speed) selected by the intelligent vehicle in the two converging gaps are obtained, namely, when the intelligent vehicle reaches the position at what speed;
when the rolling optimization process based on the double-layer optimization model predictive control is finished, the lane change time is reached, the lane change optimization problem is established, and lane change maneuver parameters (time, position and speed) of the intelligent vehicle are obtained.
The basis of the decision planning is a phased maneuver model based on optimal control, and the phased maneuver model comprises a longitudinal speed change maneuver model and a transverse lane change maneuver model.
Wherein, in the longitudinal speed change maneuver model, the decision variables of the optimal control problem comprise: longitudinal position, speed, acceleration and jerk of the intelligent vehicle at different times; moreover, start, process and end constraints need to be satisfied; the optimization objective is to minimize the longitudinal motion discomfort during vehicle maneuvers, i.e., to minimize the integration of jerk over time. Considering the longitudinal maneuver as approximately a uniform shift maneuver, the ending longitudinal position may be calculated from the starting longitudinal position, the process time, the starting and ending speeds; therefore, the optimal control problem of the longitudinal speed change maneuver model can be solved only by determining the time and the termination speed of the longitudinal speed change maneuver process, and the planning track of the process can be obtained.
In a transversal lane-change maneuver model, the vehicle model uses a two-dimensional bicycle motion model, and the decision variables for the optimal control problem include: the intelligent vehicle has the advantages of transverse and longitudinal positions, speeds, accelerations, course angles, course angular speeds, front wheel rotation angles and front wheel rotation angular speeds at different times; moreover, start, process and end constraints need to be satisfied; the optimization objective is to minimize the lateral and longitudinal discomfort during the lane change, i.e., the integral of the sum of the squares of the yaw rate and jerk. In the transverse speed change maneuver model, the optimal control problem of the transverse speed change maneuver model can be solved by only determining the time and the termination speed of the transverse speed change maneuver process, and the planning track of the process can be obtained.
In this embodiment, at an initial time, the intelligent vehicle obtains a current kinematic state including kinematic information of a vehicle and dynamic and static objects in a surrounding environment through devices such as a camera, a radar, a laser radar, a global positioning system, and an inertial navigation device.
In this embodiment, for the current import gap and the next import gap, an optimization method is used to obtain optimal maneuver parameters (i.e., time, speed, position) corresponding to the respective gaps; the output of the lower layer optimization is used as the input of the upper layer optimization; the two main line gaps are decided through upper layer optimization, and a final target afflux gap and a corresponding optimal longitudinal variable speed maneuver parameter are obtained; and executing acceleration maneuver according to the acquired optimal longitudinal speed change maneuver parameters. When the rolling optimization process of the model predictive control is finished, the intelligent vehicle reaches the channel switching time.
And obtaining optimal parameters (namely, time, speed and position) of the transverse channel changing maneuver through an optimization process, solving an optimal control problem of the transverse channel changing maneuver according to the obtained optimal transverse channel changing maneuver parameters, obtaining a channel changing process planning track, and enabling the intelligent vehicle to change channels according to the obtained channel changing process planning track so as to finish merging into a target merging gap.
Specifically, acceleration process roll optimization includes:
entry gap selection and longitudinal speed adjustment are two major issues in ramp entry strategy research. These two problems are actually a cyclic process, and this embodiment proposes a two-layer optimization strategy to solve these two problems at the same time, where the lower layer optimization determines the optimal parameters (if a feasible solution exists) of the longitudinal speed change maneuver of the own vehicle on the acceleration lane for the two gaps, and the upper layer optimization selects the optimal import gap between the gap 1 (where the own vehicle is currently located) and the gap 2 (the next gap), and the decision content is the choice of the import gap.
Longitudinal variable speed maneuver parameters pending for the own vehicle:
（1）；
planning speed of a self-vehicleIs subject to and planned in addition to upper and lower boundary constraintsTimeCoupling constraints between:
（2）；
for the initial speed of the own vehicle, the longitudinal shifting maneuver of the own vehicle approximates a ramp up process,for maximum acceleration, the target longitudinal position +.>The method comprises the following steps:
（3）；
for the initial longitudinal position of the own vehicle, three main vehicles are predicted with a uniform speed prediction model, and then their longitudinal positions at the end of the process:
（4）；
for the initial longitudinal position of the first vehicle, < >>For the initial speed of the first vehicle, +.>For the initial longitudinal position of the first vehicle, < >>For the initial speed of the first vehicle, +.>For the initial longitudinal position of the first vehicle, < >>Is the initial speed of the first vehicle.
Target longitudinal position of own vehicleConstrained by:
（5）；
wherein,longitudinal position for accelerating the end of the lane; />Is a distance threshold.
For gap 1, the headway between the own vehicle and the vehicles in front of and behind gap 1 is constrained:
（6）；
wherein,is the minimum headway acceptable between vehicles, < >>For restraint with the front car of gap 1 +.>Is the restraint of the vehicle behind the gap 1.
The optimization objective is to shorten the planning time as much as possibleIncrease planning speed +.>：
（7）；
Wherein,for positive weight coefficients (i.e. first positive weight coefficient), if the optimization problem has a feasible optimal solution, it is marked +.>。
For gap 2, the headway between the own vehicle and the vehicles in front of and behind gap 2 is constrained:
（8）；
wherein,for restraint with the front car of gap 2 +.>Is the restraint of the vehicle behind the gap 2.
The minimization goal is to minimize the planning time：
（9）；
If there is a feasible solution, then it is noted as。
If there are viable maneuver parameters for both gaps, then the optimal target gap is selected by upper layer optimization:
（10）；
wherein,(i.e. third positive weight coefficient) and +.>(i.e., the fourth positive weight coefficients) are all positive weight coefficients;the value of (i.e. the second positive weight coefficient) is determined by the following formula (11), +.>For the remaining time of the own vehicle driving at the current speed to the end of the acceleration lane, < >>And->For its larger and smaller thresholds, the target entry gap is determined by selecting the longitudinal maneuver parameters corresponding to the gap that minimizes the value of equation (10):
（11）；
（12）；
wherein,is->Minimum value->Is->Is a maximum value of (a).
Model predictive control (Model Predictive Control, MPC) is a model-based optimization control technique that can control a dynamic system under conditions that satisfy a set of constraints. The basic idea is to solve an optimal control problem in a finite time domain according to the current state and the expected output of the system in each control period to obtain a set of optimal control input sequences, then only apply the first control input, and solve the optimal control problem again in the next control period. The model predictive control can realize feedforward prediction and feedback adjustment of the system to improve the performance and robustness of the system. Which requires a more accurate system model, appropriate objective functions and constraints to describe the control objectives and system constraints.
Double-layer optimization operates in a model predictive control framework, and the predictive time domain and the control time domain are the planning time. The first action of the control sequence is performed, and the double-layer optimization is performed again with the current state as the initial state at each time step. And if both the gaps are feasible, selecting maneuvering parameters corresponding to the target gap according to the upper layer optimization. If only one of the two clearances is feasible, a corresponding longitudinal shifting maneuver is performed for the only feasible clearance. If no viable maneuver parameters exist for both gaps, a fixed deceleration is performed until the minimum speed limit is reached. In the process of rolling optimization, if the following vehicle in the gap 1 exceeds the self-vehicle, the current gap and the next gap of the self-vehicle are updated, and the new gap 1 and the new gap 2 are regarded as respectively.
If the first control input of the optimal control plan speed is directly selected, the resulting control input is too small because the speed change is relatively gentle during the initial phase. Therefore, the prescribed acceleration is selected as follows:
（13）；
wherein,indicate->Planning time of sub-optimization; />And->Respectively representing an initial speed and a planned termination speed; />Indicate->The acceleration actually selected in the sub-optimization process is selected by the above equation, instead of selecting the first control amount after actually solving the optimal control problem, so that only the optimization calculation of the parameters to be determined of the longitudinal speed change maneuver is time-consuming. Each scroll optimization takes approximately 0.03s, less than 0.05s of the simulation time step.
The forced termination conditions for model predictive control are set as follows:
(1) If the longitudinal speed change maneuvering time of the double-layer optimization selection is smaller than a threshold value, starting to execute lane change;
(2) If the distance between the own vehicle and the end of the acceleration lane is smaller than the threshold value, lane changing is started.
In this embodiment, track planning in the track changing process includes:
when the lane change time is reached, the undetermined maneuvering parameters in the lane change process of the self-vehicle are required to be determined：
（14）；
Planning speed of a self-vehicleIn addition to being constrained by upper and lower boundaries, is also subject to and programs timeCoupling constraints between:
（15）；
wherein,for acceleration coefficient +.>Is the speed before changing the track.
Approximate final longitudinal position of the own vehicle：
（16）；
For the longitudinal position before lane change of the self-vehicle, a constant speed model is still used for predicting the movement of the front vehicle and the rear vehicle in the target gap.
（17）；
Wherein,for the initial longitudinal position of the front truck in gap +.>Initial longitudinal position of the rear vehicle after clearance, +.>For the initial speed of the front vehicle in gap, +.>Is the initial speed of the vehicle after the gap.
The headway and the rear vehicle are respectively constrained with the headway of the own vehicle:
（18）；
wherein,for the final longitudinal position of the front truck in gap +.>For the final longitudinal position of the rear vehicle after the gap, +.>Is the final longitudinal position of the own vehicle.
In order to stabilize the self-vehicle during lane changing, the lane changing time cannot be too short:
（19）；
the optimization goal is to shorten the channel change time as much as possibleAnd increase the planning speed as much as possible>：
（20）；
Wherein,is a positive weight coefficient (i.e., a fifth positive weight coefficient).
Solving the nonlinear optimization problem to obtain the undetermined maneuvering parameters of the self-vehicleExecuting corresponding channel changing maneuver to complete the whole import process
Example 2:
the embodiment 2 of the invention provides a vehicle ramp afflux decision system based on double-layer optimization, which comprises the following steps:
an ingress clearance determination module configured to: acquiring motion state data of a ramp vehicle to be converged and objects in a surrounding environment, acquiring a current convergence gap and a next convergence gap on a main line lane according to the acquired motion state data, and determining respective front and rear vehicles of the two convergence gaps;
a lower layer optimization module configured to: according to the motion state data of vehicles in front of and behind the two afflux gaps, performing uniform speed prediction on the related vehicles, and performing lower layer optimization to obtain optimal longitudinal maneuvering parameters of the vehicles with the two afflux gaps, wherein the longitudinal direction is the direction of a main line lane;
an upper layer optimization module configured to: and executing upper-layer optimization on the optimal maneuver parameters of the two import gaps to obtain the optimal import gap, and performing import control according to the ramp vehicle longitudinal maneuver parameters corresponding to the optimal import gap.
The working method of the system is the same as the vehicle ramp afflux decision method based on double-layer optimization provided in embodiment 1, and is not described here again.
Example 3:
embodiment 3 of the present invention provides a computer readable storage medium having a program stored thereon, which when executed by a processor, implements the steps in the dual-layer optimization-based vehicle ramp merge decision method according to embodiment 1 of the present invention.
Example 4:
an embodiment 4 of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and capable of running on the processor, where the processor implements steps in the dual-layer optimization-based vehicle ramp merging decision method according to embodiment 1 of the present invention when executing the program.
Example 5:
the embodiment 5 of the invention provides a vehicle, which adopts the vehicle ramp converging decision method based on double-layer optimization of the embodiment 1 of the invention to perform converging control; alternatively, a computer-readable storage medium according to embodiment 3 of the present invention is included; or the electronic device described in embodiment 4 of the present invention is included.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (13)
1. The vehicle ramp afflux decision method based on double-layer optimization is characterized by comprising the following steps of:
acquiring motion state data of a ramp vehicle to be converged and objects in a surrounding environment, acquiring a current convergence gap and a next convergence gap on a main line lane according to the acquired motion state data, and determining respective front and rear vehicles of the two convergence gaps;
according to the motion state data of vehicles in front of and behind the two afflux gaps, performing uniform speed prediction on the related vehicles, and performing lower layer optimization to obtain optimal longitudinal maneuvering parameters of the vehicles with the two afflux gaps, wherein the longitudinal direction is the direction of a main line lane;
and executing upper-layer optimization on the optimal maneuver parameters of the two import gaps to obtain the optimal import gap, and performing import control according to the ramp vehicle longitudinal maneuver parameters corresponding to the optimal import gap.
2. The vehicle ramp merge decision method based on double-layer optimization as recited in claim 1, wherein,
in the lower-layer optimization of the current import gap, the minimum difference between the product of the first positive weight coefficient and the planning time and the planning speed is taken as a target; the next merge gap is in the lower optimization, targeting the minimum planning time.
3. The vehicle ramp merge decision method based on double-layer optimization as recited in claim 1, wherein,
in the upper layer optimization, taking the product of the second positive weight coefficient and the planning time as a first variable, and taking the product of the third positive weight coefficient and the headway of the ramp vehicle and the next converging gap front vehicle as a second variable;
and taking the product of the fourth positive weight coefficient and the headway of the vehicle after the ramp vehicle and the next converging gap as a third variable, and taking the minimum result of subtracting the second variable from the first variable as an optimization target to obtain the target converging gap.
4. The vehicle ramp merge decision method based on double-layer optimization as recited in claim 3, wherein,
and selecting a second positive weight coefficient according to the remaining time of the ramp vehicle from the current speed to the tail end of the acceleration lane.
5. The vehicle ramp merge decision method based on double-layer optimization as recited in any one of claims 1-4, wherein,
if the selected longitudinal speed change maneuvering time is smaller than the set time threshold, starting to execute lane change; or if the distance between the ramp vehicle and the tail end of the acceleration lane is smaller than a set threshold value, the lane change is started.
6. The vehicle ramp merge decision method based on double-layer optimization as recited in claim 5, wherein,
and obtaining the lane change maneuver parameters of the ramp vehicle by taking the product of the fifth positive value weight coefficient and the lane change time and the minimization of the difference value of the planning speed as targets, and carrying out lane change control of the ramp vehicle according to the lane change maneuver parameters.
7. A vehicle ramp afflux decision system based on double-layer optimization, comprising:
an ingress clearance determination module configured to: acquiring motion state data of a ramp vehicle to be converged and objects in a surrounding environment, acquiring a current convergence gap and a next convergence gap on a main line lane according to the acquired motion state data, and determining respective front and rear vehicles of the two convergence gaps;
a lower layer optimization module configured to: according to the motion state data of vehicles in front of and behind the two afflux gaps, performing uniform speed prediction on the related vehicles, and performing lower layer optimization to obtain optimal longitudinal maneuvering parameters of the vehicles with the two afflux gaps, wherein the longitudinal direction is the direction of a main line lane;
an upper layer optimization module configured to: and executing upper-layer optimization on the optimal maneuver parameters of the two import gaps to obtain the optimal import gap, and performing import control according to the ramp vehicle longitudinal maneuver parameters corresponding to the optimal import gap.
8. The dual-layer optimization-based vehicle ramp merge decision system as recited in claim 7, wherein,
in the lower optimization module, in the lower optimization of the current import gap, the minimum difference between the product of the first positive weight coefficient and the planning time and the planning speed is taken as a target; the next merge gap is in the lower optimization, targeting the minimum planning time.
9. The dual-layer optimization-based vehicle ramp merge decision system as recited in claim 7, wherein,
in the upper layer optimization module, taking the product of the second positive weight coefficient and the planning time as a first variable, and taking the product of the third positive weight coefficient and the headway of the ramp vehicle and the next converging gap front vehicle as a second variable;
and taking the product of the fourth positive weight coefficient and the headway of the vehicle after the ramp vehicle and the next converging gap as a third variable, and taking the minimum result of subtracting the second variable from the first variable as an optimization target to obtain the target converging gap.
10. The dual-layer optimization-based vehicle ramp merge decision system as recited in claim 7, wherein,
if the selected longitudinal speed change maneuvering time is smaller than the set time threshold, starting to execute lane change; or if the distance between the ramp vehicle and the tail end of the accelerating lane is smaller than a set threshold value, starting to execute lane change;
and obtaining the lane change maneuver parameters of the ramp vehicle by taking the product of the fifth positive value weight coefficient and the lane change time and the minimization of the difference value of the planning speed as targets, and carrying out lane change control of the ramp vehicle according to the lane change maneuver parameters.
11. A computer readable storage medium, having stored thereon a program, which when executed by a processor, implements the steps of the double-layer optimization based vehicle ramp merge decision method as claimed in any one of claims 1-6.
12. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the steps in the double-layer optimization-based vehicle ramp merge decision method as claimed in any one of claims 1-6 when the program is executed.
13. A vehicle characterized in that the vehicle ramp merge decision method based on double-layer optimization as claimed in any one of claims 1-6 is adopted for merge control; alternatively, comprising the computer-readable storage medium of claim 11; or comprises the electronic device of claim 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311460469.9A CN117198082B (en) | 2023-11-06 | 2023-11-06 | Double-layer optimization-based vehicle ramp afflux decision method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311460469.9A CN117198082B (en) | 2023-11-06 | 2023-11-06 | Double-layer optimization-based vehicle ramp afflux decision method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117198082A true CN117198082A (en) | 2023-12-08 |
| CN117198082B CN117198082B (en) | 2024-04-05 |
Family
ID=88994519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311460469.9A Active CN117198082B (en) | 2023-11-06 | 2023-11-06 | Double-layer optimization-based vehicle ramp afflux decision method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117198082B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104464317A (en) * | 2014-12-03 | 2015-03-25 | 武汉理工大学 | Expressway entrance ring road converging zone guiding control system and method |
| JP2018067234A (en) * | 2016-10-21 | 2018-04-26 | 株式会社創発システム研究所 | Automatic driving support system of vehicle |
| US20200369281A1 (en) * | 2019-05-21 | 2020-11-26 | Suzuki Motor Corporation | Driving Control Apparatus For Vehicle |
| CN113947900A (en) * | 2021-10-15 | 2022-01-18 | 苏州科技大学 | Intelligent network connection express way ramp cooperative control system |
| CN114132341A (en) * | 2021-11-12 | 2022-03-04 | 中汽院智能网联科技有限公司 | Ramp track planning model for automatically-driven vehicle in Internet of vehicles environment |
| CN114708734A (en) * | 2022-05-07 | 2022-07-05 | 合肥工业大学 | Entrance ramp network connection manual driving vehicle main line converging cooperative control method |
| WO2023159841A1 (en) * | 2022-02-23 | 2023-08-31 | 东南大学 | Connected vehicle coordinated ramp merging multi-objective optimization control method for expressway, and system |
| CN116863699A (en) * | 2023-07-25 | 2023-10-10 | 东南大学 | Active transverse and longitudinal cooperative control method for vehicles in confluence region under mixed flow environment |
-
2023
- 2023-11-06 CN CN202311460469.9A patent/CN117198082B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104464317A (en) * | 2014-12-03 | 2015-03-25 | 武汉理工大学 | Expressway entrance ring road converging zone guiding control system and method |
| JP2018067234A (en) * | 2016-10-21 | 2018-04-26 | 株式会社創発システム研究所 | Automatic driving support system of vehicle |
| US20200369281A1 (en) * | 2019-05-21 | 2020-11-26 | Suzuki Motor Corporation | Driving Control Apparatus For Vehicle |
| CN113947900A (en) * | 2021-10-15 | 2022-01-18 | 苏州科技大学 | Intelligent network connection express way ramp cooperative control system |
| CN114132341A (en) * | 2021-11-12 | 2022-03-04 | 中汽院智能网联科技有限公司 | Ramp track planning model for automatically-driven vehicle in Internet of vehicles environment |
| WO2023159841A1 (en) * | 2022-02-23 | 2023-08-31 | 东南大学 | Connected vehicle coordinated ramp merging multi-objective optimization control method for expressway, and system |
| CN114708734A (en) * | 2022-05-07 | 2022-07-05 | 合肥工业大学 | Entrance ramp network connection manual driving vehicle main line converging cooperative control method |
| CN116863699A (en) * | 2023-07-25 | 2023-10-10 | 东南大学 | Active transverse and longitudinal cooperative control method for vehicles in confluence region under mixed flow environment |
Non-Patent Citations (3)
| Title |
|---|
| 刘见振等: "基于穿越时间的交通流临界间隙模型", 数学的实践与认识, vol. 40, no. 8 * |
| 席逸元 等: "快速路入口匝道区域合流策略及优化控制研究", 中国水运, vol. 22, no. 7 * |
| 张存保;李劲松;黄传明;夏银霞;: "基于车路协同的高速公路入口匝道车辆汇入引导方法", 武汉理工大学学报(交通科学与工程版), no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117198082B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111923910B (en) | Method for planning lane change of vehicle, autonomous vehicle and storage medium | |
| CN110471408B (en) | Unmanned vehicle path planning method based on decision process | |
| CN111867911B (en) | Vehicle control method and apparatus | |
| Luo et al. | A dynamic automated lane change maneuver based on vehicle-to-vehicle communication | |
| JP6715899B2 (en) | Collision avoidance device | |
| CN110187639A (en) | A kind of trajectory planning control method based on Parameter Decision Making frame | |
| Hang et al. | Driving conflict resolution of autonomous vehicles at unsignalized intersections: A differential game approach | |
| CN111289978A (en) | Method and system for making decision on unmanned driving behavior of vehicle | |
| CN110525436A (en) | Vehicle lane-changing control method, device, vehicle and storage medium | |
| US11442469B2 (en) | Coordinated control of vehicle cohorts | |
| JP2019034591A (en) | Device and method for controlling vehicle movement, and device and method for generating target trajectory | |
| JP7282271B2 (en) | Direct and indirect control of mixed autonomous vehicle platoons | |
| US20210074162A1 (en) | Methods and systems for performing lane changes by an autonomous vehicle | |
| CN113661106B (en) | Model-based predictive control for determining input variables to vehicle actuators | |
| CN111338353A (en) | Intelligent vehicle lane change track planning method under dynamic driving environment | |
| CN112965476A (en) | High-speed unmanned vehicle trajectory planning system and method based on multi-window sampling | |
| WO2023024914A1 (en) | Vehicle avoidance method and apparatus, computer device, and storage medium | |
| US20240166242A1 (en) | Intelligent driving decision-making method, vehicle traveling control method and apparatus, and vehicle | |
| CN114707364A (en) | Ramp vehicle convergence simulation method, device, equipment and readable storage medium | |
| CN111081069A (en) | Vehicle track control method for bottleneck area of expressway | |
| WO2018225493A1 (en) | Vehicle movement controller | |
| CN114510032A (en) | Multi-vehicle cooperative control method and device for guaranteeing rapid formation stability of vehicles | |
| CN117198082B (en) | Double-layer optimization-based vehicle ramp afflux decision method and system | |
| CN115447615A (en) | Trajectory optimization method based on vehicle kinematics model predictive control | |
| CN113942512A (en) | Automatic overtaking method for unmanned vehicle |
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 |