Vehicle queue lane changing planning and control method based on staged road right game

Abstract

The invention relates to a vehicle queue lane changing planning and control method based on a staged road right game, and belongs to the technical field of automatic driving, and the method specifically comprises the following steps: S1, an automatic driving vehicle carries out the sampling of a lane changing longitudinal position, carries out the discretization of a lane changing process, and senses the surrounding environment through sensor equipment; s2, based on environment perception information, performing dynamic gaming with other vehicles through a multi-vehicle non-cooperative gaming decision-making algorithm to determine the optimal lane changing opportunity and strategy; s3, according to a decision result, generating a reference trajectory based on an artificial fish swarm algorithm, and completing vehicle queue trajectory planning; s4, performing vehicle queue motion control according to a trajectory planning result; and S5, the vehicle queue travels along a predetermined track, lane changing is carried out in stages, and the processes from S2 to S4 are repeated until lane changing is completed when the queue reaches the target lane.

Description

Technical Field

[0001] The present invention belongs to the technical field of autonomous driving and relates to a vehicle queue lane change planning and control method based on a staged road right game. Background Art

[0002] With the development of autonomous driving technology, the lane-changing behavior of vehicles has received more and more attention. Most existing lane-changing algorithms assume that the state of surrounding vehicles remains unchanged and adopt static planning methods. However, in actual traffic, the surrounding vehicles are changing dynamically, and the lane-changing strategy needs to be adjusted dynamically to ensure the safety of vehicles during the lane-changing process. In addition, vehicles traveling in a platoon can effectively improve traffic efficiency, alleviate traffic congestion, improve driving safety, and improve fuel economy. However, existing research focuses on the lane-changing decision of a single vehicle and lacks overall consideration of the lane-changing of vehicle platoons. Summary of the invention

[0003] In view of this, an object of the present invention is to provide a vehicle queue lane change planning and control method based on staged road right game.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] A vehicle platoon lane change planning and control method based on staged road right game specifically comprises the following steps:

[0006] S1: The autonomous driving vehicle samples the longitudinal position of the lane change, discretizes the lane change process, and perceives the surrounding environment through sensor equipment;

[0007] S2: Based on the information from environmental perception, a multi-vehicle non-cooperative game decision algorithm is used to dynamically compete with other vehicles to determine the best lane-changing timing and strategy;

[0008] S3: Based on the decision result, a reference trajectory is generated based on the artificial fish swarm algorithm to complete the vehicle queue trajectory planning;

[0009] S4: Carry out vehicle platoon motion control based on trajectory planning results;

[0010] S5: The vehicle queue travels along the predetermined trajectory, changes lanes in stages, and repeats the process from S2 to S4 until the lane change is completed when the queue reaches the target lane.

[0011] Furthermore, in step S1, the lateral distance between two adjacent lanes is divided into several segments, each of which is marked with a redecision line, denoted as j, where j = 1, 2, 3, ..., j max The cautious lane-changing process is considered as an iterative cycle of decision-making, trajectory planning, and motion control, repeated at least j times. max -1 times.

[0012] Further, step S2 specifically includes the following steps:

[0013] S21: Based on the information from environmental perception, the system dynamically negotiates with other vehicles to determine the best lane-changing timing and strategy. Specifically, the following decisions are considered:

[0014]

[0015] Γ LV ={B1,B2}={acceleration, deceleration}(1b)

[0016] Based on the Stackelberg game model, the extended payoff matrix is ​​established as follows:

[0017]

[0018] Where P SV and P LV Represent the benefits of the corresponding decisions of SV and LV respectively.

[0019] S22: Calculate the corresponding profit values ​​of SV and LV.

[0020] The return of SV is defined as follows:

[0021]

[0022] In the formula, represents the safety benefit of SV, represents the lane-changing efficiency gain of SV, δ SV Indicates the aggressiveness coefficient of SV.

[0023] The safety benefit of SV is calculated as:

[0024]

[0025] In the formula, h w and l w Represent the lateral safety distance and vehicle width respectively, y SV Indicates the lateral position of SV, y LV represents the lateral position of LV, e y, S ,L =y LV -y SV represents the real-time lateral distance between LV and SV, and π1 represents the safety factor of the autonomous driving vehicle queue, which is specifically expressed as follows:

[0026]

[0027] Where T S,L T represents the headway between the center of the queue and LV. d,SVrepresents the expected headway between SV and LV, which is expressed by the formula T d,SV =min(3×(n+1),T F,S ) decides, T F,S and T P,L They represent the initial headway time between FV and SV, PV and LV, respectively, T S,L , T F,S and T P,L The following definitions are given:

[0028]

[0029]

[0030] In the formula, x P represents the longitudinal position of the center point of the autonomous vehicle queue, x LV 、x FV 、x PV and x SV represent the longitudinal positions of LV, FV, PV and SV respectively, v SV and v LV Represent the velocities of SV and LV, respectively.

[0031] The efficiency gains of SV are as follows:

[0032]

[0033] The return of LV is defined as follows:

[0034]

[0035] In the formula, represents the safety yield of LV, represents the lane-changing efficiency gain of LV, δ LV Indicates the aggressiveness coefficient of LV.

[0036] Delta of human-driven vehicles LV The definition is as follows:

[0037]

[0038] Where a LV Indicates the acceleration of LV.

[0039] LV's safety benefits are as follows:

[0040]

[0041] The efficiency gains of LV are as follows:

[0042]

[0043] Where n is the vehicle serial number.

[0044] The safety factor π2 of LV is defined as:

[0045]

[0046] Where T d,LV represents the expected headway time of LV, T d,LV =min(3×(n+1),T P,L ).

[0047] S23: Find the best decision result.

[0048] In order to solve the Stackelberg game equilibrium, the solution formula is as follows:

[0049]

[0050] In the formula, Λ LV (A) represents the available decision set of LV when SV has made a decision, which is expressed as follows:

[0051]

[0052] In the formula, a min and a max Indicates the upper and lower bounds of acceleration due to mechanical properties.

[0053] Further, step S3 specifically includes the following steps:

[0054] S31: Use a fifth-order polynomial based on undetermined coefficients to describe the reference trajectory, including the longitudinal and lateral positions of the SV over time:

[0055]

[0056] Where t∈[0,T], t0 represents the generation timestamp of each optimal lane-changing decision; and denote the longitudinal and lateral position increments of the SV, respectively; T denotes the lane change duration relative to the reference trajectory; and represents the undetermined coefficient.

[0057] S32: Assuming that the speed of the SV remains constant throughout the lane-changing maneuver, the result is:

[0058]

[0059]

[0060] In the formula, represents the SV velocity at time t0, represents the initial heading angle of the SV at time t0, a0 represents the SV acceleration at time t0, X represents the final longitudinal position increment, and Y represents the final lateral position increment.

[0061] S33: Generate a reference trajectory using the method based on the artificial fish swarm algorithm, and combine equations (14)-(15) to obtain:

[0062]

[0063] Among them, X and T are the only unknown variables, which determine the final reference lane change trajectory.

[0064] In a real vehicle lane-changing scenario, the lane-changing efficiency and driving comfort of the lane-changing vehicle are key indicators for evaluating the quality of the lane-changing trajectory. The lane-changing duration and normal acceleration of the SV are usually used to characterize the lane-changing efficiency and driving comfort. Therefore, the following cost function is considered:

[0065]

[0066] In the formula, λ represents the weight factor used to balance the influence of variables, a max,l and T max denote the maximum acceleration and lane-changing duration related to mechanical performance and lane-changing rules, respectively. represents the normal acceleration of the SV, T represents the lane-changing duration; K represents the curvature of the planned trajectory. Without considering sideslip, the K curvature reaches its peak when the vehicle completes the lane change. The specific expression is as follows:

[0067]

[0068] In the formula, x SV and SV denote the longitudinal and lateral positions of SV, θ SV Indicates the vehicle heading angle.

[0069] Formula (17) can be rewritten as:

[0070]

[0071] The process of solving the cost function based on the above formula can be transformed into a typical nonlinear optimization problem. Therefore, the optimal cost J and the corresponding X and T values ​​are obtained based on the artificial fish swarm algorithm. In addition, considering the execution delay τ, the safety distance should meet the following conditions:

[0072]

[0073] In the formula, S LV and SSV They represent the safe distances of LV and SV relative to PV respectively. The advance distances of LV and PV within time T are estimated by the following formula:

[0074]

[0075] In the formula, h c and l c Represent the longitudinal safety distance and vehicle length respectively.

[0076] At the initial time, S LV,0 =x P (0)-x LV (0),S PV,0 =x PV (0)-x P (0), the constraint function satisfies:

[0077]

[0078] Based on this X and T can finally be defined.

[0079] Further, the vehicle queue motion control described in step S4 specifically includes the following steps:

[0080] S41: Longitudinal controller:

[0081] The kinematics of each autonomous vehicle is described as:

[0082]

[0083] In the formula, x i and i (i=SV,1,2,3...n) represent the longitudinal position and lateral position of vehicle i, v i represents the speed of vehicle i, v x,i and v y,i denote the longitudinal and lateral components of the velocity of vehicle i, respectively, θ i represents the heading angle of vehicle i, u x,i and u y,i They represent the control quantities of the longitudinal motion control and lateral motion control of vehicle i respectively.

[0084] Based on equation (24), the longitudinal kinematics is:

[0085]

[0086] Under the pilot-following topology PLF, the longitudinal controller of the autonomous driving vehicle is designed as follows:

[0087]

[0088] In the formula, i=1,2...,n,κ i,m and ρ i,SV They represent the communication links between vehicle m and vehicle i, and between SV and vehicle i respectively, and α1 and β1 represent the control gains with respect to the position difference and speed difference respectively.

[0089] The design of the SV longitudinal controller is as follows:

[0090]

[0091] S42: Lateral Controller:

[0092] Based on equation (24), the lateral kinematics is:

[0093]

[0094] The lateral component of the reference trajectory can be passed to all the following autonomous vehicles, and the lateral controller of the autonomous vehicle is designed as follows:

[0095]

[0096] In the formula, i=SV,1,2…,n, η i =α2e y,i (ε y 2 -e y,i 2 ) represents the virtual lateral control law, that is, the expected lateral velocity value, α2 represents η i The control gain, e y,i represents the lateral distance error boundary of vehicle i, z yv,i =e yv,i +η i represents the correlation coefficient associated with the expected lateral velocity value, and β2 represents z yv,i The control gain, z + The following conditional functions are met;

[0097]

[0098] The beneficial effect of the present invention is that the strategy of the present invention is able to generate appropriate decisions and trajectories even in cases where human-driven vehicles make suboptimal decisions due to driver uncertainty. In addition, the controller outperforms the baseline controller in terms of stability and consistency, confirming its superiority in maintaining the comfort and safety of the autonomous vehicle platoon during the vehicle platoon lane change maneuver. The proposed strategy has the potential for practical application and can improve the safety and efficiency of autonomous vehicle platoon cooperation, especially in mixed traffic environments.

[0099] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0101] Figure 1 A diagram illustrating the lane-changing planning and control method for a vehicle platoon in a multi-vehicle road right game;

[0102] Figure 2 An illustration of simultaneous lane changing of a vehicle queue controlled by multi-vehicle non-cooperative game planning. DETAILED DESCRIPTION

[0103] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0104] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0105] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the implementation cases of the present invention difficult to understand.

[0106] The present invention provides a vehicle platoon lane change planning and control method based on staged road right game to improve the lane change safety and efficiency of autonomous driving vehicles in complex traffic environments. The method includes the following steps:

[0107] S1: The autonomous vehicle samples the longitudinal position of the lane change, discretizes the lane change process, and senses the surrounding environment through sensors and other equipment, including the position and speed of other vehicles. In order to replicate the cautious lane-changing behavior of human drivers, the lateral distance between two adjacent lanes is divided into several segments, each of which is marked with a re-decision line, denoted as j, j = 1, 2, 3..., j max The cautious lane-changing process is considered as an iterative cycle of decision-making, trajectory planning, and motion control, repeated at least j times. max -1 time;

[0108] S2: Based on the information from environmental perception, the system conducts dynamic games with other vehicles to determine the best lane-changing timing and strategy, and develops a multi-vehicle non-cooperative game decision-making method that considers comfort, cost, and benefits to make the best decision;

[0109] S3: Based on the decision results, the system generates a reference trajectory based on the artificial fish swarm algorithm and completes the vehicle queue trajectory planning;

[0110] S4: The system controls the movement of the vehicle platoon according to the trajectory planning results;

[0111] S5: The vehicle queue drives along the predetermined trajectory and changes lanes in stages, repeating the process from S2 to S4 until the lane change is completed when the queue reaches the target lane. Figure 1-2 shown.

[0112] In this embodiment, it is necessary to first sense the surrounding environment through sensors and other devices, including the location, speed and other information of other vehicles. On this basis, the system conducts dynamic games with other vehicles to determine the best lane change timing and strategy, and develops a multi-vehicle non-cooperative game decision-making method. According to the decision results, a reference trajectory is generated based on the artificial fish school algorithm, and the vehicle queue trajectory planning is completed. According to the trajectory planning results, the vehicle queue motion control is performed to improve the lane change safety and efficiency of autonomous driving vehicles in complex traffic environments. Next, this embodiment describes the present invention in detail from the aspects of decision-making, trajectory planning and motion control of the multi-vehicle non-cooperative game method.

[0113] In step S2, based on the information from environmental perception, the system conducts dynamic game with other vehicles to determine the best lane change timing and strategy. Specifically, the following decisions are considered:

[0114]

[0115] Γ LV ={B1,B2}={acceleration, deceleration}(1b)

[0116] Based on the Stackelberg game model, the extended payoff matrix is ​​established as shown in Table 1.

[0117] Table 1

[0118]

[0119] In Table 1, P SV and P LV Represent the benefits of the corresponding decisions of SV and LV respectively.

[0120] The return of SV is defined as follows:

[0121]

[0122] In the formula, represents the safety benefit of SV, represents the lane-changing efficiency gain of SV, δ SV Indicates the aggressiveness coefficient of SV.

[0123] The safety benefit of SV is calculated as:

[0124]

[0125] In the formula, h w and l w Represent the lateral safety distance and vehicle width respectively, y SV Indicates the lateral position of SV, y LV represents the lateral position of LV, e y,S,L =y LV -y SV represents the real-time lateral distance between LV and SV, and π1 represents the safety factor of the autonomous driving vehicle queue, which is specifically expressed as follows:

[0126]

[0127] Where T S,L T represents the headway between the center of the queue and LV. d,SV represents the expected headway between SV and LV, which is expressed by the formula T d,SV =min(3×(n+1),T F,S ) decides, T F,S and T P,L They represent the initial headway time between FV and SV, PV and LV, respectively, T SL , T FS and T PL The following definitions are given:

[0128]

[0129] In the formula, xP represents the longitudinal position of the center point of the autonomous vehicle queue, x LV 、x FV 、x PV and x SV represent the longitudinal positions of LV, FV, PV and SV respectively, v SV and v LV Represent the velocities of SV and LV, respectively.

[0130] The efficiency gains of SV are as follows:

[0131]

[0132] The return of LV is defined as follows:

[0133]

[0134] In the formula, represents the safety yield of LV, represents the lane-changing efficiency gain of LV, δ LV Indicates the aggressiveness coefficient of LV.

[0135] Delta of human-driven vehicles LV The definition is as follows:

[0136]

[0137] Where a LV Indicates the acceleration of LV.

[0138] LV's safety benefits are as follows:

[0139]

[0140] The efficiency gains of LV are as follows:

[0141]

[0142] Where n is the vehicle serial number.

[0143] The safety factor π2 of LV is defined as:

[0144]

[0145] Where T d,LV represents the expected headway time of LV, T d,LV =min(3×(n+1),T P,L ).

[0146] Solve the Stackelberg game equilibrium, the solution formula is as follows:

[0147]

[0148] In the formula, Λ LV (A) represents the available decision set of LV when SV has made a decision, which is expressed as follows:

[0149]

[0150] In the formula, a min and a max Indicates the upper and lower bounds of acceleration due to mechanical properties.

[0151] Therefore, the optimal decisions of SV and LV based on the multi-vehicle non-cooperative game method are determined by combining equations (2), (7), (12), and (13).

[0152] In step S3, in order to implement the decision, this embodiment uses a method based on an artificial fish swarm algorithm to generate a reference trajectory.

[0153] To ensure smoothness, this embodiment uses a fifth-order polynomial based on undetermined coefficients to describe the reference trajectory, including the longitudinal position and lateral position of the SV over time:

[0154]

[0155] Where t∈[0,T], t0 represents the generation timestamp of each optimal lane-changing decision. and denote the longitudinal and lateral position increments of the SV, respectively. T denotes the lane change duration relative to the reference trajectory. and represents the undetermined coefficient.

[0156] To simplify the calculation, it is assumed that the speed of the SV remains constant throughout the lane-changing maneuver, resulting in:

[0157]

[0158]

[0159] In the formula, represents the SV velocity at time t0, represents the initial heading angle of the SV at time t0, a0 represents the SV acceleration at time t0, X represents the final longitudinal position increment, and Y represents the final lateral position increment.

[0160] Combining (14)-(15) we get:

[0161]

[0162] Among them, X and T are the only unknown variables, which determine the final reference lane change trajectory.

[0163] In a real vehicle lane-changing scenario, the lane-changing efficiency and driving comfort of the lane-changing vehicle are key indicators for evaluating the quality of the lane-changing trajectory. The lane-changing duration and normal acceleration of the SV are usually used to characterize the lane-changing efficiency and driving comfort. Therefore, the following cost function is considered:

[0164]

[0165] In the formula, λ represents the weight factor used to balance the influence of variables, a max,l and T max denote the maximum acceleration and lane-changing duration related to mechanical performance and lane-changing rules, respectively. represents the normal acceleration of the SV, T represents the lane-changing duration; K represents the curvature of the planned trajectory. Without considering sideslip, the K curvature reaches its peak when the vehicle completes the lane change. The specific expression is as follows:

[0166]

[0167] In the formula, x SV and SV denote the longitudinal and lateral positions of SV, θ SV Indicates the vehicle heading angle.

[0168] Formula (17) can be rewritten as:

[0169]

[0170] The process of solving the cost function can be transformed into a typical nonlinear optimization problem. Therefore, the optimal cost J and the corresponding X and T values ​​can be obtained based on the artificial fish swarm algorithm. In addition, considering the execution delay τ, the safety distance should meet the following conditions:

[0171]

[0172] In the formula, S LV and S SV Respectively represent the safe distance of LV and SV relative to PV. Then, the advancement distance of LV and PV in time T can be estimated by the following formula:

[0173]

[0174] Therefore, LV and PV can be obtained.

[0175]

[0176] At the initial time, S LV,0 =x P (0)-x LV(0),S PV,0 =x PV (0)-x P (0).

[0177] Therefore, the constraint function should satisfy:

[0178]

[0179] Based on this X and T can finally be defined.

[0180] In step S4, this embodiment implements motion control from two aspects: the lateral controller and the longitudinal controller:

[0181] Vertical controller:

[0182] The kinematics of each autonomous vehicle can be described as:

[0183]

[0184] In the formula, x i and i (i=SV,1,2,3...n) represent the longitudinal position and lateral position of vehicle i respectively. i represents the speed of vehicle i. x,i and v y,i They represent the longitudinal and lateral components of the velocity of vehicle i, respectively. i represents the heading angle of vehicle i, u x,i and u y,i They represent the control quantities of the longitudinal motion control and lateral motion control of vehicle i respectively.

[0185] From formula (24), we can see that the longitudinal kinematics is:

[0186]

[0187] Under PLF, the longitudinal controller of the autonomous vehicle is designed as follows:

[0188]

[0189] For i = 1, 2, ..., n. In formula (26) κ i,m and ρ i,SV They represent the communication links between vehicle m and vehicle i, and between SV and vehicle i, respectively. α1 and β1 represent the control gains with respect to the position difference and speed difference, respectively.

[0190] Similarly, the design of the SV longitudinal controller is as follows:

[0191]

[0192] Horizontal controller:

[0193] Based on equation (24), the lateral kinematics is:

[0194]

[0195] Assuming that the lateral component of the reference trajectory can be transferred to all the following autonomous vehicles, the lateral controller of the following autonomous vehicles is designed as follows:

[0196]

[0197] For i = SV, 1, 2, ..., n. In formula (29) η i =α2e y,i (ε y 2 -e y,i 2 ) represents the virtual lateral control law, that is, the expected lateral velocity value. α2 represents η i The control gain of z yv,i =e yv,i +η i represents the correlation coefficient with the expected lateral velocity value. β2 represents z yv,i The control gain of z + The function satisfies the following conditions.

[0198]

[0199] Finally, the vehicle queue travels along the predetermined trajectory, changes lanes in stages, and repeats the process from S2 to S4 until the lane change is completed when the queue reaches the target lane.

[0200] In the above embodiments, the description's reference to "this embodiment" indicates that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least some embodiments, but not necessarily all embodiments. Multiple occurrences of "this embodiment" do not necessarily all refer to the same embodiment.

[0201] In the above-described embodiments, although the invention has been described in conjunction with specific embodiments of the invention, many substitutions, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other storage structures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed. Embodiments of the invention are intended to encompass all such substitutions, modifications, and variations that fall within the broad scope of the appended claims.

[0202] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, any one of the methods in this embodiment is implemented.

[0203] This embodiment also provides an electronic terminal, including: a processor and a memory;

[0204] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods in this embodiment.

[0205] The computer-readable storage medium in this embodiment can be understood by ordinary technicians in this field: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0206] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run computer programs so that the electronic terminal executes each step of the above method.

[0207] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0208] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0209] The present invention can be used in many general or special computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like.

[0210] The present invention may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0211] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A vehicle platoon lane change planning and control method based on staged road right game, characterized by: The specific steps include: S1: The autonomous driving vehicle samples the longitudinal position of the lane change, discretizes the lane change process, and perceives the surrounding environment through sensor equipment; S2: Based on the information from environmental perception, a multi-vehicle non-cooperative game decision algorithm is used to dynamically compete with other vehicles to determine the best lane-changing timing and strategy; S3: Based on the decision result, a reference trajectory is generated based on the artificial fish swarm algorithm to complete the vehicle queue trajectory planning; S4: Carry out vehicle platoon motion control based on trajectory planning results; S5: The vehicle queue travels along the predetermined trajectory, changes lanes in stages, and repeats the process from S2 to S4 until the lane change is completed when the queue reaches the target lane.

2. The vehicle platoon lane change planning and control method based on staged road right game according to claim 1 is characterized by: In step S1, the lateral distance between two adjacent lanes is divided into several segments, each of which is marked with a redecision line, denoted as j, where j = 1, 2, 3..., j max The cautious lane-changing process is considered as an iterative cycle of decision-making, trajectory planning, and motion control, repeated at least j times. max -1 times.

3. The vehicle platoon lane change planning and control method based on staged road right game according to claim 1 is characterized by: Step S2 specifically includes the following steps: S21: Based on the information from environmental perception, the system dynamically negotiates with other vehicles to determine the best lane-changing timing and strategy, specifically considering the following decisions: Γ LV ={B1,B2}={acceleration, deceleration}(1b) Based on the Stackelberg game model, the extended payoff matrix is ​​established as follows: Where P SV and P LV Represent the benefits of the corresponding decisions of SV and LV respectively; S22: Calculate the corresponding benefit values ​​of SV and LV; The return of SV is defined as follows: In the formula, represents the safety benefit of SV, represents the lane-changing efficiency gain of SV, δ SV represents the aggressiveness coefficient of SV; The safety benefit of SV is calculated as: In the formula, h w and l w Represent the lateral safety distance and vehicle width respectively, y SV Indicates the lateral position of SV, y LV represents the lateral position of LV, e y,S,L =y LV -y SV represents the real-time lateral distance between LV and SV, and π1 represents the safety factor of the autonomous driving vehicle queue, which is specifically expressed as follows: Where T S,L T represents the headway between the center of the queue and LV. d,SV represents the expected headway between SV and LV, which is expressed by the formula T d,SV =min(3×(n+1),T F,S ) decides, T F,S and T P,L They represent the initial headway time between FV and SV, PV and LV, T S,L , T F,S and T P,L The following definitions are given: In the formula, x P represents the longitudinal position of the center point of the autonomous vehicle queue, x LV 、x FV 、x PV and x SV represent the longitudinal positions of LV, FV, PV and SV respectively, v SV and v LV denote the velocities of SV and LV, respectively; The efficiency gains of SV are as follows: The return of LV is defined as follows: In the formula, represents the safety yield of LV, represents the lane-changing efficiency gain of LV, δ LV represents the aggressiveness coefficient of LV; Delta of human-driven vehicles LV The definition is as follows: Where a LV represents the acceleration of LV; LV's safety benefits are as follows: The efficiency gains of LV are as follows: In the formula, n represents the vehicle serial number; The safety factor π2 of LV is defined as: Where T d,LV represents the expected headway time of LV, T d,LV =min(3×(n+1),T P,L ); S23: Solve the best decision result; In order to solve the Stackelberg game equilibrium, the solution formula is as follows: In the formula, Λ LV (A) represents the available decision set of LV when SV has made a decision, which is expressed as follows: In the formula, a min and a max Indicates the upper and lower bounds of acceleration due to mechanical properties.

4. The vehicle platoon lane change planning and control method based on staged road right game according to claim 1 is characterized by: Step S3 specifically includes the following steps: S31: Use a fifth-order polynomial based on undetermined coefficients to describe the reference trajectory, including the longitudinal and lateral positions of the SV over time: Where t∈[0,T], t0 represents the generation timestamp of each optimal lane-changing decision; and denote the longitudinal and lateral position increments of the SV, respectively; T denotes the lane change duration relative to the reference trajectory; and represents the undetermined coefficient; S32: Assuming that the speed of the SV remains constant throughout the lane change maneuver, the result is: In the formula, represents the SV velocity at time t0, represents the initial heading angle of SV at time t0, a0 represents the acceleration of SV at time t0, X represents the final longitudinal position increment, and Y represents the final lateral position increment; S33: Generate a reference trajectory using the method based on the artificial fish swarm algorithm, and combine equations (14)-(15) to obtain: Among them, X and T are the only unknown variables, which determine the final reference lane change trajectory; The lane changing duration and normal acceleration of SV are used to characterize the lane changing efficiency and driving comfort, and the following cost function is considered: In the formula, λ represents the weight factor used to balance the influence of variables, a max,l and T max denote the maximum acceleration and lane-changing duration related to mechanical performance and lane-changing rules, respectively. represents the normal acceleration of the SV, T represents the lane-changing duration; K represents the curvature of the planned trajectory. Without considering sideslip, the K curvature reaches its peak when the vehicle completes the lane change. The specific expression is as follows: In the formula, x SV and SV denote the longitudinal and lateral positions of SV, θ SV Indicates the vehicle heading angle; Formula (17) can be rewritten as: The process of solving the cost function based on the above formula is transformed into a typical nonlinear optimization problem. The optimal cost J and the corresponding X and T values ​​are obtained based on the artificial fish swarm algorithm. Considering the execution delay τ, the safety distance satisfies the following conditions: In the formula, S LV and S SV They represent the safe distances of LV and SV relative to PV respectively. The advance distances of LV and PV within time T are estimated by the following formula: In the formula, h c and l c They represent the longitudinal safety distance and vehicle length respectively; At the initial time, S LV,0 =x P (0)-x LV (0),S PV,0 =x PV (0)-x P (0), the constraint function satisfies: Based on this X and T can finally be defined.

5. The vehicle platoon lane change planning and control method based on staged road right game according to claim 1 is characterized by: The vehicle queue motion control described in step S4 specifically includes the following steps: S41: Longitudinal controller: The kinematics of each autonomous vehicle is described as: In the formula, x i and i (i=SV,1,2,3…n) represent the longitudinal position and lateral position of vehicle i, v i represents the speed of vehicle i, v x,i and v y,i denote the longitudinal and lateral components of the velocity of vehicle i, respectively, θ i represents the heading angle of vehicle i, u x,i and u y,i They represent the control quantities of the longitudinal motion control and lateral motion control of vehicle i respectively; Based on equation (24), the longitudinal kinematics is: Under the pilot-following topology PLF, the longitudinal controller of the autonomous driving vehicle is designed as follows: In the formula, i=1,2…,n,κ i,m and ρ i,SV denote the communication links between vehicle m and vehicle i, and between SV and vehicle i, respectively; α1 and β1 denote the control gains with respect to the position difference and speed difference, respectively; The design of the SV longitudinal controller is as follows: S42: Lateral Controller: Based on equation (24), the lateral kinematics is: The lateral component of the reference trajectory can be passed to all the following autonomous vehicles, and the lateral controller of the autonomous vehicle is designed as follows: In the formula, i=SV,1,2…,n, η i =α2e y,i (ε y 2 -e y,i 2 ) represents the virtual lateral control law, that is, the expected lateral velocity value, α2 represents η i The control gain, e y,i represents the lateral distance error boundary of vehicle i, z yv,i =e yv,i +η i represents the correlation coefficient associated with the expected lateral velocity value, and β2 represents z yv,i The control gain, z + The following conditional functions are met;

Images