Motorcade transverse decision control method and device fusing game theory and predictive control

By integrating game theory and predictive control, the optimal moment and speed of the fleet during lane change is determined, and the problem of a great impact on environmental vehicles during lane change in the prior art is solved, and the traffic efficiency is improved.

CN119002487APending Publication Date: 2024-11-22TSINGHUA UNIVERSITY
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411089509.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Existing fleet control technology ignores the impact on other environmental vehicles on the road when changing lanes, resulting in reduced traffic efficiency.

Method used

Using a fleet horizontal decision-making method that integrates game theory and predictive control, the lane change cost is determined, including driving cost and impact cost on environmental vehicles, and the time with the lowest lane change cost and Speed ​​to control lane change.

Benefits of technology

It effectively reduces the impact on environmental vehicle traffic efficiency and improves the overall efficiency during lane change.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119002487A_ABST
    Figure CN119002487A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent driving, in particular to a motorcade transverse decision control method and device integrating the game theory and predictive control. The method comprises the following steps: determining a plurality of expected lane changing moments in an expected period; the lane changing cost of the controlled vehicle team at each expected lane changing moment is determined, the lane changing cost comprises the driving cost of lane changing of the controlled vehicle team and the influence cost of lane changing on environmental vehicles, the driving cost represents the difficulty degree of lane changing, and the influence cost represents the influence degree on environmental vehicle passing; taking the expected lane changing moment with the lowest lane changing cost in the plurality of expected lane changing moments as a target lane changing moment, and determining a target lane changing speed of the controlled motorcade at the target lane changing moment; and then controlling the controlled motorcade to change lanes based on the target lane changing time and the target lane changing speed. By adopting the method, the influence on the environment vehicle passing efficiency during lane changing can be reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a lateral decision-making control method and device for a vehicle fleet that integrates game theory and predictive control. Background Art

[0002] In related technologies, unmanned guided convoys have gradually been adopted to perform transportation tasks in the fields of logistics and mining transportation. In order to improve traffic efficiency and reduce labor costs, more and more research has been conducted on intelligent and interconnected guided convoys in recent years. Usually, a guided convoy consists of a leading vehicle and several following vehicles, and only the leading vehicle is equipped with high-performance sensors and computing platforms for environmental perception. Therefore, a collaborative control strategy should be used to maintain the integrity of the convoy during driving.

[0003] In the current convoy control technology, most of them adopt the method of the rear vehicle automatically following the front vehicle to perform adaptive cruise control or the front and rear vehicles perform coordinated adaptive cruise control; in the control method of the convoy by related technologies, when choosing the timing of changing lanes (obstacle avoidance or overtaking), it is often necessary to change lanes and overtake after determining that the current road conditions meet the overtaking requirements, but this will ignore the impact on other environmental vehicles on the road, thereby reducing the traffic efficiency of other vehicles.

[0004] Therefore, how to reduce the impact on the environment and vehicle traffic efficiency when changing lanes is an urgent problem that needs to be solved. Summary of the invention

[0005] Based on this, it is necessary to provide a fleet lateral decision control method and vehicle that integrates game theory and predictive control to reduce the impact on the vehicle traffic efficiency of the environment in order to address the above technical problems.

[0006] In a first aspect, the present application provides a lateral decision control method for a convoy integrating game theory and predictive control, which is executed by a head vehicle in a controlled convoy, and the method comprises:

[0007] Collecting a plurality of expected lane change moments within an expected period, where the expected period is a future time period;

[0008] Determine the lane change cost of the controlled fleet at each expected lane change moment, wherein the lane change cost includes the driving cost of the controlled fleet changing lanes and the impact cost on the surrounding vehicles due to the lane change, wherein the driving cost represents the difficulty of the lane change, and the impact cost represents the degree of impact on the passage of surrounding vehicles;

[0009] taking the expected lane changing time with the lowest lane changing cost among the multiple expected lane changing times as the target lane changing time, and determining the target lane changing speed of the controlled vehicle fleet at the target lane changing time;

[0010] The controlled vehicle fleet is controlled to change lanes based on the target lane-changing time and the target lane-changing speed.

[0011] In one embodiment, each controlled vehicle in the controlled vehicle fleet maintains the same speed and has the same body length, the driving cost includes a first collision penalty, a deviation penalty, a comfort level, and a speed penalty, and determining the driving cost at each of the expected lane change moments includes:

[0012] Determine state information of each controlled vehicle and state information of each environment vehicle at each expected lane change moment, wherein the state information includes position and speed;

[0013] Determine a first collision penalty of the controlled vehicle fleet at each expected lane change moment based on state information of each controlled vehicle, state information of each environmental vehicle, and a first collision penalty function at each expected lane change moment; the first collision penalty function is constructed based on the position and speed of each controlled vehicle at any moment, the position and speed of the leading vehicle in front of the leading vehicle, and the body length of the leading vehicle, the leading vehicle being the frontmost controlled vehicle in the controlled vehicle fleet;

[0014] Determine the deviation penalty of the controlled vehicle fleet at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle and a deviation penalty function at each expected lane change moment, wherein the deviation penalty function is constructed based on the reference speed of the controlled vehicle fleet at any moment, the speed of the leading vehicle, the position and speed of the leading vehicle's front vehicle and the body length of the leading vehicle;

[0015] Determining the comfort of the controlled vehicle fleet at each of the expected lane change moments based on the state information of each controlled vehicle, the state information of each environment vehicle, and a comfort function, wherein the comfort function is constructed based on the acceleration of the leading vehicle at any moment;

[0016] The speed penalty of the controlled traffic jam at each expected lane change moment is determined based on the state information of each controlled vehicle, the state information of each environmental vehicle and a speed penalty function, wherein the speed penalty function is constructed based on the speed of the lead vehicle and the speed of the vehicle preceding the lead vehicle at any moment.

[0017] In one embodiment, the impact cost includes a second collision penalty and a deceleration penalty, and determining the impact cost on the environment vehicle at each expected lane change moment includes:

[0018] Determine a second collision penalty of the controlled convoy at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle, and a second collision penalty function at each expected lane change moment, wherein the second collision penalty function is constructed based on the position, body length, and speed of the leading vehicle and the speed and velocity of the following vehicle at any moment, wherein the following vehicle is an environmental vehicle behind the controlled convoy;

[0019] Based on the state information of each controlled vehicle, the state information of each environmental vehicle and the deceleration penalty function at each expected lane change moment, the deceleration penalty of the controlled vehicle fleet at each expected lane change moment is determined, and the deceleration penalty function is determined based on the initial speed of the following vehicle and the speed of the leading vehicle, and the initial speed is the speed before being affected by the lane change of the controlled vehicle fleet.

[0020] In one embodiment, the determining of the state information of each controlled vehicle and the state information of each environment vehicle at each expected lane change moment includes:

[0021] For any environment vehicle, the position of the vehicle behind the environment vehicle, the position of the environment vehicle and the speed of the leading vehicle in the controlled convoy at any time are input into the following model to obtain the speed of the environment vehicle at any time;

[0022] Inputting the real-time speed and real-time position of each controlled vehicle in the controlled vehicle fleet into the longitudinal motion model of the controlled vehicle fleet, and obtaining the position of each controlled vehicle in the controlled vehicle fleet at each expected lane change time;

[0023] The real-time position and real-time speed of each environmental vehicle are input into the longitudinal motion model of the environmental vehicle to obtain the position of each environmental vehicle at each expected lane change moment.

[0024] In one embodiment, controlling the controlled vehicle fleet to change lanes based on the target lane change time and the target lane change speed includes:

[0025] Collecting environmental information within the perception field of view, and constructing a safe driving corridor for the controlled vehicle fleet based on the environmental information, wherein the environmental information includes status information of each controlled vehicle in the controlled vehicle fleet and status information of each environmental vehicle, and the boundary of the safe driving corridor is determined based on the position and speed of the environmental vehicle;

[0026] Constructing a lateral motion model of each controlled vehicle in the controlled fleet, wherein the lateral motion model represents the relationship between the lateral speed and lateral position of the vehicle at any time and the front wheel inclination angle;

[0027] Determining a front wheel steering angle of the controlled vehicle fleet based on the safe driving corridor, the lateral motion model of each controlled vehicle, the target lane change time, and the target lane change speed;

[0028] The controlled vehicle fleet is controlled to change lanes based on the front wheel steering angle, the target lane change time, and the target lane change speed.

[0029] In one embodiment, the multiple expected lane change moments are multiple moments collected from the expected period based on a first set frequency; the environmental information is collected within the perception field of view based on a second set frequency; wherein the second set frequency is greater than the first set frequency.

[0030] In a second aspect, the present application further provides a decision control device, the device comprising: an expected lane change time acquisition module, a lane change cost determination module, a target lane change information determination module and a control module, wherein:

[0031] An expected lane change timing acquisition module, used to determine a plurality of expected lane change timings within an expected period, wherein the expected period is a future time period;

[0032] a lane change cost determination module, used to determine the lane change cost of the controlled fleet at each expected lane change moment, wherein the lane change cost includes the driving cost of the controlled fleet changing lanes and the impact cost on the surrounding vehicles due to the lane change, wherein the driving cost represents the difficulty of the lane change, and the impact cost represents the degree of impact on the passage of the surrounding vehicles;

[0033] a target lane change information determination module, configured to take the expected lane change time with the lowest lane change cost among the plurality of expected lane change times as the target lane change time, and determine a target lane change speed of the controlled vehicle fleet at the target lane change time;

[0034] A control module is used to control the controlled vehicle fleet to change lanes based on the target lane-changing time and the target lane-changing speed.

[0035] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Collecting a plurality of expected lane change moments within an expected period, where the expected period is a future time period;

[0037] Determine the lane change cost of the controlled fleet at each expected lane change moment, wherein the lane change cost includes the driving cost of the controlled fleet changing lanes and the impact cost on the surrounding vehicles due to the lane change, wherein the driving cost represents the difficulty of the lane change, and the impact cost represents the degree of impact on the passage of surrounding vehicles;

[0038] taking the expected lane changing time with the lowest lane changing cost among the multiple expected lane changing times as the target lane changing time, and determining the target lane changing speed of the controlled vehicle fleet at the target lane changing time;

[0039] The controlled vehicle fleet is controlled to change lanes based on the target lane-changing time and the target lane-changing speed.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0041] Collecting a plurality of expected lane change moments within an expected period, where the expected period is a future time period;

[0042] Determine the lane change cost of the controlled fleet at each expected lane change moment, wherein the lane change cost includes the driving cost of the controlled fleet changing lanes and the impact cost on the surrounding vehicles due to the lane change, wherein the driving cost represents the difficulty of the lane change, and the impact cost represents the degree of impact on the passage of surrounding vehicles;

[0043] taking the expected lane changing time with the lowest lane changing cost among the multiple expected lane changing times as the target lane changing time, and determining the target lane changing speed of the controlled vehicle fleet at the target lane changing time;

[0044] The controlled vehicle fleet is controlled to change lanes based on the target lane-changing time and the target lane-changing speed.

[0045] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0046] Collecting a plurality of expected lane change moments within an expected period, where the expected period is a future time period;

[0047] Determine the lane change cost of the controlled fleet at each expected lane change moment, wherein the lane change cost includes the driving cost of the controlled fleet changing lanes and the impact cost on the surrounding vehicles due to the lane change, wherein the driving cost represents the difficulty of the lane change, and the impact cost represents the degree of impact on the passage of surrounding vehicles;

[0048] taking the expected lane changing time with the lowest lane changing cost among the multiple expected lane changing times as the target lane changing time, and determining the target lane changing speed of the controlled vehicle fleet at the target lane changing time;

[0049] The controlled vehicle fleet is controlled to change lanes based on the target lane-changing time and the target lane-changing speed.

[0050] The above-mentioned fleet lateral decision-making control method integrating game theory and predictive control determines the lane changing cost of the controlled fleet at each expected lane changing moment, and then determines the expected lane changing moment with the lowest lane changing cost as the target lane changing moment, and determines the target lane changing speed of the controlled fleet at the target lane changing moment; that is, in the scheme of the embodiment of the present application, a game is played between the driving cost of the controlled fleet at each expected lane changing moment and the impact cost on the environmental vehicles, and then the expected lane changing moment with the lowest comprehensive lane changing cost is determined as the target lane changing moment, and the target lane changing speed is determined; compared with the related art, the embodiment of the present application takes into account the impact on the traffic efficiency of the environmental vehicles when determining the lane changing scheme, and thus when the controlled fleet is controlled to change lanes based on the target lane changing moment and the target lane changing speed, the impact on the traffic efficiency of the environmental vehicles can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 An application environment diagram of a lateral decision-making control method for a vehicle fleet integrating game theory and predictive control in one embodiment;

[0053] Figure 2 A schematic diagram of a flow chart of a lateral decision-making control method for a vehicle fleet integrating game theory and predictive control in one embodiment;

[0054] Figure 3 A schematic diagram of a flow chart of a step of determining prediction information in one embodiment;

[0055] Figure 4 A schematic diagram of a flow chart of a step of determining a driving cost in one embodiment;

[0056] Figure 5 A flowchart of determining the steps affecting the cost in one embodiment is shown;

[0057] Figure 6 A schematic diagram of a step flow of lateral control in an embodiment;

[0058] Figure 7 is a schematic diagram of a nonlinear bicycle model in a Frennet coordinate system in one embodiment;

[0059] Figure 8 A logical schematic diagram of lane change control for a controlled convoy in one embodiment;

[0060] Fig. 9 A structural block diagram of a decision control device in an embodiment

[0061] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0063] The lateral decision control method for a fleet integrating game theory and predictive control provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the controlled convoy includes multiple controlled vehicles, and the leading vehicle is the first controlled vehicle in the driving direction of the controlled convoy; the leading vehicle can communicate with the other controlled vehicles through the network, Bluetooth or WIFI to achieve data interaction.

[0064] The leader vehicle is equipped with environmental information collection equipment such as laser / millimeter wave radar, visual sensors, and GPS / INS sensors, which can obtain environmental information on the driving road in real time, including the position, speed, and acceleration of each environmental vehicle, and can also obtain information such as the distance from the environmental vehicle, and execute the fleet lateral decision-making control method that integrates game theory and predictive control provided in the embodiment of the present application based on the environmental information, so as to determine the target lane change time and target lane change speed; each controlled vehicle is equipped with a communication module, in which the leader vehicle can communicate with the other control vehicles to realize information exchange, thereby realizing control of each controlled vehicle in the controlled fleet.

[0065] Furthermore, the leader vehicle is equipped with a collaborative controller, which includes an information fusion module, a motion planning module and a vehicle control module, wherein:

[0066] The information fusion module includes: a sensor fusion module and a road geometry modeling module, which are used to collect environmental information; a vehicle state estimation module, which is used to predict the state (position and speed) of the controlled vehicle; and a surrounding environment prediction module, which is used to predict the state (position and speed) of the surrounding vehicle.

[0067] The motion planning module includes: an overtaking (lane change) mode analysis module, which is used to construct the interactive behavior of the controlled vehicle and the environment vehicle; an obstacle avoidance decision algorithm, which is used to determine the target overtaking time and target overtaking speed of the controlled vehicle; a safe driving channel modeling module, which is used to construct a safe driving corridor; and a target trajectory planning module, which is used to plan the overtaking trajectory of the controlled fleet.

[0068] The vehicle control module, based on the linear event model predictive control algorithm, performs lateral distributed coordinated control of the unmanned vehicle fleet (controlled fleet), so that the controlled fleet maintains a complete formation when changing lanes.

[0069] In an exemplary embodiment, Figure 2 As shown in the figure, a lateral decision control method for a fleet that integrates game theory and predictive control is provided. Figure 1 Taking the leading vehicle in the controlled convoy as an example, the method includes the following steps 10 to 60. Among them:

[0070] Step 10: Determine multiple expected lane change times within an expected period.

[0071] For the embodiments of the present application, the expected period is a time period in the future starting from the current time, wherein the expected period may be a pre-set time period and calculated from the current moment; the expected period may also be determined based on the number of environmental vehicles on the road within the perceived field of view; for example, the expected period may be set to be positively correlated with the number of environmental vehicles on the road within the perceived field of view, but the specific mapping relationship is not limited in the embodiments of the present application.

[0072] In one possible implementation of the embodiment of the present application, multiple expected lane change moments can be determined from the expected period at one time, wherein the multiple expected lane change moments can be equally spaced or randomly distributed. In another possible implementation, a certain collection frequency can be used to collect one moment each time as the expected lane change moment.

[0073] Step 20: Determine the lane change cost of the controlled fleet at each expected lane change time. The lane change cost includes the driving cost of the controlled fleet and the impact cost of the lane change on the surrounding vehicles. The driving cost represents the difficulty of the lane change, and the impact cost represents the impact on the passage of surrounding vehicles.

[0074] For the embodiment of the present application, the lane change cost includes the driving cost of the controlled fleet's lane change and the cost of the impact of the lane change on the surrounding vehicles; wherein the lane change driving cost includes the collision penalty, speed deviation penalty, comfort level (driving intensity) of each controlled vehicle, and speed penalty for too fast or too slow speed for each vehicle in the controlled fleet at the desired lane change time. By determining the lane change cost, the difficulty of the controlled fleet to change lanes at the desired lane change time can be measured.

[0075] The impact cost includes the penalty for the rear vehicles of the controlled convoy that may cause a collision with the controlled convoy when the controlled convoy changes lanes at the expected lane change time, and the penalty caused by the speed change of the rear vehicles due to the lane change of the controlled convoy at the expected lane change time. By determining the impact cost, the impact of the controlled convoy's lane change at the expected lane change time on the rear vehicles can be measured. Among them, the greater the impact cost, the greater the impact on the traffic efficiency of the rear vehicles, that is, the greater the impact cost, the greater the probability of collision between the rear vehicles and the controlled convoy and / or the greater the speed decay rate of the rear vehicles.

[0076] Step 30: taking the expected lane change time with the lowest lane change cost among the multiple expected lane change times as the target lane change time, and determining a target lane change speed of the controlled vehicle fleet at the target lane change time;

[0077] Step 40: Control the controlled vehicle fleet to change lanes based on the target lane change time and the target lane change speed.

[0078] For the embodiment of the present application, the determined lane change cost includes driving cost and impact cost, that is, the lane change cost takes into account both the feasibility of the controlled fleet's lane change (driving cost) and the impact on the traffic efficiency of the surrounding vehicles (impact cost); then, through the idea of ​​game theory, the lane change cost of the controlled fleet at each expected lane change moment is determined, and then the lane change moment with the lowest lane change cost is determined as the target lane change moment; because when determining the lane change cost at each expected lane change moment, it will be calculated based on information such as the position and speed of each vehicle in the controlled fleet and the surrounding vehicles, therefore, in the embodiment of the present application, the speed of the controlled fleet corresponding to the lane change moment is determined as the target lane change speed. Then, the leading vehicle in the controlled fleet sends the target lane change moment and the target lane change speed to each controlled vehicle, so that each controlled vehicle in the controlled fleet changes lanes.

[0079] In the embodiment of the present application, the speeds of the environment vehicle and the controlled vehicle are both their longitudinal speeds in the driving direction.

[0080] In the scheme of the embodiment of the present application, the lane changing cost of the controlled fleet at each expected lane changing moment is determined, and the lane changing cost includes the driving cost of the controlled fleet changing lanes and the impact cost on the environmental vehicles due to the lane changing, the driving cost represents the difficulty of the lane changing, and the impact cost represents the degree of impact on the passage of the environmental vehicles; then the expected lane changing moment with the lowest lane changing cost is determined as the target lane changing moment, and the target lane changing speed of the controlled fleet at the target lane changing moment is determined; that is, in the scheme of the embodiment of the present application, a game is played between the driving cost of the controlled fleet at each expected lane changing moment and the impact cost on the environmental vehicles, and then the expected lane changing moment with the lowest comprehensive lane changing cost is determined as the target lane changing moment, and the target lane changing speed is determined; compared with the related art, the embodiment of the present application takes into account the impact on the passage efficiency of the environmental vehicles when determining the lane changing scheme, and thus when the controlled fleet is controlled to change lanes based on the target lane changing moment and the target lane changing speed, the impact on the passage efficiency of the environmental vehicles can be reduced.

[0081] Furthermore, in the embodiment of the present application, the ideal state in which the vehicle body length and speed of all vehicles in the controlled fleet are consistent is used as an example. In the embodiment of the present application, since the expected lane change time is in the future, when determining the lane change cost of the controlled fleet at each expected lane change time, it is necessary to use the state information of the controlled fleet and the environmental vehicles at the expected lane change time, such as speed, position, acceleration and other information. Therefore, in the embodiment of the present application, the state information of the controlled fleet and the environmental vehicles at the expected lane change time in the future is determined by model prediction.

[0082] In one embodiment, referring to Figure 3 The method of the embodiment of the present application further includes steps 01 to 03 of determining the state information of each controlled vehicle and the state information of each environment vehicle at each expected lane change moment, wherein:

[0083] Step 01: For any environment vehicle, the position of the vehicle behind the environment vehicle, the position of the environment vehicle and the speed of the leading vehicle in the controlled fleet are input into the following model at any time to obtain the speed of the environment vehicle at any time.

[0084] Specifically, the following model is also called the intelligent driver model. In the embodiment of the present application, the following model adopts the IDM (Intelligent Driver Model), and the following model is used to predict the following behavior of the environmental vehicle. In the embodiment of the present application, the input data of the following model are the position of the vehicle behind the environmental vehicle, the position of the environmental vehicle, and the average speed of the controlled fleet; the output data of the following model is the speed of the environmental vehicle, that is, the speed in the future.

[0085] Since the speeds of all controlled vehicles in the controlled fleet are consistent, in the embodiment of the present application, the average speed of the controlled fleet is also the speed of the leading vehicle in the controlled fleet. And for the environmental vehicle in front of the leading vehicle, the vehicle behind the environmental vehicle is the leading vehicle of the controlled fleet.

[0086] Specifically, the expression function of the car-following model is: in, is the output of the car-following model, i.e., the speed of the surrounding vehicle in the future; is the position of the vehicle behind the environment vehicle, is the position of the vehicle in the environment, is the average speed of the controlled fleet; t represents the current time point, and k is any moment in the expected period.

[0087] N p is the set of controlled vehicles in the controlled fleet, N r is the set of environmental vehicles. For any controlled vehicle i∈N p , the input vector of the longitudinal motion model of the controlled vehicle is x i =s i and u i =v i , where s i is the longitudinal position of the controlled vehicle i, v i is the speed of the controlled vehicle i. For any environment vehicle j∈N r , the input vector of the longitudinal motion model of the ambient vehicle is x j =[s j ,v j ] T and u j =a j , where a j is the longitudinal acceleration of the ambient vehicle j, v j is the speed of the environment vehicle j, s j is the position of the environment vehicle j.

[0088] Step 02: Input the real-time speed and real-time position of each controlled vehicle in the controlled vehicle fleet into the longitudinal motion model of the controlled vehicle fleet to obtain the position of each controlled vehicle in the controlled vehicle fleet at each expected lane change moment.

[0089] Specifically, the longitudinal motion model of the controlled vehicle is a point mass motion model, and its function expression is: in, is the speed of the controlled vehicle, is the position of the controlled vehicle; A p and B p are the input data of the model, A pis the position of each controlled vehicle, p is the controlled fleet; B p is the speed of each controlled vehicle; is the output data of the model, and is the position of each controlled vehicle at the next moment. Therefore, the position of any controlled vehicle at each desired lane change moment can be determined by the longitudinal motion model of the controlled vehicle.

[0090] Step 03: Input the real-time position and real-time speed of each environmental vehicle into the longitudinal motion model of the environmental vehicle to obtain the position of each environmental vehicle at each expected lane change moment.

[0091] Specifically, the longitudinal motion model of the environment vehicle is a point mass motion model, and the expression function of the longitudinal motion model of the environment vehicle is: in, is the speed of the surrounding vehicle; A r is the position of each vehicle in the environment, B r is the speed of each environment vehicle, A r and B r For input data; The position of the environment vehicle at any time in the future is represented as the output data of the longitudinal motion model of the environment vehicle. Therefore, the position of any environment vehicle at each expected lane change time can be determined by the longitudinal motion model of the environment vehicle.

[0092] Furthermore, in order to evaluate the control effect of the controlled convoy during lane change and reduce the impact on the traffic efficiency of the surrounding vehicles, the embodiment of the present application uses the game theory problem of the interactive cost function to evaluate the feasibility of the overtaking maneuver. Among them, the function expression of the lane change cost at point t in the game theory problem represented by the interactive behavior model is:

[0093]

[0094] Among them, u t is the velocity at time t, x t is the position at time t; is the driving cost of all controlled vehicles, Represents the impact cost of the ambient vehicles on the lane change lane due to the lane change behavior of the controlled convoy.

[0095] Since the speed and body length of each controlled vehicle in the controlled fleet are consistent, the function expression q of the lane change cost can be expressed as:

[0096]

[0097] in, and They represent the position and average speed of the controlled vehicles in the controlled fleet, q pis the formal cost function.

[0098] In one embodiment, step 20 may specifically include the steps of determining the driving cost at each expected lane change moment and the step of determining the impact cost on the surrounding vehicle at each expected lane change moment.

[0099] The steps for determining the driving cost at each desired lane change time refer to Figure 4 , specifically may include steps 21 to 24, wherein:

[0100] Step 21, determining a first collision penalty of the controlled vehicle team at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle, and a first collision penalty function at each expected lane change moment; the first collision penalty function is constructed based on the position and speed of each controlled vehicle at any moment, the position and speed of the leading vehicle in front of the leading vehicle, and the body length of the leading vehicle;

[0101] Step 22, determining the deviation penalty of the controlled convoy at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle and the deviation penalty function at each expected lane change moment, wherein the deviation penalty function is constructed based on the reference speed of the controlled convoy at any moment, the speed of the leading vehicle, the position and speed of the leading vehicle's front vehicle and the body length of the leading vehicle;

[0102] Step 23, determining the comfort of the controlled vehicle fleet at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle, and a comfort function at each expected lane change moment, wherein the comfort function is constructed based on the acceleration of the leading vehicle at any moment;

[0103] Step 24: Determine the speed penalty of the controlled vehicle at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle, and the speed penalty function. The speed penalty function is constructed based on the speed of the lead vehicle at any moment and the speed of the vehicle preceding the lead vehicle.

[0104] Specifically, the expression of the driving cost function is: in,

[0105] in, is the first collision penalty function, is the deviation penalty function, is the comfort function, is the speed penalty function.

[0106] Specifically, v dis the expected speed of each controlled vehicle in the controlled fleet, l v is the body length of the lead vehicle in the controlled convoy. and They respectively represent the speed and position of the vehicle ahead of the leader vehicle in the lane where the controlled convoy is located; is the expected lane change time. If there is no environment vehicle in front of the lane φ at point t, and in order to make the driving cost function q p The expression is clearly defined, and is set to +∞. The local reference speed of the controlled fleet is v r It can be expressed as:

[0107]

[0108] Where, Δs 0 is the minimum safe distance between vehicles, t g is the set time interval; Δs g =v d t g +Δs0, represents the following distance threshold set by the following model; H is a unit step function,

[0109] Parameter λ s ,λ r ,λ c ,λ e represents the weighting factor. The first collision penalty is related to safety. When the actual speed of the leading vehicle in the controlled convoy is greater than that of the preceding vehicle and the following distance is small, a penalty will be imposed. The deviation penalty controls the average speed of the controlled convoy and the local reference speed v of the controlled convoy. r The rate of change of the speed of the leading vehicle in the controlled convoy reflects the comfort level. The speed penalty represents the traffic efficiency of the controlled convoy when the speed of the leading vehicle in the controlled convoy is lower than the expected speed v d When this happens, punishment will occur.

[0110] Further, the step of determining the impact cost on the surrounding vehicles at each expected lane change moment is as follows: Figure 5 , specifically including step 25 and step 26, wherein the impact cost includes a second collision penalty and a deceleration penalty:

[0111] Step 25, determining a second collision penalty for the controlled convoy at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle, and a second collision penalty function, wherein the second collision penalty function is constructed based on the position, body length, and speed of the leading vehicle at any moment, and the speed and velocity of the following vehicle, wherein the following vehicle is an environmental vehicle behind the controlled convoy;

[0112] Step 26: Determine the deceleration penalty of the controlled convoy at each expected lane change moment based on the state information of each controlled vehicle and each environment vehicle at each expected lane change moment and the deceleration penalty function. The deceleration penalty function is determined based on the initial speed of the following vehicle and the speed of the leading vehicle. The initial speed is the speed before being affected by the controlled convoy's lane change.

[0113] Specifically, the function expression affecting the cost is: H(t-τ). Among them, For the second collision penalty, Penalty for slowing down.

[0114] in, and They represent the speed and position of the front vehicle of the environmental vehicle respectively. For the first environmental vehicle behind the controlled convoy, the front vehicle of the environmental vehicle is the last controlled vehicle in the controlled convoy. is the position of the vehicle in the environment, is the position of the environment vehicle, l v' is the body length of the preceding vehicle of the environment vehicle. d,j is the initial speed of the environmental vehicle before the controlled convoy changes lanes, is the average speed of the controlled convoy (equivalent to the speed of the lead vehicle).

[0115] The second collision penalty imposes penalties for unsafe relative speeds and gaps between vehicles, and the deceleration penalty is the speed change of the surrounding vehicles due to the lane change of the controlled platoon.

[0116] Furthermore, in step 30, the expected lane changing time with the lowest lane changing cost is determined as the target lane changing time, and the target lane changing speed of the controlled vehicle fleet at the target lane changing time is determined, which can be expressed as a problem of solving the lane changing cost function:

[0117] The solution function is:

[0118] The initial conditions are: (j∈N r ,k=0,…,N o -1); the speed limit is: as well as

[0119] The complexity of solving the function is closely related to the number of feasible solutions of the expected lane change time τ. Therefore, in the embodiment of the present application: the multiple expected lane change times are multiple moments collected from the expected period based on the first set frequency; the environmental information is collected within the perception field based on the second set frequency; wherein the second set frequency is greater than the first set frequency. And in one example, the second set frequency is 10 times the first set frequency to reduce the set of solutions to solve the function.

[0120] In the embodiment of the present application, the lane change cost of each expected lane change time τ is determined; then, by searching for the minimum lane change cost, the optimal time among a finite number of feasible solutions, i.e., the target lane change time, is obtained. Furthermore, based on the target lane change time, the target lane change speed of the controlled vehicle fleet is determined by the longitudinal motion model of the target vehicle, the longitudinal motion model of the environment vehicle, and the following model, wherein the target lane change speed includes the target speed of each controlled vehicle when changing lanes.

[0121] In the embodiment of the present application, the above-determined target lane change speed is used to control the speed of the controlled convoy. Furthermore, since the controlled object in the present application is the controlled convoy, the stability of the formation of the entire convoy also needs to be considered when changing lanes. Figure 6 Step 40 may specifically include step 41 of constructing a lateral motion model of the controlled vehicle, step 42 of constructing a safe driving corridor of the controlled vehicle fleet, step 43 of determining a front wheel steering angle, and step 44 of controlling each controlled vehicle in the controlled vehicle fleet based on the lateral motion model and the safe driving corridor, wherein:

[0122] Step 41: construct a lateral motion model of each controlled vehicle in the controlled vehicle fleet, wherein the lateral motion model represents the relationship between the lateral speed and lateral position of the vehicle at any time and the front wheel inclination angle.

[0123] Specifically, for each controlled vehicle, a nonlinear dynamic bicycle model is used to describe the lateral motion of the vehicle, with the left and right wheels on each drive shaft as one wheel; Figure 7 , which is a schematic diagram of the lateral motion model of the controlled vehicle in the Frenet coordinate system; using Newton's law and moment balance, the representation function of the lateral motion model is formula (1) and formula (2), where:

[0124]

[0125]

[0126] in, and denote the total velocity and lateral velocity of the controlled vehicle in the body coordinate system, respectively. is the yaw rate, ψ is relative to Figure 7 The heading angle of the inertial coordinate system (X, Y) in the vehicle. The vehicle mass and yaw inertia are represented by m and I respectively. z Indicates that l f and l r Respectively represent the distance from the front and rear axles to the center of gravity of the vehicle. y,r 、F y,f They represent the front and rear tire pressures in the vehicle body coordinate system respectively. The tire adopts a mathematical tire model, which can be a Pacejka tire model or a linear tire model. The function expression of the tire model is formula (3), where:

[0127]

[0128] Where, *∈{f,r}, α* represents the tire slip angle, C α,* Represents the tire cornering stiffness. l is the critical tire slip angle for model switching,

[0129] B * ,C * ,D * ,E * is a constant coefficient determined by experimental data. Using the small angle approximation, the tire slip angle can be expressed by formula (4):

[0130] Among them, δ f is the front wheel steering angle.

[0131] Furthermore, the lateral motion model of the controlled vehicle is not clearly defined when the speed of the controlled vehicle is low, that is, when the speed is close to zero, there is a singular point in the expression of the tire slip angle. In order to solve this problem, at low speed (for example: 10km / h), a kinematic bicycle model is used to replace the above lateral motion model for control design. The function expression of the kinematic bicycle model is formula (5), formula (6) and formula (7), where:

[0132]

[0133]

[0134]

[0135] Where v and β represent the velocity and slip angle of the center of gravity of the vehicle, respectively.

[0136] Next, the Frenet unmanned vehicle motion model is modeled. First, the lateral reference position is set to a constant to perform the lane change task. In addition, the obstacle-free road safety constraints are described as upper and lower bounds according to Figure 7 The road alignment framework shown uses the following equations (8) and (9) to express the lateral position and orientation error dynamics, where:

[0137]

[0138]

[0139] in, represents the distance from the center of gravity of the vehicle to the center line of the lane, e ψ represents the heading angle error between the vehicle and the lane centerline, κ r Represents the road curvature.

[0140] By combining the lateral vehicle dynamics with the lateral position error dynamics, the nonlinear bicycle model in the Frenet framework can be expressed as Equation (10), where:

[0141]

[0142] Where the superscript p represents any vehicle in the row. p is the state vector, u p =δ f is the system control input, variable is the parameter vector. p The definition of depends on the speed of the controlled vehicle: if the speed is greater than 10 km / h, the dynamic model is used as formula (1) and formula (2), Otherwise, the kinematic model formula (5)-formula (7) is used, ξ p =[y,ψ,e y ,e ψ ] t Similarly, f p The definition of also depends on the speed of the controlled convoy.

[0143] However, the nonlinearity of the lateral motion model of the controlled fleet significantly increases the complexity of real-time calculation. Therefore, further, in the embodiment of the present application, the nonlinear lateral motion model is linearized, and the first-order approximation Taylor expansion nominal state is used and input The pre-Euler method is applied to discretize the linear model to obtain the linear time-varying lateral vehicle dynamics model, whose function expression is formula (11):

[0144]

[0145] in,

[0146]

[0147] Among them, T s represents the sampling step, which is the reciprocal of the second frequency. The superscript p is omitted to simplify the notation. k and B k represent the functions of the nominal state and input respectively, so formula (11) can be calculated offline by the leader vehicle of the controlled fleet, thus reducing the online calculation burden.

[0148] Step 42: Collect environmental information within the perception field of view, and construct a safe driving corridor for the controlled fleet based on the environmental information, wherein the environmental information includes status information of each controlled vehicle in the controlled fleet and status information of each environmental vehicle, and the boundary of the safe driving corridor is determined based on the position and speed of the environmental vehicle.

[0149] Specifically, a safe driving corridor for the controlled convoy is established based on the environmental information within the perception field of view. The key idea is to The longitudinal coordinates s of all objects (controlled vehicles and environmental vehicles) aligned along the road are matched into a dynamic map, so the constraints of the safety corridor can be simply expressed in the form of upper and lower boundaries. In any prediction step k, the upper and lower boundaries of the safe driving corridor are calculated based on the longitudinal motion model of the environmental vehicle and the longitudinal position and speed of the environmental vehicle predicted by the following model.

[0150] The safety corridor constraint is expressed as The time-varying piecewise line function of obeys formula (12), where:

[0151]

[0152] in, and Represents the relative longitudinal distance of the platoon control vehicles, where 1:N c ={1,…,N c}The set of surrounding vehicles on the current lane, 1:N o ={1,…,N o} is the set of surrounding vehicles in the lane after changing lanes.

[0153] are the upper and lower boundaries of the lateral displacement relative to the lane centerline. The slope of the designed piecewise affine function is related to the relative speed Based on the heuristic method, the setting The slope decreases linearly with the increase of the safety margin to ensure sufficient longitudinal safety margin. The upper and lower boundaries of the safe driving corridor and According to the real-time measurement data Make dynamic updates.

[0154] Step 43: determining the front wheel steering angle of the controlled vehicle fleet based on the safe driving corridor, the lateral motion model of each controlled vehicle, the target lane change time and the target lane change speed;

[0155] Step 44: Control the controlled convoy to change lanes based on the front wheel steering angle, the target lane change time, and the target lane change speed.

[0156] Furthermore, in an embodiment of the present application, the lateral motion model and safe driving corridor of the controlled vehicle are utilized to predict and control the lateral motion of each controlled vehicle through a linear time-varying model, and the lateral motion of any controlled vehicle i in the controlled fleet is predicted and controlled using a linear time-varying model.

[0157] Specifically, in each sampling time step, a constrained optimization problem is solved by minimizing a predefined objective function to generate a series of control input deviations. The first element of the sequence is then used to calculate the final control input. In subsequent sampling time steps, the optimization process is repeated after the data is updated at a forward-moving level to form a rolling optimization control strategy. The linear time-varying model predictive control problem for lane keeping and obstacle avoidance coupling can be described as Equation (13a)-Equation (13j), where:

[0158]

[0159]

[0160]

[0161]

[0162]

[0163]

[0164]

[0165]

[0166] ∈≥0, formula (13i);

[0167]

[0168] Among them, the symbol The current time point is represented by the subscript t, and N represents the maximum prediction step. Δ ,R δRepresents the tuning cost weight with appropriate dimensions. is the predicted state deviation at time t+k. The input deviation sequence can be converted into Substitute it into the linear model formula (13b) and calculate it. y ,e ψ ] T represents the output vector of the system, where e y is the lateral trajectory deviation, e ψ is the yaw angle deviation; the corresponding reference sequence The first addition in (13a) produces the desired output performance.

[0169] The second to fourth increments in formula (13a) penalize the size and rate of the input sequence as well as the deviation The constraints related to the control input are introduced by equations (13e) to (13h). The recursive feasibility of equation (13) for optimal control is guaranteed by enforcing all state constraints in equation (13d) as soft constraints with slack variables ∈. In equation (13a), ∈ is penalized by a weight factor ρ, which is much larger than the weight matrices Q, R, R Δ ,R δ , so that ∈ remains at 0 under normal circumstances. When formula (13) has no solution, the relaxation factor ensures its solvability. The input deviation constraint formula (13h) is used to ensure the nominal state sequence and the input sequence The accuracy of the linearized model.

[0170] Further, Using the output value of (21c), we can Applied to the nonlinear dynamic model in discrete time form, that is, in formula (10), the nominal output vector sequence is obtained

[0171] Optimize the solution of formula (13a)-formula (13j) at time t By using only the first element, the optimal control input at the target lane change time is given by the feedback control formula, and the corresponding front wheel turning angle of the lateral motion model can be obtained. The feedback control formula is:

[0172] In summary, refer to Figure 8According to the scheme of the embodiment of the present application, the leading vehicle in the controlled fleet can obtain environmental information such as the speed, position and acceleration of each controlled vehicle and environmental vehicle within the perception field of view. By processing the environmental information, the lane change mode of each free vehicle in the controlled fleet can be defined, that is, the interactive behavior of the environmental vehicle and the controlled vehicle is constructed, which is realized through the following model and the longitudinal motion model of the controlled vehicle and the environmental vehicle respectively; furthermore, on the one hand, the lane change cost at each expected lane change moment can be determined through game theory, so that the controlled fleet can achieve a balance between the feasibility of lane change and the traffic efficiency of the environmental vehicles, reducing the impact on the traffic efficiency of the environmental vehicles, so as to enable the controlled fleet to change lanes safely in complex traffic scenarios; at the same time, on the other hand, the lateral motion model and safe driving corridor of the controlled vehicle are utilized, and the lateral motion of the controlled vehicle is controlled based on the iterative linear time-varying model, so that the controlled fleet can maintain coordinated lane change, thereby enabling the controlled fleet to maintain the integrity of the formation.

[0173] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0174] Based on the same inventive concept, the embodiment of the present application also provides a decision control device for implementing the above-mentioned vehicle fleet lateral decision control method integrating game theory and predictive control. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more decision control device embodiments provided below can refer to the limitations of the method above, and will not be repeated here.

[0175] In an exemplary embodiment, Fig. 9 As shown, a decision control device is provided, which includes: an expected lane change time acquisition module 901, a lane change cost determination module 902, a target lane change information determination module 903 and a control module 904, wherein:

[0176] An expected lane change timing collection module 901 is used to determine a plurality of expected lane change timings within an expected period, where the expected period is a future time period;

[0177] The lane change cost determination module 902 is used to determine the lane change cost of the controlled fleet at each expected lane change time. The lane change cost includes the driving cost of the controlled fleet changing lanes and the impact cost on the surrounding vehicles due to the lane change. The driving cost represents the difficulty of the lane change, and the impact cost represents the impact on the passage of the surrounding vehicles.

[0178] A target lane change information determination module 903 is used to take the expected lane change time with the lowest lane change cost among the multiple expected lane change times as the target lane change time, and determine the target lane change speed of the controlled vehicle fleet at the target lane change time;

[0179] The control module 904 is used to control the controlled vehicle fleet to change lanes based on the target lane change time and the target lane change speed.

[0180] By determining the lane changing cost of the controlled vehicle fleet at each expected lane changing moment, then determining the expected lane changing moment with the lowest lane changing cost as the target lane changing moment, and determining the target lane changing speed of the controlled vehicle fleet at the target lane changing moment; that is, in the scheme of the embodiment of the present application, a game is played between the driving cost of the controlled vehicle fleet at each expected lane changing moment and the impact cost on the environmental vehicles, and then determining the expected lane changing moment with the lowest comprehensive lane changing cost as the target lane changing moment, and determining the target lane changing speed; compared with the related art, the embodiment of the present application takes into account the impact on the traffic efficiency of the environmental vehicles when determining the lane changing scheme, and thus when the controlled vehicle fleet is controlled to change lanes based on the target lane changing moment and the target lane changing speed, the impact on the traffic efficiency of the environmental vehicles can be reduced.

[0181] In one embodiment, each controlled vehicle in the controlled fleet maintains the same speed and has the same body length, and the driving cost includes a first collision penalty, a deviation penalty, a comfort level, and a speed penalty; the lane change cost determination module 902 is specifically used to:

[0182] Determine state information of each controlled vehicle and state information of each environment vehicle at each expected lane change moment, the state information including position and speed;

[0183] Based on the state information of each controlled vehicle, the state information of each environmental vehicle and the first collision penalty function at each expected lane change moment, determining the first collision penalty of the controlled vehicle team at each expected lane change moment; the first collision penalty function is constructed based on the position and speed of each controlled vehicle at any moment, the position and speed of the leading vehicle in front of the leading vehicle and the body length of the leading vehicle, and the leading vehicle is the frontmost controlled vehicle in the controlled vehicle team;

[0184] Determine the deviation penalty of the controlled convoy at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle and the deviation penalty function at each expected lane change moment, wherein the deviation penalty function is constructed based on the reference speed of the controlled convoy at any moment, the speed of the leading vehicle, the position and speed of the leading vehicle's front vehicle and the body length of the leading vehicle;

[0185] Determining the comfort of the controlled convoy at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle, and a comfort function at each expected lane change moment, wherein the comfort function is constructed based on the acceleration of the leading vehicle at any moment;

[0186] The speed penalty of the controlled traffic jam at each expected lane change moment is determined based on the state information of each controlled vehicle, the state information of each environmental vehicle and the speed penalty function. The speed penalty function is constructed based on the speed of the lead vehicle and the speed of the vehicle in front of the lead vehicle at any moment.

[0187] In one embodiment, the impact cost includes a second collision penalty and a deceleration penalty, and the lane change cost determination module 902 is specifically configured to:

[0188] Determine a second collision penalty for the controlled convoy at each expected lane change moment based on state information of each controlled vehicle, state information of each environmental vehicle, and a second collision penalty function, wherein the second collision penalty function is constructed based on the position, body length, and speed of the leading vehicle at any moment, and the speed and velocity of the following vehicle, wherein the following vehicle is an environmental vehicle behind the controlled convoy;

[0189] Based on the state information of each controlled vehicle and each environmental vehicle at each expected lane change moment and the deceleration penalty function, the deceleration penalty of the controlled convoy at each expected lane change moment is determined. The deceleration penalty function is determined based on the initial speed of the following vehicle and the speed of the leading vehicle. The initial speed is the speed before being affected by the controlled convoy's lane change.

[0190] In one embodiment, the lane change cost determination module 902 is further configured to:

[0191] For any environment vehicle, the position of the vehicle behind the environment vehicle, the position of the environment vehicle, and the speed of the leading vehicle in the controlled convoy are input into the following model to obtain the speed of the environment vehicle at any time.

[0192] Input the real-time speed and real-time position of each controlled vehicle in the controlled convoy into the longitudinal motion model of the controlled convoy to obtain the position of each controlled vehicle in the controlled convoy at each expected lane change moment;

[0193] The real-time position and real-time speed of each environmental vehicle are input into the longitudinal motion model of the environmental vehicle to obtain the position of each environmental vehicle at each expected lane change moment.

[0194] In one embodiment, the control module 904 is specifically configured to:

[0195] Collect environmental information within the perception field of view, and build a safe driving corridor for the controlled convoy based on the environmental information, wherein the environmental information includes the status information of each controlled vehicle in the controlled convoy and the status information of each environmental vehicle, and the boundary of the safe driving corridor is determined based on the position and speed of the environmental vehicle;

[0196] Construct a lateral motion model of each controlled vehicle in the controlled fleet. The lateral motion model represents the relationship between the lateral speed and lateral position of the vehicle at any time and the front wheel inclination angle.

[0197] Determine the front wheel steering angle of the controlled convoy based on the safe driving corridor, the lateral motion model of each controlled vehicle, the target lane change time and the target lane change speed;

[0198] The controlled convoy is controlled to change lanes based on the front wheel steering angle, the target lane change time, and the target lane change speed.

[0199] In one of the embodiments, the multiple expected lane change moments are multiple moments collected from an expected period based on a first set frequency; the environmental information is collected within the perception field of view based on a second set frequency; wherein the second set frequency is greater than the first set frequency.

[0200] Each module in the above decision control device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0201] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.10As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a lateral decision control method for a fleet integrating game theory and predictive control is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0202] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0203] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0204] Collecting multiple expected lane change moments within an expected period, where the expected period is a future time period;

[0205] Determine the lane-changing cost of the controlled fleet at each expected lane-changing moment. The lane-changing cost includes the driving cost of the controlled fleet's lane-changing and the impact cost on the surrounding vehicles caused by the lane-changing. The driving cost represents the difficulty of the lane-changing, and the impact cost represents the degree of impact on the passage of surrounding vehicles.

[0206] The expected lane changing time with the lowest lane changing cost among multiple expected lane changing times is taken as the target lane changing time, and the target lane changing speed of the controlled vehicle fleet at the target lane changing time is determined;

[0207] The controlled convoy is controlled to change lanes based on a target lane change time and a target lane change speed.

[0208] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0209] Collecting multiple expected lane change moments within an expected period, where the expected period is a future time period;

[0210] Determine the lane-changing cost of the controlled fleet at each expected lane-changing moment. The lane-changing cost includes the driving cost of the controlled fleet's lane-changing and the impact cost on the surrounding vehicles caused by the lane-changing. The driving cost represents the difficulty of the lane-changing, and the impact cost represents the degree of impact on the passage of surrounding vehicles.

[0211] The expected lane changing time with the lowest lane changing cost among multiple expected lane changing times is taken as the target lane changing time, and the target lane changing speed of the controlled vehicle fleet at the target lane changing time is determined;

[0212] The controlled convoy is controlled to change lanes based on a target lane change time and a target lane change speed.

[0213] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0214] Collecting multiple expected lane change moments within an expected period, where the expected period is a future time period;

[0215] Determine the lane-changing cost of the controlled fleet at each expected lane-changing moment. The lane-changing cost includes the driving cost of the controlled fleet's lane-changing and the impact cost on the surrounding vehicles caused by the lane-changing. The driving cost represents the difficulty of the lane-changing, and the impact cost represents the degree of impact on the passage of surrounding vehicles.

[0216] The expected lane changing time with the lowest lane changing cost among multiple expected lane changing times is taken as the target lane changing time, and the target lane changing speed of the controlled vehicle fleet at the target lane changing time is determined;

[0217] The controlled convoy is controlled to change lanes based on a target lane change time and a target lane change speed.

[0218] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0219] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0220] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0221] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A lateral decision-making control method for a fleet integrating game theory and predictive control, characterized in that: Performed by a leading vehicle in a controlled convoy, the method comprises: collecting a plurality of expected lane change moments within an expected period, wherein the expected period is a future time period; Determine the lane change cost of the controlled fleet at each expected lane change moment, wherein the lane change cost includes the driving cost of the controlled fleet changing lanes and the impact cost on the surrounding vehicles due to the lane change, wherein the driving cost represents the difficulty of the lane change, and the impact cost represents the degree of impact on the passage of surrounding vehicles; taking the expected lane changing time with the lowest lane changing cost among the multiple expected lane changing times as the target lane changing time, and determining the target lane changing speed of the controlled vehicle fleet at the target lane changing time; The controlled vehicle fleet is controlled to change lanes based on the target lane-changing time and the target lane-changing speed.

2. The method according to claim 1, characterized in that Each controlled vehicle in the controlled fleet maintains the same speed and has the same body length. The driving cost includes a first collision penalty, a deviation penalty, a comfort level, and a speed penalty. The driving cost at each expected lane change moment is determined, including: Determine state information of each controlled vehicle and state information of each environment vehicle at each expected lane change moment, wherein the state information includes position and speed; Determine a first collision penalty of the controlled vehicle fleet at each expected lane change moment based on state information of each controlled vehicle, state information of each environmental vehicle, and a first collision penalty function at each expected lane change moment; the first collision penalty function is constructed based on the position and speed of each controlled vehicle at any moment, the position and speed of the leading vehicle in front of the leading vehicle, and the body length of the leading vehicle, the leading vehicle being the frontmost controlled vehicle in the controlled vehicle fleet; Determine the deviation penalty of the controlled vehicle fleet at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle and a deviation penalty function at each expected lane change moment, wherein the deviation penalty function is constructed based on the reference speed of the controlled vehicle fleet at any moment, the speed of the leading vehicle, the position and speed of the leading vehicle's front vehicle and the body length of the leading vehicle; Determining the comfort of the controlled vehicle fleet at each of the expected lane change moments based on the state information of each controlled vehicle, the state information of each environment vehicle, and a comfort function, wherein the comfort function is constructed based on the acceleration of the leading vehicle at any moment; The speed penalty of the controlled traffic jam at each expected lane change moment is determined based on the state information of each controlled vehicle, the state information of each environmental vehicle and a speed penalty function, wherein the speed penalty function is constructed based on the speed of the lead vehicle and the speed of the vehicle preceding the lead vehicle at any moment.

3. The method according to claim 2, characterized in that The impact cost includes a second collision penalty and a deceleration penalty. Determining the impact cost on the environment vehicle at each expected lane change moment includes: Determine a second collision penalty of the controlled convoy at each expected lane change moment based on the state information of each controlled vehicle, the state information of each environmental vehicle, and a second collision penalty function at each expected lane change moment, wherein the second collision penalty function is constructed based on the position, body length, and speed of the leading vehicle and the speed and velocity of the following vehicle at any moment, wherein the following vehicle is an environmental vehicle behind the controlled convoy; Based on the state information of each controlled vehicle, the state information of each environmental vehicle and the deceleration penalty function at each expected lane change moment, the deceleration penalty of the controlled vehicle fleet at each expected lane change moment is determined, and the deceleration penalty function is determined based on the initial speed of the following vehicle and the speed of the leading vehicle, and the initial speed is the speed before being affected by the lane change of the controlled vehicle fleet.

4. The method according to claim 2, characterized in that: The determining of the state information of each controlled vehicle and the state information of each environment vehicle at each expected lane change moment includes: For any environment vehicle, the position of the vehicle behind the environment vehicle, the position of the environment vehicle and the speed of the leading vehicle in the controlled convoy at any time are input into the following model to obtain the speed of the environment vehicle at any time; Inputting the real-time speed and real-time position of each controlled vehicle in the controlled vehicle fleet into the longitudinal motion model of the controlled vehicle fleet, and obtaining the position of each controlled vehicle in the controlled vehicle fleet at each expected lane change time; The real-time position and real-time speed of each environmental vehicle are input into the longitudinal motion model of the environmental vehicle to obtain the position of each environmental vehicle at each expected lane change moment.

5. The method according to any one of claims 1 to 4, characterized in that: The controlling the controlled vehicle fleet to change lanes based on the target lane-changing time and the target lane-changing speed includes: Collecting environmental information within the perception field of view, and constructing a safe driving corridor for the controlled vehicle fleet based on the environmental information, wherein the environmental information includes status information of each controlled vehicle in the controlled vehicle fleet and status information of each environmental vehicle, and the boundary of the safe driving corridor is determined based on the position and speed of the environmental vehicle; Constructing a lateral motion model of each controlled vehicle in the controlled fleet, wherein the lateral motion model represents the relationship between the lateral speed and lateral position of the vehicle at any time and the front wheel inclination angle; Determining a front wheel steering angle of the controlled vehicle fleet based on the safe driving corridor, the lateral motion model of each controlled vehicle, the target lane change time, and the target lane change speed; The controlled vehicle fleet is controlled to change lanes based on the front wheel steering angle, the target lane change time, and the target lane change speed.

6. The method according to claim 4, characterized in that The multiple expected lane change moments are multiple moments collected from the expected period based on a first set frequency; the environmental information is collected within the perception field of view based on a second set frequency; wherein the second set frequency is greater than the first set frequency.

7. A decision control device, characterized in that: The device comprises: an expected lane change time acquisition module, a lane change cost determination module, a target lane change information determination module and a control module, wherein: An expected lane change timing acquisition module, used to determine a plurality of expected lane change timings within an expected period, wherein the expected period is a future time period; a lane change cost determination module, used to determine the lane change cost of the controlled fleet at each expected lane change moment, wherein the lane change cost includes the driving cost of the controlled fleet changing lanes and the impact cost on the surrounding vehicles due to the lane change, wherein the driving cost represents the difficulty of the lane change, and the impact cost represents the degree of impact on the passage of the surrounding vehicles; a target lane change information determination module, configured to take the expected lane change time with the lowest lane change cost among the plurality of expected lane change times as the target lane change time, and determine a target lane change speed of the controlled vehicle fleet at the target lane change time; A control module is used to control the controlled vehicle fleet to change lanes based on the target lane-changing time and the target lane-changing speed.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Motorcade cooperative driving abnormity monitoring method and system

    CN111696338A

  • Intelligent vehicle lane changing decision-making method based on incomplete information game

    CN112907967A

  • Lane gap selection method and device, electronic equipment and storage medium

    CN114701501A

  • Vehicle lane changing method and device, electronic equipment and storage medium

    CN115158319A

  • Intelligent networked vehicle group overtaking decision control method

    CN116415417A