Lane-changing decision-making and trajectory planning method for intelligent networked automobile

CN118928461AActive Publication Date: 2024-11-12CHONGQING UNIV

Patent Information

Application Number
CN202410982650.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-12
Estimated Expiration
2044-07-22

AI Technical Summary

Technical Problem

The existing decision-making and trajectory planning methods for changing lanes of intelligent connected vehicles fail to effectively consider changes in the movement status of surrounding vehicles, resulting in poor application results.

Method used

Using the dynamic repeat master-slave game method, by defining the game income function of the lane-changing intelligent connected vehicles and road rights competition vehicles, combining the data collected by the sensing device, the game equilibrium is solved to obtain the decision result, and the trajectory is planned based on the decision result. Considering horizontal space discretization and security constraints, optimize the lane change strategy.

Benefits of technology

The safety and efficiency of lane change are improved, and through real-time update of decisions and planning, adapting to changes in the position of surrounding vehicles, the safety and traffic efficiency of lane change process are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928461A_ABST
    Figure CN118928461A_ABST
Patent Text Reader

Abstract

The invention belongs to the field of automatic driving or auxiliary driving of intelligent networked automobiles, and discloses an intelligent networked automobile lane-changing decision-making and trajectory planning method, which comprises the following steps of: sensing a road traffic environment through sensors such as a laser radar, a millimeter wave radar and a vehicle-mounted camera carried by a lane-changing intelligent networked automobile SC; the position and speed information of a front vehicle FC of a current lane, a front vehicle PC of a target lane and a rear vehicle LC is considered, an optimal strategy is solved through a dynamic game, and the optimal lane changing track of the vehicle is planned based on different strategies and the comfort and lane changing efficiency of a driver. The safety and efficiency of lane changing can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of automatic driving or assisted driving of intelligent networked vehicles, and specifically relates to a lane changing decision and trajectory planning method for intelligent networked vehicles. Background Art

[0002] With the rapid breakthroughs in advanced technologies such as artificial intelligence, big data, 5G communications and cloud computing in recent years, the field of intelligent connected vehicles has also shown a booming development trend. Under this trend, vehicles can achieve more intelligent perception, decision-making and execution functions, providing more abundant and feasible solutions to solve problems such as traffic congestion and frequent traffic accidents. Autonomous lane changing is one of the basic functions of intelligent connected vehicles. The decision to change lanes and the corresponding lane change trajectory planning are directly related to the safety and traffic efficiency of the vehicle itself and road traffic.

[0003] By reviewing relevant patents and papers, it is found that the existing lane-changing decision-making and trajectory planning methods for intelligent connected vehicles rarely consider the impact of changes in the traffic environment around the vehicle during the lane-changing process. Patent CN106777776A discloses a vehicle lane-changing decision-making method based on a support vector machine model; Patent CN110298131B discloses a method for establishing an automatic driving lane-changing decision model in a mixed driving environment, and establishes a multi-step dynamic game framework to determine the final lane-changing decision and trajectory planning method. However, the above methods do not consider the impact of changes in the motion state of vehicles around the vehicle during the lane-changing process on lane-changing decisions and trajectory planning, and the actual application effect needs to be improved. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method for lane changing decision and trajectory planning of an intelligent connected vehicle. The present invention aims to solve the problem that the existing method does not consider the influence of the change of the motion state of surrounding vehicles during the lane changing process on the lane changing decision and trajectory planning, and the application effect is poor.

[0005] The present invention provides a method for lane changing decision and trajectory planning of an intelligent connected vehicle, comprising the following steps:

[0006] S1. Define the master-slave game profit function of the lane-changing intelligent connected car SC and the road right competing vehicle LC;

[0007] Road right competing vehicles refer to vehicles in the target lane that compete with the lane-changing intelligent connected vehicle, i.e., the rear vehicle in the target lane;

[0008] S2. Establish a plane rectangular coordinate system with the current position of the lane-changing vehicle as the origin, the horizontal driving direction as the X-axis, and the direction from the lane where the lane-changing vehicle is located to the target lane and perpendicular to the X-axis as the Y-axis;

[0009] S3. Use the sensor equipment of the intelligent connected vehicle to collect the driving status data and road environment information of itself and the lane-changing competing vehicles, and solve the game equilibrium to obtain the decision result;

[0010] If the decision result is to continue changing lanes, proceed to step S4;

[0011] If the decision result is lane keeping, proceed to step S5;

[0012] If the decision result is to return to the previous horizontal line, proceed to step S6;

[0013] S4. Planning the lane changing trajectory according to the continuous lane changing strategy obtained in step S3;

[0014] S5. Perform lane keeping trajectory planning according to the lane keeping strategy obtained in step S3;

[0015] S6. According to the fallback strategy obtained in step S3, the vehicle driving trajectory planning of falling back to the previous horizontal line position is performed;

[0016] S7. Repeat steps S3 to S6 until the intelligent connected vehicle completes the lane change.

[0017] Further, the step S1 includes the following:

[0018] S1.1 Define vehicle;

[0019] Define the lane-changing intelligent connected car as SC, the vehicle in front of the lane-changing vehicle as FC, the vehicle behind the target lane as LC, and the vehicle in front of the target lane as PC;

[0020] Among them, the lane-changing intelligent connected car SC and the road right competition vehicle LC are participants in the master-slave game, SC is the leader in the game, and LC is the follower in the game;

[0021] S1.2 calculates the game profit of SC, and the profit function is:

[0022] E SC =(1-μ SC )*E safe1 +μ SC E vel

[0023] In the formula, E SC is the total benefit of the lane-changing vehicle SC; μ SC is the weight coefficient of the vehicle SC driving style, and its value represents the driving type, μ SC The larger the value, the more aggressive the driving behavior. safe1 is the safety benefit of the lane-changing vehicle SC; E vel is the speed gain of the lane-changing vehicle SC;

[0024] E safe1 The calculation formula is as follows:

[0025]

[0026] Where L is the vehicle width; d is the lateral distance between vehicle SC and vehicle LC; a represents the lateral safety distance between the two vehicles; e1 is the safety factor of vehicle SC; T h T is the headway time of vehicle SC relative to vehicle LC; e1 represents the expected headway of vehicle SC; T1 represents the initial headway of vehicle FC and vehicle SC; W represents the lateral distance between the center lines of the two lanes; T2 represents the initial headway of vehicle PC and vehicle LC;

[0027] E vel The calculation formula is as follows:

[0028]

[0029] In the formula, v PC is the speed of the front vehicle PC in the target lane; v FC is the speed of vehicle FC; v desire is the expected speed of SC;

[0030] S1.3 Calculate the game benefits of the road right competition vehicle LC, the benefit function is:

[0031] E LC =(1-μ LC )*E safe2 +μ LC *E space

[0032] In the formula, E LC is the total revenue of vehicle LC; μ LC is the weight coefficient of the LC driver’s driving style, and its value represents the type of driver. LC The larger the value, the more aggressive the driver's driving behavior. safe2 is the safety benefit of vehicle LC; E space is the space benefit of vehicle LC;

[0033] E safe2 and E space The calculation formula is as follows:

[0034]

[0035]

[0036]

[0037] Where d is the lateral distance between vehicle SC and vehicle LC; L is the vehicle width; a represents the safe lateral distance between the two vehicles; T h is the headway time of vehicle SC relative to vehicle LC; e2 is the safety factor of vehicle LC; T e2 is the expected headway time of vehicle 2.

[0038] Furthermore, the specific content of step S2 is: taking the lateral position distance between the center line of the lane where the intelligent connected vehicle is currently located and the center line of the target lane as a reference, 5 horizontal lines are set at equal intervals along the driving direction of the vehicle to obtain the vertical coordinate yi of each horizontal line, where i represents the serial number of each horizontal line, and the value range is 1-5. Each vertical coordinate yi serves as a node for the intelligent connected vehicle to perform a repeated game.

[0039] Further, in step S3, the expression of the optimal combined error function is as follows: In step S3, the process of solving the game equilibrium to obtain the decision result is as follows:

[0040] I According to the profit function designed in steps S1.2 and S1.3, the game profit matrix {E payoff (a x ,b y )};

[0041] In the formula, E payoff represents the total profit of SC or LC under the current strategy combination; x={1,2,3}, y={1,2}, a1 represents SC continuously changing lanes, a2 represents SC along the current horizontal line y i Driving, a3 means SC returns to the previous horizontal line y i-1 , b1 represents LC acceleration, b2 represents LC deceleration, (a x ,b y ) represents the combination of game strategies;

[0042] II. Use the master-slave game payoff matrix to solve and find the game equilibrium strategy. The equation is as follows:

[0043]

[0044] In the formula, a* and b* represent the corresponding strategies to obtain the maximum benefit under the game equilibrium of SC and LC;

[0045] III. Add the minimum headway time of vehicles to the lane-changing safety constraint;

[0046] The minimum safe headway time is set to 2s, and the following formula is used:

[0047]

[0048] Where, T safe It is the safe headway distance.

[0049] Further, the step S4 includes the following sub-steps:

[0050] S4.1 fitting lane-changing trajectory according to cubic polynomial parameter equation;

[0051]

[0052] Where x(t) and y(t) are the longitudinal and lateral positions of the vehicle at time t respectively; a0, a1, a2, a3, b0, b1, b2, b3 are the coefficients of the polynomial curve;

[0053] S4.2 At each time step, the coordinate system is updated with the current vehicle position as the origin, and assuming that the velocity v of the SC is constant, we get:

[0054]

[0055] Finally, we have:

[0056]

[0057] Where, T is the total lane-changing time of the vehicle; θ i is the vehicle heading angle at the current moment; X is the longitudinal displacement of the vehicle’s lane-changing trajectory; Y is the lateral displacement of the vehicle’s lane-changing trajectory;

[0058] S4.3 Optimal trajectory planning, define the lane change cost function J as follows:

[0059]

[0060] In the formula, λ represents the driver's driving style coefficient; is the tangential acceleration at the end of the lane change, when the curvature of the lane change trajectory is the largest;

[0061]

[0062] Where J is the minimum value of the cost function; T is the time required for the optimal lane-changing trajectory; It means that t takes the value of T after taking the second-order derivative of y(t); It means that t takes the value of T after taking the first-order derivative of y(t); It means that t takes the value of T after taking the second-order derivative of x(t); It means that t takes the value of T after taking the first-order derivative of x(t);

[0063] So the longitudinal displacement X of lane change is:

[0064] X=f(v,T,θ i ,Y)

[0065] Where f(·) represents the process of solving the longitudinal displacement X when the lane-changing cost function takes the minimum value; Y represents y(T).

[0066] Beneficial effects:

[0067] The present invention takes into account the impact of real-time changes in the posture information of surrounding vehicles on the lane changing process during the lane changing process of an intelligent connected vehicle, designs a lane changing decision and trajectory planning method of dynamic repeated master-slave game, discretizes the lateral space during the lane changing process, and performs repeated games at fixed horizontal positions to achieve the update of decision and planning, which can effectively improve the safety and efficiency of lane changing.

[0068] 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

[0069] Figure 1 This is a flow chart of a lane-changing decision-making and trajectory planning method for an intelligent connected vehicle according to the present invention;

[0070] Figure 2 Schematic diagram of lane changing based on dynamic repeated master-slave game. DETAILED DESCRIPTION

[0071] In order to make the technical solutions, advantages and purposes of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of this application.

[0072] like Figure 1 and Figure 2 As shown, the present invention proposes a lane changing decision and trajectory planning method based on dynamic repeated master-slave game, which perceives the road traffic environment through sensors such as laser radar, millimeter wave radar, and vehicle-mounted camera carried by the lane changing intelligent connected car SC, considers the position and speed information of the front vehicle FC in the current lane, the front vehicle PC in the target lane, and the rear vehicle LC, solves the optimal strategy through dynamic game, and plans the optimal lane changing trajectory of the vehicle based on different strategies and the driver's comfort and lane changing efficiency.

[0073] This embodiment provides a method for lane change decision and trajectory planning of an intelligent connected vehicle, including the following steps:

[0074] S1. Define the master-slave game profit function of the lane-changing intelligent connected car SC and the road right competing vehicle LC;

[0075] Road right competing vehicles refer to vehicles in the target lane that compete with the lane-changing intelligent connected vehicle, i.e., the rear vehicle in the target lane;

[0076] S1.1 Define vehicle;

[0077] Define the lane-changing intelligent connected car as SC, the vehicle in front of the lane-changing vehicle as FC, the vehicle behind the target lane as LC, and the vehicle in front of the target lane as PC;

[0078] Among them, the lane-changing intelligent connected car SC and the road right competition vehicle LC are participants in the master-slave game, SC is the leader in the game, and LC is the follower in the game;

[0079] S1.2 calculates the game profit of SC, and the profit function is:

[0080] E SC =(1-μ SC )*E safe1 +μ SC E vel

[0081] In the formula, E SC is the total benefit of the lane-changing vehicle SC; μ SC is the weight coefficient of the vehicle SC driving style, and its value represents the driving type, μ SC The larger the value, the more aggressive the driving behavior. safe1 is the safety benefit of the lane-changing vehicle SC; E vel is the speed gain of the lane-changing vehicle SC;

[0082] E safe1 The calculation formula is as follows:

[0083]

[0084]

[0085] Where L is the vehicle width; d is the lateral distance between vehicle SC and vehicle LC; a represents the lateral safety distance between the two vehicles; e1 is the safety factor of vehicle SC; T h T is the headway time of vehicle SC relative to vehicle LC; e1 represents the expected headway of vehicle SC, represented by T e1=min(3,T1) is calculated; T1 represents the initial headway time between vehicle FC and vehicle SC; W represents the lateral distance between the center lines of the two lanes; T2 represents the initial headway time between vehicle PC and vehicle LC;

[0086] E vel The calculation formula is as follows:

[0087]

[0088] In the formula, v PC is the speed of the front vehicle PC in the target lane; v FC is the speed of vehicle FC; v desire is the expected speed of SC;

[0089] S1.3 Calculate the game benefits of the road right competition vehicle LC, the benefit function is:

[0090] E LC =(1-μ LC )*E safe2 +μ LC *E space

[0091] In the formula, E LC is the total revenue of vehicle LC; μ LC is the weight coefficient of the LC driver’s driving style, and its value represents the type of driver. LC The larger the value, the more aggressive the driver's driving behavior. safe2 is the safety benefit of vehicle LC; E space is the space benefit of vehicle LC;

[0092] E safe2 and E space The calculation formula is as follows:

[0093]

[0094]

[0095]

[0096] Where d is the lateral distance between vehicle SC and vehicle LC; L is the vehicle width; a represents the safe lateral distance between the two vehicles; T h is the headway time of vehicle SC relative to vehicle LC; e2 is the safety factor of vehicle LC; T e2 is the expected headway time of car 2, which can be obtained from T e2 =min(3,T2).

[0097] S2. Establish a plane rectangular coordinate system with the current position of the lane-changing vehicle as the origin, the horizontal driving direction as the X-axis, and the direction from the lane where the lane-changing vehicle is located to the target lane and perpendicular to the X-axis as the Y-axis;

[0098] Taking the lateral position distance between the center line of the current lane of the intelligent connected vehicle and the center line of the target lane as a benchmark, 5 horizontal lines along the driving direction of the vehicle are set at equal intervals to obtain the vertical coordinate yi of each horizontal line, where i represents the serial number of each horizontal line, with a value range of 1-5. Each vertical coordinate yi serves as a node for the intelligent connected vehicle to conduct a repeated game.

[0099] S3. Use the sensor equipment of the intelligent connected vehicle to collect the driving status data and road environment information of itself and the lane-changing competing vehicles, and solve the game equilibrium to obtain the decision result;

[0100] If the decision result is to continue changing lanes, proceed to step S4;

[0101] If the decision result is lane keeping, proceed to step S5;

[0102] If the decision result is to return to the previous horizontal line, proceed to step S6;

[0103] The process of solving the game equilibrium and obtaining the decision result is as follows:

[0104] I According to the profit function designed in steps S1.2 and S1.3, the game profit matrix {E payoff (a x ,b y )};

[0105] In the formula, E payoff represents the total profit of SC or LC under the current strategy combination; x={1,2,3}, y={1,2}, a1 represents SC continuously changing lanes, a2 represents SC along the current horizontal line y i Driving, a3 means SC returns to the previous horizontal line y i-1 , b1 represents LC acceleration, b2 represents LC deceleration, (a x ,b y ) represents the combination of game strategies;

[0106] II. Use the master-slave game payoff matrix to solve and find the game equilibrium strategy. The equation is as follows:

[0107]

[0108] In the formula, a* and b* represent the corresponding strategies to obtain the maximum benefit under the game equilibrium of SC and LC;

[0109] The game payoff matrix is ​​shown in Table 1 below:

[0110] Table 1 Game payoff matrix

[0111]

[0112] III. Add the minimum headway time of vehicles to the lane-changing safety constraint;

[0113] The minimum safe headway time is set to 2s, and the following formula is used:

[0114]

[0115] Where, T safe It is the safe headway distance.

[0116] S4. Planning the lane changing trajectory according to the continuous lane changing strategy obtained in step S3;

[0117] S4.1 fitting lane-changing trajectory according to cubic polynomial parameter equation;

[0118]

[0119] Where x(t) and y(t) are the longitudinal and lateral positions of the vehicle at time t respectively; a0, a1, a2, a3, b0, b1, b2, b3 are the coefficients of the polynomial curve;

[0120] S4.2 At each time step, the coordinate system is updated with the current vehicle position as the origin, and assuming that the velocity v of the SC is constant, we get:

[0121]

[0122] Finally, we have:

[0123]

[0124] Where, T is the total lane-changing time of the vehicle; θ i is the vehicle heading angle at the current moment; X is the longitudinal displacement of the vehicle’s lane-changing trajectory; Y is the lateral displacement of the vehicle’s lane-changing trajectory;

[0125] S4.3 The optimal trajectory planning needs to consider both the comfort and efficiency of lane changing, so the lane changing cost function J is defined as follows:

[0126]

[0127] In the formula, λ represents the driver's driving style coefficient, which is taken as 0.5 here; is the tangential acceleration at the end of the lane change, when the curvature of the lane change trajectory is the largest;

[0128]

[0129] Where J is the minimum value of the cost function; T is the time required for the optimal lane-changing trajectory; It means that t takes the value of T after taking the second-order derivative of y(t); It means that t takes the value of T after taking the first-order derivative of y(t); It means that t takes the value of T after taking the second-order derivative of x(t); It means that t takes the value of T after taking the first-order derivative of x(t);

[0130] So the longitudinal displacement X of lane change is:

[0131] X=f(v,T,θ i ,Y)

[0132] Where f(·) represents the process of solving the longitudinal displacement X when the lane-changing cost function takes the minimum value; Y represents y(T).

[0133] S5. Perform lane keeping trajectory planning according to the lane keeping strategy obtained in step S3;

[0134] When the optimal strategy is currently determined to be lane keeping, a lane keeping trajectory is generated, and the lane-changing vehicle SC maintains the current lateral position and drives straight.

[0135] S6. According to the fallback strategy obtained in step S3, the vehicle driving trajectory planning of falling back to the previous horizontal line position is performed;

[0136] When the optimal strategy is determined to be retreat, the lane-changing vehicle SC retreats to the lateral position at the previous moment and generates the following cubic polynomial lane-changing trajectory:

[0137]

[0138] Where Y represents the lateral displacement required for vehicle lane change when vehicle No. 1 is at the lateral position at the previous moment. According to the cost function defined above, the optimal longitudinal distance X in the case of retreat can be obtained as:

[0139] X=f(v,T,θ i ,Y)

[0140] Where f(·) represents the process of solving the longitudinal displacement X when the lane-changing cost function takes the minimum value; Y represents y(T).

[0141] S7. Repeat steps S3 to S6 until the intelligent connected vehicle completes the lane change.

[0142] It is hereby declared that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions, which should be included in the scope of the claims of the present invention.

Claims

1. A method for lane changing decision and trajectory planning of an intelligent connected vehicle, characterized in that: The following steps are involved: S1. Define the master-slave game profit function of the lane-changing intelligent connected car SC and the road right competing vehicle LC; Road right competing vehicles refer to vehicles in the target lane that compete with the lane-changing intelligent connected vehicle, i.e., the rear vehicle in the target lane; S2. Establish a plane rectangular coordinate system with the current position of the lane-changing vehicle as the origin, the horizontal driving direction as the X-axis, and the direction from the lane where the lane-changing vehicle is located to the target lane and perpendicular to the X-axis as the Y-axis; S3. Use the sensor equipment of the intelligent connected vehicle to collect the driving status data and road environment information of itself and the lane-changing competing vehicles, and solve the game equilibrium to obtain the decision result; If the decision result is to continue changing lanes, proceed to step S4; If the decision result is lane keeping, proceed to step S5; If the decision result is to return to the previous horizontal line, proceed to step S6; S4. Planning the lane changing trajectory according to the continuous lane changing strategy obtained in step S3; S5. Perform lane keeping trajectory planning according to the lane keeping strategy obtained in step S3; S6. According to the fallback strategy obtained in step S3, the vehicle driving trajectory planning of falling back to the previous horizontal line position is performed; S7. Repeat steps S3 to S6 until the intelligent connected vehicle completes the lane change.

2. The method for lane changing decision and trajectory planning of an intelligent connected vehicle according to claim 1, characterized in that: The step S1 includes the following: S1.1 Define vehicle; Define the lane-changing intelligent connected car as SC, the vehicle in front of the lane-changing vehicle as FC, the vehicle behind the target lane as LC, and the vehicle in front of the target lane as PC; Among them, the lane-changing intelligent connected car SC and the road right competition vehicle LC are participants in the master-slave game, SC is the leader in the game, and LC is the follower in the game; S1.2 calculates the game profit of SC, and the profit function is: And SC =(1-μ SC )*E safe1 +μ SC And vel In the formula, E SC is the total benefit of the lane-changing vehicle SC; μ SC is the weight coefficient of the vehicle SC driving style, and its value represents the driving type, μ SC The larger the value, the more aggressive the driving behavior. safe1 is the safety benefit of the lane-changing vehicle SC; E vel is the speed gain of the lane-changing vehicle SC; E safe1 The calculation formula is as follows: Where L is the vehicle width; d is the lateral distance between vehicle SC and vehicle LC; a represents the lateral safety distance between the two vehicles; e1 is the safety factor of vehicle SC; T h T is the headway time of vehicle SC relative to vehicle LC; e1 represents the expected headway of vehicle SC; T1 represents the initial headway of vehicle FC and vehicle SC; W represents the lateral distance between the center lines of the two lanes; T2 represents the initial headway of vehicle PC and vehicle LC; E vel The calculation formula is as follows: In the formula, v PC is the speed of the front vehicle PC in the target lane; v FC is the speed of vehicle FC; v desire is the expected speed of SC; S1.3 Calculate the game benefits of the road right competition vehicle LC, the benefit function is: And LC =(1-μ LC )*E safe2 +μ LC *E space In the formula, E LC is the total revenue of vehicle LC; μ LC is the weight coefficient of the LC driver’s driving style, and its value represents the type of driver. LC The larger the value, the more aggressive the driver's driving behavior. safe2 is the safety benefit of vehicle LC; E space is the space benefit of vehicle LC; E safe2 and E space The calculation formula is as follows: Where d is the lateral distance between vehicle SC and vehicle LC; L is the vehicle width; a represents the safe lateral distance between the two vehicles; T h is the headway time of vehicle SC relative to vehicle LC; e2 is the safety factor of vehicle LC; T e2 is the expected headway time of vehicle 2.

3. The method for lane changing decision and trajectory planning of an intelligent connected vehicle according to claim 2, characterized in that: The specific content of step S2 is: taking the lateral position distance between the center line of the lane where the intelligent connected vehicle is currently located and the center line of the target lane as a reference, 5 horizontal lines are set at equal intervals along the driving direction of the vehicle to obtain the vertical coordinate yi of each horizontal line, where i represents the serial number of each horizontal line, and the value range is 1-5. Each vertical coordinate yi serves as a node for the intelligent connected vehicle to perform a repeated game.

4. The method for lane changing decision and trajectory planning of an intelligent connected vehicle according to claim 3, characterized in that: In step S3, the process of solving the game equilibrium and obtaining the decision result is as follows: I According to the profit function designed in steps S1.2 and S1.3, the game profit matrix {E payoff (a x ,b y )}; In the formula, E payoff represents the total profit of SC or LC under the current strategy combination; x={1,2,3}, y={1,2}, a1 represents SC continuously changing lanes, a2 represents SC along the current horizontal line y i Driving, a3 means SC returns to the previous horizontal line y i-1 , b1 represents LC acceleration, b2 represents LC deceleration, (a x ,b y ) represents the combination of game strategies; II. Use the master-slave game payoff matrix to solve and find the game equilibrium strategy. The equation is as follows: In the formula, a* and b* represent the corresponding strategies to obtain the maximum benefit under the game equilibrium of SC and LC; III. Add the minimum headway time of vehicles to the lane-changing safety constraint; The minimum safe headway time is set to 2s, and the following formula is used: Where, T safe It is the safe headway distance.

5. The method for lane changing decision and trajectory planning of an intelligent connected vehicle according to claim 4, characterized in that: The step S4 comprises the following sub-steps: S4.1 fitting lane-changing trajectory according to cubic polynomial parameter equation; Where x(t) and y(t) are the longitudinal and lateral positions of the vehicle at time t respectively; a0, a1, a2, a3, b0, b1, b2, b3 are the coefficients of the polynomial curve; S4.2 At each time step, the coordinate system is updated with the current vehicle position as the origin, and assuming that the velocity v of the SC is constant, we get: Finally, we have: Where T is the total lane-changing time of the vehicle; θ i is the vehicle heading angle at the current moment; X is the longitudinal displacement of the vehicle’s lane-changing trajectory; Y is the lateral displacement of the vehicle’s lane-changing trajectory; S4.3 Optimal trajectory planning, define the lane change cost function J as follows: In the formula, λ represents the driver's driving style coefficient; is the tangential acceleration at the end of the lane change, when the curvature of the lane change trajectory is the largest; Where J is the minimum value of the cost function; T is the time required for the optimal lane-changing trajectory; It means that t takes the value of T after taking the second-order derivative of y(t); It means that t takes the value of T after taking the first-order derivative of y(t); It means that t takes the value of T after taking the second-order derivative of x(t); It means that t takes the value of T after taking the first-order derivative of x(t); So the longitudinal displacement X of lane change is: X=f(v,T,θ i ,Y) Where f(·) represents the process of solving the longitudinal displacement X when the lane-changing cost function takes the minimum value; Y represents y(T).

Citation Information

Patent Citations

  • Vehicle lane change decision-making method based on support vector machine model

    CN106777776A

  • A Method for Establishing a Lane Changing Decision Model for Autonomous Driving in a Hybrid Driving Environment

    CN110298131B

  • Automatic driving vehicle lane changing trajectory planning method based on multi-person game

    CN116185027A

  • Lane changing trajectory planning method based on cyber-physical iterative game

    CN116252796A

  • Automatic driving vehicle game lane changing decision-making method and device considering driving style

    CN118182524A

Cited By

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

    CN119536062A

  • A vehicle platoon lane-changing planning and control method based on stage-based road right game

    CN119536062B